B N Anoop, Li Karl, Honnorat Nicolas, Rashid Tanweer, Wang Di, Li Jinqi, Fadaee Elyas, Charisis Sokratis, Walker Jamie M, Richardson Timothy E, Wolk David A, Fox Peter T, Cavazos José E, Seshadri Sudha, Wisse Laura E M, Habes Mohamad
Neuroimage Analytics Laboratory and Biggs Institute Neuroimaging Core, Glenn Biggs Institute for Neurodegenerative Disorders, University of Texas Health Science Center at San Antonio, San Antonio, TX, USA; Department of Information and Communication Technology, Manipal Institute of Technology, Manipal, Manipal Academy of Higher Education (MAHE), Manipal, Karnaaka, 576104, India.
Neuroimage Analytics Laboratory and Biggs Institute Neuroimaging Core, Glenn Biggs Institute for Neurodegenerative Disorders, University of Texas Health Science Center at San Antonio, San Antonio, TX, USA.
J Neurosci Methods. 2025 Mar;415:110359. doi: 10.1016/j.jneumeth.2024.110359. Epub 2025 Jan 2.
The hippocampus plays a crucial role in memory and is one of the first structures affected by Alzheimer's disease. Postmortem MRI offers a way to quantify the alterations by measuring the atrophy of the inner structures of the hippocampus. Unfortunately, the manual segmentation of hippocampal subregions required to carry out these measures is very time-consuming.
In this study, we explore the use of fully automated methods relying on state-of-the-art Deep Learning approaches to produce these annotations. More specifically, we propose a new segmentation framework made of a set of encoder-decoder blocks embedding self-attention mechanisms and atrous spatial pyramidal pooling to produce better maps of the hippocampus and identify four hippocampal regions: the dentate gyrus, the hippocampal head, the hippocampal body, and the hippocampal tail.
Trained using slices extracted from 15 postmortem T1-weighted, T2-weighted, and susceptibility-weighted MRI scans, our new approach produces hippocampus parcellations that are better aligned with the manually delineated parcellations provided by neuroradiologists.
Four standard deep learning segmentation architectures: UNet, Double UNet, Attention UNet, and Multi-resolution UNet have been utilized for the qualitative and quantitative comparison of the proposed hippocampal region segmentation model.
Postmortem MRI serves as a highly valuable neuroimaging technique for examining the effects of neurodegenerative diseases on the intricate structures within the hippocampus. This study opens the way to large sample-size postmortem studies of the hippocampal substructures.
海马体在记忆中起着关键作用，是最早受阿尔茨海默病影响的结构之一。尸检磁共振成像（MRI）提供了一种通过测量海马体内结构萎缩来量化改变的方法。不幸的是，进行这些测量所需的海马体亚区域手动分割非常耗时。
在本研究中，我们探索使用依赖于最先进深度学习方法的全自动方法来生成这些标注。更具体地说，我们提出了一个新的分割框架，它由一组嵌入自注意力机制和空洞空间金字塔池化的编码器 - 解码器模块组成，以生成更好的海马体图谱并识别四个海马体区域：齿状回、海马头部、海马体部和海马尾部。
使用从15例尸检T1加权、T2加权和 susceptibility加权MRI扫描中提取的切片进行训练，我们的新方法产生的海马体分割与神经放射科医生提供的手动勾勒的分割更好地对齐。
四种标准的深度学习分割架构：UNet、双UNet、注意力UNet和多分辨率UNet已被用于对所提出的海马体区域分割模型进行定性和定量比较。
尸检MRI是一种非常有价值的神经成像技术，用于检查神经退行性疾病对海马体内复杂结构的影响。本研究为海马体亚结构的大样本尸检研究开辟了道路。
