Liver disease classification from ultrasound using multi-scale CNN

• Published in: International journal for computer assisted radiology and surgery Vol. 16; no. 9; pp. 1537 - 1548
• Main Authors: Che, Hui, Brown, Lloyd G., Foran, David J., Nosher, John L., Hacihaliloglu, Ilker
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.09.2021; Springer Nature B.V
• Subjects: Accuracy; Artificial neural networks; Classification; Computer architecture; Computer Imaging; Computer Science; Deep learning; Design; Health Informatics; Image filters; Imaging; Liver; Liver diseases; Machine learning; Medical imaging; Medicine; Medicine & Public Health; Original Article; Pattern Recognition and Graphics; Radiology; Surgery; Ultrasonic imaging; Vision; Deep learning; Nonalcoholic fatty liver disease; Ultrasound; Classification
• ISSN: 1861-6410; 1861-6429; 1861-6429
• DOI: 10.1007/s11548-021-02414-0

Purpose Ultrasound (US) is the preferred modality for fatty liver disease diagnosis due to its noninvasive, real-time, and cost-effective imaging capabilities. However, traditional B-mode US is qualitative, and therefore, the assessment is very subjective. Computer-aided diagnostic tools can improve the specificity and sensitivity of US and help clinicians to perform uniform diagnoses. Methods In this work, we propose a novel deep learning model for nonalcoholic fatty liver disease classification from US data. We design a multi-feature guided multi-scale residual convolutional neural network (CNN) architecture to capture features of different receptive fields. B-mode US images are combined with their corresponding local phase filtered images and radial symmetry transformed images as multi-feature inputs for the network. Various fusion strategies are studied to improve prediction accuracy. We evaluate the designed network architectures on B-mode in vivo liver US images collected from 55 subjects. We also provide quantitative results by comparing our proposed multi-feature CNN architecture against traditional CNN designs and machine learning methods. Results Quantitative results show an average classification accuracy above 90% over tenfold cross-validation. Our proposed method achieves a 97.8% area under the ROC curve (AUC) for the patient-specific leave-one-out cross-validation (LOOCV) evaluation. Comprehensive validation results further demonstrate that our proposed approaches achieve significant improvements compared to training mono-feature CNN architectures ( p < 0.05 ). Conclusions Feature combination is valuable for the traditional classification methods, and the use of multi-scale CNN can improve liver classification accuracy. Based on the promising performance, the proposed method has the potential in practical applications to help radiologists diagnose nonalcoholic fatty liver disease.