International Journal of Imaging Systems and Technology最新文献

{"title":"DINO-SAM: Combining DINO Detector and Fine-Tuned SAM for Automatic Pulmonary Nodule Segmentation in CT Image","authors":"Yan Li,&nbsp;Huiqin Jiang,&nbsp;Lei Yang,&nbsp;Yaojun Jiang,&nbsp;Jianbo Gao","doi":"10.1002/ima.70448","DOIUrl":"https://doi.org/10.1002/ima.70448","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate pulmonary nodule segmentation in computed tomography (CT) images is important for the quantitative assessment of nodule morphology. However, the small size, low contrast, and heterogeneous appearance of pulmonary nodules make it difficult to delineate their boundaries accurately. Although the Segment Anything Model (SAM) has demonstrated strong general-purpose segmentation capability, its dependence on manual prompts and limited adaptability to pulmonary CT images hinder fully automatic segmentation. To address these challenges, we propose DINO-SAM, a fully automatic pulmonary nodule segmentation framework that combines a DINO detector with a parameter-efficiently fine-tuned SAM. The DINO detector automatically localizes pulmonary nodules and generates prompts for SAM, thereby eliminating manual interaction. Low-Rank Adaptation (LoRA) is incorporated into the SAM image encoder and mask decoder, while position and feature adapters are introduced into the image encoder to enhance pulmonary-nodule-specific representation learning with a limited number of trainable parameters. DINO-SAM was evaluated on the public LIDC-IDRI dataset and achieved a Dice of 92.42%, an IoU of 86.11%, an HD of 2.44 pixels, an ACC of 99.52%, an SE of 93.37%, and an SP of 99.72%. The proposed method outperformed the compared task-specific and SAM-based foundation models. These results demonstrate that detector-guided prompt generation and parameter-efficient SAM adaptation provide an effective approach to fully automatic pulmonary nodule segmentation in CT images.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146841","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":"Can Annotation-Free Deep Learning Detect Periapical Bone Rarefactions on Panoramic Radiographs? A Paired Diagnostic Validation Study","authors":"José Evando da Silva-Filho,&nbsp;Caio Marques Silva,&nbsp;Giovanna Tacchi,&nbsp;Igor Rodrigues-Fontenele,&nbsp;Mateus Bôtto-Marques,&nbsp;Sâmela Débora Mendes-Dias,&nbsp;André Wescley Oliveira de Aguiar,&nbsp;Pedro Pedrosa Rebouças Filho,&nbsp;Paulo Leonardo Pontes Marques,&nbsp;Danielle Frota de Albuquerque,&nbsp;Eduardo Diogo Gurgel-Filho","doi":"10.1002/ima.70451","DOIUrl":"https://doi.org/10.1002/ima.70451","url":null,"abstract":"<p>This study aimed to compare an annotation-free deep learning (DL) model with human evaluators for detecting periapical bone rarefactions (PBRs) on panoramic radiographs (PRs) and to assess the clinical acceptability of AI-supported dental imaging. A mixed-methods diagnostic validation was conducted using 238 PRs, equally distributed between images with (<i>n</i> = 119) and without (<i>n</i> = 119) PBRs. Model performance was compared with that of four calibrated dentists: two oral and maxillofacial radiologists and two endodontists. The reference standard was based on internationally accepted radiographic criteria applied by calibrated researchers under expert supervision, with final classifications verified by the principal investigator. Diagnostic performance was assessed using standard diagnostic metrics, chance-corrected agreement statistics and receiver operating characteristic analysis, while clinical acceptability was explored through questionnaires and thematically analysed semi-structured interviews. At the sensitivity-oriented decision threshold of 0.27, the DL model achieved a sensitivity of 0.924, a specificity of 0.109, an accuracy of 0.517, a precision of 0.509 and an <i>F</i>1-score of 0.657. Threshold-independent binary discrimination was moderate (ROC-AUC = 0.726). Human evaluators showed more balanced profiles, with accuracy ranging from 0.655 to 0.752 and <i>F</i>1-scores from 0.654 to 0.779. Professional perception was generally favourable, although responses varied among evaluators. The annotation-free DL model showed high sensitivity and moderate discrimination for PBR detection. Although low specificity limits autonomous use, the findings support annotation-free learning as a potentially scalable strategy, warranting further training with larger and more heterogeneous datasets.</p>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 6","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ima.70451","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149068141","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":"MambaPolyp: Gated State-Space Modeling With Multi-Scale Context and Boundary-Refinement for Colorectal Polyp Segmentation","authors":"Manoj Kumar Singh,&nbsp;Satish Chand,&nbsp;Kalicharan Sahu","doi":"10.1002/ima.70445","DOIUrl":"https://doi.org/10.1002/ima.70445","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate segmentation of colorectal polyps in colonoscopy images is crucial for the early detection and prevention of colorectal cancer (CRC). However, polyp segmentation remains challenging due to variations in size, shape, texture, and boundary ambiguity caused by specular highlights, motion blur, and low contrast. In this paper, we propose MambaPolyp, a novel encoder-decoder architecture that integrates efficient long-sequence modeling, multi-scale context aggregation, and fine boundary enhancement for precise colorectal polyp segmentation. The core component of our design is the MambaGate module, which leverages dynamic state-space models (SSMs) to capture long-range dependencies in spatial features while adaptively gating irrelevant context. To enhance multi-scale semantic understanding, we incorporate an atrous spatial pyramid pooling (ASPP) module at the bottleneck, enabling the model to aggregate features from varying receptive fields. The decoder is equipped with a Multi-Mamba refinement mechanism, where stacked MambaBlocks progressively refine the fused features at each resolution level. A Boundary-Refinement Module is introduced to sharpen the polyp edges and improve boundary localization. Furthermore, a deep supervision strategy is adopted across multiple decoder stages to guide training with rich hierarchical information. The model is evaluated on five benchmark datasets, Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, ETIS-Larib, and CVC-300, demonstrating that MambaPolyp outperforms several state-of-the-art (SOTA) segmentation models in terms of Dice coefficient, Intersection over Union (IoU), and boundary-based metrics, while maintaining lower computational efficiency, making it suitable for real-time clinical applications during colonoscopy.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942732","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":"Progressive Refinement Autoencoder for Low-Dose Computed Tomography Enhancement","authors":"Ahmet Demir,&nbsp;Mohamad M. A. Ashames,&nbsp;Omer N. Gerek,&nbsp;Semih Ergin,&nbsp;Mehmet Fidan,&nbsp;Mehmet Koc,&nbsp;M. Bilginer Gulmezoglu,&nbsp;Rifat Edizkan,&nbsp;Idil Isikli Esener,&nbsp;Gulin Elibol Secil,&nbsp;Sezgin Secil,&nbsp;Atalay Barkana,&nbsp;Cuneyt Calisir","doi":"10.1002/ima.70438","DOIUrl":"https://doi.org/10.1002/ima.70438","url":null,"abstract":"&lt;p&gt;The use of ionizing radiation in diagnostic imaging is a common practice worldwide. However, the imaging process itself carries relative risks. Therefore, it is recommended to employ the lowest possible dose of ionizing radiation, especially in computed tomography (CT) imaging, where a series of X-ray scans are utilized to reconstruct images of body tissue sections. A common strategy for radiation dose reduction in CT imaging is known as the quarter-dose technique, which reduces the X-ray dose but can cause noise and loss of image sharpness. Since CT image reconstruction from directional X-rays is a nonlinear process, it is analytically difficult to correct the effects of dose reduction on image quality. Recent and popular deep-learning approaches provide an intriguing possibility of low-dose CT image enhancement. This study aims to develop a U-Net-based deep-learning method with decoder-side refinement modules for enhancing quarter-dose CT images while preserving diagnostically relevant image details. A novel autoencoder approach is proposed that preserves the conventional encoding backbone of U-Net while integrating lightweight refinement modules exclusively within the decoding path. The refinement module consists of residual blocks for both coarse and fine resolutions, and the proposed method progressively updates feature representations to enhance fine details. The proposed architecture is evaluated through experiments conducted on the Low Dose CT Grand Challenge dataset by comparing it with well-known architectures. The dataset consists of quarter-dose and full-dose CT slice images from 10 patients. The model is evaluated using both an initial fixed-interval test set and an additional patient-wise stratified random test set comprising 300 paired slices, and the remaining images are divided into training (&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mn&gt;90&lt;/mn&gt;\u0000 &lt;mo&gt;%&lt;/mo&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ 90% $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;) and validation (&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mn&gt;10&lt;/mn&gt;\u0000 &lt;mo&gt;%&lt;/mo&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ 10% $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;) sets. Moreover, blind tests conducted by practicing radiologists demonstrate that the enhanced quarter-dose CT images received higher radiologist-rated diagnostic acceptability scores than the original quarter-dose images and are often preferred in subjective comparison with the full-dose CT images. The proposed progressive refinement U-Net provides a decoder-side refinement strategy for quarter-dose CT enhancement and achieves competitive quantitative performance. Beyond demonstrating successful image enhancement, the study also highlights the importance of radiologist-rated diagnostic acceptability and structured subjective co","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ima.70438","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942392","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":"Real-Time Polyp Detection Using an Enhanced YOLOv12 Framework With Adaptive Feature Routing and Auxiliary Self-Distillation","authors":"Deva Raj Mahanta,&nbsp;Lipi B. Mahanta,&nbsp;Manish Chowdhury","doi":"10.1002/ima.70442","DOIUrl":"https://doi.org/10.1002/ima.70442","url":null,"abstract":"<div>\u0000 \u0000 <p>Early detection of gastric and colorectal polyps during endoscopic procedures is essential for preventing cancer progression; however, manual identification remains challenging due to subtle lesion appearance, size variability, and the fast pace of clinical workflows. YOLO-based object detection models have demonstrated strong potential for real-time computer-aided detection. Still, limitations persist in multiscale representation, small polyp detection, and maintaining accuracy without increasing computational cost. To address these challenges, we developed an enhanced YOLOv12s-based imaging framework tailored for endoscopic polyp detection. The proposed system integrates three key innovations: (1) RouteHead, an adaptive multiscale feature routing mechanism that dynamically fuses features from multiple feature-pyramid levels (P2-P5), enabling improved detection of small and fine-grained lesions; (2) auxiliary detection heads employed during training for self-distillation, enhancing representational learning without affecting inference-time performance; and (3) task-specific loss functions, including α-CIoU for precise localization, edge-aware loss for boundary refinement, and self-distillation loss for deeper feature consistency. The model was evaluated on a comprehensive multicenter colonoscopy dataset comprising 2188 images aggregated from four publicly available benchmarks: Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, and ETIS-LaribPolypDB. For datasets lacking bounding box annotations, YOLO-format labels were systematically generated from segmentation masks to ensure consistency in annotations across datasets. Training was performed using a stratified data partitioning strategy with a held-out independent test set and fivefold cross-validation to obtain robust performance estimates. The enhanced model achieved a mAP@50–95 of 0.6976, a precision of 0.9300, a recall of 0.9069, and an F1-score of 0.9182, consistently matching or exceeding the baseline YOLOv12s architecture across validation folds and achieving detection accuracy statistically comparable to that of substantially larger detectors at a fraction of their computational cost. Despite improved accuracy, the proposed framework remains computationally efficient with 8.81 million parameters and 7.92 GFLOPs. By combining adaptive multiscale feature routing with self-distillation-based training, the proposed imaging system effectively overcomes key limitations of existing real-time endoscopic detection approaches. The strong balance between detection accuracy, robustness across multiple datasets, and computational efficiency makes the framework suitable for practical computer-aided endoscopy systems, with the potential to enhance early detection rates and reduce cognitive burden on clinicians during routine examinations.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942391","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 Comprehensive Study of Transfer Learning, Resolution Reduction, and Multi-View Classification for Breast Cancer Detection in Mammograms","authors":"Daniel G. P. Petrini,&nbsp;Hae Yong Kim","doi":"10.1002/ima.70436","DOIUrl":"https://doi.org/10.1002/ima.70436","url":null,"abstract":"<p>Mammography, an X-ray–based imaging technique, remains central to the early detection of breast cancer. Recent advances in artificial intelligence have enabled increasingly sophisticated computer-aided diagnostic methods, evolving from patch-based classifiers to whole-image approaches and then to multi-view architectures that jointly analyze complementary projections. Despite this progress, several critical questions remain unanswered. Although individual aspects of CNN-based mammogram classification—such as patch pretraining, backbone transferability, and multi-view fusion—have been studied separately in prior work, no unified comparison has examined them under controlled conditions across datasets of contrasting image quality. In this study, we close that gap through a systematic empirical investigation organized around five interrelated questions: (1) the role of patch classifiers, (2) the transferability of natural-image-trained backbones, (3) the advantages of “learn-to-resize” over conventional downscaling, (4) the contribution of multi-view integration, and (5) the robustness of findings across varying image quality. Questions (3) and (5) are addressed here for the first time, while questions (1), (2), and (4) are re-examined within a unified protocol that reveals dataset-quality dependencies invisible to prior single-dataset studies. Beyond benchmarking, our experiments demonstrate clear performance gains over prior work. For the CBIS-DDSM dataset, we improved single-view AUC from 0.8153 to 0.8343, and multiple-view AUC from 0.8483 to 0.8658. We also introduce a comparative protocol that places single- and multi-view classifiers on the same evaluation footing—by aggregating per-view single-view predictions into per-exam scores—enabling a statistically valid comparison between the two; using this protocol, we measured a 0.0217 AUC gain from extending single- to multi-view analysis on CBIS-DDSM. On the complete VinDr-Mammo dataset, the multiple-view approach further improved results, achieving a 0.0492 AUC increase over single view and reaching 0.8511 AUC overall. These results establish new state-of-the-art benchmarks, providing clear evidence of the advantages of multi-view architectures for mammogram interpretation. Beyond performance, our analysis offers principled insights into model design and transfer learning strategies, contributing to the development of more accurate and reliable breast cancer screening tools. The inference code and trained models are publicly available at https://github.com/dpetrini/multiple-view.</p>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ima.70436","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942465","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":"CADG-UNet: Coordinate Attention and Dynamic Gated UNet for Muscle Segmentation in Musculoskeletal Ultrasound Images","authors":"Yan Zhang,&nbsp;Zetong Cai,&nbsp;Xiaoqing Zhang,&nbsp;Boyu Jia,&nbsp;Rui Wang","doi":"10.1002/ima.70439","DOIUrl":"https://doi.org/10.1002/ima.70439","url":null,"abstract":"<div>\u0000 \u0000 <p>Quantitative assessment of neuromuscular disorders relies on accurate musculoskeletal ultrasound (MSKUS) image segmentation. However, speckle noise and ambiguous anatomical boundaries pose continuous challenges. Existing convolutional networks often exhibit limitations in balancing detail preservation with noise suppression. Furthermore, traditional multi-scale fusion is prone to transmitting low-level artifacts, causing false positive misclassifications. To address these issues, a robust segmentation network termed CADG-UNet is proposed. The architecture incorporates two tailored modules to process specific acoustic interference. In the encoding path, the Coordinate Attention and Dynamic Spatial Attention (CADSA) module is designed, combining directional positional encoding with content-adaptive dynamic convolutions. This design suppresses spatially heterogeneous noise while precisely anchoring muscle boundaries. In the decoding path, the Dynamic Gated Fusion (DGF) module is designed for skip connections, employing a post-gating local residual refinement mechanism to filter high-frequency reverberation artifacts from shallow features before multi-scale fusion. The proposed method is evaluated on the MUST and DeepACSA datasets. CADG-UNet achieves mean intersection over union (mIoU) scores of 83.31% and 90.97%, respectively. Statistical significance tests indicate stable cross-dataset performance compared to leading baseline methods. Furthermore, the network yields improved boundary and clinical metrics, including reduced 95th percentile Hausdorff Distance (HD95), lower Average Surface Distance (ASD), and cross-sectional area (CSA) estimations. It also demonstrates significant robustness under multiplicative speckle noise conditions. These results suggest that CADG-UNet provides a reliable approach for automated clinical morphological measurements.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942449","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":"HDS-Net: A Hybrid Deformable-Swin Network for Dual-Domain Sparse-View CT Reconstruction","authors":"Zhuangzhuang Han,&nbsp;Tingyue Liu,&nbsp;Hangqi Wu,&nbsp;Zhen Sun,&nbsp;Jinxin Luo,&nbsp;Pengcheng Zhang","doi":"10.1002/ima.70435","DOIUrl":"https://doi.org/10.1002/ima.70435","url":null,"abstract":"<div>\u0000 \u0000 <p>To address the ill-posed inverse problem of sparse-view CT reconstruction, dual-domain networks have demonstrated considerable success by leveraging the powerful mapping capability of deep learning. However, existing dual-domain architectures are inherently limited to model geometric transformations due to the fixed geometric structures of standard building blocks. Furthermore, the inadequate receptive fields of current dual-domain models fail to effectively capture multiscale features, resulting in blurred edges and loss of texture details. To address these limitations, we propose a novel dual-domain end-to-end network, named Hybrid Deformable-Swin Network (HDS-Net), for sparse-view CT reconstruction. In the projection domain, we employ a Modulated Deformable Module that adaptively adjusts spatial sampling locations to focus on pertinent regions and effectively model geometric transformations. In the image domain, a U-Net architecture is adopted as the backbone to refine reconstructed details. Specifically, we design a GL-DRF block to construct the encoder by utilizing parallel dilated convolutions with various rates to maximize the receptive field and capture the contextual information at multiple scales. Extensive experiments on the clinical Mayo and Piglet datasets demonstrate that the proposed HDS-Net achieves superior performance on both quantitative metrics and visual quality, effectively suppressing artifacts while preserving anatomical details. This study provides a robust solution for high-quality sparse-view CT reconstruction, holding significant potential for diagnostic accuracy enhancement.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942332","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":"Enhancing fNIRS-Based Decoding: A Heterogeneous Ensemble Network for Six-Class Movement Classification","authors":"Urooj Abid,&nbsp;Hafiz Zia Ur Rehman,&nbsp;Osama Zulfiqar,&nbsp;Hammad Nazeer,&nbsp;Noman Naseer","doi":"10.1002/ima.70437","DOIUrl":"https://doi.org/10.1002/ima.70437","url":null,"abstract":"<div>\u0000 \u0000 <p>Neurological upper-limb impairments severely affect functional independence, motivating the development of brain-computer interface (BCI) systems for decoding motor intention. Although functional near-infrared spectroscopy (fNIRS) is a promising modality, its low signal-to-noise ratio and large inter-subject variability make multi-class motor decoding difficult. In this study, a Heterogeneous Controlled Temporal Ensemble Network (HCTE-Net) is proposed to classify six different upper-limb motor tasks based on fNIRS signals. Twenty healthy participants were included for the data acquisition from the motor cortex region of the brain and standardized hemodynamic modeling was used for pre-processing of signals to include task-related dynamics. HCTE-Net combines temporal representations of LSTM, Bi-LSTM, and Peephole LSTM by probabilistic ensemble fusion. Among conventional machine learning models, XGBoost achieved the highest average accuracy of 69.68%, outperforming SVM (39.09%), LR (37.64%), DT (36.87%), RF (48.54%), LDA (39.39%), and NB (34.58%). The proposed HCTE-Net achieved a maximum accuracy of 95.46%, exceeding LSTM (84.35%), Bi-LSTM (87.17%), and Peephole LSTM (73.58%). The results of statistical analysis revealed significant differences among all methods (F = 659.324, <i>p</i> = 4.234 × 10⁻¹⁵²), and Tukey's HSD test showed significant improvement (<i>p</i> &lt; 0.001). Experimental results demonstrate that HCTE-Net consistently outperforms single models across multiple evaluation metrics.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148943399","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 Hybrid Deep Learning Model for Colorectal Polyp Detection and Classification From Endoscopic Images","authors":"Yao-Tien Chen,&nbsp;Debalke Embeyale Sahilu","doi":"10.1002/ima.70433","DOIUrl":"https://doi.org/10.1002/ima.70433","url":null,"abstract":"<div>\u0000 \u0000 <p>Globally, colorectal cancer (CRC) remains a key contributor to cancer-related death, with most malignancies developing through the progression of colorectal polyps. Early detection and accurate histological classification of polyps during colonoscopy are essential for effective CRC screening and prevention. However, conventional colonoscopy may fail to detect certain lesions and exhibits variability in diagnostic performance due to operator dependence and challenging imaging conditions. To address these limitations, this study proposes a hybrid deep learning (DL) model that integrates YOLOv10 for polyp detection and feature extraction with a customized Convolutional Neural Network (CNN) for the histological classification of colorectal polyps into hyperplastic and adenomatous categories. A total of 6000 endoscopic images obtained from the Harvard Dataverse PolypsSet repository were used for model development and evaluation. To improve robustness and generalization, data augmentation techniques were applied during training, and stratified 5-fold cross-validation was employed to prevent data leakage between training and validation sets. Experimental results demonstrated that the proposed YOLOv10–CNN model achieved an average detection mAP@50 of 0.9848 and a classification accuracy of 0.9913 across the cross-validation folds. External validation on an independent dataset achieved mAP@50 of 0.926, indicating good generalization ability to unseen data. Furthermore, the model achieved an inference speed of approximately 120 frames per second (FPS), demonstrating efficient computational performance. A web-based graphical user interface was also developed to facilitate visualization of detection and classification results from colonoscopy videos. The findings suggest that the proposed hybrid model provides accurate and efficient polyp detection and classification while maintaining stable performance across internal and external evaluations. The proposed approach may serve as a supporting computer-aided analysis tool for colorectal polyp screening.</p>\u0000 </div>","PeriodicalId":14027,"journal":{"name":"International Journal of Imaging Systems and Technology","volume":"36 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2026-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148849158","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}