SHIVA-CMB: A Deep-Learning-based Robust Cerebral Microbleed Segmentation Tool Trained on Multi-Source T2*GRE- and Susceptibility- weighted MRI

Author:

Tsuchida Ami1,Goubet Martin2,Boutinaud Philippe3,Astafeva Iana1,Nozais Victor3,Hervé Pierre-Yves3,Tourdias Thomas4,Debette Stéphanie5,Joliot Marc1

Affiliation:

1. GIN, IMN-UMR5293, CEA, CNRS, Université de Bordeaux

2. CHU de Clermont-Ferrand

3. Fealinx

4. CHU de Bordeaux

5. BPH-U1219, INSERM, Université de Bordeaux

Abstract

Abstract

Cerebral microbleeds (CMB) represent a feature of cerebral small vessel disease (cSVD), a prominent vascular contributor to age-related cognitive decline, dementia, and stroke. They are visible as spherical hypointense signals on T2*- or susceptibility-weighted magnetic resonance imaging (MRI) sequences. An increasing number of automated CMB detection methods being proposed are based on supervised deep learning (DL). Yet, the lack of open sharing of pre-trained models hampers the practical application and evaluation of these methods beyond specific data sources used in each study. Here, we present the SHIVA-CMB detector, a 3D Unet-based tool trained on 450 scans taken from seven acquisitions in six different cohort studies that included both T2*- and susceptibility-weighted MRI. In a held-out testset of 96 scans, it achieved an average sensitivity, precision, and F1(or Dice similarity coefficient) score of 0.72, 0.76, and 0.72 per image, with less than one false positive detection per image (FPavg = 0.62) and per CMB (FPcmb = 0.15). It achieved a similar level of performance in a separate, evaluation-only dataset with acquisitions never seen during the training (0.73, 0.81, 0.75, 0.5, 0.07 for average sensitivity, precision, F1 score, FPavg, and FPcmb). Further demonstrating its generalizability, it showed a high correlation (Pearson’s R = 0.89, p < 0.0001) with a visual count by expert raters in another independent set of 1992 T2*-weighted scans from a large, multi-center cohort study. Importantly, we publicly share both the code and pre-trained models to the research community to promote the active application and evaluation of our tool. We believe this effort will help accelerate research on the pathophysiology and functional consequences of CMB by enabling rapid characterization of CMB in large-scale studies.

Publisher

Springer Science and Business Media LLC

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3