A Novel Computer-Aided Diagnostic System for Early Assessment of Hepatocellular Carcinoma

Early assessment of liver cancer patients with hepatocellular carcinoma (HCC) is of immense importance to provide the proper treatment plan. In this paper, we developed a two-stage classification computer-aided diagnostic (CAD) system that has the ability to detect and grade the liver observations from multiphase contrast enhanced magnetic resonance imaging (CE-MRI). The proposed approach consists of three main steps. First, a pre-processing is applied to the CE-MRI scans to delineate the tumor lesions that will be used as a region of interest (ROI) across the four different phases of the CE-MRI, (namely, the pre-contrast, late-arterial, portal-venous, and delayed-contrast). Second, a group of three features are modeled to provide a quantitative discrimination between the tumor lesions, namely: (i) the tumor appearance that is modeled using a set of texture features, (namely; the first-order histogram features, second-order gray-level co-occurrence matrix (GLCM) features, and second-order gray-level run-length matrix (GLRLM) features), to capture any discrimination that may appear in the lesion texture; (ii) the spherical harmonics (SH) based shape features that have the ability to describe the shape complexity of the liver tumors; and (iii) the functional features that are based on the calculation of the wash-in/wash-out slopes to evaluate the intensity changes across different phases. Finally, the aforementioned individual features were integrated together to obtain the combined features to be fed to a machine learning classifier towards getting the final diagnostic decision. The proposed CAD system was tested using hepatic observations obtained from 85 participating patients, 34 patients with benign tumors (LR-1 = 17 and LR-2 = 17), 34 patients with intermediate tumors (LR-3) and 34 with malignant tumors (LR-4 = 17 and LR-5 = 17). Using a random forests classifier with a leave-one-subject-out (LOSO) cross-validation, the developed CAD system achieved an 87.1% accuracy in distinguishing malignant, intermediate and benign tumors (i.e. First stage classification). Using the same classifier and validation, the LR-1 lesions were classified from LR-2 benign lesions with 91.2% accuracy, while 85.3% accuracy was achieved differentiating between LR-4 and LR-5 malignant tumors. The classification performance was then evaluated using k-fold (10 and 5-fold) cross-validation approaches to examine the robustness of the system. The obtained results hold a promise of the proposed framework to be reliably used as a noninvasive diagnostic tool for the early detection and grading of liver cancer tumors.

[1]  Francis K. H. Quek,et al.  Attribute bagging: improving accuracy of classifier ensembles by using random feature subsets , 2003, Pattern Recognit..

[2]  Fatma Taher,et al.  A new framework for incorporating appearance and shape features of lung nodules for precise diagnosis of lung cancer , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[3]  M. Wurnig,et al.  MRI texture analysis for differentiation of malignant and benign hepatocellular tumors in the non-cirrhotic liver , 2018, Heliyon.

[4]  Wen Liu,et al.  3D gray level co-occurrence matrix and its application to identifying collapsed buildings , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[5]  Ayman El-Baz,et al.  Spherical harmonic analysis of cortical complexity in autism and dyslexia , 2012, Translational neuroscience.

[6]  Wilhelm Burger,et al.  Digital Image Processing - An Algorithmic Introduction using Java , 2008, Texts in Computer Science.

[7]  F. Cendes,et al.  Texture analysis of medical images. , 2004, Clinical radiology.

[8]  Rui Li,et al.  Perfusion Characteristics of Hepatocellular Carcinoma at Contrast-enhanced Ultrasound: Influence of the Cellular differentiation, the Tumor Size and the Underlying Hepatic Condition , 2018, Scientific Reports.

[9]  Mary M. Galloway,et al.  Texture analysis using gray level run lengths , 1974 .

[10]  O. Abe,et al.  Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study. , 2017, Radiology.

[11]  Amir A. Borhani,et al.  Computer‐aided diagnosis program for classifying the risk of hepatocellular carcinoma on MR images following liver imaging reporting and data system (LI‐RADS) , 2018, Journal of magnetic resonance imaging : JMRI.

[12]  Jacob D. Furst,et al.  CO-OCCURRENCE MATRICES FOR VOLUMETRIC DATA , 2004 .

[13]  J. Soto,et al.  Effect of disease progression on liver apparent diffusion coefficient and T2 values in a murine model of hepatic fibrosis at 11.7 Tesla MRI , 2012, Journal of magnetic resonance imaging : JMRI.

[14]  M. Supanich,et al.  Deep learning LI-RADS grading system based on contrast enhanced multiphase MRI for differentiation between LR-3 and LR-4/LR-5 liver tumors , 2020, Annals of translational medicine.

[15]  Arie Nakhmani,et al.  Quantifying liver fibrosis through the application of texture analysis to diffusion weighted imaging. , 2014, Magnetic resonance imaging.

[16]  Benjamin Spilseth,et al.  Contrast Enhanced MRI in the Diagnosis of HCC , 2015, Diagnostics.

[17]  Robert M. Marks,et al.  White paper of the Society of Abdominal Radiology hepatocellular carcinoma diagnosis disease-focused panel on LI-RADS v2018 for CT and MRI , 2018, Abdominal Radiology.

[18]  Fatma Taher,et al.  A Novel Autoencoder-Based Diagnostic System for Early Assessment of Lung Cancer , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[19]  A. Gamst,et al.  Imaging Outcomes of Liver Imaging Reporting and Data System Version 2014 Category 2, 3, and 4 Observations Detected at CT and MR Imaging. , 2016, Radiology.

[20]  A. A. Abdel Razek,et al.  Liver Imaging Reporting and Data System Version 2018: What Radiologists Need to Know , 2020, Journal of computer assisted tomography.

[21]  Simon Hein,et al.  Current and future applications of machine and deep learning in urology: a review of the literature on urolithiasis, renal cell carcinoma, and bladder and prostate cancer , 2019, World Journal of Urology.

[22]  G. Carrafiello,et al.  CT-MRI LI-RADS v2017: A Comprehensive Guide for Beginners , 2018, Journal of clinical and translational hepatology.

[23]  Kathryn J Fowler,et al.  Deep convolutional neural network applied to the liver imaging reporting and data system (LI-RADS) version 2014 category classification: a pilot study , 2019, Abdominal Radiology.

[24]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  S. Venkatesh,et al.  Hepatocellular Carcinoma: State of the Art Imaging and Recent Advances , 2019, Journal of clinical and translational hepatology.

[26]  A. A. Abdel Razek,et al.  Interobserver Agreement of Magnetic Resonance Imaging of Liver Imaging Reporting and Data System Version 2018. , 2020, Journal of computer assisted tomography.

[27]  Andriy Fedorov,et al.  Computational Radiomics System to Decode the Radiographic Phenotype. , 2017, Cancer research.

[28]  Aya Kamaya,et al.  2017 Version of LI-RADS for CT and MR Imaging: An Update. , 2017, Radiographics : a review publication of the Radiological Society of North America, Inc.

[29]  S. Furui,et al.  Hepatic tumor classification using texture and topology analysis of non-contrast-enhanced three-dimensional T1-weighted MR images with a radiomics approach , 2019, Scientific Reports.

[30]  Jian Zhu,et al.  Texture-based classification of different single liver lesion based on SPAIR T2W MRI images , 2017, BMC Medical Imaging.

[31]  M.,et al.  Statistical and Structural Approaches to Texture , 2022 .

[32]  Run-Length Matrices For Texture Analysis , 2011, The Insight Journal.

[33]  L. Bolondi,et al.  Comparison of International Guidelines for Noninvasive Diagnosis of Hepatocellular Carcinoma , 2012, Liver Cancer.

[34]  Fred L. Drake,et al.  Python 3 Reference Manual , 2009 .