PURPOSE: Auto-segmentation algorithms offer a potential solution to eliminate the labor-intensive, time-consuming, and observer-dependent manual delineation of organs-at-risk (OARs) in radiotherapy treatment planning. This study aimed to develop a deep learning-based automated OAR delineation method to tackle the current challenges remaining in achieving reliable expert performance with the state-of-the-art auto-delineation algorithms. METHODS: The accuracy of OAR delineation is expected to be improved by utilizing the complementary contrasts provided by CT (bony-structure contrast) and MRI (soft-tissue contrast). Given CT images, synthetic MR images were firstly generated by a pre-trained cycle-consistent generative adversarial network. The features of CT and synthetic MRI were then extracted and combined for final delineation of organs using mask scoring regional convolutional neural network. Both in-house and public datasets containing CT scans from head-and-neck (HN) cancer patients were adopted to quantitatively evaluate the performance of the proposed method against current state-of-the-art algorithms in metrics including Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and residual mean square distance (RMS). RESULTS: Across all of 18 OARs in our in-house dataset, the proposed method achieved an average DSC, HD95, MSD, and RMS of 0.77 (0.58 - 0.90), 2.90 mm (1.32 mm - 7.63 mm), 0.89 mm (0.42 mm - 1.85 mm), and 1.44 mm (0.71 mm - 3.15 mm), respectively, outperforming the current state-of-the-art algorithms by 6%, 16%, 25%, and 36%, respectively. On public datasets, for all 9 OARs, an average DSC of 0.86 (0.73 - 0.97) were achieved, 6% better than the competing methods. CONCLUSION: We demonstrated the feasibility of a synthetic MRI-aided deep learning framework for automated delineation of OARs in HN radiotherapy treatment planning. The proposed method could be adopted into routine HN cancer radiotherapy treatment planning to rapidly contour OARs with high accuracy. This article is protected by copyright. All rights reserved.
PURPOSE: Auto-segmentation algorithms offer a potential solution to eliminate the labor-intensive, time-consuming, and observer-dependent manual delineation of organs-at-risk (OARs) in radiotherapy treatment planning. This study aimed to develop a deep learning-based automated OAR delineation method to tackle the current challenges remaining in achieving reliable expert performance with the state-of-the-art auto-delineation algorithms. METHODS: The accuracy of OAR delineation is expected to be improved by utilizing the complementary contrasts provided by CT (bony-structure contrast) and MRI (soft-tissue contrast). Given CT images, synthetic MR images were firstly generated by a pre-trained cycle-consistent generative adversarial network. The features of CT and synthetic MRI were then extracted and combined for final delineation of organs using mask scoring regional convolutional neural network. Both in-house and public datasets containing CT scans from head-and-neck (HN) cancerpatients were adopted to quantitatively evaluate the performance of the proposed method against current state-of-the-art algorithms in metrics including Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and residual mean square distance (RMS). RESULTS: Across all of 18 OARs in our in-house dataset, the proposed method achieved an average DSC, HD95, MSD, and RMS of 0.77 (0.58 - 0.90), 2.90 mm (1.32 mm - 7.63 mm), 0.89 mm (0.42 mm - 1.85 mm), and 1.44 mm (0.71 mm - 3.15 mm), respectively, outperforming the current state-of-the-art algorithms by 6%, 16%, 25%, and 36%, respectively. On public datasets, for all 9 OARs, an average DSC of 0.86 (0.73 - 0.97) were achieved, 6% better than the competing methods. CONCLUSION: We demonstrated the feasibility of a synthetic MRI-aided deep learning framework for automated delineation of OARs in HN radiotherapy treatment planning. The proposed method could be adopted into routine HN cancer radiotherapy treatment planning to rapidly contour OARs with high accuracy. This article is protected by copyright. All rights reserved.
Entities:
Keywords:
deep learning; multi-organ segmentation; synthetic MRI
Authors: Asma Amjad; Jiaofeng Xu; Dan Thill; Colleen Lawton; William Hall; Musaddiq J Awan; Monica Shukla; Beth A Erickson; X Allen Li Journal: Med Phys Date: 2022-02-07 Impact factor: 4.071
Authors: Petros Kalendralis; Matthijs Sloep; Nibin Moni George; Jasper Snel; Joeri Veugen; Frank Hoebers; Frederik Wesseling; Mirko Unipan; Martijn Veening; Johannes A Langendijk; Andre Dekker; Johan van Soest; Rianne Fijten Journal: Phys Imaging Radiat Oncol Date: 2022-09-17