Ensemble U‐net‐based method for fully automated detection and segmentation of renal masses on computed tomography images

• Published in: Medical physics (Lancaster) Vol. 47; no. 9; pp. 4032 - 4044
• Main Authors: Fatemeh, Zabihollahy, Nicola, Schieda, Satheesh, Krishna, Eranga, Ukwatta
• Format: Journal Article
• Language: English
• Published: United States 01.09.2020
• Subjects: Algorithms; contrast‐enhanced computed tomography (CECT) images; ensemble learning system; Humans; Image Processing, Computer-Assisted; Kidney Neoplasms - diagnostic imaging; Neural Networks, Computer; renal mass; Tomography, X-Ray Computed; U‐Net; ensemble learning system; renal mass; U-Net; contrast-enhanced computed tomography (CECT) images
• ISSN: 0094-2405; 2473-4209; 2473-4209
• DOI: 10.1002/mp.14193

Purpose Detection and accurate localization of renal masses (RM) are important steps toward future potential classification of benign vs malignant RM. A fully automated algorithm for detection and localization of RM may eliminate the observer variability in the clinical workflow. Method In this paper, we describe a fully automated methodology for accurate detection and segmentation of RM from contrast‐enhanced computed tomography (CECT) images. We first determine the boundaries of the kidneys on the CECT images utilizing a convolutional neural network‐based method to be used as a region of interest to search for RM. We then employ a homogenous U‐Net‐based ensemble learning model to identify and delineate RM. We used an institutional dataset comprised of CECT images in 315 patients to train and evaluate the proposed method. We compared results of our method to those of three‐dimensional (3D) U‐Net for RM localization and further evaluated our algorithm using the kidney tumor segmentation (KiTS19) challenge dataset. Results The developed algorithm reported a Dice similarity coefficient (DSC) of 95.79% ± 5.16% and 96.25 ± 3.37 (mean ± standard deviation) for segmentation accuracy of kidney boundary from 125 and 60 test images from institutional and KiTS19 datasets, respectively. Using our method, RM were detected in 125 and 52 test cases, which corresponds to 100% and 86.67% sensitivity at patient level in institutional and KiTS19 test images. Our ensemble method for RM localization yielded a mean DSC of 88.65% ± 7.31% and 87.91% ± 6.82% on the institutional and KiTS19 test datasets, respectively. The mean DSC for RM delineation from CECT institutional test images using 3D U‐Net was 85.95% ± 1.46%. Conclusion We describe a method for automated localization of RM using CECT images. Our results are important in terms of clinical perspective as fully automated detection of RM is a fundamental step for further diagnosis of cystic vs solid RM and eventually benign vs malignant solid RM, that has not been reported previously.