Medical Imaging

Delineation of the post-prostatectomy clinical target volume using deep learning for prostate cancer radiotherapy Delineation of the post-prostatectomy clinical target volume using deep learning for prostate cancer radiotherapy

Organ Segmentation and Treatment Target Delineation

Accurate delineation of tumors and sensitive structures is important for many medical applications. One example is treatment planning in cancer radiotherapy. Although many auto-segmentation algorithms have been developed and implemented in clinical practice, none of them are satisfactory and manual contouring is often required. Such failure is mainly because conventional segmentation methods are purely based on local information in the images. Especially for treatment target delineation we often rely on information beyond the images which is very challenging, if not impossible, for conventional methods. We have been investigating deep learning based strategies to solve this problem.

The figure below shows an example of delineating the post-prostatectomy clinical target volume using deep learning for prostate cancer radiotherapy, where in addition to CT images, we need to use information like surgery reports, surgical pathology, pre-operative MRI knowledge of tumor location and organ invasion, etc.

Publications

  1. Balagopal A, Dohopolski M, Kwon YS, Montalvo S, Morgan H, Bai Y, Nguyen D, Liang X, Zhong X, Lin MH, Desai N, Jiang S. (2023) Deep learning (DL)-based automatic segmentation of the internal pudendal artery (IPA) for reduction of erectile dysfunction in definitive radiotherapy of localized prostate cancer. (arXiv preprint) 
  2. Liang X, Morgan H, Bai T, Dohopolski M, Nguyen D, Jiang S. (2023) Deep learning based direct segmentation assisted by deformable image registration for cone-beam CT based auto-segmentation for adaptive radiotherapy. Phys Med Biol. (journal) 
  3. Liang X, Chun J, Morgan HE, Bai T, Nguyen D, Park J, Jiang S. (2023) Evaluating a personalized deep-learning-based auto-segmentation method for CBCT-based adaptive radiotherapy. Int J Radiat Oncol Biol Phys. (journal) 
  4. Balagopal A, Nguyen D, Bai T, Dohopolski M, Lin MH, Jiang S. (2023) Prior guided deep difference meta-learner for fast adaptation to stylized segmentation. (arXiv preprint) 
  5. Liang X, Chun J, Morgan H, Bai T, Nguyen D, Park J, Jiang S. (2023) Segmentation by test‐time optimization for CBCT‐based adaptive radiation therapy. Med Phys. (journal)
  6. Bai T, Balagopal A, Dohopolski M, Morgan H, McBeth R, Tan J, Lin MH, Sher D, Nguyen D, Jiang S. (2022) A proof-of-concept study of artificial intelligence–assisted contour editing. Radiology: AI. (journal)
  7. Liang X, Morgan H, Bai T, Dohopolski M, Nguyen D, Jiang S. (2022) Exploring the combination of deep-learning based direct segmentation and deformable image registration for cone-beam CT based auto-segmentation for adaptive radiotherapy. (arXiv preprint)
  8. Wang A, Bai T, Nguyen D, Jiang S. (2022) Octree boundary transfiner: efficient transformers for tumor segmentation refinement. Lecture Notes in Computer Science, Springer. (journal) 
  9. Wang B, Dohopolski M, Bai T, Wu J, Hannan R, Desai N, Garant A, Nguyen D, Wang X, Lin MH, Timmerman R, Jiang S. (2022) Performance deterioration of deep learning models after clinical deployment: A case study with auto-segmentation for definitive prostate cancer radiotherapy. (arXiv preprint) 
  10. Peng T, Wang C, Zhang Y, Wang J. (2022) H-SegNet: Hybrid segmentation network for lung segmentation in chest radiographs using mask region-based convolutional neural network and adaptive closed polyline searching method. Phys Med Biol. (journal) 
  11. Wang K, George‐Jones NA, Chen L, Hunter JB, Wang J. (2022) Joint vestibular schwannoma enlargement prediction and segmentation using a deep multi‐task model. The Laryngoscope. (journal) 
  12. Shao HV, Li T, Dohopolski M, Wang J, Cai J, Tan J, Wang K, Zhang Y. (2022) Real-time MRI motion estimation through an unsupervised K-space-driven deformable registration network (KS-RegNet). Phys Med Biol. (journal) 
  13. Liang X, Morgan H, Nguyen D, Jiang S. (2021) Deep learning based CT-to-CBCT deformable image registration for autosegmentation in head and neck adaptive radiation therapy. (arXiv preprint)
  14. Balagopal A, Nguyen D, Mashayekhi M, Morgan H, Garant A, Desai N, Hannan R, Lin MH, Jiang S. (2021) Dosimetric impact of physician style variations in contouring CTV for post-operative prostate cancer: A deep learning-based simulation study. (arXiv preprint) 
  15. Gonzalez Y, Shen C, Jung H, Nguyen D, Jiang S, Albuquerque K, Jia X. (2021) Semi-automatic sigmoid colon segmentation in CT for radiation therapy treatment planning via an iterative 2.5-D deep learning approach. Med Image Anal. (journal) 
  16. Balagopal A, Morgan H, Dohopolski M, Timmerman R, Shan J, Heitjan D, Nguyen D, Hannan R, Garant A, Desai N, Jiang S. (2021) PSA-Net: Deep learning–based physician style–aware segmentation network for postoperative prostate cancer clinical target volumes. Artif Intell Med. (journal)
  17. Yu S, Zhang E, Wu J, Yu H, Yang Z, Ma L, Chen M, Gu X, Lu W. (2020) Robustness study of noisy annotation in deep learning based medical image segmentation. (arXiv)
  18. Balagopal A, Nguyen D, Morgan H, Weng Y, Dohopolski M, Lin MH, Barkousaraie AS, Gonzalez Y, Garant A, Desai N, Hannan R, Jiang S. (2020) A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy. Med Image Anal. (journal) (arXiv) 
  19. Yang Q, Chao H, Nguyen D, Jiang S. (2019) A novel deep learning framework for standardizing the label of OARs in CT. In Workshop on Artificial Intelligence in Radiation Therapy. (journal)
  20. Li S, Xu P, Li B, Chen L, Zhou Z, Hao H, ... Jiang S. (2019) Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features. Phys Med Biol. (journal) (arXiv)
  21. Zhou Z, Li S, Qin G, Folkert M, Jiang S, Wang J. (2019) Multi-objective based radiomic feature selection for lesion malignancy classification. J Biomed Inform. (journal) (arXiv)
  22. Balagopal A, Kazemifar S, Nguyen D, Lin, MH, Hannan R, Owrangi A, Jiang S. (2018) Fully automated organ segmentation in male pelvic CT images. Phys Med Biol. (journal) (arXiv)
  23. Kazemifar S, Balagopal A, Nguyen D, McGuire S, Hannan R, Jiang S, Owrangi A. (2018) Segmentation of the prostate and organs at risk in male pelvic CT images using deep learning. BPEX. (journal) (arXiv)
  24. Liu Y, Stojadinovic S, Hrycushko B, Wardak Z, Lau S, Lu W, ... Nedzi L. (2017) A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery. PloS One. (journal)
  25. Rozario T, Long T, Chen M, Lu W, Jiang S. (2017) Towards automated patient data cleaning using deep learning: a feasibility study on the standardization of organ labeling. (arXiv)
  26. Liu Y, Stojadinovic S, Hrycushko B, Wardak Z, Lu W, Yan Y, ... Gu X. (2016) Automatic metastatic brain tumor segmentation for stereotactic radiosurgery applications. Phys Med Biol. (journal)

Image Reconstruction and Restoration

By introduction of machine learning and data-driven methods, a paradigm shift has happened in the field of imaging in general and accordingly these new methods have a high translational impact in the area of medical imaging.

These impacts are not limited to only image analysis and pattern recognition techniques but also they are used widely in the field of image reconstruction. Recently, multiple groups worldwide, with encouraging results and increasing interest, are actively exploring deep learning techniques for image reconstruction and other inverse problems.

Currently, our team is working on developing new machine learning based methods for implementing MRI-only planning into the clinic. Challenges include producing robust MRI-only patient models and synthetic CT scans with accurate geometry and electron densities.

However, our novel machine learning based method allows us to simultaneously achieve electron density map for dose calculation and automatic segmentation of the target and OAR.

The successful completion of this research will provide essential tools to establish effective MRI-based RT planning in routine clinical practice, which will improve normal and target tissue delineation and localization for more accurate radiation delivery. 

Publications

  1. Liang X, Yen A, Bai T, Godley A, Shen C, Wu J, Meng B, Lin MH, Medin P, Yan Y, Owrangi A, Desai N, Hannan R, Garant A, Jiang S, Deng J. (2023) Bony structure enhanced synthetic CT generation using Dixon sequences for pelvis MR‐only radiotherapy. Med Phys. (journal) 
  2. Olberg S, Su Choi B, Park I, Liang X, Sung Kim J, Deng J, Yan Y, Jiang S, Park JC. (2023) Ensemble learning and personalized training for the improvement of unsupervised deep learning‐based synthetic CT reconstruction. Med Phys. (journal)
  3. Shao HC, Li Y, Wang J, Jiang S, Zhang Y. (2023) Real‐time liver motion estimation via deep learning‐based angle‐agnostic X‐ray imaging. Med Phys. (journal)
  4. Bai Y, Lin MH, Liang X, Wang B, Dohopolski M, Cai B, Nguyen D, Jiang S. (2022) Region specific optimization (RSO)-based deep interactive registration. (arXiv)
  5. Shao HC, Wang J, Bai T, Chun J, Park J, Jiang S, Zhang Y. (2022) Real-time liver tumor localization via a single X-ray projection using deep graph neural network-assisted biomechanical modeling. Phys Med Biol. (journal)
  6. Lee H, Park YK, Duan X, Jia X, Jiang S, Yang M. (2021) Convolutional neural network based proton stopping-power-ratio estimation with dual-energy CT: A feasibility study. Phys Med Biol. (journal)
  7. Bai T, Wang B, Nguyen D, Jiang S. (2021) Deep dose plugin: Towards real-time Monte Carlo dose calculation through a deep learning-based denoising algorithm. Mach Learn: Sci Technol. (journal)
  8. Bai T, Nguyen D, Wang B, Jiang S. (2021) Deep high-resolution network for low dose X-ray CT denoising. (arXiv)
  9. Bai T, Wang B, Nguyen D, Wang B, Dong B, Cong W, Kalra MK, Jiang S. (2021) Deep interactive denoiser (DID) for X-ray computed tomography. IEEE Trans Med Imag. (journal)
  10. Li W, Kazemifar S, Bai T, Nguyen D, Weng Y, Li Y, Xia J, Xiong J, Xie Y, Owrangi A, Jiang S. (2021) Synthesizing CT images from MR images with deep learning: model generalization for different datasets through transfer learning. BPEX. (journal) 
  11. Shao HC, Huang X, Folkert MR, Wang J, Zhang Y. (2021) Automatic liver tumor localization using deep learning‐based liver boundary motion estimation and biomechanical modeling (DL‐Bio). Med Phys. (journal)
  12. Huang X, Zhang Y, Chen L, Wang J. (2020) U‐net‐based deformation vector field estimation for motion‐compensated 4D‐CBCT reconstruction. Med Phys. (journal)
  13. Zhang E, Yang Z, Seiler S, Chen M, Lu W, Gu X. (2020) Breast ultrasound computer-aided diagnosis using structure-aware triplet path networks. (arXiv)
  14. Bai T, Nguyen D, Wang B, Jiang S. (2020) Probabilistic self-learning framework for low-dose CT denoising. (arXiv)
  15. Kazemifar S, Montero AMB, Souris K, Rivas S, Timmerman R, Park Y, Jiang S, Geets X, Sterpin E, Owrangi A. (2020) Dosimetric evaluation of synthetic CT generated with GANs for MRI‐only proton therapy treatment planning of brain tumors. J Appl Clin Med Phys. (journal)
  16. Liang X, Nguyen D, Jiang S. (2020) Generalizability issues with deep learning models in medicine and their potential solutions: Illustrated with cone-beam computed tomography (CBCT) to computed tomography (CT) image conversion. Mach Learn: Sci Technol. (journal) (arXiv)
  17. Chen L, Liang X, Shen C, Jiang S, Wang J. (2020) Synthetic CT generation from CBCT images via deep learning. Med Phys. (journal)
  18. Jia X, Wang S, Liang X, Balagopal A, Nguyen D, Yang M, ... Jiang S. (2019) Cone-beam computed tomography (CBCT) segmentation by adversarial learning domain adaptation. In International Conference on Medical Image Computing and Computer-Assisted Intervention. (journal)
  19. Iqbal Z, Nguyen D, Jiang S. (2019) Super-resolution 1H magnetic resonance spectroscopic imaging utilizing deep learning. Front Oncol. (journal) (arXiv)
  20. Kazemifar S, McGuire S, Timmerman R, Wardak Z, Nguyen D, Park Y, ... Owrangi A. (2019) MRI-only brain radiotherapy: Assessing the dosimetric accuracy of synthetic CT images generated using a deep learning approach. Rad & Onc. (journal) (arXiv)
  21. Liang X, Chen L, Nguyen D, Zhou Z, Gu X, Yang M, ... Jiang S. (2019) Generating synthesized computed tomography (CT) from cone-beam computed tomography (CBCT) using CycleGAN for adaptive radiation therapy. Phys Med Biol. (journal) (arXiv)
  22. Ma G, Shen C, Jia X. (2019) Low dose CT reconstruction assisted by an image manifold prior. SPIE. (journal) (arXiv)
  23. Zhong Y, Vinogradskiy Y, Chen L, Myziuk N, Castillo R, Castillo E, Wang J. (2019) Deriving ventilation imaging from 4 DCT by deep convolutional neural network. Med Phys. (journal) (arXiv)
  24. Iqbal Z, Nguyen D, Thomas MA, Jiang S. (2018) Acceleration and quantitation of localized correlated spectroscopy using deep learning: A pilot simulation study. (arXiv)
  25. Shen C, Gonzalez Y, Chen L, Jiang SB, Jia X. (2018) Intelligent parameter tuning in optimization-based iterative CT reconstruction via deep reinforcement learning. IEEE Trans Med Imaging. (journal) (arXiv)

Other Publications

  1. Ali SR, Nguyen D, Wang B, Jiang S, Sadek HA. (2020) Deep learning identifies cardiomyocyte nuclei with high precision. Circ Res. (journal)