Organ-aware CBCT Enhancement Via Dual Path Learning for Prostate Cancer Treatment

Overview

Journal Med Phys

Specialty Biophysics

Date 2023 Sep 26

PMID 37751497

Authors

Xu Chen

Yunkui Pang

Sahar Ahmad

Trevor Royce

Andrew Wang

Jun Lian

Pew-Thian Yap

Affiliations

Soon will be listed here.

Abstract

Background: Cone-beam computed tomography (CBCT) plays a crucial role in the intensity modulated radiotherapy (IMRT) of prostate cancer. However, poor image contrast and fuzzy organ boundaries pose challenges to precise targeting for dose delivery and plan reoptimization for adaptive therapy.

Purpose: In this work, we aim to enhance pelvic CBCT images by translating them to high-quality CT images with a particular focus on the anatomical structures important for radiotherapy.

Methods: We develop a novel dual-path learning framework, covering both global and local information, for organ-aware enhancement of the prostate, bladder and rectum. The global path learns coarse inter-modality translation at the image level. The local path learns organ-aware translation at the regional level. This dual-path learning architecture can serve as a plug-and-play module adaptable to other medical image-to-image translation frameworks.

Results: We evaluated the performance of the proposed method both quantitatively and qualitatively. The training dataset consists of unpaired 40 CBCT and 40 CT scans, the validation dataset consists of 5 paired CBCT-CT scans, and the testing dataset consists of 10 paired CBCT-CT scans. The peak signal-to-noise ratio (PSNR) between enhanced CBCT and reference CT images is 27.22 ± 1.79, and the structural similarity (SSIM) between enhanced CBCT and the reference CT images is 0.71 ± 0.03. We also compared our method with state-of-the-art image-to-image translation methods, where our method achieves the best performance. Moreover, the statistical analysis confirms that the improvements achieved by our method are statistically significant.

Conclusions: The proposed method demonstrates its superiority in enhancing pelvic CBCT images, especially at the organ level, compared to relevant methods.

References

Emami H, Dong M, Nejad-Davarani S, Glide-Hurst C . Generating synthetic CTs from magnetic resonance images using generative adversarial networks. Med Phys. 2018; . PMC: 6294710. DOI: 10.1002/mp.13047. View

Peng J, Qiu R, Wynne J, Chang C, Pan S, Wang T . CBCT-Based synthetic CT image generation using conditional denoising diffusion probabilistic model. Med Phys. 2023; 51(3):1847-1859. PMC: 11747767. DOI: 10.1002/mp.16704. View

Chen X, Lian C, Wang L, Deng H, Kuang T, Fung S . Anatomy-Regularized Representation Learning for Cross-Modality Medical Image Segmentation. IEEE Trans Med Imaging. 2020; 40(1):274-285. PMC: 8120796. DOI: 10.1109/TMI.2020.3025133. View

Li Y, Shao H, Liang X, Chen L, Li R, Jiang S . Zero-Shot Medical Image Translation via Frequency-Guided Diffusion Models. IEEE Trans Med Imaging. 2023; 43(3):980-993. PMC: 11000254. DOI: 10.1109/TMI.2023.3325703. View

Nie D, Cao X, Gao Y, Wang L, Shen D . Estimating CT Image from MRI Data Using 3D Fully Convolutional Networks. Deep Learn Data Label Med Appl (2016). 2017; 2016:170-178. PMC: 5654583. DOI: 10.1007/978-3-319-46976-8_18. View

Han X . MR-based synthetic CT generation using a deep convolutional neural network method. Med Phys. 2017; 44(4):1408-1419. DOI: 10.1002/mp.12155. View

Costa P, Galdran A, Meyer M, Niemeijer M, Abramoff M, Mendonca A . End-to-End Adversarial Retinal Image Synthesis. IEEE Trans Med Imaging. 2017; 37(3):781-791. DOI: 10.1109/TMI.2017.2759102. View

Dalmaz O, Yurt M, Cukur T . ResViT: Residual Vision Transformers for Multimodal Medical Image Synthesis. IEEE Trans Med Imaging. 2022; 41(10):2598-2614. DOI: 10.1109/TMI.2022.3167808. View

Klopp A, Yeung A, Deshmukh S, Gil K, Wenzel L, Westin S . Patient-Reported Toxicity During Pelvic Intensity-Modulated Radiation Therapy: NRG Oncology-RTOG 1203. J Clin Oncol. 2018; 36(24):2538-2544. PMC: 6097832. DOI: 10.1200/JCO.2017.77.4273. View

10.

Kerkhof E, van der Put R, Raaymakers B, van der Heide U, van Vulpen M, Lagendijk J . Variation in target and rectum dose due to prostate deformation: an assessment by repeated MR imaging and treatment planning. Phys Med Biol. 2008; 53(20):5623-34. DOI: 10.1088/0031-9155/53/20/004. View

11.

Armanious K, Jiang C, Fischer M, Kustner T, Hepp T, Nikolaou K . MedGAN: Medical image translation using GANs. Comput Med Imaging Graph. 2019; 79:101684. DOI: 10.1016/j.compmedimag.2019.101684. View