Medical Image Processing

One of the main challenges in lung cancer radiation therapy is how to reduce the treatment margin but accommodate the geometric uncertainty of moving tumor. 4D-CT is able to provide the full range of motion information for the lung and tumor. However, accurate estimation of lung motion with respect to the respiratory phase is difficult due to various challenges in image registration, e.g., motion artifacts and large interslice thickness in 4D-CT. Meanwhile, the temporal coherence across respiration phases is usually not guaranteed in the conventional registration methods which consider each phase image in 4D-CT independently. To address these challenges, the authors present a unified approach to estimate the respiratory lung motion with two iterative steps. Methods: First, the authors propose a novel spatiotemporal registration algorithm to align all phase images of 4D-CT (in low-resolution) to a high-resolution group-mean image in the common space. The temporal coherence of registration is maintained by a set of temporal fibers that delineate temporal correspondences across different respiratory phases. Second, a super-resolution technique is utilized to build the high-resolution group-mean image with more anatomical details than any individual phase image, thus largely alleviating the registration uncertainty especially in correspondence detection. In particular, the authors use the concept of sparse representation to keep the group-mean image as sharp as possible. Results: The performance of our 4D motion estimation method has been extensively evaluated on both the simulated datasets and real lung 4D-CT datasets. In all experiments, our method achieves more accurate and consistent results in lung motion estimation than all other state-of-the-art approaches under comparison. Conclusions: The authors have proposed a novel spatiotemporal registration method to estimate the lung motion in 4D-CT. Promising results have been obtained, which indicates the high applicability of our method in clinical lung cancer radiation therapy.

Visual quality of volume rendering for medical imagery strongly depends on the underlying transfer function. Conventional Windows-Icons-Menus-Pointer interfaces typically refer the user to browse a lengthy catalog of predefined transfer functions or to pain-staking refine the transfer function by clicking and dragging several independent handles. To turn the standard design process less difficult and tedious, this paper proposes novel interactions on a sketch-based interface that supports the design of 1D transfer functions via touch gestures to directly control voxel

Analyzing medical volume datasets requires interactive visualization so that users can extract anatomo-physiological information in real-time. Conventional volume rendering systems rely on 2D input devices, such as mice and keyboards, which are known to hamper 3D analysis as users often struggle to obtain the desired orientation that is only achieved after several attempts. In this paper, we address which 3D analysis tools are better performed with 3D hand cursors operating on a touchless interface comparatively to a 2D input devices running on a conventional WIMP interface. The main goals of this paper are to explore the capabilities of (simple) hand gestures to facilitate sterile manipulation of 3D medical data on a touchless interface, without resorting on wearables, and to evaluate the surgical feasibility of the proposed interface next to senior surgeons (N = 5) and interns (N = 2). To this end, we developed a touchless interface controlled via hand gestures and body postures t...

Sugarcane leaf diseases are major agricultural
issues that lead to reduced production and economic losses.
Early detection is crucial for controlling their spread. This
study introduces a solution for identifying sugarcane leaf
diseases using image processing and deep learning techniques.
Preprocessing steps include normalization for pixel scale
stabilization and Gaussian blur for noise reduction. Features
are extracted using a pre-trained DenseNet201 model, and
classification is performed using a Support Vector Machine
(SVM) with an RBF kernel. The proposed hybrid DCNN-SVM
architecture achieves a test accuracy of 96.74%, demonstrating
effectiveness in disease classification. Comprehensive
evaluations highlight the model’s strengths and areas for
improvement, providing a foundation for future research in
plant disease detection.

The objective of content-based image retrival (CBIR) is to retrieve relevant medical images from the medical database with reference to the query image in a shorter span of time. All the proposed approaches are different, yet the research goal is to attain better accuracy in a reasonable amount of time. The initial phase of this research presents a feature selection technique that aims to improvise the medical image diagnosis by selecting prominent features. The second phase of the research extracts features and the association rules are formed by the proposed classification based on highly strong association rules (CHiSAR). Finally, the rule subset classifier is employed to classify between the images. The last pert of our work extracts the features from the kidney images and the association rules are reduced for better performance. The image relevance inference is performed and finally, binary and the best first search classification is employed to classify between the images.

Objectives: Spinal mobility is clinically important in managing mechanical low back pain. Manual methods are commonly used for diagnosis and treatment in orthopedic practice. This study quantified changes in sagittal plane lumbar segmental motion using ultrasound imaging (USI) following common joint mobilization techniques in asymptomatic individuals. Additionally, tibial H-reflexes and sagittal plane trunk motion in standing were evaluated for association with lumbar segmental motion. Participants aged ≤ 30 or ≥ 50 years were recruited from among students, faculty, and affiliates of the Department of Physical Therapy at Winston-Salem State University and randomized to receive L4 central posterior-to-anterior (CPA) mobilization or left lumbar rotation mobilization interventions. Joint laxity was assessed using the Beighton score, and standing sagittal plane trunk motion was measured using the fingertip-to-floor method. Lumbar segmental motion was evaluated using USI in neutral, extension, and flexion positions at baseline, immediately following joint mobilization, and following 5 minutes of prone resting. Tibial H-reflexes were measured at baseline, immediately following joint mobilization, and in realtime during CPA mobilization. The primary outcome was lumbar segmental motion analyzed by position, mobilization group, sex, age category, and Beighton risk. Results: Repeated measures ANOVA revealed significant increases in L4/5 flexion (p = .01, ƞ 2 =.21) and combined flexion and extension (p = .03, ƞ 2 =.15). These changes persisted following 5 minutes of prone resting, regardless of mobilization technique. Significant interactions between segmental motion, sex, and/or Beighton risk were observed. Discussion/Conclusion: Significant increases were observed in L4/5 flexion immediately following joint mobilization regardless of mobilization group, with significant statistical interactions observed between segmental motion, sex, and/or Beighton risk. This is the first investigation to demonstrate the value of USI for quantifying lumbar segmental motion following joint mobilization. Quantifying lumbar segmental motion helps clarify the underlying mechanisms of manual therapy. Future studies should include patients with low back pain.

Books are essential in finding knowledge, even as entertainment. Information for recommendations to search for book titles becomes very helpful to determine the reference of books with the same topic. The problem is that the number of books increases every year, making it difficult for readers to find suitable book references or similar books that are already needed. A recommendation system is needed in these situations. The technique used in this study is the Hybrid Filtering method; this method combines the Collaborative Filtering method and Content-based Filtering method, the advantages of the Hybrid method can provide recommendations not only from the similarity of content (Content-based) but also from the similarity of user tastes (Collaborative), the results obtained by using Hybrid Filtering method get a mean absolute error value at 0.37.

Road detection is an essential facilitator for the development of the autonomous robot navigation and the driver assistant system. It plays vital tasks in intelligent transportation systems and various applications. The main goal of this paper is to detect the driveable road region from the other entire region. Also this paper focuses on investigating the suitability of probability neural network for video based road detection. Through PNN boundary and nonboundary regions are differentiated efficiently. The proposed method is finally evaluated on the several videos.

Given the enormous number of mammograms performed during last years, computerbased diagnosis of breast cancer turned into a necessity. In particular, the diagnosis of breast masses and their classification currently arouse great interest. Indeed, the complexity of the processed forms and the difficulty encountered in order to discern them require the use of appropriate descriptors. This article is placed in the context of evaluating the results of supervised classification algorithms and their comparison. In this work, we conduct some experiments using the Wisconsin diagnosis Breast Cancer (WDBC) dataset in order to classify the dataset samples to be either benign or malignant. We show that the best results are obtained using our new proposed neighboring Support Vector Classifier (NSVC).

With the success of VTK and ITK, there are more attentions to the toolkit development issue in medical imaging community. This paper introduces MITK, an integrated medical image processing and analyzing toolkit. Its main purpose is to provide a consistent framework to combine the function of medical image segmentation, registration and visualization. The design goals, overall framework and implementation of some key technologies are provided in details, and some application examples are also given to demonstrate the ability of MITK. We hope that MITK will become another available choice for the medical imaging community.

la sécurisation de la chaîne de transmission devient de plus en plus nécessaire avec l'évolution des communications en terme de nombre d'utilisateur et nature d'information à transmettre. Durant ces années, des nouvelles méthodes de modulation qui utilise le chaos dans les systèmes de transmission sont développées [BEN 06], ces méthodes ont poussé les recherches vers l'amélioration de la qualité de l'information reçu ainsi que la robustesse des algorithmes qui traitent cette information transmise. Pour cela, actuellement tous système de télécommunication performant nécessite un système de cryptage robuste afin de se protéger envers les attaques possible. Notre travail est d'une part, une étude de robustesse des algorithmes de cryptages, d'autre part une validation de ces algorithmes dans la chaîne de transmission. Dans ce papier, nous étudions la possibilité d'utiliser le chaos, partant de ses différentes propriétés et de son comportement spécifique, pour chiffrer l'information dans une transmission sécurisée. Nous étudions une méthode de cryptage proposée par Baptista [BAP 98], [SHU 04]. Nous testons la sécurité de cette méthode en appliquant une attaque à texte en clair choisi comme outil de cassage du système de cryptage [ALV 05], [ALV 06]. Par suite, nous apportons une amélioration à cette méthode de cryptage afin d'arriver à une version modifiée qui résiste aux attaques appliquées.

Artificial intelligence (AI) has been applied widely in our daily lives in a variety of ways with numerous successful stories. AI has also contributed to dealing with the coronavirus disease (COVID-19) pandemic, which has been happening around the globe. This paper presents a survey of AI methods being used in various applications in the fight against the COVID-19 outbreak and outlines the crucial roles of AI research in this unprecedented battle. We touch on a number of areas where AI plays as an essential component, from medical image processing, data analytics, text mining and natural language processing, the Internet of Things, to computational biology and medicine. A summary of COVID-19 related data sources that are available for research purposes is also presented. Research directions on exploring the potentials of AI and enhancing its capabilities and power in the battle are thoroughly discussed. We highlight 13 groups of problems related to the COVID-19 pandemic and point ou...

Hemoglobin değerinin belirli bir referans aralığının altına düşmesiyle ortaya çıkan ve aynı zamanda kansızlık olarak adlandırılan anemi, teşhis ve tedavisi için birçok kan testine, radyolojik görüntülere, tahlillere ihtiyaç duyar. Bu gibi çok fazla üretilen tıbbi verilerin yanında hastalık teşhisinin konulmasında doktor kararı gereklidir. Hastalardan alınan tıbbi veriler işlenerek yeni hasta bireyler için hastalıkların tahminleri yapılabilir ve bu tahminlerle doktorlar için karar destek mekanizmaları kurulabilmektedir. Doktorların hastalar için koyacağı teşhisteki yanılma payını azaltma konusunda oldukça önemli olan bu yöntemler sayesinde sağlık kurumlarındaki veri kayıtlarının değerlendirilmesi hasta ve hastaneler için de önem arz etmektedir. Literatürde anemi hastalığı sınıflandırma problemi için çeşitli yöntemler kullanılmış olup, veri setlerindeki hasta kayıt sayılarının değişiklik göstermesi, kan parametrelerin sayısının ve özelliklerinin farklı olması gibi durumlardan dolayı önerilen algoritmaların performansları veri setlerine göre değişiklik göstermektedir. Bu çalışmada Kaggle veri tabanından alınan anemi veri seti üzerinde kandaki verilere dayalı olarak anemi hastalığı sınıflandırması problemini çözmek amacıyla Yapay Sinir Ağları (YSA) yöntemleri kullanılmıştır. Öğrenmeli Vektör Kuantalama (LVQ), Rekabetçi Katman Sinir Ağı (CLNN), Örüntü Tanıma Yapay Sinir Ağı (PRNN), Kendiliğinden Organize Olan Harita (SOM) yapay sinir ağı yöntemleri kullanılarak başarım oranları hesaplanmıştır. Elde edilen sonuçların doğruluk değerleri ve karışıklık matrisleri verilerek önerilen dört yöntem karşılaştırılmıştır. En iyi başarı performansı %100 hassasiyet ve %99,88 doğruluk, %99,86 özgüllük, %99,43 kesinlik ile PRNN olduğu, onu takiben LVQ olduğu sonucuna ulaşılmıştır.

Globally, glaucoma is the major cause of visual impairment. It is a chronic eye disease in which optic nerve damages progressively due to the raised Intraocular Pressure (IOP) of the eye. The technique proposed in this paper allows automatic detection of the glaucoma using digital fundus image by extracting the features like vertical cup to disc ratio (CDR), its area ratio, horizontal to vertical CDR and the ratio of area of blood vessels in inferior-superior region to that in the nasal-temporal region of the Optic Disc (OD) (ISNT Ratio) by segmenting OD, cup and blood vessels. The method proposed for OD segmentation is based on geodesic active contour model. The cup segmentation method is based on the structural properties and color information of the cup region and blood vessels are segmented by morphological technique. The performance evaluation of the proposed technique has been carried out on 200 images comprising 100 normal and 100 glaucomatous images. Support Vector Machine (...

Multimodal medical image registration is a highly regarded technique in medical imaging because it involves the merging of cross-sectional information through various imaging modalities like CT, MRI, and PET. This technique surely resembles the union of physics with organic cell matter, since it cannot find its most important applications before the multi-planar, clinical-corroborative, multimodal images have been formed at appropriate spatialintensity scales. Therefore, it serves the unique purpose of visualizing both the detailed anatomy and functional details, hence giving improved diagnostic features, treatment planning, and disease follow-up on subjects. Congratulations are particularly in order for metamorphosing this kind of interesting insight for the low-lying dimension visualizations of the "images' visual goodness." Advanced algorithms such as wavelet transform, deep learning, and optimization techniques are used as common concrete units to exploit the exact, fast mapping of fusion. In this review paper, we introduce the importance, methods, and application now in multimodal image fusing in a modern healthcare system, and highlight how these can affect clinical outcomes and patient care. Keywords-multimodal medical image fusion, deep learning, convolutional neural networks (cnns), transformers in medical imaging, feature-level fusion, pixel-level fusion, computed tomography (ct), magnetic resonance imaging (mri), peak signal-to-noise ratio (psnr), positron emission tomography (pet), principal component analysis (pca)

Tensor voting is a well-known robust technique for extracting perceptual information from clouds of points. This chapter proposes a general methodology to adapt tensor voting to different types of images in the specific context of image structure estimation. This methodology is based on the structural relationships between tensor voting and the so-called structure tensor, which is the most popu-

The large number of misinformation and fake news which proliferates on digital
platforms, they have become a major social challenge as people make decisions based
on fake news. Traditional methods of gathering information on the spread of fake news
cannot keep up with its rapid dissemination, and artificial intelligence and natural
language processing is a necessary undertaking to do away with the fake. In this paper,
an AI based approach of fake news detection framework using deep learning and
analytical feature is proposed to classify the news articles as real or fake. We employ
transformer based models including BERT, RoBERTa and XLNet as well as graph
based method to analyze contextual credibility. Furthermore, the adversarial
robustness is investigated in order to circumvent biased AI news generated through
adversarial techniques. They also integrate explainable AI (XAI) methodologies to
increase the model’s transparency and trustworthiness in the study. Finally, we evaluate
our model against benchmarks (LIAR, FakeNewsNet and BuzzFeedNews) and show our
results are state of the art compared to conventional models. Experimental results
demonstrate the importance of semantic, stylistic and discourse features in aiding in
detection; in fact, a combination of these features produces the best detection results.
Based on this study, new type of robust, scalable and interpretable AI systems for fake
news detection are developed, which are applicable to journalism, social media
platforms, and regulatory bodies.

Lung diseases rank as the third most prevalent cause of mortality globally. Accurate identification of lung disease is essential to provide appropriate medical intervention for patients. This research devised a categorization system for lung diseases using chest X-Rays (CXR). The system can identify bacterial pneumonia, viral pneumonia, COVID-19, tuberculosis, and normal CXR. The approach for detecting lung diseases utilize a combination of hybrid transfer learning and bidirectional long short-term memory. The research included convolutional neural network (CNN) models including Resnet50-BiLSTM, VGG19-BiLSTM, InceptionV3-BiLSTM, Resnet50, VGG19, and InceptionV3. The Resnet50-BiLSTM model outperforms other models in terms of accuracy and overall performance. The Resnet50-BiLSTM model achieved an accuracy of 99.87%. The models that achieve the second greatest accuracy are Resnet50, VGG19-BiLSTM, VGG19, InceptionV3-BiLSTM, and InceptionV3. The research utilizes precision, recall, and F1-Measure to demonstrate that Resnet50-BiLSTM outperforms other methods by achieving the greatest value. This research improves the performance outcomes when compared to earlier studies.

Type 2 diabetes mellitus (T2DM) is a major global health issue that significantly reduces life expectancy and impairs overall quality of life. Early diagnosis of T2DM is critical, as it can help prevent or delay the development of associated complications. This study aims to assess the effectiveness of a stacked ensemble machine learning model, incorporating a meta-model approach, for the early detection of T2DM. In the first stage of modeling (Level 1), two base models-random forest (RF) and support vector machines (SVM)-are trained using distinct feature selection, tuning, and optimization strategies. In the second stage, ensemble methods, such as voting and stacking classifiers, are employed to combine the predictions from these base models. The final prediction is made by a meta-model, specifically a gradient boosting classifier (GBC), which classifies individuals as either positive or negative for T2DM. Further classification of positive instances is based on low-, moderate-, or high-risk levels. The system is designed for deployment to enable real-time assessment of diabetes risk. The Meta-Model (GBC), with an accuracy of 99.13%, a precision of 100%, specificity of 100%, and an F1 score of 99.25%, consistently outperforms the base models (SVM and RF) and ensemble models (voting and stacking classifiers), proving highly effective in the early detection of T2DM. This significant accuracy highlights the enormous promise of machine learning methods for assisting in the early identification of T2DM. The findings of this study will significantly enhance precision medicine screening for T2DM, empowering healthcare professionals to diagnose the condition early and ultimately improve patient outcomes.

Ensemble learning combines multiple base models to enhance predictive performance and generalize better on unseen data. In the context of Computed Tomography (CT) image processing, ensemble techniques often leverage diverse machine learning or deep learning architectures to achieve the best results. Ensemble machine learning and deep learning techniques have revolutionized the field of CT image processing by significantly improving accuracy, robustness, and efficiency in various medical imaging tasks. These methods have been instrumental in tasks such as image reconstruction, segmentation, classification, and disease diagnosis. The ensemble models can be divided into those based on decision fusion strategies, bagging, boosting, stacking, negative correlation, explicit/implicit ensembles, homogeneous/heterogeneous ensembles, and explicit/implicit ensembles. In comparison to shallow or traditional, machine learning models and deep learning architectures are currently performing better. Also, a brief discussion of the various ensemble models used in CT images is provided. We wrap up this work by outlining a few possible avenues for further investigation.

Parkinson's disease (PD) is a neurodegenerative disorder caused by the loss of dopaminergic neurons in the substantia nigra. Traditional treatments include dopamine precursors (levodopa), deep brain stimulation (DBS), and gene therapies, but these have limitations. Quantum Medicine Approach Quantum mechanics offers new paradigms for treating PD, using quantum tunneling, entanglement, coherence, and nanotechnology to improve drug delivery, neural regeneration, and targeted therapy. 🔬 1. Quantum Dot-Based Neuroprotective Therapy Concept Quantum dots (QDs) engineered from sugar-derived carbon nanoparticles can be used to protect and regenerate dopaminergic neurons by targeting oxidative stress and inflammation. Quantum Principles ✔ Quantum Confinement: QDs can be engineered to emit specific infrared (IR) or blue light that stimulates dopaminergic neuron growth. ✔ Exciton Dynamics: Light-activated QDs reduce free radicals in the brain, minimizing neuronal death.

Leukemia is a blood cancer originating in the bone marrow that leads to
the production of abnormal blood cells, impacting cell functionality and efficiency. According to Globocan, statistics for 2022 show that Viet Nam has 180,480 new cancer cases and 120,184 deaths, of which leukemia has 5,789 new cases, ranking 8th among cancer types (accounting for 3.2%) and 4,330 deaths, ranking 6th in mortality rate among cancer types (accounting for 3.6%). Depending on the progression rate, leukemia can be identified as either acute or chronic. Acute leukemia affects blood cells in the early stages of development, causing the disease to become more severe, while chronic leukemia affects more developed blood cells, and the disease tends to develop slowly. Another way to classify leukemia is by the specific blood cell type it targets, either myeloid or lymphoid cells. Understanding the affected cell type is essential for diagnosis and treatment planning, as it influences disease behavior and response to treatment. This paper focuses on identifying and classifying ALL (Acute Lymphoblastic Leukemia) blasts in the most prevalent childhood cancer type using transfer learning of the Alexnet network model in Matlab software. Diagnosing ALL disease using peripheral blood smear (PBS) images helps screen and treat the disease early, contributing to improving treatment effectiveness for patients. Laboratory users often face challenges when examining PBS images, as the non-specific signs and symptoms of ALL can result in frequent misdiagnoses and diagnostic errors. The research presents a model for analyzing peripheral blood smear images, aimed at identifying ALL cell types and distinguishing among its malignant subtypes. The ALexnet model will be trained in 3 different ways including: Train with no parameters (Training a Neural Network from Scratch), train the pretrained network but change the fullyConnected layer at the end and train the pretrained network but change the 14th layer onwards. The results show that the model using the second training method achieves the best performance when reaching 98.664% accuracy on the validation set, while methods 1 and 3 are 92.292% and 89.825% respectively. Finally, the second model is saved to design the user application using AppDesigner.

Diabetic Retinopathy (DR), a complication of diabetes, is one of the primary causes of blindness across the globe. Detecting subtle abnormalities in retinal images, such as microaneurysms, hemorrhages, exudates, and changes in the macula, is crucial for diagnosing DR. However, manual evaluation of these images is a tedious and timeintensive process. Computer-aided systems can enhance the accuracy and efficiency of this task, enabling timely intervention to prevent or slow down vision loss. Artificial intelligence (AI), particularly in recent years, has emerged as a powerful tool for automating the detection and classification of DR in retinal fundus images. This study explores the application of advanced deep-learning models to identify diabetic retinopathy in retinal images. Specifically, we employed Convolutional Neural Networks (CNNs), which have demonstrated exceptional performance in computer vision tasks, including medical image analysis. A publicly accessible dataset from Kaggle was utilized to train and validate the model, ensuring the reproducibility and scalability of the proposed approach. We designed a web app to give medical practitioners support and a trustworthy second opinion on disorders that can be discovered through medical imaging. Using artificial intelligence, the platform analyzes these medical photos and classifies them into several categories. This program is intended to provide you with accurate, dependable, and quick results.

The process of endovascular treatment of cerebral aneurysms requires intensive use of 3D rotational angiography in planning and monitoring the entire process. 3D RA allows unlimited manipulation of model blood vessels and defining the morphology of the aneurysm without using radiation. The purpose of the study was to compare the results of the analysis of residue or recurrence of the aneurysm after endovascular treatment using 3D RA and 2D digital subtraction. Method. In 68 patients with 76 cerebral aneurysms, we made regular controls using both techniques, 2D DSA and 3D RA. Residual and recurrent aneurysms are classified into five stages, and the pictures taken by both modalities are compared. Results. 2D DSA detected the residual and recurrent aneurysm in 53.70% of cases (29/54 aneurysms), and 3D RA in 66.67% (36/54 aneurysms). In nine cases in 2D DSA did not detected residues of which was discovered in 3D RA, and 3 cases of 2D DSA reveals little short neck aneurysm, which is on the 3D RA, in fact, a small aneurysm. In five cases from the use of 3D RA reduced the level of classification aneurysm. Conclusion: 3D RA reveals more residues aneurysms.

Sa??etak: Computer aided diagnosis of lung CT image has been a revolutionary step in the early diagnosing of lung diseases. The best method of implementing computer aided diagnosis for medical image analysis is first to preprocess the image in order to segment it ...

Kanser payudara ialah penyebab utama kematian di kalangan pesakit kanser yang melanda wanita dan kanser kedua paling lazim di seluruh dunia. Pengimejan Resonans Magnetik (MRI) adalah salah satu daripada alat-alat radiologi yang paling berkesan untuk menyaring kanser payudara. Bagaimanapun, teknik-teknik pemprosesan imej diperlukan bagi membantu pakar radiologi dalam mentafsir imej dan memisahkan wilayah tumor bagi mengurangkan jumlah positif yang palsu. Dalam kajian ini, pendekatan segmentasi dengan ciri-ciri automatik dibangunkan untuk tumor MRI payudara. Kaedah bermula dengan pemerolehan data diikuti oleh proses prapemprosesan. Ini diikuti dengan proses pengecualian garis kulit payudara menggunakan kaedah bersepadu Level Set Active Contour and Morphological Thinning. Berikutnya, kesan penting dikesan menggunakan kaedah Mean Maximum Raw Thresholding (MMRT) dicadangkan. Kemudian, pada fasa segmentasi tumor, dua kaedah diubahsuai Seeded Region Growing (SRG) dicadangkan; iaitu Breast ...

The goal of edge detection is to determine whether a point in an image is an edge point. This is done by applying first and second derivative operators to detect the greatest change in image intensity. In this paper, we propose a new method where the threshold, represented by the average 𝑎 ̅, is calculated within a neighborhood of I(x1,x2). This approach not only reduces processing time but also ensures that no pixels are missed. Pixels below the threshold are replaced after enhancement. We extend this work by applying the Canny edge detector (CED) to detect boundaries in MRI images of abnormal brains affected by intraventricular hemorrhage (IVH). Two thresholds are used: the hysteresis threshold in the CED and our proposed statistical threshold, which works alongside traditional edge operators like Sobel, Prewitt, and Laplacian.

11th International Conference on Image and Signal Processing (ISPR 2025) is a forum for presenting new advances and research results in the fields of Digital Image Processing. The conference will bring together leading researchers, engineers and scientists in the domain of interest from around the world. The scope of the conference covers all theoretical and practical aspects of the Signal, Image Processing & Pattern Recognition. Authors are solicited to contribute to the conference by submitting articles that illustrate research results, projects, surveying works and industrial experiences.

In this paper we compare Mixed-Integer Evolution Strategies (MI-ES) and standard Evolution Strategies (ES) when applied to find optimal solutions for artificial test problems and medical image processing problems. MI-ES are special instantiations of standard ES that can solve optimization problems with different objective variable types (continuous, integer, and nominal discrete). Artificial test problems are generated with a mixed-integer test generator. The practical image processing problem iss the detection of the lumen boundary in IntraVascular UltraSound (IVUS) images. Based on the experimental results, it is shown that MI-ES generally perform better than standard ES on both artifical and practical image processing problems. Moreover it is shown that MI-ES can effectively improve the parameters settings for the IVUS lumen detection algorithm.

Along with rich health-related metadata, medical images have been acquired for over 40,000 male and female UK Biobank participants, aged 44-82, since 2014. Phenotypes derived from these images, such as measurements of body composition from MRI, can reveal new links between genetics, cardiovascular disease, and metabolic conditions. In this work, six measurements of body composition and adipose tissues were automatically estimated by image-based, deep regression with ResNet50 neural networks from neck-to-knee body MRI. Despite the potential for high speed and accuracy, these networks produce no output segmentations that could indicate the reliability of individual measurements. The presented experiments therefore examine uncertainty quantification with mean-variance regression and ensembling to estimate individual measurement errors and thereby identify potential outliers, anomalies, and other failure cases automatically. In 10-fold cross-validation on data of about 8,500 subjects, mean-variance regression and ensembling showed complementary benefits, reducing the mean absolute error across all predictions by 12%. Both improved the calibration of uncertainties and their ability to identify high prediction errors. With intra-class correlation coefficients (ICC) above 0.97, all targets except the liver fat content yielded relative measurement errors below 5%. Testing on another 1,000 subjects showed consistent performance, and the method was finally deployed for inference to 30,000 subjects with missing reference values. The results indicate that deep regression ensembles could ultimately provide automated, uncertainty-aware measurements of body composition for more than 120,000 UK Biobank neck-to-knee body MRI that are to be acquired within the coming years.

The construction of a high-resolution panoramic image from a sequence of input overlapping images of the same scene is called image stitching/mosaic. It is considered as an important, challenging topic in computer vision, multimedia, and computer graphics. Therefore, the main objective of this project is to get a panoramic image with minimum overlapping- together to create high quality, high resolution panorama. To process that we implement feature matching based using some algorithm such SIFT which is much less sensitive to rotation and Scale and homograph. Most image stitching techniques require exact overlap between image and its exposures to give better result

High efficiency video coding (HEVC) is the newest video codec to increase significantly the coding efficiency of its ancestor H.264/Advance Video Coding. However, the HEVC delivers a highly increased computation complexity. In this paper, a coding unit partitioning pattern optimization method based on particle swarm optimization (PSO) is proposed to reduce the computational complexity of hierarchical quadtree-based coding unit partitioning. The required coding unit partitioning pattern for exhaustive partitioning and the rate distortion cost are efficiently considered as the chromosome and the fitness function of the PSO, respectively. To reduce the computational time, the cellular automata-based (CA) rule based time limit is used in order to find out the best possible modes of operation. Compared to the current state of the art algorithms, this scheme is computationally simple and achieves superior reconstructed video quality (12% increase in PSNR compared to existing methods) at less computational complexity (overall delay by 40%), Increasing the bandwidth and reducing the errors..

The purpose of this study was to investigate the number of intermediate states required to adequately approximate the clinically relevant cumulative dose to deforming/moving thoracic anatomy in four-dimensional ͑4D͒ conformal radiotherapy that uses 6 MV photons to target tumors. Four patients were involved in this study. For the first three patients, computed tomography images acquired at exhale and inhale were available; they were registered using B-spline deformation model and the computed transformation was further used to simulate intermediate states between exhale and inhale. For the fourth patient, 4D-acquired, phase-sorted datasets were available and each dataset was registered with the exhale dataset. The exhale-inhale transformation was also used to simulate intermediate states in order to compare the cumulative doses computed using the actual and the simulated datasets. Doses to each state were calculated using the Dose Planning Method ͑DPM͒ Monte Carlo code and dose was accumulated for scoring on the exhale anatomy via the transformation matrices for each state and time weighting factors. Cumulative doses were estimated using increasing numbers of intermediate states and compared to simpler scenarios such as a "2-state" model which used only the exhale and inhale datasets or the dose received during the average phase of the breathing cycle. Dose distributions for each modeled state as well as the cumulative doses were assessed using dose volume histograms and several treatment evaluation metrics such as mean lung dose, normal tissue complication probability, and generalized uniform dose. Although significant "point dose" differences can exist between each breathing state, the differences decrease when cumulative doses are considered, and can become less significant yet in terms of evaluation metrics depending upon the clinical end point. This study suggests that for certain "clinical" end points of importance for lung cancer, satisfactory predictions of accumulated total dose to be received by the distorting anatomy can be achieved by calculating the dose to but a few ͑or even simply the average͒ phases of the breathing cycle.

To develop a method for retrospective artifact elimination of MRS data. This retrospective method was based on an approach that combines jackknife analyses with the correlation of spectral windows, and therefore termed "JKC." Methods: Twelve healthy volunteers performed 3 separate measurement protocols using a 3T MR system. One protocol consisted of 2 cerebellar MEGA-PRESS measurements: 1 reference and 1 measurement including head movements. One-third of the artifact-influenced datasets were treated as training data for the implementation the JKC method, and the rest were used for validation. The implemented JKC method correctly characterized most of the validation data. Additionally, after elimination of the detected artifacts, the resulting concentrations were much closer to those computed for the reference datasets. Moreover, when the JKC method was applied to the reference data, the estimated concentrations were not affected, compared with standard averaging. The implemented JKC method can be applied without any extra cost to MRS data, regardless of whether the dataset has been contaminated by artifacts. Furthermore, the results indicate that the JKC method could be used as a quality control of a dataset, or as an indication of whether a shift in voxel placement has occurred during the measurement.

This study aims to optimize convolutional neural networks (CNN)-based ensemble learning models to enhance accuracy and stability in detecting herbal leaf diseases. The dataset used in this study is sourced from the "Lontar Taru Pramana" collection, which includes various images of herbal leaves affected by different diseases such as ancak bacterial spot, dapdap mosaic virus, and kelor powdery mildew. Several CNN models, including VGG16, AlexNet, ResNet50, DenseNet121, MobileNetV2, and InceptionV2, were evaluated. Among these, the ensemble models combining VGG16, DenseNet121, and MobileNetV2 were selected due to their superior performance. The ensemble model achieved precision scores of 0.81 for class 1, 0.76 for class 2, and 0.78 for class 3, with corresponding recall scores of 0.8167, 0.74, and 0.7633, and F1-scores of 0.8133, 0.75, and 0.7717 respectively. These results indicate significant improvements in model performance and robustness.

Oral squamous cell carcinoma (OSCC) is emerging as a significant global health concern, underscoring the need for prompt detection and treatment. Our study introduces an innovative diagnostic method for OSCC, leveraging the capabilities of artificial intelligence (AI) and histopathological images (HIs). Our primary objective is to expedite the identification process for medical professionals. To achieve this, we employ transfer learning and incorporate renowned models such as VGG16, VGG19, MobileNet_v1, MobileNet_v2, DenseNet, and InceptionV3. A key feature of our approach is the meticulous optimization of the VGG19 architecture, paired with advanced image preprocessing techniques such as contrast limited adaptive histogram equalization (CLAHE) and median blur. We conducted an ablation study with optimized hyperparameters, culminating in an impressive 95.32% accuracy. This groundbreaking research ensures accurate and timely diagnoses, leading to improved patient outcomes, and represents a significant advancement in the application of AI for oral cancer diagnostics. Utilizing a substantial dataset of 5,192 meticulously categorized images into OSCC and normal categories, our work pioneers the field of OSCC detection. By providing medical professionals with a robust tool to enhance their diagnostic capabilities, our method has the potential to revolutionize the sector and usher in a new era of more effective and efficient oral cancer treatment.

Retinopathy is an eye disease caused by diabetes, and early detection and treatment can potentially reduce the risk of blindness in diabetic retinopathy sufferers. Using retinal Fundus images, diabetic retinopathy can be diagnosed, recognized, and treated. In the current state of the art, sensitivity and specificity are lacking. However, there are still a number of problems to be solved in state-of-the-art techniques like performance, accuracy, and being able to identify DR disease effectively with greater accuracy. In this paper, we have developed a new approach based on a combination of image processing and artificial intelligence that will meet the performance criteria for the detection of disease-causing diabetes retinopathy in Fundus images. Automatic detection of diabetic retinopathy has been proposed and has been carried out in several stages. The analysis was carried out in MATLAB using software-based simulation, and the results were then compared with those of expert ophtha...

Mammography is a noninvasive diagnostic technique widely used for early cancer detection in women breast. The automatic detection and classification of some abnormali ties in mammograms is of challenging scientific and tech nical interest because of the associated research topics and the potential clinical applications. Therefore. the design of a medical CAD (Computer-Aided Diagnosis or Detection) system for the analysis of mammographies involves a team composed by both medical and technical experts. In this pa per we show the interaction that occurs between computer scientists and radiologists in the development and evalua tion of a CAD system for the detection of clusters of micro calcifications.

In blood cell image analysis, segmentation is an indispensable step in quantitative cytophotometry. Blood cell images have become particularly useful in medical diagnostic tools for cases involving blood. The aim of our research is to develop an effective algorithm for segmentation of the blood cell images. In this paper, we present a framework of comparison cell images segmentation by using unsupervised clustering techniques with the purpose of acquiring the best method to segment the cell images. We use blood cell images infected with malaria parasites as cell images for our framework. Methods that involved in this comparison framework are Fuzzy C Means, K Means and Means Shift Analysis. The outcome from these methods will help to identify which technique or algorithm is the best for cell segmentation. Results from the segmented cell will be use for further classification and recognition.

Puji syukur kami panjatkan kehadirat Tuhan Yang Maha Esa yang telah
memberikan rahmat serta karunia-Nya kepada kami sehingga kami berhasil menyelesaikan Buku dengan judul Pidato Pengukuhan Guru Besar sesuai yang ditargetkan.
Buku ini berisikan peranan sistem informasi geografis dalam
pengelolaan ekosistem pesisir dan pulau-pulau keci, peranan data science dalam perkembangan dunia medis dan agriculture melalui data citra, inovasi varietas jagung unggul dalam mendukung ketahanan dan kedaulatan pangan di pulau madura, potensi dan pengembangan sumber daya genetik lokal madura untuk pemuliaan ketahanan tanaman terhadap cekaman abiotik kekeringan, inovasi teknologi deteksi abnormal paru-paru berbasis artificial intelligence untuk mempercepat diagnosis penyakit dalam.
Kami menyadari bahwa buku ini masih jauh dari sempurna, oleh karena
itu kritik dan saran dari semua pihak yang bersifat membangun selalu kami harapkan demi kesempurnaan buku ini.
Akhir kata, kami sampaikan terima kasih kepada semua pihak yang telah
berperan serta dalam penyusunan buku ini dari awal sampai akhir. Semoga Tuhan yang maha esa senantiasa meridhoi segala usaha kita. Amin.

This paper aims to measure the impact of
Differential Privacy (DP) on the performance of AI models. This
is done by experimenting on two models: one without differential
privacy and the other with differential privacy. Both models are
trained on the same dataset to ensure a fair comparison. The
independent variable in this experiment is differential privacy,
while the dependent variables are the performance metrics, such
as accuracy, precision, recall, and F1 score. The paper also
discusses the ethical implications of differential privacy in AI and
its significance for the future of data privacy and protection.
Keywords-Differential Privacy; Machine Learning; Noise
Injection; Performance Metrics; Ethical Considerations

There are different kind of options for liver cancer treatment. This analysis focuses one amoung the formost necessary fields of image processing and image segmentation. The treatment choices involve surgery, interventional therapy, radiation, and therefore the combination of those techniques. All of them may be expedited with package tools that create the liver analysis additional precise and fewer enthusiastic about the operator. In this research focus on the special attention to increase the efficiency of the projected algorithms in additionally to their accuracy. According to clinical outcomes a software package workflow is beneficial once the computation time between beginning a perform and visualizing its result doesn't exceed half minute. The algorithms bestowed during this research were designed to resolve advanced clinical issues with efficiency. The author developed an innovative human machine interface technique for machine driven liver lesion detection in particular ...

INTRODUCTION: Malaria, a persistent global health threat caused by Plasmodium parasites, necessitates rapid and accurate identification for effective treatment and containment. This study investigates the utilization of convolutional neural networks (CNNs) to enhance the precision and speed of malaria detection through the classification of cell images infected with malaria.
OBJECTIVES: The primary objective of this research is to explore the effectiveness of CNNs in accurately classifying malaria-infected cell images. By employing various deep learning models, including ResNet50, AlexNet, Inception V3, VGG19, VGG16, and MobileNetV2, the study aims to assess the performance of each model and identify their strengths and weaknesses in malaria diagnosis.
METHODS: A balanced dataset comprising approximately 8,000 enhanced images of blood cells, evenly distributed between infected and uninfected classes, was utilized for model training and evaluation. Performance evaluation metrics such as precision, recall, F1-score, and accuracy were employed to assess the efficacy of each CNN model in malaria classification.
RESULTS: The results demonstrate high accuracy across all models, with AlexNet and VGG19 exhibiting the highest levels of accuracy. However, the selection of a model should consider specific application requirements and constraints, as each model presents unique trade-offs between computational efficiency and performance.
CONCLUSION: This study contributes to the burgeoning field of deep learning in healthcare, particularly in utilizing medical imaging for disease diagnosis. The findings underscore the considerable potential of CNNs in enhancing malaria diagnosis. Future research directions may involve further model optimization, exploration of larger and more diverse datasets, and the integration of CNNs into practical diagnostic tools for real-world deployment.

Optical coherence tomography (OCT) technology enables experts to analyze coronary lesions from high-resolution intravascular images. Studies have shown a relationship between vascular bifurcation and a higher occurrence of wall thickening and lesions in these areas. Some level of automation could benefit experts since the visual analysis of pullback frames is a laborious and time-consuming task. Although convolutional neural networks (CNNs) have shown promising results in classifying medical images, in this paper, we found no studies using CNNs in IVOCT images to classify the vascular bifurcation. In this paper, we evaluated four different CNN architectures in the bifurcation classification task trained with the IVOCT images from nine pullbacks from nine different patients. We used data augmentation to balance the dataset, due to the small number of bifurcation-labeled frames, and also applied transfer learning methods to incorporate the knowledge from a lumen segmentation task into some of the evaluated networks. Our classification outperforms other works in this literature, presenting AUC = 99.72%, obtained by a CNN with transferred knowledge.

Ensemble learning combines multiple base models to enhance predictive performance and generalize better on unseen data. In the context of Computed Tomography (CT) image processing, ensemble techniques often leverage diverse machine learning or deep learning architectures to achieve the best results. Ensemble machine learning and deep learning techniques have revolutionized the field of CT image processing by significantly improving accuracy, robustness, and efficiency in various medical imaging tasks. These methods have been instrumental in tasks such as image reconstruction, segmentation, classification, and disease diagnosis. The ensemble models can be divided into those based on decision fusion strategies, bagging, boosting, stacking, negative correlation, explicit/implicit ensembles, homogeneous/heterogeneous ensembles, and explicit/implicit ensembles. In comparison to shallow or traditional, machine learning models and deep learning architectures are currently performing better. Also, a brief discussion of the various ensemble models used in CT images is provided. We wrap up this work by outlining a few possible avenues for further investigation.

Introduction: Gynecological cancers pose a significant threat to women worldwide, especially those in resource-limited settings. Human analysis of images remains the primary method of diagnosis, but it can be inconsistent and inaccurate. Deep learning (DL) can potentially enhance image-based diagnosis by providing objective and accurate results. This systematic review and meta-analysis aimed to summarize the recent advances of deep learning (DL) techniques for gynecological cancer diagnosis using various images and explore their future implications. The study followed the PRISMA-2 guidelines, and the protocol was registered in PROSPERO. Five databases were searched for articles published from January 2018 to December 2022. Articles that focused on five types of gynecological cancer and used DL for diagnosis were selected. Two reviewers assessed the articles for eligibility and quality using the QUADAS-2 tool. Data was extracted from each study, and the performance of DL techniques for gynecological cancer classification was estimated by pooling and transforming sensitivity and specificity values using a random-effects model. The review included 48 studies, and the meta-analysis included 24 studies. The studies used different images and models to diagnose different gynecological cancers. The most popular models were ResNet, VGGNet, and UNet. DL algorithms showed more sensitivity but less specificity compared to machine learning (ML) methods. The AUC of the summary receiver operating characteristic plot was higher for DL algorithms than for ML methods. Of the 48 studies included, 41 were at low risk of bias. This review highlights the potential of DL in improving the screening and diagnosis of gynecological cancer, particularly in resource-limited settings.