Transfer learning based fully automated kidney segmentation on MR images

Rohini Gaikar; Fatemeh Zabihollahy; Nadia Farrag; Mohamed W. Elfaal; Nicola Schieda; Eranga Ukwatta

doi:10.1117/12.2607526

4 April 2022 Transfer learning based fully automated kidney segmentation on MR images

Rohini Gaikar, Fatemeh Zabihollahy, Nadia Farrag, Mohamed W. Elfaal, Nicola Schieda, Eranga Ukwatta

Proceedings Volume 12036, Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging; 120361M (2022) https://doi.org/10.1117/12.2607526
Event: SPIE Medical Imaging, 2022, San Diego, California, United States

Conference Poster

Abstract

Multi-parametric magnetic resonance imaging (mp-MRI) is a promising tool for diagnosis of renal masses and may outperform computed tomography (CT) to differentiate between benign and malignant renal masses due to superior soft tissue contrast. Deep learning (DL)-based methods for kidney segmentation are under-explored in mp-MRI which consists of several pulse sequences, including primarily T2-weighted (T2W) and contrast-enhanced (CE) images. Multi-parametric MRI images have domain shift due to differences in acquisition systems and image protocols, leading to lack of generalizability of methods for image segmentation. To perform similar automated kidney segmentation on another mp- MRI sequence, the model needs a large dataset with manual segmentations to train a model from scratch, which is labor intensive and time consuming. In this paper, we first trained a DL-based method using 108 cases of labeled data to contour kidneys using T1 weighted-Nephrographic Phase CE-MRI (T1W-NG). We then applied a transfer learning approach to other mp-MRI images using pre-trained weights from the source domain, thus eliminating the need for large manually annotated datasets in target domain. The fully automated 2D U-Net for kidney segmentation in source domain containing total 108 3D images of T1W-NG, yielded Dice-similarity coefficient (DSC) of 0.91 ± 0.07 on test cases. The transfer learning of pretrained weights of T1W-NG model on the smaller target domain T2W dataset containing total 50 3D images for automated kidney segmentation generated DSC of 0.90 ± 0.06 (p<0.05), which was an improvement of 3.43% in DSC by compared to the without transfer learning approach (T2W-UNet model).

Conference Presentation

Citation Download Citation

Rohini Gaikar, Fatemeh Zabihollahy, Nadia Farrag, Mohamed W. Elfaal, Nicola Schieda, and Eranga Ukwatta "Transfer learning based fully automated kidney segmentation on MR images", Proc. SPIE 12036, Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging, 120361M (4 April 2022); https://doi.org/10.1117/12.2607526

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available