M-DDC: MRI based demyelinative diseases classification with U-Net segmentation and convolutional network

• Published in: Neural networks Vol. 169; pp. 108 - 119
• Main Authors: Zhou, Deyang, Xu, Lu, Wang, Tianlei, Wei, Shaonong, Gao, Feng, Lai, Xiaoping, Cao, Jiuwen
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2024
• Subjects: Aromatic-L-Amino-Acid Decarboxylases; Brain - diagnostic imaging; Child; Deep learning; Humans; Image classification; Image Processing, Computer-Assisted - methods; Image segmentation; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Neuromyelitis Optica - diagnostic imaging; Neuromyelitis Optica - pathology; Pediatric demyelinating disease; U-Net; Deep learning; Image segmentation; Magnetic resonance imaging; Pediatric demyelinating disease; U-Net; Image classification
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2023.10.010

Childhood demyelinative diseases classification (DDC) with brain magnetic resonance imaging (MRI) is crucial to clinical diagnosis. But few attentions have been paid to DDC in the past. How to accurately differentiate pediatric-onset neuromyelitis optica spectrum disorder (NMOSD) from acute disseminated encephalomyelitis (ADEM) based on MRI is challenging in DDC. In this paper, a novel architecture M-DDC based on joint U-Net segmentation network and deep convolutional network is developed. The U-Net segmentation can provide pixel-level structure information, that helps the lesion areas location and size estimation. The classification branch in DDC can detect the regions of interest inside MRIs, including the white matter regions where lesions appear. The performance of the proposed method is evaluated on MRIs of 201 subjects recorded from the Children’s Hospital of Zhejiang University School of Medicine. The comparisons show that the proposed DDC achieves the highest accuracy of 99.19% and dice of 71.1% for ADEM and NMOSD classification and segmentation, respectively.