Transfer learning on fused multiparametric MR images for classifying histopathological subtypes of rhabdomyosarcoma

• Published in: Computerized medical imaging and graphics Vol. 65; pp. 167 - 175
• Main Authors: Banerjee, Imon, Crawley, Alexis, Bhethanabotla, Mythili, Daldrup-Link, Heike E, Rubin, Daniel L.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.04.2018; Elsevier Science Ltd
• Subjects: Adolescent; Alveoli; Artificial intelligence; Artificial neural networks; Chelates; Child; Child, Preschool; Computer aided diagnosis; Cutting parameters; Deep Learning; Deep neural networks; Diagnosis; Diagnosis, Differential; Differential diagnosis; Gadolinium; Humans; Image classification; Image fusion; Image Interpretation, Computer-Assisted - methods; Image processing; Infant; Machine learning; Magnetic Resonance Imaging; Medical diagnosis; Medical imaging; Model accuracy; Neural networks; Retrospective Studies; Rhabdomyosarcoma; Rhabdomyosarcoma - classification; Rhabdomyosarcoma - diagnostic imaging; Transfer learning; Young Adult; Deep neural networks; Computer aided diagnosis; Transfer learning; Image fusion; Rhabdomyosarcoma
• ISSN: 0895-6111; 1879-0771; 1879-0771
• DOI: 10.1016/j.compmedimag.2017.05.002

•A deep-learning based CADx for diagnosis of embryonal and alveolar subtypes.•Diagnosis has been performed by solely by analyzing multiparametric MR images.•Created a fusion of diffusion-weighted and T1-weighted MR scans.•A pre-trained deep neural network has been fine-tuned based on the fused images.•Achieved 85% cross validation accuracy for classifying the two RMS subtypes.•The system can provide an efficient and reproducible diagnosis with less human interaction. This paper presents a deep-learning-based CADx for the differential diagnosis of embryonal (ERMS) and alveolar (ARMS) subtypes of rhabdomysarcoma (RMS) solely by analyzing multiparametric MR images. We formulated an automated pipeline that creates a comprehensive representation of tumor by performing a fusion of diffusion-weighted MR scans (DWI) and gadolinium chelate-enhanced T1−weighted MR scans (MRI). Finally, we adapted transfer learning approach where a pre-trained deep convolutional neural network has been fine-tuned based on the fused images for performing classification of the two RMS subtypes. We achieved 85% cross validation prediction accuracy from the fine-tuned deep CNN model. Our system can be exploited to provide a fast, efficient and reproducible diagnosis of RMS subtypes with less human interaction. The framework offers an efficient integration between advanced image processing methods and cutting-edge deep learning techniques which can be extended to deal with other clinical domains that involve multimodal imaging for disease diagnosis.