Deep-learning system to improve the quality and efficiency of volumetric heart segmentation for breast cancer
Abstract Although artificial intelligence algorithms are often developed and applied for narrow tasks, their implementation in other medical settings could help to improve patient care. Here we assess whether a deep-learning system for volumetric heart segmentation on computed tomography (CT) scans...
Main Authors: | , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-03-01
|
Series: | npj Digital Medicine |
Online Access: | https://doi.org/10.1038/s41746-021-00416-5 |
id |
doaj-8becf93bb4f941d09c80914e23c4335a |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Roman Zeleznik Jakob Weiss Jana Taron Christian Guthier Danielle S. Bitterman Cindy Hancox Benjamin H. Kann Daniel W. Kim Rinaa S. Punglia Jeremy Bredfeldt Borek Foldyna Parastou Eslami Michael T. Lu Udo Hoffmann Raymond Mak Hugo J. W. L. Aerts |
spellingShingle |
Roman Zeleznik Jakob Weiss Jana Taron Christian Guthier Danielle S. Bitterman Cindy Hancox Benjamin H. Kann Daniel W. Kim Rinaa S. Punglia Jeremy Bredfeldt Borek Foldyna Parastou Eslami Michael T. Lu Udo Hoffmann Raymond Mak Hugo J. W. L. Aerts Deep-learning system to improve the quality and efficiency of volumetric heart segmentation for breast cancer npj Digital Medicine |
author_facet |
Roman Zeleznik Jakob Weiss Jana Taron Christian Guthier Danielle S. Bitterman Cindy Hancox Benjamin H. Kann Daniel W. Kim Rinaa S. Punglia Jeremy Bredfeldt Borek Foldyna Parastou Eslami Michael T. Lu Udo Hoffmann Raymond Mak Hugo J. W. L. Aerts |
author_sort |
Roman Zeleznik |
title |
Deep-learning system to improve the quality and efficiency of volumetric heart segmentation for breast cancer |
title_short |
Deep-learning system to improve the quality and efficiency of volumetric heart segmentation for breast cancer |
title_full |
Deep-learning system to improve the quality and efficiency of volumetric heart segmentation for breast cancer |
title_fullStr |
Deep-learning system to improve the quality and efficiency of volumetric heart segmentation for breast cancer |
title_full_unstemmed |
Deep-learning system to improve the quality and efficiency of volumetric heart segmentation for breast cancer |
title_sort |
deep-learning system to improve the quality and efficiency of volumetric heart segmentation for breast cancer |
publisher |
Nature Publishing Group |
series |
npj Digital Medicine |
issn |
2398-6352 |
publishDate |
2021-03-01 |
description |
Abstract Although artificial intelligence algorithms are often developed and applied for narrow tasks, their implementation in other medical settings could help to improve patient care. Here we assess whether a deep-learning system for volumetric heart segmentation on computed tomography (CT) scans developed in cardiovascular radiology can optimize treatment planning in radiation oncology. The system was trained using multi-center data (n = 858) with manual heart segmentations provided by cardiovascular radiologists. Validation of the system was performed in an independent real-world dataset of 5677 breast cancer patients treated with radiation therapy at the Dana-Farber/Brigham and Women’s Cancer Center between 2008–2018. In a subset of 20 patients, the performance of the system was compared to eight radiation oncology experts by assessing segmentation time, agreement between experts, and accuracy with and without deep-learning assistance. To compare the performance to segmentations used in the clinic, concordance and failures (defined as Dice < 0.85) of the system were evaluated in the entire dataset. The system was successfully applied without retraining. With deep-learning assistance, segmentation time significantly decreased (4.0 min [IQR 3.1–5.0] vs. 2.0 min [IQR 1.3–3.5]; p < 0.001), and agreement increased (Dice 0.95 [IQR = 0.02]; vs. 0.97 [IQR = 0.02], p < 0.001). Expert accuracy was similar with and without deep-learning assistance (Dice 0.92 [IQR = 0.02] vs. 0.92 [IQR = 0.02]; p = 0.48), and not significantly different from deep-learning-only segmentations (Dice 0.92 [IQR = 0.02]; p ≥ 0.1). In comparison to real-world data, the system showed high concordance (Dice 0.89 [IQR = 0.06]) across 5677 patients and a significantly lower failure rate (p < 0.001). These results suggest that deep-learning algorithms can successfully be applied across medical specialties and improve clinical care beyond the original field of interest. |
url |
https://doi.org/10.1038/s41746-021-00416-5 |
work_keys_str_mv |
AT romanzeleznik deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT jakobweiss deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT janataron deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT christianguthier deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT daniellesbitterman deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT cindyhancox deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT benjaminhkann deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT danielwkim deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT rinaaspunglia deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT jeremybredfeldt deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT borekfoldyna deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT parastoueslami deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT michaeltlu deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT udohoffmann deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT raymondmak deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer AT hugojwlaerts deeplearningsystemtoimprovethequalityandefficiencyofvolumetricheartsegmentationforbreastcancer |
_version_ |
1724224161998438400 |
spelling |
doaj-8becf93bb4f941d09c80914e23c4335a2021-03-11T12:39:59ZengNature Publishing Groupnpj Digital Medicine2398-63522021-03-01411710.1038/s41746-021-00416-5Deep-learning system to improve the quality and efficiency of volumetric heart segmentation for breast cancerRoman Zeleznik0Jakob Weiss1Jana Taron2Christian Guthier3Danielle S. Bitterman4Cindy Hancox5Benjamin H. Kann6Daniel W. Kim7Rinaa S. Punglia8Jeremy Bredfeldt9Borek Foldyna10Parastou Eslami11Michael T. Lu12Udo Hoffmann13Raymond Mak14Hugo J. W. L. Aerts15Artificial Intelligence in Medicine (AIM) Program, Brigham and Women’s Hospital, Harvard Medical SchoolArtificial Intelligence in Medicine (AIM) Program, Brigham and Women’s Hospital, Harvard Medical SchoolCardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical SchoolDepartment of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical SchoolDepartment of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical SchoolDepartment of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical SchoolArtificial Intelligence in Medicine (AIM) Program, Brigham and Women’s Hospital, Harvard Medical SchoolDepartment of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical SchoolDepartment of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical SchoolDepartment of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical SchoolArtificial Intelligence in Medicine (AIM) Program, Brigham and Women’s Hospital, Harvard Medical SchoolCardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical SchoolCardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical SchoolArtificial Intelligence in Medicine (AIM) Program, Brigham and Women’s Hospital, Harvard Medical SchoolDepartment of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical SchoolArtificial Intelligence in Medicine (AIM) Program, Brigham and Women’s Hospital, Harvard Medical SchoolAbstract Although artificial intelligence algorithms are often developed and applied for narrow tasks, their implementation in other medical settings could help to improve patient care. Here we assess whether a deep-learning system for volumetric heart segmentation on computed tomography (CT) scans developed in cardiovascular radiology can optimize treatment planning in radiation oncology. The system was trained using multi-center data (n = 858) with manual heart segmentations provided by cardiovascular radiologists. Validation of the system was performed in an independent real-world dataset of 5677 breast cancer patients treated with radiation therapy at the Dana-Farber/Brigham and Women’s Cancer Center between 2008–2018. In a subset of 20 patients, the performance of the system was compared to eight radiation oncology experts by assessing segmentation time, agreement between experts, and accuracy with and without deep-learning assistance. To compare the performance to segmentations used in the clinic, concordance and failures (defined as Dice < 0.85) of the system were evaluated in the entire dataset. The system was successfully applied without retraining. With deep-learning assistance, segmentation time significantly decreased (4.0 min [IQR 3.1–5.0] vs. 2.0 min [IQR 1.3–3.5]; p < 0.001), and agreement increased (Dice 0.95 [IQR = 0.02]; vs. 0.97 [IQR = 0.02], p < 0.001). Expert accuracy was similar with and without deep-learning assistance (Dice 0.92 [IQR = 0.02] vs. 0.92 [IQR = 0.02]; p = 0.48), and not significantly different from deep-learning-only segmentations (Dice 0.92 [IQR = 0.02]; p ≥ 0.1). In comparison to real-world data, the system showed high concordance (Dice 0.89 [IQR = 0.06]) across 5677 patients and a significantly lower failure rate (p < 0.001). These results suggest that deep-learning algorithms can successfully be applied across medical specialties and improve clinical care beyond the original field of interest.https://doi.org/10.1038/s41746-021-00416-5 |