{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T00:55:15Z","timestamp":1771548915065,"version":"3.50.1"},"reference-count":30,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"crossref","award":["2022-YGJC-52"],"award-info":[{"award-number":["2022-YGJC-52"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Medical image segmentation is essential to image-based disease analysis and has proven to be significantly helpful for doctors to make decisions. Due to the low-contrast of some medical images, the accurate segmentation of medical images has always been a challenging problem. The experiment found that UNet with current loss functions cannot capture subtle information in target contours or regions in low-contrast medical images, which are crucial for subsequent disease diagnosis. We propose a robust loss by incorporating the difference in average radial derivative (ARD), length and region area to further help the network to achieve more accurate segmentation results. We evaluated the proposed loss function using UNet as the base segmentation network compared to five conventional loss functions on one private and four public medical image datasets. Experimental results illustrate that UNet with the proposed loss function can achieve the best segmentation performance, even better than the outstanding deep learning models with original loss functions. Furthermore, three representative datasets were chosen to validate the effectiveness of the proposed <jats:italic>\u03b4<\/jats:italic>ARD loss function with seven different models. The experiments revealed <jats:italic>\u03b4<\/jats:italic>ARD loss\u2019s plug-and-play feature and its robustness over multiple models and datasets.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad1d06","type":"journal-article","created":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T22:26:06Z","timestamp":1704925566000},"page":"015013","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["\u03b4ARD\n\t   loss for low-contrast medical image segmentation"],"prefix":"10.1088","volume":"5","author":[{"given":"Yu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiadong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5054-3586","authenticated-orcid":true,"given":"He","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Sang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,1,19]]},"reference":[{"key":"mlstad1d06bib1","doi-asserted-by":"publisher","first-page":"729","DOI":"10.3390\/healthcare10040729","article-title":"Busis: a benchmark for breast ultrasound image segmentation","volume":"10","author":"Zhang","year":"2022","journal-title":"Healthcare"},{"key":"mlstad1d06bib2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102035","article-title":"Loss odyssey in medical image segmentation","volume":"71","author":"Jun","year":"2021","journal-title":"Med. Image Anal."},{"key":"mlstad1d06bib3","first-page":"pp 11632","article-title":"Learning active contour models for medical image segmentation","author":"Chen","year":"2019"},{"key":"mlstad1d06bib4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101851","article-title":"Boundary loss for highly unbalanced segmentation","volume":"67","author":"Kervadec","year":"2021","journal-title":"Med. Image Anal."},{"key":"mlstad1d06bib5","first-page":"pp 285","article-title":"Boundary loss for highly unbalanced segmentation","author":"Kervadec","year":"2019"},{"key":"mlstad1d06bib6","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1109\/TMI.2019.2930068","article-title":"Reducing the hausdorff distance in medical image segmentation with convolutional neural networks","volume":"39","author":"Karimi","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad1d06bib7","article-title":"Bridging category-level and instance-level semantic image segmentation","author":"Zifeng","year":"2016"},{"key":"mlstad1d06bib8","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstad1d06bib9","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46976-8_19","article-title":"The importance of skip connections in biomedical image segmentation","author":"Drozdzal","year":"2016"},{"key":"mlstad1d06bib10","first-page":"pp 851","article-title":"Rethinking dice loss for medical image segmentation","author":"Zhao","year":"2020"},{"key":"mlstad1d06bib11","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2012","journal-title":"Commun. ACM"},{"key":"mlstad1d06bib12","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"mlstad1d06bib13","first-page":"pp 3","article-title":"Unet++: A nested u-net architecture for medical image segmentation","volume":"vol 11045","author":"Zhou","year":"2018"},{"key":"mlstad1d06bib14","first-page":"pp 11624","article-title":"Learning active contour models for medical image segmentation","author":"Chen","year":"2019"},{"key":"mlstad1d06bib15","first-page":"pp 7132","article-title":"Squeeze-and-excitation networks","author":"Jie","year":"2017"},{"key":"mlstad1d06bib16","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.neucom.2019.07.006","article-title":"Use-net: incorporating squeeze-and-excitation blocks into u-net for prostate zonal segmentation of multi-institutional mri datasets","volume":"365","author":"Rundo","year":"2019","journal-title":"Neurocomputing"},{"key":"mlstad1d06bib17","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ac53bd","article-title":"A few-shot u-net deep learning model for lung cancer lesion segmentation via pet\/ct imaging","volume":"8","author":"Protonotarios","year":"2022","journal-title":"Biomed. Phys. Eng. Express"},{"key":"mlstad1d06bib18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0221535","article-title":"An rdau-net model for lesion segmentation in breast ultrasound images","volume":"14","author":"Zhuang","year":"2019","journal-title":"PLoS One"},{"key":"mlstad1d06bib19","doi-asserted-by":"publisher","first-page":"729","DOI":"10.3390\/healthcare10040729","article-title":"Busis: a benchmark for breast ultrasound image segmentation","volume":"10","author":"Xian","year":"2018","journal-title":"Healthcare"},{"key":"mlstad1d06bib20","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1118\/1.1386426","article-title":"Automatic segmentation of breast lesions on ultrasound","volume":"28","author":"Horsch","year":"2001","journal-title":"Med. Phys."},{"key":"mlstad1d06bib21","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"mlstad1d06bib22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_4","article-title":"Medical transformer: gated axial-attention for medical image segmentation","author":"Valanarasu","year":"2021","journal-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI"},{"key":"mlstad1d06bib23","doi-asserted-by":"publisher","first-page":"4512","DOI":"10.21037\/qims-22-33","article-title":"Dilated transformer: residual axial attention for breast ultrasound image segmentation","volume":"12","author":"Shen","year":"2022","journal-title":"Quant. Imaging Med. Surg."},{"key":"mlstad1d06bib24","article-title":"Transunet: transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"mlstad1d06bib25","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1118\/1.3265959","article-title":"A F C Infantosi and W C A Pereira 2010 Computerized lesion segmentation of breast ultrasound based on marker-controlled watershed transformation","volume":"37","author":"G\u00f3mez","journal-title":"Med. Phys."},{"key":"mlstad1d06bib26","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863","article-title":"Dataset of breast ultrasound images","volume":"28","author":"Al-Dhabyani","year":"2020","journal-title":"Data Brief"},{"key":"mlstad1d06bib27","doi-asserted-by":"publisher","first-page":"1380","DOI":"10.1109\/TMI.2019.2947628","article-title":"A multi-organ nucleus segmentation challenge","volume":"39","author":"Kumar","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad1d06bib28","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.media.2016.08.008","article-title":"Gland segmentation in colon histology images: the glas challenge contest","volume":"35","author":"Sirinukunwattana","year":"2017","journal-title":"Med. Image Anal."},{"key":"mlstad1d06bib29","article-title":"Attention u-net: learning where to look for the pancreas","author":"Oktay","year":"2018"},{"key":"mlstad1d06bib30","doi-asserted-by":"publisher","first-page":"97457","DOI":"10.1109\/ACCESS.2021.3094925","article-title":"Ghost-unet: an asymmetric encoder-decoder architecture for semantic segmentation from scratch","volume":"9","author":"Abaspur Kazerouni","year":"2021","journal-title":"IEEE Access"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1d06","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1d06\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1d06","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1d06\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1d06\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1d06\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1d06\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1d06\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T10:34:00Z","timestamp":1705660440000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1d06"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1,19]]},"published-print":{"date-parts":[[2024,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad1d06","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,19]]},"assertion":[{"value":"\u03b4ARD\n\t   loss for low-contrast medical image segmentation","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-10-11","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-01-10","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-01-19","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}