Texture analysis for muscular dystrophy classification in MRI with improved class activation mapping. (February 2019)

• Record Type: Journal Article
• Authors: Cai, Jinzheng; Xing, Fuyong; Batra, Abhinandan; Liu, Fujun; Walter, Glenn A.; Vandenborne, Krista; Yang, Lin
• Is Part Of: Pattern recognition. Volume 86(2019:Feb.)
• Page Start: 368
• Page End: 375
• Publication Date: 2019-02
• Subjects: Muscular dystrophy -- Convolutional neural network -- MRI analysis -- Texture classification -- Abnormality detection; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.08.012
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: The muscular dystrophies are made up of a diverse group of rare genetic diseases characterized by progressive loss of muscle strength and muscle damage. Since there is no cure for muscular dystrophy and clinical outcome measures are limited, it is critical to assess the progression of MD objectively. Imaging muscle replacement by fibrofatty tissue has been shown to be a robust biomarker to monitor disease progression in DMD. In magnetic resonance imaging (MRI) data, specific texture patterns are found to correlate to certain MD subtypes and thus present a potential way for automatic assessment. In this paper, we first apply state-of-the-art convolutional neural networks (CNNs) to perform accurate MD image classification and then propose an effective visualization method to highlight the important image textures. With a dystrophic MRI dataset, we found that the best CNN model delivers an 91.7% classification accuracy, which significantly outperforms non-deep learning methods, e.g ., > 40% improvement has been found over the traditional mean fat fraction (MFF) criterion for DMD and CMD classification. After investigating every single neuron at the top layer of CNN model, we found the superior classification ability of CNN can be explained by its 91 and 118 neurons were performing better than the MFF criterion under the measurements of Euclidean and Chi-square distance, respectively. In order to further interpret CNNs predictions, we tested an improved class activation mapping (ICAM) method to visualize the important regions in the MRI images. With this ICAM, CNNs are able to locate the most discriminative texture patterns of DMD in soleus, lateral gastrocnemius, and medial gastrocnemius; for CMD, the critical texture patterns are highlighted in soleus, tibialis posterior, and peroneus.