Department of Neuroradiology-Brest University Hospital, Boulevard Tanguy Prigent, 29200, Brest, France.
Inserm, UMR 1101 (Laboratoire de Traitement de l'Information Médicale-LaTIM), Université de Bretagne Occidentale, 5 Avenue Foch, 29200, Brest, France.
Eur Radiol Exp. 2024 Sep 12;8(1):104. doi: 10.1186/s41747-024-00508-3.
The intricate three-dimensional anatomy of the inner ear presents significant challenges in diagnostic procedures and critical surgical interventions. Recent advancements in deep learning (DL), particularly convolutional neural networks (CNN), have shown promise for segmenting specific structures in medical imaging. This study aimed to train and externally validate an open-source U-net DL general model for automated segmentation of the inner ear from computed tomography (CT) scans, using quantitative and qualitative assessments.
In this multicenter study, we retrospectively collected a dataset of 271 CT scans to train an open-source U-net CNN model. An external set of 70 CT scans was used to evaluate the performance of the trained model. The model's efficacy was quantitatively assessed using the Dice similarity coefficient (DSC) and qualitatively assessed using a 4-level Likert score. For comparative analysis, manual segmentation served as the reference standard, with assessments made on both training and validation datasets, as well as stratified analysis of normal and pathological subgroups.
The optimized model yielded a mean DSC of 0.83 and achieved a Likert score of 1 in 42% of the cases, in conjunction with a significantly reduced processing time. Nevertheless, 27% of the patients received an indeterminate Likert score of 4. Overall, the mean DSCs were notably higher in the validation dataset than in the training dataset.
This study supports the external validation of an open-source U-net model for the automated segmentation of the inner ear from CT scans.
This study optimized and assessed an open-source general deep learning model for automated segmentation of the inner ear using temporal CT scans, offering perspectives for application in clinical routine. The model weights, study datasets, and baseline model are worldwide accessible.
A general open-source deep learning model was trained for CT automated inner ear segmentation. The Dice similarity coefficient was 0.83 and a Likert score of 1 was attributed to 42% of automated segmentations. The influence of scanning protocols on the model performances remains to be assessed.
内耳复杂的三维解剖结构给诊断程序和关键手术干预带来了重大挑战。深度学习（DL），特别是卷积神经网络（CNN）的最新进展，在医学成像中对特定结构的分割显示出了良好的前景。本研究旨在使用定量和定性评估，训练和外部验证一个用于从计算机断层扫描（CT）自动分割内耳的开源 U 型网络深度学习通用模型。
在这项多中心研究中，我们回顾性地收集了 271 例 CT 扫描数据集来训练一个开源 U 型网络 CNN 模型。一个外部的 70 例 CT 扫描数据集用于评估训练模型的性能。使用 Dice 相似系数（DSC）进行模型效能的定量评估，使用 4 级李克特评分进行定性评估。为了进行比较分析，手动分割作为参考标准，对训练和验证数据集进行评估，并对正常和病理亚组进行分层分析。
优化后的模型平均 DSC 为 0.83，42%的病例达到了 4 级李克特评分 1，同时处理时间显著缩短。然而，27%的患者获得了不确定的 4 级李克特评分。总体而言，验证数据集的平均 DSCs 明显高于训练数据集。
本研究支持了从 CT 扫描自动分割内耳的开源 U 型网络模型的外部验证。
本研究使用颞骨 CT 扫描优化并评估了一种用于自动分割内耳的开源通用深度学习模型，为该模型在临床常规中的应用提供了思路。该模型的权重、研究数据集和基础模型在全球范围内均可获取。
为 CT 自动内耳分割训练了一个通用的开源深度学习模型。Dice 相似系数为 0.83，42%的自动分割获得了 4 级李克特评分 1。扫描方案对模型性能的影响有待进一步评估。
