International Journal of Imaging Systems and Technology最新文献

{"title":"Rectal Cancer Segmentation: A Methodical Approach for Generalizable Deep Learning in a Multi-Center Setting","authors":"Jovana Panic,&nbsp;Arianna Defeudis,&nbsp;Lorenzo Vassallo,&nbsp;Stefano Cirillo,&nbsp;Marco Gatti,&nbsp;Roberto Sghedoni,&nbsp;Michele Avanzo,&nbsp;Angelo Vanzulli,&nbsp;Luca Sorrentino,&nbsp;Luca Boldrini,&nbsp;Huong Elena Tran,&nbsp;Giuditta Chiloiro,&nbsp;Giuseppe Roberto D'Agostino,&nbsp;Enrico Menghi,&nbsp;Roberta Fusco,&nbsp;Antonella Petrillo,&nbsp;Vincenza Granata,&nbsp;Martina Mori,&nbsp;Claudio Fiorino,&nbsp;Barbara Alicja Jereczek-Fossa,&nbsp;Marianna Alessandra Gerardi,&nbsp;Serena Dell'Aversana,&nbsp;Antonio Esposito,&nbsp;Daniele Regge,&nbsp;Samanta Rosati,&nbsp;Gabriella Balestra,&nbsp;Valentina Giannini","doi":"10.1002/ima.70076","DOIUrl":"https://doi.org/10.1002/ima.70076","url":null,"abstract":"<p>Noninvasive Artificial Intelligence (AI) techniques have shown great potential in assisting clinicians through the analysis of medical images. However, significant challenges remain in integrating these systems into clinical practice due to the variability of medical data across multi-center databases and the lack of clear implementation guidelines. These issues hinder the ability to achieve robust, reproducible, and statistically significant results. This study thoroughly analyzes several decision-making steps involved in managing a multi-center database and developing AI-based segmentation models, using rectal cancer as a case study. A dataset of 1212 Magnetic Resonance Images (MRIs) from 14 centers was used. The study examined the impact of different image normalization techniques, network hyperparameters, and training set compositions (in terms of size and construction strategies). The findings emphasize the critical role of image normalization in reducing variability and improving performance. Additionally, the study underscores the importance of carefully selecting network structures and loss functions based on the desired outcomes. The potential of clustering approaches to identify representative training subsets, even with limited data sizes, was also evaluated. While no definitive preprocessing pipeline was identified, several networks developed during the study produced promising results on the external validation set. The insights and methodologies presented may help raise awareness and promote more informed decisions when implementing AI systems in medical imaging.</p>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"35 3","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ima.70076","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143762100","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":"Modal Feature Supplementation Enhances Brain Tumor Segmentation","authors":"Kaiyan Zhu,&nbsp;Weiye Cao,&nbsp;Jianhao Xu,&nbsp;Tong Liu,&nbsp;Yue Liu,&nbsp;Weibo Song","doi":"10.1002/ima.70079","DOIUrl":"https://doi.org/10.1002/ima.70079","url":null,"abstract":"<div>\u0000 \u0000 <p>For patients with brain tumors, effectively utilizing the complementary information between multimodal medical images is crucial for accurate lesion segmentation. However, effectively utilizing the complementary features across different modalities remains a challenging task. To address these challenges, we propose a modal feature supplement network (MFSNet), which extracts modality features simultaneously using both a main and an auxiliary network. During this process, the auxiliary network supplements the modality features of the main network, enabling accurate brain tumor segmentation. We also design a modal feature enhancement module (MFEM), a cross-layer feature fusion module (CFFM), and an edge feature supplement module (EFSM). MFEM enhances the network performance by fusing the modality features from the main and auxiliary networks. CFFM supplements additional contextual information by fusing features from adjacent encoding layers at different scales, which are then passed into the corresponding decoding layers. This aids the network in preserving more details during upsampling. EFSM improves network performance by using deformable convolution to extract challenging boundary lesion features, which are then used to supplement the final output of the decoding layer. We evaluated MFSNet on the BraTS2018 and BraTS2021 datasets. The Dice scores for the whole tumor, tumor core, and enhancing tumor regions were 90.86%, 90.59%, 84.72%, and 92.28%, 92.47%, 86.07%, respectively. This validates the accuracy of MFSNet in brain tumor segmentation, demonstrating its superiority over other networks of similar type.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"35 3","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143770075","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":"Interactive CNN and Transformer-Based Cross-Attention Fusion Network for Medical Image Classification","authors":"Shu Cai,&nbsp;Qiude Zhang,&nbsp;Shanshan Wang,&nbsp;Junjie Hu,&nbsp;Liang Zeng,&nbsp;Kaiyan Li","doi":"10.1002/ima.70077","DOIUrl":"https://doi.org/10.1002/ima.70077","url":null,"abstract":"<div>\u0000 \u0000 <p>Medical images typically contain complex structures and abundant detail, exhibiting variations in texture, contrast, and noise across different imaging modalities. Different types of images contain both local and global features with varying expressions and importance, making accurate classification highly challenging. Convolutional neural network (CNN)-based approaches are limited by the size of the convolutional kernel, which restricts their ability to capture global contextual information effectively. In addition, while transformer-based models can compensate for the limitations of convolutional neural networks by modeling long-range dependencies, they are difficult to extract fine-grained local features from images. To address these issues, we propose a novel architecture, the Interactive CNN and Transformer for Cross Attention Fusion Network (IFC-Net). This model leverages the strengths of CNNs for efficient local feature extraction and transformers for capturing global dependencies, enabling it to preserve local features and global contextual relationships. Additionally, we introduce a cross-attention fusion module that adaptively adjusts the feature fusion strategy, facilitating efficient integration of local and global features and enabling dynamic information exchange between the CNN and transformer components. Experimental results on four benchmark datasets, ISIC2018, COVID-19, and liver cirrhosis (line array, convex array), demonstrate that the proposed model achieves superior classification performance, outperforming both CNN and transformer-only architectures.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"35 3","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143749366","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":"Multiscale Three-Dimensional Features and Spatial Feature Evaluation of Human Pulmonary Tuberculosis","authors":"Xiaojiang Zhao,&nbsp;Yun Ding,&nbsp;Bowen Zhang,&nbsp;Huaye Wei,&nbsp;Ting Li,&nbsp;Xin Li","doi":"10.1002/ima.70069","DOIUrl":"https://doi.org/10.1002/ima.70069","url":null,"abstract":"<p>The low detection rate of <i>Mycobacterium tuberculosis</i> in clinical practice leads to a high rate of missed diagnoses for pulmonary tuberculosis (PTB). This study aimed to assess the imaging and pathological characteristics of PTB lesions from different multiple dimensions, with a focus on evaluating their three-dimensional(3D) and spatial features. This study employed multiple methods to evaluate the three-dimensional characteristics of PTB. CT was used to visually assess the density and spatial positioning of PTB lesions, and acid-fast staining was used to evaluate the two-dimensional histological features of PTB. Using fMOST technology, a total of 2399 consecutive single-cell resolution images of human PTB tissue were obtained. These images were subsequently reconstructed in 3D to evaluate the pathological characteristics of PTB in three dimensions. The 3D imaging precisely extracted the distribution of different CT values (HU values) and accurately obtained the spatial location information of the lesions, achieving precise localization. Using fMOST technology, we clearly identified the microscopic structures within both normal lung tissue and PTB lesions, revealing the loose structure, continuous alveolar septa, and clearly visible blood vessels of normal lung tissue. In contrast, typical characteristics of PTB lesions included the destruction of normal lung structure, tissue proliferation, necrosis, and inflammatory infiltration, with a significant increase in overall density. 3D observations of the necrotic areas showed high tissue density but low cellular density, primarily composed of necrotic tissue, consistent with the histological characteristics commonly seen in PTB lesions. This enhanced our understanding of the spatial distribution of PTB lesions. The 3D visualization of imaging and pathology enables a more comprehensive identification of the pathological features of PTB lesions. The multiscale model based on the fMOST system provides more detailed structural information and displays the spatial distribution of lesions more accurately. This is particularly beneficial in the evaluation of complex lesions, demonstrating its potential for optimizing diagnostic methods and supporting clinical decision-making.</p>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"35 3","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ima.70069","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726857","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":"An Explainable Graph Neural Network Approach for Patch Selection Using a New Patch Score Metric in Breast Cancer Detection","authors":"Eranjoli Nalupurakkal Subhija,&nbsp;Vaninirappuputhenpurayil Gopalan Reju","doi":"10.1002/ima.70078","DOIUrl":"https://doi.org/10.1002/ima.70078","url":null,"abstract":"<div>\u0000 \u0000 <p>This study aims to develop an algorithm for selecting the most informative and diverse patches from breast histopathology images while excluding irrelevant areas to enhance cancer detection. A key contribution of the method is the creation of a new metric called patch score that integrates SHAP values with Haralick features, improving both explainability and diagnostic accuracy. The algorithm begins by calculating Haralick features and measuring cosine similarity between patches to construct a graph, which is then used to train a graph neural network (GNN). To assess each patch's contribution to the analysis, we employ a SHAP explainer on the GNN model. The SHAP values and the features from each patch are then used to calculate a score called the patch score, which determines the importance of each patch. Additionally, to incorporate diversity in the selected patches, all patches are clustered based on local binary patterns, and the patch with the highest patch score from each cluster is selected to obtain the final patches for image classification. Features extracted from these patches using a ResNeXt 50 model, fused with 3-norm pooling, are used to classify the images as benign or malignant. The proposed framework was evaluated on the BreakHis dataset and demonstrated superior accuracy and precision compared to existing methods. By integrating both explainability and diversity into patch selection, the algorithm delivers a robust, interpretable model, offering dependable diagnostic support for pathologists.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"35 3","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726855","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":"CS U-NET: A Medical Image Segmentation Method Integrating Spatial and Contextual Attention Mechanisms Based on U-NET","authors":"Zhang Fanyang,&nbsp;Zhang Fan","doi":"10.1002/ima.70072","DOIUrl":"https://doi.org/10.1002/ima.70072","url":null,"abstract":"<div>\u0000 \u0000 <p>Medical image segmentation is a crucial process in medical image analysis, with convolutional neural network (CNN)-based methods achieving notable success in recent years. Among these, U-Net has gained widespread use due to its simple yet effective architecture. However, CNNs still struggle to capture global, long-range semantic information. To address this limitation, we present CS U-NET, a novel method built upon Swin-U-Net, which integrates spatial and contextual attention mechanisms. This hybrid approach combines the strengths of both transformers and U-Net architectures to enhance segmentation performance. In this framework, tokenized image patches are processed through a transformer-based U-shaped encoder-decoder, enabling the learning of both local and global semantic features via skip connections. Our method achieves a Dice Similarity Coefficient of 78.64% and a 95% Hausdorff distance of 21.25 on the Synapse multiorgan segmentation dataset, outperforming Trans-U-Net and other state-of-the-art U-Net variants by 4% and 6%, respectively. The experimental results highlight the significant improvements in prediction accuracy and edge detail preservation provided by our approach.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"35 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143707268","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":"Foreground Background Difference Knowledge-Based Small Sample Target Segmentation for Image-Guided Radiation Therapy","authors":"Yuanzhi Cheng,&nbsp;Pengfei Zhang,&nbsp;Chang Liu,&nbsp;Changyong Guo,&nbsp;Shinichi Tamura","doi":"10.1002/ima.70075","DOIUrl":"https://doi.org/10.1002/ima.70075","url":null,"abstract":"<p>The aim of this paper is to exploit a small sample (data scarcity) target segmentation technique for image-guided radiation therapy. The technique is grounded on a prototype-based approach—widely used small sample segmentation method. In this paper, we propose a foreground–background difference knowledge learning framework to perform the small sample target segmentation task. Its main differences from the traditional prototype-based approaches and novel contributions may be enumerated in two aspects: (1) A subdivision strategy to generate multiple foreground–background prototypes for each class in the support images, and the generated prototype is used to build a collection of query foreground and background prototypes. (2) A cross-prototype attention module to learn the correlation and difference knowledge of inter-class prototypes and transfer the knowledge to the query prototype for iterative updates. The main advantage of our framework is that: (1) the intra-class prototype set can comprehensively reflect the class features, avoiding the high computational complexity caused by dense matching; and (2) knowledge of inter-class differences provides comprehensive foreground–background segmentation information, greatly supporting accurate segmentation of the query set. In the 5-shot SegRap dataset experiment, the proposed model achieved Dice coefficients of 82.23% in the same-domain setting and 81.01% in the cross-domain setting. Similarly, in the 5-shot HECKTOR2022 dataset experiment, it achieved 83.59% in the same-domain setting and 81.48% in the cross-domain setting. For the 5-shot BTCV and CHAOS datasets, the model attained Dice coefficients of 79.00% and 79.70%, respectively. These results demonstrate the model's accuracy, efficiency, and generalization. This study presents a significant advancement in medical image segmentation by introducing a prototype-based model that effectively addresses data scarcity. By leveraging intra- and inter-class attention mechanisms, the model ensures robust generalization and reliable performance across datasets, paving the way for efficient and precise clinical applications with minimal reliance on large annotated datasets.</p>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"35 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698779","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":"Bottom Double Branch Path Networks With Confidence Calibration for Intracranial Aneurysms Detection in 3D MRA","authors":"Shuhuinan Zheng,&nbsp;Qichang Fu,&nbsp;Wei Jin,&nbsp;Xiaomei Xu,&nbsp;Jianqing Wang,&nbsp;Xiaobo Lai,&nbsp;Lilin Guo","doi":"10.1002/ima.70071","DOIUrl":"https://doi.org/10.1002/ima.70071","url":null,"abstract":"<div>\u0000 \u0000 <p>Intracranial aneurysms (IAs) are characterized by abnormal dilation of the brain blood vessel wall, the rupture of which often leads to subarachnoid hemorrhage with a high mortality rate. Current detections rely heavily on radiologists' interpretation of magnetic resonance angiography (MRA) images, but manual identification is time-consuming and laborious. Therefore, it is urgent to carry out automatic detection tools for IAs, and various intelligent models have been developed in recent years. However, the size of IAs is relatively small compared with the high voxel resolution MRA images, and thus the data imbalance leads to a high false positive (FP) rate. To address these challenges, we have proposed an innovative 3D voxel detection framework based on Feature Pyramid Network (FPN) architecture, which is called bottom double branch path network with confidence calibration (BCOC for short). BCOC shows better effects on small objects for preserving diversities of feature maps and also creates efficient feature extractors by reducing the number of channels per layer, making it particularly advantageous for handling large three-dimensional resolutions. Additionally, optimal transport (OT) has been applied for matching the detection and ground truth bounding boxes during the post-process phase to refine bounding box positions, thereby further improving the detection performance. Moreover, the confidence score of model output is calibrated via calibration loss during training to make correct detections with higher confidence and wrong detections with lower confidence, which can reduce the FP rate. Our proposed model achieves mean average precision (AP) of 0.8186 and 0.8533, sensitivity of 93.91% and 98.43%, FPs/case of 0.1332 and 0.0541 on two public MRA datasets including cases with IAs collected from different hospitals, respectively, outperforming other state-of-the-art methods. The results show that BCOC is a promising detection method for IAs automatic recognition.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"35 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689516","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":"IMDF-Net: Iterative U-Net With Multi-Kernel Dilated Convolution and Fusion Modules for Enhanced Retinal Vessel Segmentation","authors":"Jiale Deng,&nbsp;Lina Yang,&nbsp;Yuwen Lin","doi":"10.1002/ima.70073","DOIUrl":"https://doi.org/10.1002/ima.70073","url":null,"abstract":"<div>\u0000 \u0000 <p>In the early diagnosis of diabetic retinopathy, the morphological properties of blood vessels serve as an important reference for doctors to assess a patient's condition, facilitating scientific diagnostic and therapeutic interventions. However, vascular deformations, proliferation, and rupture caused by retinal diseases are often difficult to detect in the early stages. The assessment of retinal vessel morphology is subjective, time-consuming, and heavily dependent on the professional experience of the physician. Therefore, computer-aided diagnostic systems have gradually played a significant role in this field. Existing neural networks, particularly U-Net and its variants, have shown promising results in retinal vessel segmentation. However, due to the information loss caused by multiple pooling operations and the insufficient handling of local contextual features in skip connections, most segmentation methods still face challenges in accurately detecting microvessels. To address these limitations and assist medical staff in the early diagnosis of retinal diseases, we propose an iterative retinal vessel segmentation network with multi-dimensional attention and multi-scale feature fusion, named IMDF-Net. The network consists of a backbone network and an iterative refinement network. In the backbone network, we have designed a cascaded multi-kernel dilated convolution module and a multi-scale feature fusion module during the upsampling phase. These components expand the receptive field, effectively combine global information and local features, and propagate deep features to the shallow layers. Additionally, we have designed an iterative network to further capture missing information and correct erroneous segmentation results. Experimental results demonstrate that IMDF-Net outperforms several state-of-the-art methods on the DRIVE dataset, achieving the best performance across all evaluation metrics. On the CHASE_DB1 dataset, it achieves optimal performance in four metrics. It demonstrates its superiority in both overall performance and visual results, with a significant improvement in the segmentation of microvessels.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"35 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689515","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":"Multiscale Feature Fusion Booster Network for Segmentation of Colorectal Polyp","authors":"Malik Abdul Manan,&nbsp;Jinchao Feng,&nbsp;Shahzad Ahmed,&nbsp;Abdul Raheem","doi":"10.1002/ima.70068","DOIUrl":"https://doi.org/10.1002/ima.70068","url":null,"abstract":"<div>\u0000 \u0000 <p>Addressing the challenges posed by colorectal polyp variability and imaging inconsistencies in endoscopic images, we propose the multiscale feature fusion booster network (MFFB-Net), a novel deep learning (DL) framework for the semantic segmentation of colorectal polyps to aid in early colorectal cancer detection. Unlike prior models, such as the pyramid vision transformer-based cascaded attention decoder (PVT-CASCADE) and the parallel reverse attention network (PraNet), MFFB-Net enhances segmentation accuracy and efficiency through a unique fusion of multiscale feature extraction in both the encoder and decoder stages, coupled with a booster module for refining fine-grained details and a bottleneck module for efficient feature compression. The network leverages multipath feature extraction with skip connections, capturing both local and global contextual information, and is rigorously evaluated on seven benchmark datasets, including Kvasir, CVC-ClinicDB, CVC-ColonDB, ETIS, CVC-300, BKAI-IGH, and EndoCV2020. MFFB-Net achieves state-of-the-art (SOTA) performance, with Dice scores of 94.38%, 91.92%, 91.21%, 80.34%, 82.67%, 76.92%, and 74.29% on CVC-ClinicDB, Kvasir, CVC-300, ETIS, CVC-ColonDB, EndoCV2020, and BKAI-IGH, respectively, outperforming existing models in segmentation accuracy and computational efficiency. MFFB-Net achieves real-time processing speeds of 26 FPS with only 1.41 million parameters, making it well suited for real-world clinical applications. The results underscore the robustness of MFFB-Net, demonstrating its potential for real-time deployment in computer-aided diagnosis systems and setting a new benchmark for automated polyp segmentation.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"35 2","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143688927","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}