Deep Learning-Based Cardiac Chamber Segmentation in Magnetic Resonance-Guided Adaptive Radiation Therapy

Purpose: Accurate cardiac chamber segmentation is crucial for improving cardiac sparing in magnetic resonance (MR)-guided adaptive radiation therapy, especially in patients at risk for radiation-induced cardiotoxicity. Here, we developed and evaluated automatic segmentation models for cardiac chambe...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinru Chen, PhD, Yao Ding, PhD, Julius Weng, MD, Carol C. Wu, MD, Yao Zhao, PhD, Angela Sobremonte, BS, Mustefa Mohammedsaid, MS, Zhan Xu, PhD, Xiaodong Zhang, PhD, Joshua S. Niedzielski, PhD, Sanjay S. Shete, PhD, Laurence E. Court, PhD, Zhongxing Liao, MD, Jihong Wang, PhD, Ergys Subashi, PhD, Percy P. Lee, MD, Jinzhong Yang, PhD
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Advances in Radiation Oncology
Online Access:http://www.sciencedirect.com/science/article/pii/S2452109425001320
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849338316838666240
author Xinru Chen, PhD
Yao Ding, PhD
Julius Weng, MD
Carol C. Wu, MD
Yao Zhao, PhD
Angela Sobremonte, BS
Mustefa Mohammedsaid, MS
Zhan Xu, PhD
Xiaodong Zhang, PhD
Joshua S. Niedzielski, PhD
Sanjay S. Shete, PhD
Laurence E. Court, PhD
Zhongxing Liao, MD
Jihong Wang, PhD
Ergys Subashi, PhD
Percy P. Lee, MD
Jinzhong Yang, PhD
author_facet Xinru Chen, PhD
Yao Ding, PhD
Julius Weng, MD
Carol C. Wu, MD
Yao Zhao, PhD
Angela Sobremonte, BS
Mustefa Mohammedsaid, MS
Zhan Xu, PhD
Xiaodong Zhang, PhD
Joshua S. Niedzielski, PhD
Sanjay S. Shete, PhD
Laurence E. Court, PhD
Zhongxing Liao, MD
Jihong Wang, PhD
Ergys Subashi, PhD
Percy P. Lee, MD
Jinzhong Yang, PhD
author_sort Xinru Chen, PhD
collection DOAJ
description Purpose: Accurate cardiac chamber segmentation is crucial for improving cardiac sparing in magnetic resonance (MR)-guided adaptive radiation therapy, especially in patients at risk for radiation-induced cardiotoxicity. Here, we developed and evaluated automatic segmentation models for cardiac chambers that use daily MR images acquired on a 1.5-T MR-Linac system. Methods and Materials: Twenty healthy volunteers underwent daily MR scanning on a 1.5-T MR-Linac, with 2 radial sequences: T2/T1 3DVaneXD balanced fast field echo with spectral attenuated inversion recovery (bFFE-SPAIR) and T1 3DVaneXD mDixon. Three flip angles were tested for each sequence to determine optimal image quality for chamber segmentation. Full-resolution 3D nnU-Net models were trained for the following: (1) bFFE-SPAIR (bFFE model); (2) T1 mDixon (mDixon model); and (3) both sequences (hybrid model). Models were evaluated based on Dice similarity coefficient (DSC) and mean surface distance against manual contours. Clinical acceptance of the automatic segmentation was assessed with a 5-point Likert scale. An in-silico planning study was performed to assess cardiac chamber sparing during plan adaptation. Results: The average contrast-to-noise ratios in bFFE-SPAIR were 8.7 (20°), 34.2 (50°), and 37.3 (80°); for T1 mDixon, these values were 3.6 (5°), 5.9 (10°), and 4.9 (20°). The bFFE model achieved the highest segmentation performance (average DSC 0.85 ± 0.05 and mean surface distance 2.2 ± 0.6 mm). The T1 mDixon sequence, despite lower contrast-to-noise ratios, provided similar segmentation accuracy (DSC 0.83 ± 0.06). A hybrid model combining both sequences showed no significant improvement over the bFFE model. Clinical evaluation indicated that 95% of the autosegmented contours from the bFFE model were acceptable for clinical use (score ≥4). Adaptive plan greatly reduced individual cardiac chamber dose while maintaining similar target coverage. Conclusions: This study demonstrated the feasibility of using bFFE-SPAIR and T1 mDixon sequences to accurately segment cardiac chambers on a 1.5-T MR-Linac. These models offer potential for improved cardiac sparing in MR-guided adaptive radiation therapy.
format Article
id doaj-art-e4e095d69fe64f828af83b683364ef67
institution Kabale University
issn 2452-1094
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Advances in Radiation Oncology
spelling doaj-art-e4e095d69fe64f828af83b683364ef672025-08-20T03:44:27ZengElsevierAdvances in Radiation Oncology2452-10942025-09-0110910184510.1016/j.adro.2025.101845Deep Learning-Based Cardiac Chamber Segmentation in Magnetic Resonance-Guided Adaptive Radiation TherapyXinru Chen, PhD0Yao Ding, PhD1Julius Weng, MD2Carol C. Wu, MD3Yao Zhao, PhD4Angela Sobremonte, BS5Mustefa Mohammedsaid, MS6Zhan Xu, PhD7Xiaodong Zhang, PhD8Joshua S. Niedzielski, PhD9Sanjay S. Shete, PhD10Laurence E. Court, PhD11Zhongxing Liao, MD12Jihong Wang, PhD13Ergys Subashi, PhD14Percy P. Lee, MD15Jinzhong Yang, PhD16Department of Radiation Physics, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas; The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TexasDepartment of Radiation Physics, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TexasDepartment of Radiation Oncology, City of Hope National Medical Center, Los Angeles, CaliforniaDepartment of Thoracic Imaging, Division of Diagnostic Imaging, The University of Texas MD Anderson Cancer Center, Houston, TexasDepartment of Radiation Physics, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TexasDepartment of Radiation Oncology, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TexasDepartment of Radiation Oncology, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TexasDepartment of Radiation Physics, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TexasDepartment of Radiation Physics, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas; The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TexasDepartment of Radiation Physics, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas; The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TexasThe University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, Texas; Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TexasDepartment of Radiation Physics, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas; The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TexasDepartment of Thoracic Radiation Oncology, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TexasDepartment of Radiation Physics, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TexasDepartment of Radiation Physics, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TexasDepartment of Radiation Oncology, City of Hope National Medical Center, Los Angeles, CaliforniaDepartment of Radiation Physics, Division of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas; The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, Texas; Corresponding author: Jinzhong Yang, PhDPurpose: Accurate cardiac chamber segmentation is crucial for improving cardiac sparing in magnetic resonance (MR)-guided adaptive radiation therapy, especially in patients at risk for radiation-induced cardiotoxicity. Here, we developed and evaluated automatic segmentation models for cardiac chambers that use daily MR images acquired on a 1.5-T MR-Linac system. Methods and Materials: Twenty healthy volunteers underwent daily MR scanning on a 1.5-T MR-Linac, with 2 radial sequences: T2/T1 3DVaneXD balanced fast field echo with spectral attenuated inversion recovery (bFFE-SPAIR) and T1 3DVaneXD mDixon. Three flip angles were tested for each sequence to determine optimal image quality for chamber segmentation. Full-resolution 3D nnU-Net models were trained for the following: (1) bFFE-SPAIR (bFFE model); (2) T1 mDixon (mDixon model); and (3) both sequences (hybrid model). Models were evaluated based on Dice similarity coefficient (DSC) and mean surface distance against manual contours. Clinical acceptance of the automatic segmentation was assessed with a 5-point Likert scale. An in-silico planning study was performed to assess cardiac chamber sparing during plan adaptation. Results: The average contrast-to-noise ratios in bFFE-SPAIR were 8.7 (20°), 34.2 (50°), and 37.3 (80°); for T1 mDixon, these values were 3.6 (5°), 5.9 (10°), and 4.9 (20°). The bFFE model achieved the highest segmentation performance (average DSC 0.85 ± 0.05 and mean surface distance 2.2 ± 0.6 mm). The T1 mDixon sequence, despite lower contrast-to-noise ratios, provided similar segmentation accuracy (DSC 0.83 ± 0.06). A hybrid model combining both sequences showed no significant improvement over the bFFE model. Clinical evaluation indicated that 95% of the autosegmented contours from the bFFE model were acceptable for clinical use (score ≥4). Adaptive plan greatly reduced individual cardiac chamber dose while maintaining similar target coverage. Conclusions: This study demonstrated the feasibility of using bFFE-SPAIR and T1 mDixon sequences to accurately segment cardiac chambers on a 1.5-T MR-Linac. These models offer potential for improved cardiac sparing in MR-guided adaptive radiation therapy.http://www.sciencedirect.com/science/article/pii/S2452109425001320
spellingShingle Xinru Chen, PhD
Yao Ding, PhD
Julius Weng, MD
Carol C. Wu, MD
Yao Zhao, PhD
Angela Sobremonte, BS
Mustefa Mohammedsaid, MS
Zhan Xu, PhD
Xiaodong Zhang, PhD
Joshua S. Niedzielski, PhD
Sanjay S. Shete, PhD
Laurence E. Court, PhD
Zhongxing Liao, MD
Jihong Wang, PhD
Ergys Subashi, PhD
Percy P. Lee, MD
Jinzhong Yang, PhD
Deep Learning-Based Cardiac Chamber Segmentation in Magnetic Resonance-Guided Adaptive Radiation Therapy
Advances in Radiation Oncology
title Deep Learning-Based Cardiac Chamber Segmentation in Magnetic Resonance-Guided Adaptive Radiation Therapy
title_full Deep Learning-Based Cardiac Chamber Segmentation in Magnetic Resonance-Guided Adaptive Radiation Therapy
title_fullStr Deep Learning-Based Cardiac Chamber Segmentation in Magnetic Resonance-Guided Adaptive Radiation Therapy
title_full_unstemmed Deep Learning-Based Cardiac Chamber Segmentation in Magnetic Resonance-Guided Adaptive Radiation Therapy
title_short Deep Learning-Based Cardiac Chamber Segmentation in Magnetic Resonance-Guided Adaptive Radiation Therapy
title_sort deep learning based cardiac chamber segmentation in magnetic resonance guided adaptive radiation therapy
url http://www.sciencedirect.com/science/article/pii/S2452109425001320
work_keys_str_mv AT xinruchenphd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT yaodingphd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT juliuswengmd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT carolcwumd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT yaozhaophd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT angelasobremontebs deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT mustefamohammedsaidms deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT zhanxuphd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT xiaodongzhangphd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT joshuasniedzielskiphd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT sanjaysshetephd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT laurenceecourtphd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT zhongxingliaomd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT jihongwangphd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT ergyssubashiphd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT percypleemd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy
AT jinzhongyangphd deeplearningbasedcardiacchambersegmentationinmagneticresonanceguidedadaptiveradiationtherapy