{"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/generalised-wasserstein-dice-score-for","title":"Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation using Holistic Convolutional Networks","arxiv_id":"1707.00478","date":"2017-07-03","proceeding":null,"authors":["Lucas Fidon","Wenqi Li","Luis C. Garcia-Peraza-Herrera","Jinendra Ekanayake","Neil Kitchen","Sebastien Ourselin","Tom Vercauteren"],"abstract":"The Dice score is widely used for binary segmentation due to its robustness\nto class imbalance. Soft generalisations of the Dice score allow it to be used\nas a loss function for training convolutional neural networks (CNN). Although\nCNNs trained using mean-class Dice score achieve state-of-the-art results on\nmulti-class segmentation, this loss function does neither take advantage of\ninter-class relationships nor multi-scale information. We argue that an\nimproved loss function should balance misclassifications to favour predictions\nthat are semantically meaningful. This paper investigates these issues in the\ncontext of multi-class brain tumour segmentation. Our contribution is\nthreefold. 1) We propose a semantically-informed generalisation of the Dice\nscore for multi-class segmentation based on the Wasserstein distance on the\nprobabilistic label space. 2) We propose a holistic CNN that embeds spatial\ninformation at multiple scales with deep supervision. 3) We show that the joint\nuse of holistic CNNs and generalised Wasserstein Dice scores achieves\nsegmentations that are more semantically meaningful for brain tumour\nsegmentation.","url_abs":"http://arxiv.org/abs/1707.00478v4","url_pdf":"http://arxiv.org/pdf/1707.00478v4.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":"generalised-wasserstein-dice-score-for","repo_url":"https://github.com/LucasFidon/GeneralizedWassersteinDiceLoss","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.00478","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}