当前位置: X-MOL 学术IEEE Trans. Med. Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Propagating Uncertainty Across Cascaded Medical Imaging Tasks for Improved Deep Learning Inference
IEEE Transactions on Medical Imaging ( IF 8.9 ) Pub Date : 2021-09-20 , DOI: 10.1109/tmi.2021.3114097
Raghav Mehta 1 , Thomas Christinck 1, 2 , Tanya Nair 1 , Aurélie Bussy 3 , Swapna Premasiri 3 , Manuela Costantino 3 , M. Mallar Chakravarthy 3 , Douglas L. Arnold 4, 5 , Yarin Gal 6 , Tal Arbel 1, 7
Affiliation  

Although deep networks have been shown to perform very well on a variety of medical imaging tasks, inference in the presence of pathology presents several challenges to common models. These challenges impede the integration of deep learning models into real clinical workflows, where the customary process of cascading deterministic outputs from a sequence of image-based inference steps (e.g. registration, segmentation) generally leads to an accumulation of errors that impacts the accuracy of downstream inference tasks. In this paper, we propose that by embedding uncertainty estimates across cascaded inference tasks, performance on the downstream inference tasks should be improved. We demonstrate the effectiveness of the proposed approach in three different clinical contexts: (i) We demonstrate that by propagating T2 weighted lesion segmentation results and their associated uncertainties, subsequent T2 lesion detection performance is improved when evaluated on a proprietary large-scale, multi-site, clinical trial dataset acquired from patients with Multiple Sclerosis. (ii) We show an improvement in brain tumour segmentation performance when the uncertainty map associated with a synthesised missing MR volume is provided as an additional input to a follow-up brain tumour segmentation network, when evaluated on the publicly available BraTS-2018 dataset. (iii) We show that by propagating uncertainties from a voxel-level hippocampus segmentation task, the subsequent regression of the Alzheimer’s disease clinical score is improved.

中文翻译:


在级联医学成像任务中传播不确定性以改进深度学习推理



尽管深度网络已被证明在各种医学成像任务上表现良好,但在病理存在的情况下进行推理对常见模型提出了一些挑战。这些挑战阻碍了深度学习模型集成到实际的临床工作流程中,其中从一系列基于图像的推理步骤(例如配准、分割)级联确定性输出的常规过程通常会导致错误累积,从而影响下游的准确性推理任务。在本文中,我们建议通过在级联推理任务中嵌入不确定性估计,可以提高下游推理任务的性能。我们证明了所提出的方法在三种不同临床环境中的有效性:(i)我们证明,通过传播 T2 加权病变分割结果及其相关的不确定性,在专有的大规模、多层次评估上进行评估时,后续的 T2 病变检测性能得到了提高。网站,从多发性硬化症患者获得的临床试验数据集。 (ii) 当在公开的 BraTS-2018 数据集上进行评估时,当与合成缺失 MR 体积相关的不确定性图作为后续脑肿瘤分割网络的附加输入提供时,我们显示了脑肿瘤分割性能的改进。 (iii)我们表明,通过传播体素水平海马分割任务的不确定性,阿尔茨海默病临床评分的后续回归得到了改善。
更新日期:2021-09-20
down
wechat
bug