arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.06131cs.CVcs.LG
收藏

UniverSeg:通用医学图像分割

UniverSeg: Universal Medical Image Segmentation

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);Cornell University(康奈尔大学);MGH(麻省总医院);HMS(哈佛医学院)

Victor Ion Butoi, Jose Javier Gonzalez Ortiz, Tianyu Ma, Mert R. Sabuncu, John Guttag, Adrian V. Dalca

AI总结:

UniverSeg 提出一种无需额外训练的通用医学图像分割方法,通过 Cross-Block 机制和包含 53 个数据集、超 22,000 次扫描的 MegaMedical 集合,在未见分割任务上显著优于现有方法。

摘要:

尽管深度学习模型已成为医学图像分割的主流方法,但它们通常无法泛化到涉及新解剖结构、成像模态或标签的未见分割任务。面对新的分割任务,研究人员通常需要训练或微调模型,这不仅耗时,而且对往往缺乏训练神经网络所需资源和专业知识的临床研究人员构成了重大障碍。我们提出 UniverSeg,一种无需额外训练即可解决未见医学分割任务的方法。给定一个查询图像以及定义新分割任务的图像-标签示例集,UniverSeg 采用一种新的 Cross-Block 机制来生成准确的分割图,而无需额外训练。为了实现对新任务的泛化,我们收集并标准化了 53 个开放获取的医学分割数据集,包含超过 22,000 次扫描,我们将其称为 MegaMedical。我们利用该集合在多样化的解剖结构和成像模态上训练 UniverSeg。我们证明 UniverSeg 在未见任务上显著优于若干相关方法,并对所提出系统的重要方面进行了深入分析和洞察。UniverSeg 的源代码和模型权重可在 https://universeg.csail.mit.edu 免费获取。

英文摘要:

While deep learning models have become the predominant method for medical image segmentation, they are typically not capable of generalizing to unseen segmentation tasks involving new anatomies, image modalities, or labels. Given a new segmentation task, researchers generally have to train or fine-tune models, which is time-consuming and poses a substantial barrier for clinical researchers, who often lack the resources and expertise to train neural networks. We present UniverSeg, a method for solving unseen medical segmentation tasks without additional training. Given a query image and example set of image-label pairs that define a new segmentation task, UniverSeg employs a new Cross-Block mechanism to produce accurate segmentation maps without the need for additional training. To achieve generalization to new tasks, we have gathered and standardized a collection of 53 open-access medical segmentation datasets with over 22,000 scans, which we refer to as MegaMedical. We used this collection to train UniverSeg on a diverse set of anatomies and imaging modalities. We demonstrate that UniverSeg substantially outperforms several related methods on unseen tasks, and thoroughly analyze and draw insights about important aspects of the proposed system. The UniverSeg source code and model weights are freely available at https://universeg.csail.mit.edu

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑