{"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/supervised-saliency-map-driven-segmentation","title":"Supervised Saliency Map Driven Segmentation of the Lesions in Dermoscopic Images","arxiv_id":"1703.00087","date":"2017-02-28","proceeding":null,"authors":["Mostafa Jahanifar","Neda Zamani Tajeddin","Babak Mohammadzadeh Asl","Ali Gooya"],"abstract":"Lesion segmentation is the first step in most automatic melanoma recognition\nsystems. Deficiencies and difficulties in dermoscopic images such as color\ninconstancy, hair occlusion, dark corners and color charts make lesion\nsegmentation an intricate task. In order to detect the lesion in the presence\nof these problems, we propose a supervised saliency detection method tailored\nfor dermoscopic images based on the discriminative regional feature integration\n(DRFI). DRFI method incorporates multi-level segmentation, regional contrast,\nproperty, background descriptors, and a random forest regressor to create\nsaliency scores for each region in the image. In our improved saliency\ndetection method, mDRFI, we have added some new features to regional property\ndescriptors. Also, in order to achieve more robust regional background\ndescriptors, a thresholding algorithm is proposed to obtain a new\npseudo-background region. Findings reveal that mDRFI is superior to DRFI in\ndetecting the lesion as the salient object in dermoscopic images. The proposed\noverall lesion segmentation framework uses detected saliency map to construct\nan initial mask of the lesion through thresholding and post-processing\noperations. The initial mask is then evolving in a level set framework to fit\nbetter on the lesion's boundaries. The results of evaluation tests on three\npublic datasets show that our proposed segmentation method outperforms the\nother conventional state-of-the-art segmentation algorithms and its performance\nis comparable with most recent approaches that are based on deep convolutional\nneural networks.","url_abs":"http://arxiv.org/abs/1703.00087v4","url_pdf":"http://arxiv.org/pdf/1703.00087v4.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":"supervised-saliency-map-driven-segmentation","repo_url":"https://github.com/mjahanifar/mDRFI_matlab","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"lesion-segmentation","task_name":"Lesion Segmentation"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}