{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T21:12:23Z","timestamp":1789506743703,"version":"build-2803163510"},"reference-count":51,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n The rising global incidence of renal tumors necessitates precise diagnostic interventions. Accurate segmentation of computed tomography (CT) scans is essential for nephron-sparing surgery and radiotherapy. However, conventional manual delineation is labor-intensive and prone to significant interobserver variability due to tumor morphological heterogeneity. There is an urgent clinical demand for robust, automated segmentation solutions.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to develop and validate GAM-DeepLabV3+, an automated framework designed to address boundary ambiguity and high false-positive rates in complex renal imaging scenarios.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We propose an optimized encoder-decoder architecture specifically tailored for renal mass detection. The framework incorporates three key innovations: (1) a lightweight MobileNetV2 backbone to minimize computational overhead for clinical deployment; (2) an Atrous Spatial Pyramid Pooling (ASPP) module to capture multiscale contextual information; and (3) a Global Attention Mechanism (GAM) in the decoder to enhance channel-spatial interactions, thereby refining boundary delineation by suppressing background noise. The model was rigorously evaluated on a private clinical dataset (n=218) and the KiTS19 benchmark (n=210).<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n GAM-DeepLabV3+ consistently outperformed state-of-the-art baselines. On the private dataset, the model achieved a mean Dice similarity coefficient (DSC) of 0.939 (SD 0.008), significantly surpassing feature pyramid network (FPN; mean 0.893, SD 0.008;\n P<\/jats:italic>\n <.001) and no-new-Net (nnU-Net; 2D, custom; mean 0.908, SD 0.013;\n P<\/jats:italic>\n <.001). It also achieved a mean 95% Hausdorff distance (HD95) of 1.485 (SD 0.522) pixels. On the KiTS19 dataset, it maintained a mean robust DSC of 0.928 (SD 0.006). To facilitate clinical translation, a demonstration-only online platform was developed.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The GAM-DeepLabV3+ framework provides an accurate, efficient, and fully automated solution for renal tumor segmentation. By overcoming boundary ambiguity and optimizing feature fusion, this approach shows potential as a decision-support aid, pending future validation with 3D reconstruction.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/78523","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T13:45:06Z","timestamp":1784641506000},"page":"e78523-e78523","source":"Crossref","is-referenced-by-count":0,"title":["Automated Renal Tumor Segmentation in Computed Tomography Images Using a Global Attention\u2013Based DeepLabV3+ Model: Algorithm Development and Validation"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7231-0349","authenticated-orcid":false,"given":"Yueyan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2293-0785","authenticated-orcid":false,"given":"Jianqiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1443-8350","authenticated-orcid":false,"given":"Lingyu","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2974-9701","authenticated-orcid":false,"given":"Lin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8984-5759","authenticated-orcid":false,"given":"Zhaoqing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6264-8289","authenticated-orcid":false,"given":"Yujie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4930-1231","authenticated-orcid":false,"given":"Jiaxin","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4822-6049","authenticated-orcid":false,"given":"Xinyao","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7028-4166","authenticated-orcid":false,"given":"Shuyan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4939-8104","authenticated-orcid":false,"given":"Jianhong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5743-4539","authenticated-orcid":false,"given":"Boming","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"issue":"1_suppl","key":"R1","doi-asserted-by":"publisher","first-page":"4","DOI":"10.3233\/KCA-230023","article-title":"Differential diagnosis of renal neoplasia with clear cell cytology","volume":"9","author":"Baniak","journal-title":"Kidney Cancer"},{"issue":"5","key":"R2","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1159\/000545812","article-title":"Oncocytic tumors in the kidney: a trifocal review - integrated pathological, cytopathological, and molecular perspectives (Part 1)","volume":"69","author":"Paner","journal-title":"Acta Cytol"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3410833","article-title":"A systematic kidney tumour segmentation and classification framework using adaptive and attentive-based deep learning networks with improved crayfish optimization algorithm","volume":"12","author":"Vasantbhai Patel","journal-title":"IEEE Access"},{"issue":"7","key":"R4","doi-asserted-by":"publisher","first-page":"4163","DOI":"10.1007\/s11831-024-10112-8","article-title":"A comprehensive study of deep learning methods for kidney tumor, cyst, and stone diagnostics and detection using CT images","volume":"31","author":"Kumar","journal-title":"Arch Computat Methods Eng"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.32074\/1591-951X-818","article-title":"What\u2019s new in the WHO 2022 classification of kidney tumours?","volume":"115","author":"Alaghehbandan","journal-title":"Pathologica"},{"issue":"6","key":"R6","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1097\/MOU.0000000000000814","article-title":"Applications of neural networks in urology: a systematic review","volume":"30","author":"Checcucci","journal-title":"Curr Opin Urol"},{"issue":"17","key":"R7","doi-asserted-by":"publisher","first-page":"3474","DOI":"10.7150\/jca.19953","article-title":"Prognostic value of clinical and pathological features in Chinese patients with chromophobe renal cell carcinoma: a 10-year single-center study","volume":"8","author":"Xie","journal-title":"J Cancer"},{"issue":"7","key":"R8","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.2967\/jnumed.124.267417","article-title":"Utility of PSMA PET\/CT in staging and restaging of renal cell carcinoma: a systematic review and metaanalysis","volume":"65","author":"Sadaghiani","journal-title":"J Nucl Med"},{"issue":"2","key":"R9","doi-asserted-by":"publisher","first-page":"127","DOI":"10.3322\/caac.21552","article-title":"Artificial intelligence in cancer imaging: clinical challenges and applications","volume":"69","author":"Bi","journal-title":"CA Cancer J Clin"},{"issue":"4","key":"R10","doi-asserted-by":"publisher","first-page":"333","DOI":"10.3322\/caac.21713","article-title":"Molecular imaging in oncology: current impact and future directions","volume":"72","author":"Rowe","journal-title":"CA Cancer J Clin"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","DOI":"10.1186\/s12894-025-01889-2","article-title":"The role of three-dimensional reconstruction in partial nephrectomy for ipsilateral multifocal renal tumors: a multicenter retrospective study","volume":"25","author":"Liu","journal-title":"BMC Urol"},{"issue":"8","key":"R12","doi-asserted-by":"publisher","first-page":"4060","DOI":"10.1109\/TIP.2019.2905537","article-title":"Crossbar-Net: a novel convolutional neural network for kidney tumor segmentation in CT images","volume":"28","author":"Yu","journal-title":"IEEE Trans Image Process"},{"key":"R13","doi-asserted-by":"crossref","unstructured":"Myronenko A Hatamizadeh A . 3D kidneys and kidney tumor semantic segmentation using boundary-aware networks. arXiv. Preprint posted online on Sep 14, 2019. [doi: 10.48550\/arXiv.1909.06684]","DOI":"10.24926\/548719.009"},{"issue":"6_suppl","key":"R14","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1200\/JCO.2020.38.6_suppl.626","article-title":"An international challenge to use artificial intelligence to define the state-of-the-art in kidney and kidney tumor segmentation in CT imaging","volume":"38","author":"Heller","journal-title":"J Clin Oncol"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2020.100357","article-title":"MSS U-Net: 3D segmentation of kidneys and tumors from CT images with a multi-scale supervised U-Net","volume":"19","author":"Zhao","journal-title":"Inform Med Unlocked"},{"key":"R16","doi-asserted-by":"crossref","unstructured":"Guo J Zeng W Yu S Xiao J . RAU-net: u-net model based on residual and attention for kidney and kidney tumor segmentation. Presented at: 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE); Jan 15-17, 2021; Guangzhou, China. URL: https:\/\/ieeexplore.ieee.org\/xpl\/mostRecentIssue.jsp?punumber=9341295 [Accessed 22-08-2026] [doi: 10.1109\/ICCECE51280.2021.9342530]","DOI":"10.1109\/ICCECE51280.2021.9342530"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC48229.2022.9871443","article-title":"Boundary attention U-Net for kidney and kidney tumor segmentation","volume":"2022","author":"Zhao","journal-title":"Annu Int Conf Eng Med Biol Soc"},{"issue":"20","key":"R18","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13203244","article-title":"Optimizing inference distribution for efficient kidney tumor segmentation using a UNet-PWP deep-learning model with XAI on CT scan images","volume":"13","author":"Rao","journal-title":"Diagnostics (Basel)"},{"key":"R19","doi-asserted-by":"crossref","unstructured":"Ranjbarzadeh R Kele\u015f A Crane M et al. Ebtag: explainable brain tumor segmentation with efficientnetv2, attention mechanism, and grad-cam in clinical and public datasets. SSRN. Preprint posted online on December 3, 2024. [doi: 10.2139\/ssrn.5023648]","DOI":"10.2139\/ssrn.5023648"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s00530-025-02075-y","article-title":"Explainable deep learning framework for brain tumor segmentation using vision transformer and conditional random fields","volume":"32","author":"Safarpour","journal-title":"Multimedia Systems"},{"key":"R21","doi-asserted-by":"crossref","unstructured":"Choi SR Ko K Baek SJ Lee S Lee J Lee M . Enhanced kidney tumor segmentation in CT scans using a simplified UNETR with organ information. Presented at: 2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC); Feb 19-22, 2024; Osaka, Japan. [doi: 10.1109\/ICAIIC60209.2024.10463270]","DOI":"10.1109\/ICAIIC60209.2024.10463270"},{"issue":"3","key":"R22","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8030055","article-title":"Kidney tumor semantic segmentation using deep learning: a survey of state-of-the-art","volume":"8","author":"Abdelrahman","journal-title":"J Imaging"},{"key":"R23","doi-asserted-by":"crossref","unstructured":"Ranjbarzadeh R Anari S Crane M Bendechache M . A hybrid UNet and vision transformer architecture with multi-scale fusion for brain tumor segmentation. Presented at: 2024 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2024); Feb 19-22, 2024; Osaka, Japan. [doi: 10.1007\/978-981-96-3863-5_44]","DOI":"10.1007\/978-981-96-3863-5_44"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Safarpour H Anari S Ranjbarzadeh R Safavi S Bendechache M . A dual-phase segmentation framework utilizing gumbel-softmax and a cascaded swin transformer for multi-class brain tumor segmentation. In Review. Preprint posted online on July 25, 2025. [doi: 10.21203\/rs.3.rs-7093467\/v1]","DOI":"10.21203\/rs.3.rs-7093467\/v1"},{"issue":"3","key":"R25","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1007\/s42044-025-00258-4","article-title":"The impact of backbone selection in YOLOv8 models on brain tumor localization","volume":"8","author":"Ranjbarzadeh","journal-title":"Iran J Comput Sci"},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Ranjbarzadeh R Keles A Ozisik PA et al. Combining DeepLabV3 with attention mechanisms for accurate brain tumor segmentation: insights from BraTS 2020 and a private clinical dataset. Presented at: 2024 12th European Workshop on Visual Information Processing (EUVIP); Sep 8-11, 2024; Geneva, Switzerland. [doi: 10.1109\/EUVIP61797.2024.10772776]","DOI":"10.1109\/EUVIP61797.2024.10772776"},{"issue":"12","key":"R27","doi-asserted-by":"publisher","first-page":"7193","DOI":"10.1016\/j.acra.2025.08.020","article-title":"Automated kidney tumor segmentation in CT images using deep learning: a multi-stage approach","volume":"32","author":"Kan","journal-title":"Acad Radiol"},{"issue":"4","key":"R28","doi-asserted-by":"publisher","first-page":"3915","DOI":"10.1007\/s42835-026-02620-3","article-title":"Deep learning based segmentation of renal cancer detection and segmentation enhanced 3D CT images","volume":"21","author":"Swapna","journal-title":"J Electr Eng Technol"},{"issue":"7","key":"R29","doi-asserted-by":"publisher","first-page":"5021","DOI":"10.1007\/s00330-020-07608-9","article-title":"Automated segmentation of kidney and renal mass and automated detection of renal mass in CT urography using 3D U-Net-based deep convolutional neural network","volume":"31","author":"Lin","journal-title":"Eur Radiol"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","first-page":"83","DOI":"10.3169\/mta.13.83","article-title":"[Paper] Kidney and renal tumor segmentation by nnU-Net Using 3D CT data from different sources","volume":"13","author":"Gido","journal-title":"ITE Trans Media Technol Appl"},{"key":"R31","unstructured":"Vaswani A Shazeer N Parmar N et al. Attention is all you need. In: Guyon I von Luxburg U Bengio S et al, editors. Advances in Neural Information Processing Systems 30 Proceedings of the 31st Annual Conference on Neural Information Processing Systems. Curran Associates; 2017:5998-6008. URL: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","DOI":"10.3390\/tomography11010003","article-title":"Dual-stage AI model for enhanced CT imaging: precision segmentation of kidney and tumors","volume":"11","author":"Karunanayake","journal-title":"Tomography"},{"key":"R33","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101821","article-title":"The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: results of the KiTS19 challenge","volume":"67","author":"Heller","journal-title":"Med Image Anal"},{"key":"R34","unstructured":"KiTS19. GitHub. URL: https:\/\/github.com\/neheller\/kits19 [Accessed 08-08-2026]"},{"key":"R35","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106501","article-title":"Eres-UNet++: liver CT image segmentation based on high-efficiency channel attention and Res-UNet++","volume":"158","author":"Li","journal-title":"Comput Biol Med"},{"key":"R36","doi-asserted-by":"crossref","unstructured":"Chen LC Zhu Y Papandreou G Schroff F Adam H . Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari V Hebert M Sminchisescu C Weiss Y , editors. Computer Vision \u2013 ECCV 2018 Lecture Notes in Computer Science. Vol 11211. Springer; :801-818. [doi: 10.1007\/978-3-030-01234-2_49]","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"R37","doi-asserted-by":"crossref","unstructured":"Chollet F . Xception: deep learning with depthwise separable convolutions. Presented at: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Jul 21-26, 2017; Honolulu, HI. [doi: 10.1109\/CVPR.2017.195]","DOI":"10.1109\/CVPR.2017.195"},{"key":"R38","doi-asserted-by":"crossref","unstructured":"Sandler M Howard A Zhu M Zhmoginov A Chen LC . MobileNetV2: inverted residuals and linear bottlenecks. Presented at: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); Jun 18-23, 2018; Salt Lake City, UT. [doi: 10.1109\/CVPR.2018.00474]","DOI":"10.1109\/CVPR.2018.00474"},{"issue":"4","key":"R39","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs","volume":"40","author":"Chen","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"R40","unstructured":"Liu Y Shao Z Hoffmann N . Global attention mechanism: retain information to enhance channel-spatial interactions. arXiv. Preprint posted online on December 10 2021. [doi: 10.48550\/arXiv.2112.05561]"},{"key":"R41","doi-asserted-by":"crossref","unstructured":"Wang Q Wu B Zhu P Li P Zuo W Hu Q . ECA-net: efficient channel attention for deep convolutional neural networks. Presented at: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); Jun 13-19, 2020; Seattle, WA, USA. URL: https:\/\/ieeexplore.ieee.org\/xpl\/mostRecentIssue.jsp?punumber=9142308 [Accessed 23-08-2026] [doi: 10.1109\/CVPR42600.2020.01155]","DOI":"10.1109\/CVPR42600.2020.01155"},{"issue":"1","key":"R42","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-020-00435-w","article-title":"Weakly-supervised convolutional neural networks of renal tumor segmentation in abdominal CTA images","volume":"20","author":"Yang","journal-title":"BMC Med Imaging"},{"key":"R43","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116270","article-title":"Kidney tumor segmentation from computed tomography images using DeepLabv3+ 2.5D model","volume":"192","author":"da Cruz","journal-title":"Expert Syst Appl"},{"issue":"6","key":"R44","doi-asserted-by":"publisher","first-page":"1673","DOI":"10.1007\/s11517-024-03025-y","article-title":"ASD-Net: a novel U-Net based asymmetric spatial-channel convolution network for precise kidney and kidney tumor image segmentation","volume":"62","author":"Ji","journal-title":"Med Biol Eng Comput"},{"key":"R45","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101721","article-title":"MB-FSGAN: Joint segmentation and quantification of kidney tumor on CT by the multi-branch feature sharing generative adversarial network","volume":"64","author":"Ruan","journal-title":"Med Image Anal"},{"issue":"10","key":"R46","doi-asserted-by":"publisher","first-page":"1772","DOI":"10.3390\/math8101772","article-title":"Kidney and renal tumor segmentation using a hybrid V-Net-based model","volume":"8","author":"T\u00fcrk","journal-title":"Mathematics"},{"issue":"1","key":"R47","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-023-02189-1","article-title":"2.5D MFFAU-Net: a convolutional neural network for kidney segmentation","volume":"23","author":"Sun","journal-title":"BMC Med Inform Decis Mak"},{"key":"R48","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2018.00215","article-title":"Deep learning renal segmentation for fully automated radiation dose estimation in unsealed source therapy","volume":"8","author":"Jackson","journal-title":"Front Oncol"},{"key":"R49","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.853281","article-title":"Kidney tumor segmentation based on FR2PAttU-Net model","volume":"12","author":"Sun","journal-title":"Front Oncol"},{"key":"R50","unstructured":"KAI. Central Platform of Digital Disease (CPPDD). URL: http:\/\/www.cppdd.cn\/KAI [Accessed 08-08-2026]"},{"key":"R51","unstructured":"GAM-deeplabv3plus-kidneytumor. GitHUb. URL: https:\/\/github.com\/yueyanzhaocs-byte\/GAM-DeepLabv3Plus-KidneyTumor [Accessed 08-08-2026]"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T20:53:18Z","timestamp":1789505598000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e78523"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"references-count":51,"URL":"https:\/\/doi.org\/10.2196\/78523","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]},"article-number":"v14i1_supple78523"}}