{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/uldor-a-universal-lesion-detector-for-ct","title":"ULDor: A Universal Lesion Detector for CT Scans with Pseudo Masks and Hard Negative Example Mining","arxiv_id":"1901.06359","date":"2019-01-18","proceeding":null,"authors":["Youbao Tang","Ke Yan","Yu-Xing Tang","Jiamin Liu","Jing Xiao","Ronald M. Summers"],"abstract":"Automatic lesion detection from computed tomography (CT) scans is an\nimportant task in medical imaging analysis. It is still very challenging due to\nsimilar appearances (e.g. intensity and texture) between lesions and other\ntissues, making it especially difficult to develop a universal lesion detector.\nInstead of developing a specific-type lesion detector, this work builds a\nUniversal Lesion Detector (ULDor) based on Mask R-CNN, which is able to detect\nall different kinds of lesions from whole body parts. As a state-of-the-art\nobject detector, Mask R-CNN adds a branch for predicting segmentation masks on\neach Region of Interest (RoI) to improve the detection performance. However, it\nis almost impossible to manually annotate a large-scale dataset with\npixel-level lesion masks to train the Mask R-CNN for lesion detection. To\naddress this problem, this work constructs a pseudo mask for each lesion region\nthat can be considered as a surrogate of the real mask, based on which the Mask\nR-CNN is employed for lesion detection. On the other hand, this work proposes a\nhard negative example mining strategy to reduce the false positives for\nimproving the detection performance. Experimental results on the NIH DeepLesion\ndataset demonstrate that the ULDor is enhanced using pseudo masks and the\nproposed hard negative example mining strategy and achieves a sensitivity of\n86.21% with five false positives per image.","url_abs":"http://arxiv.org/abs/1901.06359v1","url_pdf":"http://arxiv.org/pdf/1901.06359v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"uldor-a-universal-lesion-detector-for-ct","repo_url":"https://github.com/fsafe/Capstone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computed-tomography-ct","task_name":"Computed Tomography (CT)"},{"task_slug":"lesion-detection","task_name":"Lesion Detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.06359","atlas_url":"https://app.syntology.ai/?focus=1901.06359","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}