Daniel Capellán-Martín, Zhifan Jiang, Abhijeet Parida, Xinyang Liu, Van Lam, Hareem Nisar, Austin Tapp, Sarah Elsharkawi, Maria J. Ledesma-Carbayo, Syed Muhammad Anwar, Marius George Linguraru
{"title":"磁共振成像中的脑肿瘤分割模型组合","authors":"Daniel Capellán-Martín, Zhifan Jiang, Abhijeet Parida, Xinyang Liu, Van Lam, Hareem Nisar, Austin Tapp, Sarah Elsharkawi, Maria J. Ledesma-Carbayo, Syed Muhammad Anwar, Marius George Linguraru","doi":"arxiv-2409.08232","DOIUrl":null,"url":null,"abstract":"Segmenting brain tumors in multi-parametric magnetic resonance imaging\nenables performing quantitative analysis in support of clinical trials and\npersonalized patient care. This analysis provides the potential to impact\nclinical decision-making processes, including diagnosis and prognosis. In 2023,\nthe well-established Brain Tumor Segmentation (BraTS) challenge presented a\nsubstantial expansion with eight tasks and 4,500 brain tumor cases. In this\npaper, we present a deep learning-based ensemble strategy that is evaluated for\nnewly included tumor cases in three tasks: pediatric brain tumors (PED),\nintracranial meningioma (MEN), and brain metastases (MET). In particular, we\nensemble outputs from state-of-the-art nnU-Net and Swin UNETR models on a\nregion-wise basis. Furthermore, we implemented a targeted post-processing\nstrategy based on a cross-validated threshold search to improve the\nsegmentation results for tumor sub-regions. The evaluation of our proposed\nmethod on unseen test cases for the three tasks resulted in lesion-wise Dice\nscores for PED: 0.653, 0.809, 0.826; MEN: 0.876, 0.867, 0.849; and MET: 0.555,\n0.6, 0.58; for the enhancing tumor, tumor core, and whole tumor, respectively.\nOur method was ranked first for PED, third for MEN, and fourth for MET,\nrespectively.","PeriodicalId":501289,"journal":{"name":"arXiv - EE - Image and Video Processing","volume":"17 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Model Ensemble for Brain Tumor Segmentation in Magnetic Resonance Imaging\",\"authors\":\"Daniel Capellán-Martín, Zhifan Jiang, Abhijeet Parida, Xinyang Liu, Van Lam, Hareem Nisar, Austin Tapp, Sarah Elsharkawi, Maria J. Ledesma-Carbayo, Syed Muhammad Anwar, Marius George Linguraru\",\"doi\":\"arxiv-2409.08232\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Segmenting brain tumors in multi-parametric magnetic resonance imaging\\nenables performing quantitative analysis in support of clinical trials and\\npersonalized patient care. This analysis provides the potential to impact\\nclinical decision-making processes, including diagnosis and prognosis. In 2023,\\nthe well-established Brain Tumor Segmentation (BraTS) challenge presented a\\nsubstantial expansion with eight tasks and 4,500 brain tumor cases. In this\\npaper, we present a deep learning-based ensemble strategy that is evaluated for\\nnewly included tumor cases in three tasks: pediatric brain tumors (PED),\\nintracranial meningioma (MEN), and brain metastases (MET). In particular, we\\nensemble outputs from state-of-the-art nnU-Net and Swin UNETR models on a\\nregion-wise basis. Furthermore, we implemented a targeted post-processing\\nstrategy based on a cross-validated threshold search to improve the\\nsegmentation results for tumor sub-regions. The evaluation of our proposed\\nmethod on unseen test cases for the three tasks resulted in lesion-wise Dice\\nscores for PED: 0.653, 0.809, 0.826; MEN: 0.876, 0.867, 0.849; and MET: 0.555,\\n0.6, 0.58; for the enhancing tumor, tumor core, and whole tumor, respectively.\\nOur method was ranked first for PED, third for MEN, and fourth for MET,\\nrespectively.\",\"PeriodicalId\":501289,\"journal\":{\"name\":\"arXiv - EE - Image and Video Processing\",\"volume\":\"17 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Image and Video Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.08232\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Image and Video Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08232","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Model Ensemble for Brain Tumor Segmentation in Magnetic Resonance Imaging
Segmenting brain tumors in multi-parametric magnetic resonance imaging
enables performing quantitative analysis in support of clinical trials and
personalized patient care. This analysis provides the potential to impact
clinical decision-making processes, including diagnosis and prognosis. In 2023,
the well-established Brain Tumor Segmentation (BraTS) challenge presented a
substantial expansion with eight tasks and 4,500 brain tumor cases. In this
paper, we present a deep learning-based ensemble strategy that is evaluated for
newly included tumor cases in three tasks: pediatric brain tumors (PED),
intracranial meningioma (MEN), and brain metastases (MET). In particular, we
ensemble outputs from state-of-the-art nnU-Net and Swin UNETR models on a
region-wise basis. Furthermore, we implemented a targeted post-processing
strategy based on a cross-validated threshold search to improve the
segmentation results for tumor sub-regions. The evaluation of our proposed
method on unseen test cases for the three tasks resulted in lesion-wise Dice
scores for PED: 0.653, 0.809, 0.826; MEN: 0.876, 0.867, 0.849; and MET: 0.555,
0.6, 0.58; for the enhancing tumor, tumor core, and whole tumor, respectively.
Our method was ranked first for PED, third for MEN, and fourth for MET,
respectively.