{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T09:08:15Z","timestamp":1784538495349,"version":"3.55.0"},"reference-count":33,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Accurate segmentation of kidneys and renal tumors in computed tomography (CT) images is important for renal cancer diagnosis, treatment planning, and quantitative image analysis. However, abdominal CT volumes often show anisotropic resolution, with lower resolution along the slice direction than within the axial plane. This characteristic may reduce the effectiveness of conventional 3D convolutions and make it difficult to accurately segment tumors and boundary regions. In this study, we propose Adaptive anisotropic convolutional U-Net (AAsU-Net), an anisotropy-aware 3D segmentation network for renal neoplasm segmentation. The network includes an adaptive anisotropic convolution (AAs-conv) module, which combines spatially separable convolution and standard 3D convolution in parallel and adaptively fuses their features to improve representation under anisotropic imaging conditions. We also introduce a cross-scale feature fusion (CSFF) module in the encoder to preserve shallow structural details and reduce information loss during repeated downsampling. We evaluated the proposed method on the KiTS19 and KiTS21 datasets. On KiTS19, AAsU-Net achieved Dice scores of 0.970 \u00b1 0.018 for kidney segmentation and 0.851 \u00b1 0.031 for tumor segmentation, improving upon the baseline 3D U-Net by 1.19% and 3.30%, respectively. On KiTS21, the proposed method achieved a tumor Dice score of 0.879 \u00b1 0.039 and an HD95 of 7.93 \u00b1 2.74\u00a0mm, outperforming several recent methods, including 3D UX-Net, nnFormer, and SegMamba. These results suggest that AAsU-Net can improve segmentation accuracy and boundary delineation in anisotropic CT images and may provide useful support for automated renal tumor analysis.<\/jats:p>","DOI":"10.7717\/peerj-cs.4047","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:47:01Z","timestamp":1784537221000},"page":"e4047","source":"Crossref","is-referenced-by-count":0,"title":["AAsU-Net: adaptive anisotropic convolutional network for renal neoplasm segmentation"],"prefix":"10.7717","volume":"12","author":[{"given":"Lei","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuqiang","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"10.7717\/peerj-cs.4047\/ref-1","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1007\/978-3-319-46723-8_49","article-title":"3D U-Net: learning dense volumetric segmentation from sparse annotation","author":"\u00c7i\u00e7ek","year":"2016"},{"key":"10.7717\/peerj-cs.4047\/ref-2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.07781","article-title":"3D TransUNet: advancing medical image segmentation through vision transformers","author":"Chen","year":"2023"},{"issue":"2","key":"10.7717\/peerj-cs.4047\/ref-3","doi-asserted-by":"publisher","first-page":"103280","DOI":"10.1016\/j.media.2024.103280","article-title":"TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of transformers","volume":"98","author":"Chen","year":"2024","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.4047\/ref-4","doi-asserted-by":"publisher","first-page":"04846","DOI":"10.48550\/arXiv.2205.04846","article-title":"MNet: rethinking 2D\/3D networks for anisotropic medical image segmentation","volume":"2205","author":"Dong","year":"2022","journal-title":"International Joint Conference on Artificial Intelligence"},{"issue":"2","key":"10.7717\/peerj-cs.4047\/ref-5","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: images are more than pictures, they are data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"10.7717\/peerj-cs.4047\/ref-6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.00752","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"10.7717\/peerj-cs.4047\/ref-7","first-page":"1748","article-title":"UNETR: transformers for 3D medical image segmentation","author":"Hatamizadeh","year":"2022"},{"issue":"1","key":"10.7717\/peerj-cs.4047\/ref-8","doi-asserted-by":"publisher","first-page":"101821","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","year":"2021","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.4047\/ref-9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.01984","article-title":"The KiTS21 challenge: automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT","author":"Heller","year":"2023"},{"key":"10.7717\/peerj-cs.4047\/ref-10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.00445","article-title":"The KiTS19 challenge data: 300 kidney tumor cases with clinical context, CT semantic segmentations, and surgical outcomes","author":"Heller","year":"2019"},{"key":"10.7717\/peerj-cs.4047\/ref-11","first-page":"80","article-title":"A two-stage cascaded deep neural network with multi-decoding paths for kidney tumor segmentation","author":"He","year":"2022"},{"key":"10.7717\/peerj-cs.4047\/ref-12","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"issue":"2","key":"10.7717\/peerj-cs.4047\/ref-13","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nature Methods"},{"issue":"5","key":"10.7717\/peerj-cs.4047\/ref-14","doi-asserted-by":"publisher","first-page":"103334","DOI":"10.1016\/j.bspc.2021.103334","article-title":"Renal tumors segmentation in abdomen CT images using 3D-CNN and ConvLSTM","volume":"72","author":"Kang","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.7717\/peerj-cs.4047\/ref-15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.15076","article-title":"3D UX-net: a large kernel volumetric ConvNet modernizing hierarchical transformer for medical image segmentation","author":"Lee","year":"2022"},{"key":"10.7717\/peerj-cs.4047\/ref-16","first-page":"562","article-title":"Deeply-supervised nets","author":"Lee","year":"2015"},{"key":"10.7717\/peerj-cs.4047\/ref-17","first-page":"2906","article-title":"Z-Net: an anisotropic 3D DCNN for medical CT volume segmentation","author":"Li","year":"2020"},{"key":"10.7717\/peerj-cs.4047\/ref-18","first-page":"510","article-title":"Selective kernel networks","author":"Li","year":"2019"},{"issue":"13","key":"10.7717\/peerj-cs.4047\/ref-19","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.4047\/ref-20","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1007\/978-3-030-00934-2_94","article-title":"3D anisotropic hybrid network: transferring convolutional features from 2D images to 3D anisotropic volumes","volume":"11071","author":"Liu","year":"2018"},{"issue":"7","key":"10.7717\/peerj-cs.4047\/ref-21","doi-asserted-by":"publisher","first-page":"3523","DOI":"10.1109\/TPAMI.2021.3059968","article-title":"Image segmentation using deep learning: a survey","volume":"44","author":"Minaee","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.4047\/ref-22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.03999","article-title":"Attention U-Net: learning where to look for the pancreas","author":"Oktay","year":"2018"},{"issue":"3","key":"10.7717\/peerj-cs.4047\/ref-23","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1007\/s11845-022-03113-8","article-title":"Tumorous kidney segmentation in abdominal CT images using active contour and 3D-UNet","volume":"192","author":"Pandey","year":"2023","journal-title":"Irish Journal of Medical Science"},{"key":"10.7717\/peerj-cs.4047\/ref-24","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation, medical image computing and computer-assisted intervention\u2014MICCAI 2015","volume-title":"Lecture Notes in Computer Science","volume":"9351","author":"Ronneberger","year":"2015"},{"issue":"12","key":"10.7717\/peerj-cs.4047\/ref-25","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1001\/jama.2024.12848","article-title":"Renal cell carcinoma: a review","volume":"332","author":"Rose","year":"2024","journal-title":"The Journal of the American Medical Association"},{"key":"10.7717\/peerj-cs.4047\/ref-26","first-page":"20730","article-title":"Self-supervised pre-training of swin transformers for 3D medical image analysis","author":"Tang","year":"2022"},{"key":"10.7717\/peerj-cs.4047\/ref-27","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"issue":"2","key":"10.7717\/peerj-cs.4047\/ref-28","doi-asserted-by":"publisher","first-page":"e345","DOI":"10.1016\/j.clgc.2018.07.024","article-title":"Imaging in suspected renal-cell carcinoma: systematic review","volume":"17","author":"Vogel","year":"2019","journal-title":"Clinical Genitourinary Cancer"},{"issue":"4","key":"10.7717\/peerj-cs.4047\/ref-29","doi-asserted-by":"publisher","first-page":"102258","DOI":"10.1016\/j.compmedimag.2023.102301","article-title":"MDM-U-Net: a novel network for renal cancer structure segmentation","volume":"108","author":"Weng","year":"2023","journal-title":"Computerized Medical Imaging and Graphics"},{"issue":"4","key":"10.7717\/peerj-cs.4047\/ref-30","doi-asserted-by":"publisher","first-page":"1524","DOI":"10.1049\/cit2.12179","article-title":"Short-term and long-term memory self-attention network for segmentation of tumours in 3D medical images","volume":"8","author":"Wen","year":"2023","journal-title":"CAAI Transactions on Intelligence Technology"},{"key":"10.7717\/peerj-cs.4047\/ref-31","first-page":"578","article-title":"SegMamba: long-range sequential modeling Mamba for 3D medical image segmentation","author":"Xing","year":"2024"},{"issue":"12","key":"10.7717\/peerj-cs.4047\/ref-32","doi-asserted-by":"publisher","first-page":"100357","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","year":"2020","journal-title":"Informatics in Medicine Unlocked"},{"key":"10.7717\/peerj-cs.4047\/ref-33","doi-asserted-by":"publisher","first-page":"4036","DOI":"10.1109\/TIP.2023.3293771","article-title":"nnFormer: volumetric medical image segmentation via a 3D transformer","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Transactions on Image Processing"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-4047.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-4047.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-4047.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-4047.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:47:05Z","timestamp":1784537225000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-4047"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":33,"alternative-id":["10.7717\/peerj-cs.4047"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.4047","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]},"article-number":"e4047"}}