Huang Lan, Zhao Ziqi, An Liying, Gong Yingchun, Wang Yao, Yang Qixing, Wang Zhuo, Hu Geli, Wang Yan, Guo Chunjie
Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun, China.
Department of Radiology, the First Hospital of Jilin University, Changchun, China.
Quant Imaging Med Surg. 2024 Jan 3;14(1):273-290. doi: 10.21037/qims-23-846. Epub 2023 Nov 15.
Multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD) are the two mimic autoimmune diseases of the central nervous system, which are rare in East Asia. Quantitative detection of contrast-enhancing lesions (CELs) on contrast-enhancing T1-weighted magnetic resonance (MR) images is of great significance for assessing the disease activity of MS and NMOSD. However, it is challenging to develop automatic segmentation algorithms due to the lack of data. In this work, we present an automatic segmentation model of CELs based on Fully Convolutional with Attention DenseNet (FCA-DenseNet) and transfer learning strategy to address the challenge of CEL quantification in small-scale datasets.
A transfer learning approach was employed in this study, whereby pretraining was conducted using 77 MS subjects from the open access datasets (MICCAI 2016, MICCAI 2017, ISBI 2015) for white matter hyperintensity segmentation, followed by fine-tuning using 24 MS and NMOSD subjects from the local dataset for CEL segmentation. The proposed FCA-DenseNet combined the Fully Convolutional DenseNet and Convolutional Block Attention Module in order to improve the learning capability. A 2.5D data slicing strategy was used to process complex 3D MR images. U-Net, ResUNet, TransUNet, and Attention-UNet are used as comparison models to FCA-DenseNet. Dice similarity coefficient (DSC), positive predictive value (PPV), true positive rate (TPR), and volume difference (VD) are used as evaluation metrics to evaluate the performances of different models.
FCA-DenseNet outperforms all other models in terms of all evaluation metrics, with a DSC of 0.661±0.187, PPV of 0.719±0.201, TPR of 0.680±0.254, and VD of 0.388±0.334. Transfer learning strategy has achieved success in building segmentation models on a small-scale local dataset where traditional deep learning approaches fail to train effectively.
The improved FCA-DenseNet, combined with transfer learning strategy and 2.5D data slicing strategy, has successfully addressed the challenges in constructing deep learning models on small-scale datasets, making it conducive to clinical quantification of brain CELs and diagnosis of MS and NMOSD.
多发性硬化症（MS）和视神经脊髓炎谱系障碍（NMOSD）是中枢神经系统的两种自身免疫性模仿疾病，在东亚地区较为罕见。在对比增强T1加权磁共振（MR）图像上定量检测对比增强病灶（CEL）对于评估MS和NMOSD的疾病活动具有重要意义。然而，由于缺乏数据，开发自动分割算法具有挑战性。在这项工作中，我们提出了一种基于全卷积注意力密集网络（FCA-DenseNet）和迁移学习策略的CEL自动分割模型，以应对小规模数据集中CEL量化的挑战。
本研究采用迁移学习方法，首先使用来自开放获取数据集（MICCAI 2016、MICCAI 2017、ISBI 2015）的77名MS受试者进行白质高信号分割的预训练，然后使用来自本地数据集的24名MS和NMOSD受试者进行CEL分割的微调。所提出的FCA-DenseNet结合了全卷积密集网络和卷积块注意力模块，以提高学习能力。采用2.5D数据切片策略处理复杂的3D MR图像。将U-Net、ResUNet、TransUNet和注意力U-Net用作与FCA-DenseNet比较的模型。使用骰子相似系数（DSC）、阳性预测值（PPV）、真阳性率（TPR）和体积差异（VD）作为评估指标来评估不同模型的性能。
FCA-DenseNet在所有评估指标方面均优于所有其他模型，DSC为0.661±0.187，PPV为0.719±0.201，TPR为0.680±0.254，VD为0.388±0.334。迁移学习策略成功地在传统深度学习方法无法有效训练的小规模本地数据集上构建了分割模型。
改进后的FCA-DenseNet结合迁移学习策略和2.5D数据切片策略，成功应对了在小规模数据集上构建深度学习模型的挑战，有助于脑CEL的临床量化以及MS和NMOSD的诊断。
