Style Transfer-assisted Deep Learning Method for Kidney Segmentation at Multiphase MRI

Authors

Junyu Guo
Manu Goyal
Yin Xi
Lauren Hinojosa
Gaelle Haddad
Emin Albayrak
Ivan Pedrosa

Language

English

Publication Date

11-1-2023

Journal

Radiology: Artificial Intelligence

DOI

10.1148/ryai.230043

PMID

38074795

PMCID

PMC10698598

PubMedCentral® Posted Date

9-13-2023

PubMedCentral® Full Text Version

Post-print

Abstract

Purpose: To develop and validate a semisupervised style transfer-assisted deep learning method for automated segmentation of the kidneys using multiphase contrast-enhanced (MCE) MRI acquisitions.

Materials and methods: This retrospective, Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included 125 patients (mean age, 57.3 years; 67 male, 58 female) with renal masses. Cohort 1 consisted of 102 coronal T2-weighted MRI acquisitions and 27 MCE MRI acquisitions during the corticomedullary phase. Cohort 2 comprised 92 MCE MRI acquisitions (23 acquisitions during four phases each, including precontrast, corticomedullary, early nephrographic, and nephrographic phases). The kidneys were manually segmented on T2-weighted images. A cycle-consistent generative adversarial network (CycleGAN) was trained to generate anatomically coregistered synthetic corticomedullary style images using T2-weighted images as input. Synthetic images for precontrast, early nephrographic, and nephrographic phases were then generated using the synthetic corticomedullary images as input. Mask region-based convolutional neural networks were trained on the four synthetic phase series for kidney segmentation using T2-weighted masks. Segmentation performance was evaluated in a different cohort of 20 originally acquired MCE MRI examinations by using Dice and Jaccard scores.

Results: The CycleGAN network successfully generated anatomically coregistered synthetic MCE MRI-like datasets from T2-weighted acquisitions. The proposed deep learning approach for kidney segmentation achieved high mean Dice scores in all four phases of the original MCE MRI acquisitions (0.91 for precontrast, 0.92 for corticomedullary, 0.91 for early nephrographic, and 0.93 for nephrographic).

Conclusion: The proposed deep learning approach achieved high performance in kidney segmentation on different MCE MRI acquisitions.Keywords: Kidney Segmentation, Generative Adversarial Network, CycleGAN, Convolutional Neural Network, Transfer Learning Supplemental material is available for this article. Published under a CC BY 4.0 license.

Keywords

Kidney Segmentation, Generative Adversarial Network, CycleGAN, Convolutional Neural Network, Transfer Learning

Comments

Supplemental material is available for this article.

Published Open-Access

yes

Recommended Citation

Guo, Junyu; Goyal, Manu; Xi, Yin; et al., "Style Transfer-assisted Deep Learning Method for Kidney Segmentation at Multiphase MRI" (2023). Faculty, Staff and Student Publications. 6409.
https://digitalcommons.library.tmc.edu/uthgsbs_docs/6409