The montage method improves the classification of suspected acute ischemic stroke using the convolution neural network and brain MRI

• Published in: Radiological physics and technology 2024-03, Vol.17 (1), p.297-305
• Main Authors: Oura, Daisuke, Gekka, Masayuki, Sugimori, Hiroyuki
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Diffusion coefficient; Hemorrhage; Imaging; Machine learning; Magnetic resonance imaging; Medical and Radiation Physics; Medical imaging; Medicine; Medicine & Public Health; Nuclear Medicine; Radiology; Radiotherapy; Stroke; Technical Note
• ISSN: 1865-0333; 1865-0341
• DOI: 10.1007/s12194-023-00754-x

This study investigated the usefulness of the montage method that combines four different magnetic resonance images into one images for automatic acute ischemic stroke (AIS) diagnosis with deep learning method. The montage image was consisted from diffusion weighted image (DWI), fluid attenuated inversion recovery (FLAIR), arterial spin labeling (ASL), and apparent diffusion coefficient (ASL). The montage method was compared with pseudo color map (pCM) which was consisted from FLAIR, ASL and ADC. 473 AIS patients were classified into four categories: mechanical thrombectomy, conservative therapy, hemorrhage, and other diseases. The results showed that the montage image significantly outperformed pCM in terms of accuracy (montage image = 0.76 ± 0.01, pCM = 0.54 ± 0.05) and the area under the curve (AUC) (montage image = 0.94 ± 0.01, pCM = 0.76 ± 0.01). This study demonstrates the usefulness of the montage method and its potential for overcoming the limitations of pCM.