Symtosis: A liver ultrasound tissue characterization and risk stratification in optimized deep learning paradigm. (March 2018)

• Record Type: Journal Article
• Authors: Biswas, Mainak; Kuppili, Venkatanareshbabu; Edla, Damodar Reddy; Suri, Harman S.; Saba, Luca; Marinhoe, Rui Tato; Sanches, J. Miguel; Suri, Jasjit S.
• Is Part Of: Computer methods and programs in biomedicine. Volume 155(2018)
• Page Start: 165
• Page End: 177
• Publication Date: 2018-03
• Subjects: Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2017.12.016
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Deep Learning (DL) technique is applied for detection of hypoechoic FLD and stratification of normal and abnormal US liver images under the class of Symtosis. This paper provides comprehensive analysis and comparison of three ML-based classification methodologies: namely, support vector machines, extreme learning machines and deep learning. A specialized deep learning operation called inception is comprehensively investigated. Abstract: Background and Objective: Fatty Liver Disease (FLD) - a disease caused by deposition of fat in liver cells, is predecessor to terminal diseases such as liver cancer. The machine learning (ML) techniques applied for FLD detection and risk stratification using ultrasound (US) have limitations in computing tissue characterization features, thereby limiting the accuracy. Methods: Under the class of Symtosis for FLD detection and risk stratification, this study presents a Deep Learning (DL)-based paradigm that computes nearly seven million weights per image when passed through a 22 layered neural network during the cross-validation (training and testing) paradigm. The DL architecture consists of cascaded layers of operations such as: convolution, pooling, rectified linear unit, dropout and a special block called inception model that provides speed and efficiency. All data analysis is performed in optimized tissue region, obtained by removing background information. We benchmark the DL system against the conventional ML protocols: support vector machine (SVM) and extreme learning machine (ELM). Results: The liver US data consists of 63 patients (27 normal/36 abnormal). Using the K10 cross-validation protocol (90% training and 10% testing), the detection and risk stratification accuracies are: 82%, 92% and 100% for SVM, ELM and DL systems, respectively. The corresponding area under the curve is: 0.79, 0.92 and 1.0, respectively. We further validate our DL system using two class biometric facial data that yields an accuracy of 99%. Conclusion: DL system shows a superior performance for liver detection and risk stratification compared to conventional machine learning systems: SVM and ELM.