International Journal of Imaging Systems and Technology最新文献

{"title":"Integrating VGG 19 U-Net for Breast Thermogram Segmentation and Hybrid Enhancement With Optimized Classifier Selection: A Novel Approach to Breast Cancer Diagnosis","authors":"A. Arul Edwin Raj,&nbsp;Nabihah Binti Ahmad,&nbsp;S. Ananiah Durai,&nbsp;R. Renugadevi","doi":"10.1002/ima.23210","DOIUrl":"https://doi.org/10.1002/ima.23210","url":null,"abstract":"<div>\u0000 \u0000 <p>Early diagnosis of breast cancer is essential for improving patient survival rates and reducing treatment costs. Despite breast thermogram images having high quality, doctors in developing countries often struggle with early diagnosis due to difficulties in interpreting subtle details. Implementing a Computer-Aided Diagnosis (CAD) system can assist doctors in accurately analyzing these details. This article presents an innovative approach to breast cancer diagnosis using thermal images. The proposed method enhances the quality and clarity of relevant features while preserving sharp and curved edges through U-Net-based segmentation for automatic selection of the ROI, advanced hybrid image enhancement techniques, and a machine learning classifier. Subjective analysis compares the processed images with five conventional enhancement techniques, demonstrating the efficiency of the proposed method. The quantitative analysis further validates the effectiveness of the proposed method against five conventional methods using four quality measures. The proposed method achieves superior performance with PSNR of 15.27 for normal and 14.31 for malignant images, AMBE of 6.594 for normal and 7.46 for malignant images, SSIM of 0.829 for normal and 0.80 for malignant images, and DSSIM of 0.084 for normal and 0.14 for malignant images. The classification phase evaluates four classifiers using 13 features from three categories. The Random Forest (RF) classifier with Discrete Wavelet Transform (DWT) based features initially outperformed other classifier features but had limited performance, with accuracy, sensitivity and specificity of 81.8%, 88.8%, and 91%, respectively. To improve this, three categories of features were normalized and converted into two principal components using Principal Component Analysis (PCA) to train the RF classifier, which then showed superior performance with 97.7% accuracy, 96.5% sensitivity, and 98.2% specificity. The dataset utilized in this article is obtained from the Indira Gandhi Centre for Atomic Research (IGCAR), Kalpakkam, India. The entire proposed model is implemented in a Jupyter notebook.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DAG-Net: Dual-Branch Attention-Guided Network for Multi-Scale Information Fusion in Lung Nodule Segmentation","authors":"Bojie Zhang,&nbsp;Hongqing Zhu,&nbsp;Ziying Wang,&nbsp;Lan Luo,&nbsp;Yang Yu","doi":"10.1002/ima.23209","DOIUrl":"https://doi.org/10.1002/ima.23209","url":null,"abstract":"<div>\u0000 \u0000 <p>The development of deep learning has played an increasingly crucial role in assisting medical diagnoses. Lung cancer, as a major disease threatening human health, benefits significantly from the use of auxiliary medical systems to assist in segmenting pulmonary nodules. This approach effectively enhances both the accuracy and speed of diagnosis for physicians, thereby reducing the risk of patient mortality. However, pulmonary nodules are characterized by irregular shapes and a wide range of diameter variations. They often reside amidst blood vessels and various tissue structures, posing significant challenges in designing an automated system for lung nodule segmentation. To address this, we have developed a three-dimensional dual-branch attention-guided network (DAG-Net) for multi-scale information fusion, aimed at segmenting lung nodules of various types and sizes. First, a dual-branch encoding structure is employed to provide the network with prior knowledge about nodule texture information, which aids the network in better identifying different types of lung nodules. Next, we designed a structure to extract global information, which enhances the network's ability to localize lung nodules of different sizes by fusing information from multiple resolutions. Following that, we fused multi-scale information in a parallel structure and used attention mechanisms to guide the network in suppressing the influence of non-nodule regions. Finally, we employed an attention-based structure to guide the network in achieving more accurate segmentation by progressively using high-level semantic information at each layer. Our proposed network achieved a DSC value of 85.6% on the LUNA16 dataset, outperforming state-of-the-art methods, demonstrating the effectiveness of the network.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Embedded System-Based Malaria Detection From Blood Smear Images Using Lightweight Deep Learning Model","authors":"Abdus Salam,&nbsp;S. M. Nahid Hasan,&nbsp;Md. Jawadul Karim,&nbsp;Shamim Anower,&nbsp;Md Nahiduzzaman,&nbsp;Muhammad E. H. Chowdhury,&nbsp;M. Murugappan","doi":"10.1002/ima.23205","DOIUrl":"https://doi.org/10.1002/ima.23205","url":null,"abstract":"<div>\u0000 \u0000 <p>The disease of malaria, transmitted by female Anopheles mosquitoes, is highly contagious, resulting in numerous deaths across various regions. Microscopic examination of blood cells remains one of the most accurate methods for malaria diagnosis, but it is time-consuming and can produce inaccurate results occasionally. Due to machine learning and deep learning advances in medical diagnosis, improved diagnostic accuracy can now be achieved while costs can be reduced compared to conventional microscopy methods. This work utilizes an open-source dataset with 26 161 blood smear images in RGB for malaria detection. Our preprocessing resized the original dimensions of the images into 64 × 64 due to the limitations in computational complexity in developing embedded systems-based malaria detection. We present a novel embedded system approach using 119 154 trainable parameters in a lightweight 17-layer SqueezeNet model for the automatic detection of malaria. Incredibly, the model is only 1.72 MB in size. An evaluation of the model's performance on the original NIH malaria dataset shows that it has exceptional accuracy, precision, recall, and F1 scores of 96.37%, 95.67%, 97.21%, and 96.44%, respectively. Based on a modified dataset, the results improved further to 99.71% across all metrics. Compared to current deep learning models, our model significantly outperforms them for malaria detection, making it ideal for embedded systems. This model has also been rigorously tested on the Jetson Nano B01 edge device, demonstrating a rapid single image prediction time of only 0.24 s. The fusion of deep learning with embedded systems makes this research a crucial step toward improving malaria diagnosis. In resource-constrained settings, the model's lightweight architecture and accuracy enhancements hold great promise for addressing the critical challenge of malaria detection.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142555477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing Leukocyte Classification: A Cutting-Edge Deep Learning Approach for AI-Driven Clinical Diagnosis","authors":"Ahmadsaidulu Shaik,&nbsp;Abhishek Tiwari,&nbsp;Balachakravarthy Neelapu,&nbsp;Puneet Kumar Jain,&nbsp;Earu Banoth","doi":"10.1002/ima.23204","DOIUrl":"https://doi.org/10.1002/ima.23204","url":null,"abstract":"<div>\u0000 \u0000 <p>White blood cells (WBCs) are crucial components of the immune system, responsible for detecting and eliminating pathogens. Accurate detection and classification of WBCs are essential for various clinical diagnostics. This study aims to develop an AI framework for detecting and classifying WBCs from microscopic images using a customized YOLOv5 model with three key modifications. Firstly, the C3 module in YOLOv5's backbone is replaced with the innovative C3TR structure to enhance feature extraction and reduce background noise. Secondly, the BiFPN is integrated into the neck to improve feature localization and discrimination. Thirdly, an additional layer in the head enhances detection of small WBCs. Experiments on the BCCD dataset, comprising 352 microscopic blood smear images with leukocytes, demonstrated the framework's superiority over state-of-the-art methods, achieving 99.4% accuracy. Furthermore, the model exhibits computational efficiency, operating over five times faster than existing YOLO models. These findings underscore the framework's promise in medical diagnostics, showcasing deep learning's supremacy in automated cell classification.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142541033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fast-MedNeXt: Accelerating the MedNeXt Architecture to Improve Brain Tumour Segmentation Efficiency","authors":"Bin Liu,&nbsp;Bing Li,&nbsp;Yaojing Chen,&nbsp;Victor Sreeram,&nbsp;Shuofeng Li","doi":"10.1002/ima.23196","DOIUrl":"https://doi.org/10.1002/ima.23196","url":null,"abstract":"<div>\u0000 \u0000 <p>With the rapid development of medical imaging technology, 3D image segmentation technology has gradually become a mainstream method, especially in brain tumour detection and diagnosis showing its unique advantages. The technique makes full use of 3D spatial information to locate and analyze tumours more accurately, thus playing an important role in improving diagnostic accuracy, optimising treatment planning and promoting research. However, it also suffers from significant computational expenditure and delayed processing pace. In this paper, we propose an innovative optimisation scheme to address this problem. We thoroughly investigate the MedNeXt network and propose Fast-MedNeXt, which aims to increase the processing speed while maintaining accuracy. First, we introduce the partial convolution (PConv) technique, which replaces the deep convolutional layers in the network. This improvement effectively reduces computation and memory requirements while maintaining efficient feature extraction. Second, based on PConv, we propose PConv-Down and PConv-Up modules, which are applied to the up-sampling and down-sampling modules to further optimise the network structure and improve efficiency. To confirm the efficacy of the approach, we carried out a sequence of tests in the multimodal brain tumour segmentation challenge 2021 (BraTS2021). By comparing with the MedNeXt series network, the Fast-MedNeXt reduced the latency by 22.1%, 20.5%, 15.8%, and 11.4% respectively, while the average accuracy also increased by 0.475% and 0.2% respectively. These significant performance improvements demonstrate the effectiveness of Fast-MedNeXt in 3D medical image segmentation tasks and provide a new and more efficient solution for the field.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142525459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Dictionary Learning Algorithm Based on Prior Knowledge for fMRI Data Analysis","authors":"Fangmin Sheng,&nbsp;Yuhu Shi,&nbsp;Lei Wang,&nbsp;Ying Li,&nbsp;Hua Zhang,&nbsp;Weiming Zeng","doi":"10.1002/ima.23195","DOIUrl":"https://doi.org/10.1002/ima.23195","url":null,"abstract":"<div>\u0000 \u0000 <p>Task-based functional magnetic resonance imaging (fMRI) has been widely utilized for brain activation detection and functional network analysis. In recent years, the K-singular value decomposition (K-SVD) algorithm has gained increasing attention in the research of fMRI data analysis methods. In this study, we propose a novel temporal feature region-growing constrained K-SVD algorithm that incorporates task-based fMRI temporal prior knowledge and utilizes a region-growing algorithm to infer potential activation locations. The algorithm incorporates temporal and spatial constraints to enhance the detection of brain activation. Specifically, this paper improves the three stages of the traditional K-SVD algorithm. First, in the dictionary initialization stage, the automatic target generation process with an independent component analysis algorithm is utilized in conjunction with prior knowledge to enhance the accuracy of initialization. Second, in the sparse coding stage, the region-growing algorithm is employed to infer potential activation locations based on temporal prior knowledge, thereby imposing spatial constraints to limit the extent of activation regions. Finally, in the dictionary learning stage, soft constraints and low correlation constraints are applied to reinforce the consistency with prior knowledge and enhance the robustness of learning for task-related atoms. The proposed method was validated on simulated and real fMRI data, showing superior performance in detecting brain activation compared with traditional methods. The results indicate that the algorithm accurately identifies activated brain regions, providing an effective approach for studying brain function in clinical applications.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142525460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated, Reproducible, and Reconfigurable Human Head Phantom for Experimental Testing of Microwave Systems for Stroke Classification","authors":"Tomas Pokorny,&nbsp;Tomas Drizdal,&nbsp;Marek Novak,&nbsp;Jan Vrba","doi":"10.1002/ima.23200","DOIUrl":"https://doi.org/10.1002/ima.23200","url":null,"abstract":"<p>Microwave systems for prehospital stroke classification are currently being developed. In the future, these systems should enable rapid recognition of the type of stroke, shorten the time to start treatment, and thus significantly improve the prognosis of patients. In this study, we realized a realistic and reconfigurable 3D human head phantom for the development, testing, and validation of these newly developed diagnostic methods. The phantom enables automated and reproducible measurements for different positions of the stroke model. The stroke model itself is also interchangeable, so measurements can be made for different types, sizes, and shapes of strokes. Furthermore, an extensive series of measurements was performed at a frequency of 1 GHz, and an SVM classification algorithm was deployed, which successfully identified ischemic stroke in 80% of the corresponding measured data. If similar classification accuracy could be achieved in patients, it would lead to a dramatic reduction in the consequences of strokes.</p>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ima.23200","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142525317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Image Segmentation Evaluation With the Dice Index: Methodological Issues","authors":"Mohamed L. Seghier","doi":"10.1002/ima.23203","DOIUrl":"https://doi.org/10.1002/ima.23203","url":null,"abstract":"&lt;p&gt;In this editorial, I call for more clarity and transparency when calculating and reporting the Dice index to evaluate the performance of biomedical image segmentation methods. Despite many existing guidelines for best practices for assessing and reporting the performance of automated methods [&lt;span&gt;1, 2&lt;/span&gt;], there is still a lack of clarity on why and how performance metrics were selected and assessed. I have seen articles where, for instance, Dice indices (i) were erroneously reported as smaller than intersection-over-union values, (ii) oddly increased from moderate to excellent values after including images with no actual positive instances, (iii) were drastically affected by image cropping or zero-padding, (iv) did not make sense in the light of the reported precision and sensitivity values, (v) showed opposite trends to F1 scores, (vi) were wrongly interpreted as accuracy measures, (vii) used as a measure of detection success rather than segmentation success, (viii) were used to rank methods that varied considerably in terms of the number of false positives and false negatives, (ix) were averaged across segmented structures of interest with highly variable sizes, and (x) were directly compared to other Dice indices from previous studies despite being tested on completely different datasets. It is important to remind our authors what one can (or cannot) do with the Dice index for biomedical image segmentation.&lt;/p&gt;&lt;p&gt;As the Dice index is one of the preferred metrics to assess segmentation performance and is widely used in many challenges and benchmarks to rank models [&lt;span&gt;3&lt;/span&gt;], it is paramount that authors calculate it correctly and report it clearly and transparently. Below, I discuss conceptual and methodological issues about the Dice index before providing a list of 10 simple rules for optimal and transparent reporting of the Dice index. By improving transparency and clarity, I believe readers will draw the right conclusions about methods evaluation, which will ultimately help improve interpretability and replicability in biomedical data processing.&lt;/p&gt;&lt;p&gt;The discussion below applies to any image segmentation problem, imaging modality, 2D (slices) or 3D (volumes) inputs, and segmentation tasks (e.g., segmenting abnormalities or typical structures and organs). Examples will be taken from the automated segmentation of stroke lesions in brain scans.&lt;/p&gt;&lt;p&gt;Put another way, the Dice index codes how the positives declared by an automated method match the actual positives of the ground truth. We have &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mtext&gt;Dice&lt;/mtext&gt;\u0000 &lt;mfenced&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;A&lt;/mi&gt;\u0000 &lt;mo&gt;,&lt;/mo&gt;\u0000 &lt;mi&gt;A&lt;/mi&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;/mfenced&gt;\u0000 &lt;mo&gt;=&lt;/mo&gt;\u0000 &lt;mn&gt;1&lt;/mn&gt;\u0000 &lt;mo&gt;","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ima.23203","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142525312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal Connectivity-Guided Glioma Segmentation From Magnetic Resonance Images via Cascaded 3D Residual U-Net","authors":"Xiaoyan Sun,&nbsp;Chuhan Hu,&nbsp;Wenhan He,&nbsp;Zhenming Yuan,&nbsp;Jian Zhang","doi":"10.1002/ima.23206","DOIUrl":"https://doi.org/10.1002/ima.23206","url":null,"abstract":"<div>\u0000 \u0000 <p>Glioma is a type of brain tumor with a high mortality rate. Magnetic resonance imaging (MRI) is commonly used for examination, and the accurate segmentation of tumor regions from MR images is essential to computer-aided diagnosis. However, due to the intrinsic heterogeneity of brain glioma, precise segmentation is very challenging, especially for tumor subregions. This article proposed a two-stage cascaded method for brain tumor segmentation that considers the hierarchical structure of the target tumor subregions. The first stage aims to identify the whole tumor (WT) from the background area; and the second stage aims to achieve fine-grained segmentation of the subregions, including enhanced tumor (ET) region and tumor core (TC) region. Both stages apply a deep neural network structure combining modified 3D U-Net with a residual connection scheme to tumor region and subregion segmentation. Moreover, in the training phase, the 3D masks generation of subregions with potential incomplete connectivity are guided by the completely connected regions. Experiments were performed to evaluate the performance of the methods on both area and boundary accuracy. The average dice score of the WT, TC, and ET regions on BraTS 2020 dataset is 0.9168, 0.0.8992, 0.8489, and the Hausdorff distance is 6.021, 9.203, 12.171, respectively. The proposed method outperforms current works, especially in segmenting fine-grained tumor subregions.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142525215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Recognition of Diabetic Retinopathy Grades Based on Data Augmentation and Attention Mechanisms","authors":"Xueri Li,&nbsp;Li Wen,&nbsp;Fanyu Du,&nbsp;Lei Yang,&nbsp;Jianfang Wu","doi":"10.1002/ima.23201","DOIUrl":"https://doi.org/10.1002/ima.23201","url":null,"abstract":"<div>\u0000 \u0000 <p>Diabetic retinopathy is a complication of diabetes and one of the leading causes of vision loss. Early detection and treatment are essential to prevent vision loss. Deep learning has been making great strides in the field of medical image processing and can be used as an aid for medical practitioners. However, unbalanced datasets, sparse focal areas, small differences between adjacent disease grades, and varied manifestations of the same grade disease challenge deep learning model training. Generalization performance and robustness are inadequate. To address the problem of unbalanced sample numbers between classes in the dataset, this work proposes using VQ-VAE for reconstructing affine transformed images to enrich and balance the dataset. Test results show the model's average reconstruction error is 0.0001, and the mean structural similarity between reconstructed and original images is 0.967. This proves reconstructed images differ from originals yet belong to the same category, expanding and diversifying the dataset. Addressing the issues of focal area sparsity and disease grade disparity, this work utilizes ResNeXt50 as the backbone network and constructs diverse attention networks by modifying the network structure and embedding different attention modules. Experiments demonstrate that the convolutional attention network outperforms ResNeXt50 in terms of Precision, Sensitivity, Specificity, F1 Score, Quadratic Weighted Kappa Coefficient, Accuracy, and robustness against Salt and Pepper noise, Gaussian noise, and gradient perturbation. Finally, the heat maps of each model recognizing the fundus image were plotted using the Grad-CAM method. The heat maps show that the attentional network is more effective than the non-attentional network ResNeXt50 at attending to the fundus image.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"34 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142525053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}