Cargando…
Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease
Organ volume measurements are a key metric for managing ADPKD (the most common inherited renal disease). However, measuring organ volumes is tedious and involves manually contouring organ outlines on multiple cross-sectional MRI or CT images. The automation of kidney contouring using deep learning h...
Autores principales: | , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9326744/ https://www.ncbi.nlm.nih.gov/pubmed/35894017 http://dx.doi.org/10.3390/tomography8040152 |
_version_ | 1784757360840933376 |
---|---|
author | Sharbatdaran, Arman Romano, Dominick Teichman, Kurt Dev, Hreedi Raza, Syed I. Goel, Akshay Moghadam, Mina C. Blumenfeld, Jon D. Chevalier, James M. Shimonov, Daniil Shih, George Wang, Yi Prince, Martin R. |
author_facet | Sharbatdaran, Arman Romano, Dominick Teichman, Kurt Dev, Hreedi Raza, Syed I. Goel, Akshay Moghadam, Mina C. Blumenfeld, Jon D. Chevalier, James M. Shimonov, Daniil Shih, George Wang, Yi Prince, Martin R. |
author_sort | Sharbatdaran, Arman |
collection | PubMed |
description | Organ volume measurements are a key metric for managing ADPKD (the most common inherited renal disease). However, measuring organ volumes is tedious and involves manually contouring organ outlines on multiple cross-sectional MRI or CT images. The automation of kidney contouring using deep learning has been proposed, as it has small errors compared to manual contouring. Here, a deployed open-source deep learning ADPKD kidney segmentation pipeline is extended to also measure liver and spleen volumes, which are also important. This 2D U-net deep learning approach was developed with radiologist labeled T2-weighted images from 215 ADPKD subjects (70% training = 151, 30% validation = 64). Additional ADPKD subjects were utilized for prospective (n = 30) and external (n = 30) validations for a total of 275 subjects. Image cropping previously optimized for kidneys was included in training but removed for the validation and inference to accommodate the liver which is closer to the image border. An effective algorithm was developed to adjudicate overlap voxels that are labeled as more than one organ. Left kidney, right kidney, liver and spleen labels had average errors of 3%, 7%, 3%, and 1%, respectively, on external validation and 5%, 6%, 5%, and 1% on prospective validation. Dice scores also showed that the deep learning model was close to the radiologist contouring, measuring 0.98, 0.96, 0.97 and 0.96 on external validation and 0.96, 0.96, 0.96 and 0.95 on prospective validation for left kidney, right kidney, liver and spleen, respectively. The time required for manual correction of deep learning segmentation errors was only 19:17 min compared to 33:04 min for manual segmentations, a 42% time saving (p = 0.004). Standard deviation of model assisted segmentations was reduced to 7, 5, 11, 5 mL for right kidney, left kidney, liver and spleen respectively from 14, 10, 55 and 14 mL for manual segmentations. Thus, deep learning reduces the radiologist time required to perform multiorgan segmentations in ADPKD and reduces measurement variability. |
format | Online Article Text |
id | pubmed-9326744 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-93267442022-07-28 Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease Sharbatdaran, Arman Romano, Dominick Teichman, Kurt Dev, Hreedi Raza, Syed I. Goel, Akshay Moghadam, Mina C. Blumenfeld, Jon D. Chevalier, James M. Shimonov, Daniil Shih, George Wang, Yi Prince, Martin R. Tomography Article Organ volume measurements are a key metric for managing ADPKD (the most common inherited renal disease). However, measuring organ volumes is tedious and involves manually contouring organ outlines on multiple cross-sectional MRI or CT images. The automation of kidney contouring using deep learning has been proposed, as it has small errors compared to manual contouring. Here, a deployed open-source deep learning ADPKD kidney segmentation pipeline is extended to also measure liver and spleen volumes, which are also important. This 2D U-net deep learning approach was developed with radiologist labeled T2-weighted images from 215 ADPKD subjects (70% training = 151, 30% validation = 64). Additional ADPKD subjects were utilized for prospective (n = 30) and external (n = 30) validations for a total of 275 subjects. Image cropping previously optimized for kidneys was included in training but removed for the validation and inference to accommodate the liver which is closer to the image border. An effective algorithm was developed to adjudicate overlap voxels that are labeled as more than one organ. Left kidney, right kidney, liver and spleen labels had average errors of 3%, 7%, 3%, and 1%, respectively, on external validation and 5%, 6%, 5%, and 1% on prospective validation. Dice scores also showed that the deep learning model was close to the radiologist contouring, measuring 0.98, 0.96, 0.97 and 0.96 on external validation and 0.96, 0.96, 0.96 and 0.95 on prospective validation for left kidney, right kidney, liver and spleen, respectively. The time required for manual correction of deep learning segmentation errors was only 19:17 min compared to 33:04 min for manual segmentations, a 42% time saving (p = 0.004). Standard deviation of model assisted segmentations was reduced to 7, 5, 11, 5 mL for right kidney, left kidney, liver and spleen respectively from 14, 10, 55 and 14 mL for manual segmentations. Thus, deep learning reduces the radiologist time required to perform multiorgan segmentations in ADPKD and reduces measurement variability. MDPI 2022-07-13 /pmc/articles/PMC9326744/ /pubmed/35894017 http://dx.doi.org/10.3390/tomography8040152 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Sharbatdaran, Arman Romano, Dominick Teichman, Kurt Dev, Hreedi Raza, Syed I. Goel, Akshay Moghadam, Mina C. Blumenfeld, Jon D. Chevalier, James M. Shimonov, Daniil Shih, George Wang, Yi Prince, Martin R. Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease |
title | Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease |
title_full | Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease |
title_fullStr | Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease |
title_full_unstemmed | Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease |
title_short | Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease |
title_sort | deep learning automation of kidney, liver, and spleen segmentation for organ volume measurements in autosomal dominant polycystic kidney disease |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9326744/ https://www.ncbi.nlm.nih.gov/pubmed/35894017 http://dx.doi.org/10.3390/tomography8040152 |
work_keys_str_mv | AT sharbatdaranarman deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT romanodominick deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT teichmankurt deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT devhreedi deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT razasyedi deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT goelakshay deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT moghadamminac deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT blumenfeldjond deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT chevalierjamesm deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT shimonovdaniil deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT shihgeorge deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT wangyi deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease AT princemartinr deeplearningautomationofkidneyliverandspleensegmentationfororganvolumemeasurementsinautosomaldominantpolycystickidneydisease |