Kidney segmentation from computed tomography images using deep neural network.

Autor: da Cruz LB; Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Brazil. Electronic address: luana.b.cruz@nca.ufma.br., Araújo JDL; Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Brazil., Ferreira JL; Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Brazil., Diniz JOB; Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Brazil; Federal Institute of Maranhão, Brazil., Silva AC; Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Brazil., de Almeida JDS; Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Brazil., de Paiva AC; Applied Computing Group (NCA - UFMA), Federal University of Maranhão, Brazil., Gattass M; Pontifical Catholic University of Rio de Janeiro, Brazil.
Jazyk: angličtina
Zdroj: Computers in biology and medicine [Comput Biol Med] 2020 Aug; Vol. 123, pp. 103906. Date of Electronic Publication: 2020 Jul 11.
DOI: 10.1016/j.compbiomed.2020.103906
Abstrakt: Background: The precise segmentation of kidneys and kidney tumors can help medical specialists to diagnose diseases and improve treatment planning, which is highly required in clinical practice. Manual segmentation of the kidneys is extremely time-consuming and prone to variability between different specialists due to their heterogeneity. Because of this hard work, computational techniques, such as deep convolutional neural networks, have become popular in kidney segmentation tasks to assist in the early diagnosis of kidney tumors. In this study, we propose an automatic method to delimit the kidneys in computed tomography (CT) images using image processing techniques and deep convolutional neural networks (CNNs) to minimize false positives.
Methods: The proposed method has four main steps: (1) acquisition of the KiTS19 dataset, (2) scope reduction using AlexNet, (3) initial segmentation using U-Net 2D, and (4) false positive reduction using image processing to maintain the largest elements (kidneys).
Results: The proposed method was evaluated in 210 CTs from the KiTS19 database and obtained the best result with an average Dice coefficient of 96.33%, an average Jaccard index of 93.02%, an average sensitivity of 97.42%, an average specificity of 99.94% and an average accuracy of 99.92%. In the KiTS19 challenge, it presented an average Dice coefficient of 93.03%.
Conclusion: In our method, we demonstrated that the kidney segmentation problem in CT can be solved efficiently using deep neural networks to define the scope of the problem and segment the kidneys with high precision and with the use of image processing techniques to reduce false positives.
(Copyright © 2020 Elsevier Ltd. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: