Loading...
Thumbnail Image
Publication

Feasibility of the soft attention-based models for automatic segmentation of OCT kidney images

Moradi, Mousa
Du, Xian
Huan, Tianxiao
Chen, Yu
Citations
Altmetric:
Student Authors
Faculty Advisor
Academic Program
UMass Chan Affiliations
Document Type
Journal Article
Publication Date
2022-04-11
Keywords
Subject Area
Embargo Expiration Date
Abstract

Clinically, optical coherence tomography (OCT) has been utilized to obtain the images of the kidney's proximal convoluted tubules (PCTs), which can be used to quantify the morphometric parameters such as tubular density and diameter. Such parameters are useful for evaluating the status of the donor kidney for transplant. Quantifying PCTs from OCT images by human readers is a time-consuming and tedious process. Despite the fact that conventional deep learning models such as conventional neural networks (CNNs) have achieved great success in the automatic segmentation of kidney OCT images, gaps remain regarding the segmentation accuracy and reliability. Attention-based deep learning model has benefits over regular CNNs as it is intended to focus on the relevant part of the image and extract features for those regions. This paper aims at developing an Attention-based UNET model for automatic image analysis, pattern recognition, and segmentation of kidney OCT images. We evaluated five methods including the Residual-Attention-UNET, Attention-UNET, standard UNET, Residual UNET, and fully convolutional neural network using 14403 OCT images from 169 transplant kidneys for training and testing. Our results show that Residual-Attention-UNET outperformed the other four methods in segmentation by showing the highest values of all the six metrics including dice score (0.81 ± 0.01), intersection over union (IOU, 0.83 ± 0.02), specificity (0.84 ± 0.02), recall (0.82 ± 0.03), precision (0.81 ± 0.01), and accuracy (0.98 ± 0.08). Our results also show that the performance of the Residual-Attention-UNET is equivalent to the human manual segmentation (dice score = 0.84 ± 0.05). Residual-Attention-UNET and Attention-UNET also demonstrated good performance when trained on a small dataset (3456 images) whereas the performance of the other three methods dropped dramatically. In conclusion, our results suggested that the soft Attention-based models and specifically Residual-Attention-UNET are powerful and reliable methods for tubule lumen identification and segmentation and can help clinical evaluation of transplant kidney viability as fast and accurate as possible.

Source

Moradi M, Du X, Huan T, Chen Y. Feasibility of the soft attention-based models for automatic segmentation of OCT kidney images. Biomed Opt Express. 2022 Apr 11;13(5):2728-2738. doi: 10.1364/BOE.449942. PMID: 35774323; PMCID: PMC9203082.

Year of Medical School at Time of Visit
Sponsors
Dates of Travel
DOI
10.1364/BOE.449942
PubMed ID
35774323
Other Identifiers
Notes
Funding and Acknowledgements
Corresponding Author
Related Resources
Related Resources
Repository Citation
Rights
© 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement. Optica Publishing Group Open Access License for Publisher-Formatted Journal Article PDFs (Versions of Record) Open access journal article PDFs may be governed by the Optica Publishing Group Open Access Publishing Agreement signed by the author and any applicable copyright laws. Authors and readers may use, reuse, and build upon the article, or use it for text or data mining without asking prior permission from the publisher or the Author(s), as long as the purpose is non-commercial and appropriate attribution is maintained.
Distribution License