TY - JOUR
T1 - Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network
AU - Zabihollahy, Fatemeh
AU - Viswanathan, Akila N.
AU - Schmidt, Ehud J.
AU - Lee, Junghoon
N1 - Publisher Copyright:
© 2022 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals, LLC on behalf of The American Association of Physicists in Medicine.
PY - 2022/9
Y1 - 2022/9
N2 - Purpose: Contouring clinical target volume (CTV) from medical images is an essential step for radiotherapy (RT) planning. Magnetic resonance imaging (MRI) is used as a standard imaging modality for CTV segmentation in cervical cancer due to its superior soft-tissue contrast. However, the delineation of CTV is challenging as CTV contains microscopic extensions that are not clearly visible even in MR images, resulting in significant contour variability among radiation oncologists depending on their knowledge and experience. In this study, we propose a fully automated deep learning–based method to segment CTV from MR images. Methods: Our method begins with the bladder segmentation, from which the CTV position is estimated in the axial view. The superior–inferior CTV span is then detected using an Attention U-Net. A CTV-specific region of interest (ROI) is determined, and three-dimensional (3-D) blocks are extracted from the ROI volume. Finally, a CTV segmentation map is computed using a 3-D U-Net from the extracted 3-D blocks. Results: We developed and evaluated our method using 213 MRI scans obtained from 125 patients (183 for training, 30 for test). Our method achieved (mean ± SD) Dice similarity coefficient of 0.85 ± 0.03 and the 95th percentile Hausdorff distance of 3.70 ± 0.35 mm on test cases, outperforming other state-of-the-art methods significantly (p-value < 0.05). Our method also produces an uncertainty map along with the CTV segmentation by employing the Monte Carlo dropout technique to draw physician's attention to the regions with high uncertainty, where careful review and manual correction may be needed. Conclusions: Experimental results show that the developed method is accurate, fast, and reproducible for contouring CTV from MRI, demonstrating its potential to assist radiation oncologists in alleviating the burden of tedious contouring for RT planning in cervical cancer.
AB - Purpose: Contouring clinical target volume (CTV) from medical images is an essential step for radiotherapy (RT) planning. Magnetic resonance imaging (MRI) is used as a standard imaging modality for CTV segmentation in cervical cancer due to its superior soft-tissue contrast. However, the delineation of CTV is challenging as CTV contains microscopic extensions that are not clearly visible even in MR images, resulting in significant contour variability among radiation oncologists depending on their knowledge and experience. In this study, we propose a fully automated deep learning–based method to segment CTV from MR images. Methods: Our method begins with the bladder segmentation, from which the CTV position is estimated in the axial view. The superior–inferior CTV span is then detected using an Attention U-Net. A CTV-specific region of interest (ROI) is determined, and three-dimensional (3-D) blocks are extracted from the ROI volume. Finally, a CTV segmentation map is computed using a 3-D U-Net from the extracted 3-D blocks. Results: We developed and evaluated our method using 213 MRI scans obtained from 125 patients (183 for training, 30 for test). Our method achieved (mean ± SD) Dice similarity coefficient of 0.85 ± 0.03 and the 95th percentile Hausdorff distance of 3.70 ± 0.35 mm on test cases, outperforming other state-of-the-art methods significantly (p-value < 0.05). Our method also produces an uncertainty map along with the CTV segmentation by employing the Monte Carlo dropout technique to draw physician's attention to the regions with high uncertainty, where careful review and manual correction may be needed. Conclusions: Experimental results show that the developed method is accurate, fast, and reproducible for contouring CTV from MRI, demonstrating its potential to assist radiation oncologists in alleviating the burden of tedious contouring for RT planning in cervical cancer.
KW - cervical cancer
KW - clinical target volume
KW - deep learning segmentation
KW - magnetic resonance imaging
KW - radiotherapy
UR - http://www.scopus.com/inward/record.url?scp=85135163519&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85135163519&partnerID=8YFLogxK
U2 - 10.1002/acm2.13725
DO - 10.1002/acm2.13725
M3 - Article
C2 - 35894782
AN - SCOPUS:85135163519
SN - 1526-9914
VL - 23
JO - Journal of applied clinical medical physics
JF - Journal of applied clinical medical physics
IS - 9
M1 - e13725
ER -