International Journal of Imaging Systems and Technology最新文献_第3页

GSFDoubleU-Net: A Dual-Branch Architecture Incorporating Gated Self-Attention Fusion for Enhanced Gastric Polyp Image Segmentation GSFDoubleU-Net：基于门控自关注融合的双分支结构增强胃息肉图像分割

IF 3 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-08-23 DOI: 10.1002/ima.70432

Wenbin Yang, Xin Chang, Xiaojuan Wang

{"title":"GSFDoubleU-Net: A Dual-Branch Architecture Incorporating Gated Self-Attention Fusion for Enhanced Gastric Polyp Image Segmentation","authors":"Wenbin Yang, Xin Chang, Xiaojuan Wang","doi":"10.1002/ima.70432","DOIUrl":"https://doi.org/10.1002/ima.70432","url":null,"abstract":"<div>\u0000 \u0000 <p>Gastric polyps are clinically important lesions whose accurate delineation in endoscopic images can support lesion assessment and treatment planning. However, small size, weak contrast, irregular morphology, indistinct boundaries, and interference from surrounding gastric tissues make automatic segmentation difficult. To address these challenges, this study proposes GSFDoubleU-Net, a lightweight dual-branch architecture for gastric polyp segmentation. The first branch employs a pretrained VGG19 encoder and a Lightweight Atrous Spatial Pyramid Pooling (L-ASPP) module to capture multi-scale contextual information, whereas the second lightweight encoder–decoder branch focuses on contextual perception and fine-grained feature recovery with limited computational overhead. A Gated Self-Attention Feature Fusion (GSFF) module is further introduced to integrate complementary dual-branch features, model long-range dependencies, suppress irrelevant background responses, and refine lesion boundaries. On CVC-ClinicDB, GSFDoubleU-Net achieved a Dice score of 0.957 and a Precision of 0.970; on Kvasir-SEG, it obtained a Dice score of 0.949, an mIoU of 0.898, and a Precision of 0.953. When evaluated on the independent internal clinical dataset, the model achieved a Dice score of 0.857 and an mIoU of 0.832, while obtaining lower HD and MSD values than the compared methods. These results indicate that GSFDoubleU-Net provides a favorable balance between segmentation accuracy, boundary delineation, and computational efficiency, and may serve as a useful framework for computer-assisted endoscopic image analysis.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848749","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}

引用次数: 0

MultiVIT: Cross-Region Vision Transformers for Structured Regression in High-Resolution Histopathology Images MultiVIT：用于高分辨率组织病理学图像结构化回归的跨区域视觉变压器

IF 3 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-08-21 DOI: 10.1002/ima.70430

Amra Sghaier, Mariem Agrebi, Amani Gueddas, Ayda Ben Slama, Mahdi Ksiaa, Bassem Charfeddine

{"title":"MultiVIT: Cross-Region Vision Transformers for Structured Regression in High-Resolution Histopathology Images","authors":"Amra Sghaier, Mariem Agrebi, Amani Gueddas, Ayda Ben Slama, Mahdi Ksiaa, Bassem Charfeddine","doi":"10.1002/ima.70430","DOIUrl":"https://doi.org/10.1002/ima.70430","url":null,"abstract":"<div>\u0000 \u0000 <p>Continuous regression on high-resolution images remains a challenging problem due to spatial heterogeneity, long-range dependencies, and scale variability, particularly in digital histopathology. In this paper, we propose MultiVIT, a Vision Transformer framework designed for structured spatial regression from high-resolution images. The proposed architecture introduces a cross-region attention mechanism that explicitly models interactions between complementary spatial regions, enabling more informative representations than region-independent approaches. Unlike discretized formulations, MultiVIT directly predicts continuous density values using a constrained regression head, improving stability and interpretability. Experiments conducted on a public immunohistochemistry dataset demonstrate that MultiVIT outperforms CNN and standard ViT baselines, achieving a reduction of MAE from 4.91 to 3.84 and improving <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msup>\u0000 <mi>R</mi>\u0000 <mn>2</mn>\u0000 </msup>\u0000 </mrow>\u0000 <annotation>$$ {R}^2 $$</annotation>\u0000 </semantics></math> from 0.73 to 0.84. Extended baselines (Swin-B, TransMIL, HIPT) and cross-dataset validation on TCGA-CRC and Lizard further confirm generalizability. Ablation studies confirm the effectiveness of cross-region attention and constrained regression. These results highlight MultiVIT as an effective and general framework for structured regression in high-resolution image analysis, while also identifying key limitations related to dataset scale and generalization.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148785114","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}

引用次数: 0

Quantitative Feature Analysis and Diagnostic Value of Dual-Energy CT Imaging in Solid Lung Lesions 肺实性病变双能CT定量特征分析及诊断价值

IF 3 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-08-19 DOI: 10.1002/ima.70431

Yunfei Liu, Qiuyan Wang, Zhoupeng Ma, Jie Meng, Hao Zhang, Miaomiao Chen, Xifu Wang, Xiaobo Tang

{"title":"Quantitative Feature Analysis and Diagnostic Value of Dual-Energy CT Imaging in Solid Lung Lesions","authors":"Yunfei Liu, Qiuyan Wang, Zhoupeng Ma, Jie Meng, Hao Zhang, Miaomiao Chen, Xifu Wang, Xiaobo Tang","doi":"10.1002/ima.70431","DOIUrl":"https://doi.org/10.1002/ima.70431","url":null,"abstract":"<div>\u0000 \u0000 <p>This study included 53 patients with pathologically confirmed pulmonary solid lesions, divided into a malignant group of 35 cases and a benign group of 18 cases. All patients underwent dual phase energy spectrum CT enhanced scanning, measuring GSI quantitative parameters such as 40–100 keV single energy CT value, iodine concentration, water content, and multi interval energy spectrum curve slope. The differences in parameters between the two groups were compared and the diagnostic value was evaluated. The results showed that the iodine concentration in the arterial and venous phases of the malignant group was higher than that of the benign group, and the water content in both phases was lower than that of the benign group. There was no statistical difference in the difference in iodine concentration and water content between the two groups. At various energy levels of 40–100 keV, the CT values of the arterial and venous phases in the malignant group were higher than those in the benign group. The energy spectrum curves of both groups gradually decreased with the increase of keV, and the slope of the energy spectrum curves in most energy intervals in the malignant group was greater than that in the benign group. ROC analysis suggests that the parameters of iodine concentration and water content in the venous phase have good discriminatory efficacy, and the differentiation effect of low-energy CT values is outstanding. Research has shown that the quantitative parameters of dual energy CT energy spectrum can be used for the differentiation of benign and malignant lung solid lesions. The diagnostic value of intravenous iodine concentration, 40–60 keV low-energy CT values, and corresponding spectral curve slopes is optimal, and can be used as a supplementary tool for traditional CT morphological diagnosis.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784887","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}

引用次数: 0

A Novel Boundary-Aware Hybrid CNN–Transformer Framework for Breast Cancer Detection in Ultrasound Images 一种新的边界感知混合CNN-Transformer框架用于超声图像中的乳腺癌检测

IF 3 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-08-13 DOI: 10.1002/ima.70429

Aamir Mehmood, Yue Hu, Julian Hoxha, Hassan Wasfi, Arshad Ali, Ibrahim Abdullah Zalah, Saddam Hussain Khan

{"title":"A Novel Boundary-Aware Hybrid CNN–Transformer Framework for Breast Cancer Detection in Ultrasound Images","authors":"Aamir Mehmood, Yue Hu, Julian Hoxha, Hassan Wasfi, Arshad Ali, Ibrahim Abdullah Zalah, Saddam Hussain Khan","doi":"10.1002/ima.70429","DOIUrl":"https://doi.org/10.1002/ima.70429","url":null,"abstract":"<div>\u0000 \u0000 <p>Recent advancements in breast cancer detection using deep CNNs and vision transformers (ViTs) on breast ultrasound images (BUSI) have demonstrated strong performance. However, model complexity and variations in contrast, texture, and morphology continue to limit effectiveness. This study introduces the CB-Res-RBCMT, a hybrid framework that combines customized residual CNNs with ViT components for detailed BUSI cancer analysis. The RBCMT integrates stem convolution blocks and CNN-Meet-Transformer (CMT) modules, followed by regional-boundary (RB) feature operations. These operations apply the Laplacian of Gaussian (LoG) filter to enhance homogeneity, reduce speckle noise, and highlight structural transitions, while boundary operations capture malignant morphological changes. The CMT module utilizes multi-head attention for global context interactions, improving computational efficiency. New inverse residual blocks and stem CNNs further extract malignant texture information and address vanishing gradients. A multiscale channel fusion and attention (MSCFA) block enhances feature representation by combining global context with boundary-aware cues. The Channel-Boosted (CB) strategy fuses RBCMT and residual CNN feature maps to increase feature diversity for the limited BUSI dataset. Finally, a spatial attention block refines channels for optimal pixel selection and reduced redundancy. The CB-Res-RBCMT achieves 95.63% accuracy, 95.57% F1-score, 96.42% precision, and 94.79% sensitivity, outperforming existing CNN and ViT-based approaches. Furthermore, cross-dataset generalization on mammographic images validates the model's robust clinical applicability across diverse screening scenarios.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148753480","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}

引用次数: 0

Quantum-Guided Textural–Spatial Fusion Network for Thyroid Nodule Classification in Ultrasound Imaging 超声成像中甲状腺结节分类的量子引导纹理-空间融合网络

IF 3 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-08-11 DOI: 10.1002/ima.70428

Chandravardhan Singh Raghaw, Tanisha Jitendra Sahu, Prajakta Darade, Shahid Shafi Dar, Nagendra Kumar

{"title":"Quantum-Guided Textural–Spatial Fusion Network for Thyroid Nodule Classification in Ultrasound Imaging","authors":"Chandravardhan Singh Raghaw, Tanisha Jitendra Sahu, Prajakta Darade, Shahid Shafi Dar, Nagendra Kumar","doi":"10.1002/ima.70428","DOIUrl":"https://doi.org/10.1002/ima.70428","url":null,"abstract":"<div>\u0000 \u0000 <p>Thyroid cancer is among the most common malignancies, and ultrasound is the primary imaging modality due to its safety and wide availability. Accurate diagnosis remains difficult because of low contrast, acoustic shadowing, and subtle visual differences between benign and malignant nodules. These factors increase observer variability and lead to missed or incorrect diagnoses. Prior deep learning methods address this problem only partially by selectively focusing on spatial information and failing to capture long-range dependencies. Other approaches rely on handcrafted texture descriptors and overlook critical grayscale patterns in ultrasound. This paper presents a <b>Q</b>uantum-guided <b>Tex</b>tural–<b>S</b>patial Fusion <b>Net</b>work (QTexS-Net) for thyroid nodule classification in ultrasound imaging. The proposed framework jointly learns complementary spatial and textural representations. A spatial-aware autoencoder captures local structures and global contextual dependencies, while a texture-aware branch preserves fine-grained grayscale characteristics relevant to malignancy. A quantum-inspired fusion mechanism models interactions between spatial and textural features, leading to more discriminative representations and improved training efficiency. Experiments on three public benchmark datasets show that QTexS-Net consistently outperforms existing methods. Ablation studies and cross-dataset evaluations confirm the contribution of each component. Explainability analyses further highlight clinically meaningful regions, supporting reliable, interpretable decision-making in thyroid nodule assessment and providing transparent decision support for clinicians.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148753358","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}

引用次数: 0

Cross Fusion-CapNets: Interpretable Modeling for Benign-Malignant Classification of Lung Nodules 交叉融合- capnets：肺结节良恶性分类的可解释模型

IF 3 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-08-07 DOI: 10.1002/ima.70426

Yinheng Xu, Huiyun Long, Fangfang Gou, Guangqian Kong, Xun Duan

{"title":"Cross Fusion-CapNets: Interpretable Modeling for Benign-Malignant Classification of Lung Nodules","authors":"Yinheng Xu, Huiyun Long, Fangfang Gou, Guangqian Kong, Xun Duan","doi":"10.1002/ima.70426","DOIUrl":"https://doi.org/10.1002/ima.70426","url":null,"abstract":"<div>\u0000 \u0000 <p>Early and reliable classification of benign and malignant pulmonary nodules remains challenging because nodule appearances are highly heterogeneous and most deep learning models provide limited diagnostic transparency. To address these issues, we propose Cross Fusion-CapNets, an interpretable model that combines a Multi-scale Fusion Network (MSFNet) with a capsule-based explanation module. MSFNet integrates wavelet-based local features and attention-based global features through a Multi-feature Fusion (MFF) Block, while the capsule module learns attribute-oriented representations associated with eight radiological characteristics from LIDC-IDRI. Experiments on LIDC-IDRI achieved 95.4% accuracy and 99.2% AUC for benign-malignant nodule classification. As a cross-modality image-level assessment on the LC25000 dataset, five-fold stratified cross-validation and independent partition evaluation yielded 99.96% ± 0.04% validation accuracy and 99.97% ± 0.03% evaluation accuracy. These results show that the proposed model combines accurate classification with attribute-level interpretability.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148753265","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}

引用次数: 0

Advanced Multimodal Feature Fusion of ECG and PCG Signals for Precise Cardiovascular Disease Diagnosis Using a Fuzzy-Based Approach 基于模糊的心电和PCG信号多模态特征融合用于心血管疾病的精确诊断

IF 3 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-08-07 DOI: 10.1002/ima.70399

Gorapalli Srinivasa Rao, G. Muneeswari

{"title":"Advanced Multimodal Feature Fusion of ECG and PCG Signals for Precise Cardiovascular Disease Diagnosis Using a Fuzzy-Based Approach","authors":"Gorapalli Srinivasa Rao, G. Muneeswari","doi":"10.1002/ima.70399","DOIUrl":"https://doi.org/10.1002/ima.70399","url":null,"abstract":"<div>\u0000 \u0000 <p>The phonocardiogram (PCG) and electrocardiogram (ECG) are widely used for early detection and prevention of cardiovascular diseases (CVDs) due to their noninvasive acquisition and accurate representation of heart function from different perspectives. However, it is still challenging to extract discriminative characteristics without losing essential information, and few studies have successfully integrated PCG and ECG for CVD screening. Therefore, this research introduces a novel multimodal fused feature-based CVD classification framework that uniquely integrates advanced preprocessing, modality-specific feature extraction, and optimized classification. Raw ECG and PCG signals are preprocessed using multispectral adaptive wavelet denoising (MAWD) for noise removal, a U-Net-based sequence-to-sequence fully convolutional network (U-TSS) for precise segmentation, and a frequency transformation layer (FTL) for frequency domain conversion. Novelty lies in the tailored feature extraction strategy employing a parallel convolutional neural network (PCNN) for PCG and HCR-Net for ECG, followed by a Multi-scale Contextual Feature Fusion (MC2F) based feature fusion mechanism that preserves complementary information across modalities. Classification is performed using the proposed Deep Maxout Fuzzy EfficientNet (DMFE), enabling highly discriminative decision boundaries and robust generalization. Experimental results demonstrate that the proposed ECG–PCG fusion approach surpasses existing methods, achieving 99.18% accuracy, 99.09% sensitivity, and 99.03% specificity. These results highlight the method's strong potential for practical medical deployment, offering high performance, flexibility, and comprehensive characterization of cardiac health.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148752855","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}

引用次数: 0

AE-VMUNet: Attention-Enhanced Vision Mamba U-Net With Multi-Scale Feature Refinement for Prostate Tumor Segmentation in T2-Weighted MRI AE-VMUNet：基于多尺度特征细化的注意力增强视觉曼巴U-Net在t2加权MRI中用于前列腺肿瘤分割

IF 3 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-08-06 DOI: 10.1002/ima.70427

Xueting Wei, Yuehui Liao, Feng Gao, Ruipeng Li, Haote Chen, Panfei Li, Xiaobo Lai, Jingyu Zhu, Yasheng Huang

{"title":"AE-VMUNet: Attention-Enhanced Vision Mamba U-Net With Multi-Scale Feature Refinement for Prostate Tumor Segmentation in T2-Weighted MRI","authors":"Xueting Wei, Yuehui Liao, Feng Gao, Ruipeng Li, Haote Chen, Panfei Li, Xiaobo Lai, Jingyu Zhu, Yasheng Huang","doi":"10.1002/ima.70427","DOIUrl":"https://doi.org/10.1002/ima.70427","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate segmentation of prostate tumors on T2-weighted magnetic resonance imaging (MRI) scans is essential for diagnosis and treatment planning. However, this remains challenging due to the heterogeneous appearance of tumors, their indistinct boundaries, and the frequent occurrence of small lesions. We propose AE-VMUNet, an attention-enhanced Vision Mamba U-Net that performs stage-wise feature refinement within a state-space encoder-decoder framework. The model integrates the following: (i) an Adaptive State-space Enhanced Feature (ASF) block in the encoder, which couples long-range dependency modelling with channel-wise recalibration; (ii) an Attention-Gate-based Skip Connection Fusion (SCF) module, which performs spatially selective, multi-scale aggregation; and (iii) an Efficient State-space Guided (ESG) block in the decoder, which preserves global context while enabling detail-aware reconstruction. Experiments on the public PI-CAI 2022 dataset and an independent, private clinical cohort demonstrate that the AE-VMUNet model achieves Dice scores of 59.51% and 48.83% respectively, with HD95 values of 14.21 and 18.96 mm. These results outperform those of representative CNN-, attention- and Mamba-based segmentation baselines. Further evaluations on PROMISE12 and ACDC demonstrate strong cross-dataset and cross-anatomy generalization, achieving Dice scores of 92.19% and 91.64%, respectively. Overall, these results suggest that combining state-space modelling with lightweight attention mechanisms can lead to precise and robust medical image segmentation.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148752958","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}

引用次数: 0

DTCA-Net: A Dilated Transformer Channel Attention With External Attention-Based Network for Oral Cancer Segmentation DTCA-Net：一种扩展的变压器通道注意与外部注意网络用于口腔癌分割

IF 3 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-08-03 DOI: 10.1002/ima.70421

Shivam Singh, Surya Majumder, Akash Halder, Mahantapas Kundu, Ram Sarkar

{"title":"DTCA-Net: A Dilated Transformer Channel Attention With External Attention-Based Network for Oral Cancer Segmentation","authors":"Shivam Singh, Surya Majumder, Akash Halder, Mahantapas Kundu, Ram Sarkar","doi":"10.1002/ima.70421","DOIUrl":"https://doi.org/10.1002/ima.70421","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate segmentation of oral cancer in histopathological images is essential for early diagnosis and treatment. While U-Net-based architectures have shown promise, balancing high accuracy with low computational complexity remains a key challenge. This work aims to design an efficient model that enhances feature extraction without significantly increasing model size. We propose DTCA-Net, an enhanced U-Net variant that integrates three key modules: (1) a Dilated Convolution and Transformer Channel Attention (DTCA) block to capture global and local features, (2) an Inverted External Attention (IEA) block to model intersample relationships and dataset-level context, and (3) an Attention Bridge (AB) module connecting encoder and decoder to improve multiscale feature fusion. The model was evaluated on two public datasets: Oral Cavity-Derived Cancer (OCDC) and ORal Cancer Annotated (ORCA). DTCA-Net achieved strong performance, with a Dice score of 91.45% and IoU of 84.44% on the OCDC dataset. On the ORCA dataset, it obtained a Dice score of 83.66% and IoU of 71.96%, surpassing existing baselines in both accuracy and efficiency. We effectively combine lightweight architecture with rich feature extraction capabilities, making DTCA-Net a promising tool for automatic oral cancer segmentation in clinical workflows. The entire codes of our model are publicly available through this Github Link: https://github.com/shivamsingh-gpu/dtca-net.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148752598","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}

引用次数: 0

DSBNet: A Dual Sampling–Bottleneck Optimization Network for Efficient Pulmonary Nodule Segmentation DSBNet：用于肺结节分割的双采样瓶颈优化网络

IF 3 4区计算机科学

International Journal of Imaging Systems and Technology Pub Date : 2026-08-02 DOI: 10.1002/ima.70425

Kaixin Ma, Huiyun Long, Fangfang Gou, Guangqian Kong, Xun Duan

{"title":"DSBNet: A Dual Sampling–Bottleneck Optimization Network for Efficient Pulmonary Nodule Segmentation","authors":"Kaixin Ma, Huiyun Long, Fangfang Gou, Guangqian Kong, Xun Duan","doi":"10.1002/ima.70425","DOIUrl":"https://doi.org/10.1002/ima.70425","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate segmentation of pulmonary nodules is crucial for lung cancer screening and diagnosis. However, nodules often present irregular boundaries and heterogeneous morphology, making automatic segmentation challenging. U-Net-based methods remain limited by feature degradation during sampling, insufficient global representation at the bottleneck, and substantial computational overhead. To address these issues, we propose DSBNet, a dual-stage optimization framework built upon Attention U-Net. A contour-guided attention wavelet module enhances feature fusion and boundary preservation during upsampling, an adaptive Fourier neural operator at the bottleneck enables efficient global context modeling, and a cross-scale token encoder captures long-range dependencies with limited overhead. Lightweight feature fusion operations further reduce parameter count and memory consumption. Experiments on LUNA16 and LIDC show that DSBNet improves IoU by 2.27% and 3.24% over the Attention U-Net baseline, while reducing the parameter count by approximately 25%, FLOPs by approximately 40%, and memory consumption by approximately 15%. DSBNet achieves a favorable balance between segmentation accuracy and computational efficiency, demonstrating its potential for computer-aided pulmonary nodule diagnosis. For further implementation details, please refer to the official DSBNet GitHub repository at https://github.com/mkx0mkx/DSBNet.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148752589","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}

引用次数: 0