I am Medical Physics Resident at the University of Maryland Medical Center. I got my PhD from the Biomedical Engineering Program Medical Physics Track at UT Southwestern Medical Center (UTSW), advised by Dr. Jing Wang. I worked at Medical Artificial Intelligence and Automation (MAIA) Lab and Advanced Imaging and Informatics for Radiation Therapy (AIRT) Lab for my PhD dissertation, my projects mainly focus on radiomics-based cancer radiotherapy outcome prediction . Before coming to UTSW, I worked with Dr. Xuanqin Mou and Dr. Xi Chen at the Institute of Image Processing and Pattern Recognition (IIPPR)
on Field Emission X-ray Source Array based Imaging Methods for my master’s thesis.
My research interest includes medical image analysis, cancer treatment outcome prediction, radiomics, and medical imaging.
🎓 Educations
- 2023.07 - 2025.06 (Expected), Medical Physics Residency Program, University of Maryland Medical Center (UMMC), Baltimore, MD
- 2018.08 - 2023.05, PhD, BME Medical Physics (CAMPEP Accredited), University of Texas Southwestern Medical Center (UTSW), Dallas, TX
- 2015.09 - 2018.06, MS, Information and Communication Engineering, Xi’an Jiaotong University (XJTU), Shaanxi, China
- 2011.09 - 2015.06, BS, Information Engineering, Xi’an Jiaotong University (XJTU), Shaanxi, China
📚 Experience
-
🏥 Clinical Observation
- Varian TrueBeam/VitalBeam, Patient-specific/Weekly/Monthly/Annual Machine QA, UTSW, 2019.09 and 2022.09.
- Elekta Unity MR Linac, Monthly/Annual Machine QA, UTSW, 2022.10.
- Varian Halcyon, Patient-specific QA, UTSW, 2022.10.
- Conventional Simulation (General), IMRT Planning, and Electron Planning, UTSW, 2019.10.
-
Gamma Knife Stereotactic Radiosurgery, UTSW, 2019.11.
-
📖 Research
- 2019.08 - 2022.08, Head and Neck Cancer Radiotherapy Treatment Outcome Prediction,
UTSW.
- Proposed a multiple-classifier multi-objective multiple-modality predictive (mCOM) model for HNC locoregional recurrence pre-treatment prediction.
- Utilized delta-radiomics feature for HNC locoregional recurrence post-treatment prediction.
- Investigated the additive benefit of CT and intra-treatment CBCT features for HNC radiotherapy outcome prediction.
- Built a deep transfer learning model for predicting the need of aggressive nutritional supplementation for patients receiving radiotherapy.
- Proposed an automatic segmentation guided cancer recurrence-free survival prediction model.
- Introduced learning with rejection option strategy for improving prediction reliability on selected patient group.
- 2021.10 - 2022.06, Optimal PTV Margin for Postoperative Prostatic Fossa Daily ART,
UTSW.
- Investigated the post-treatment CTV coverage when different PTV margins were applied on CTV delineated before daily ART.
- Evaluated the time dependence of CTV coverage using different PTV margins.
- 2021.05 - Present, Pancreatic Cancer Treatment Outcome Prediction,
UTSW.
- Built a delta-radiomics-based survival model for predicting the treatment outcome of patients undergoing surgical resection of PDAC following neoadjuvant therapy.
- Evaluated the predictive ability of features extracted from peritumoral area and the therapy induced feature change for PDAC patient treatment outcome prediction.
- 2019.05 - 2021.06, Lateral Skull Base Tumor Growth Prediction,
UTSW.
- Developed a lateral skull base tumor automatic segmentation method using MRI image.
- Investigated the stability of tumor delineation by human expert and auto-segmentation.
- Proposed a joint tumor enlargement prediction and segmentation model using intitial diagnostic MR image for vestibular schwannoma.
- Build a prediction model for vestibular schwannoma enlargement after radiosurgery using tumor shape and MRI texture features.
- 2019.08 - 2019.12, High-Resolution Brain PET Imaging,
UTSW.
- Simulated the coincidence signal can be detected by a high-resolution low-sensitivity detecor and a low-resolution high-sensitivity detector using Monte Carlo method.
- Constructed a conversion (inverse method) matrix for calculating the coincidence signal can be detected by a virtual high-resolution and high-sensitivity detecor for high-resolution brain PET imaging.
- 2019.01 - 2019.07, Similar Patients Retrieval for Radiotherapy Treatment Planning,
UTSW.
- Proposed a relational autoencoder based descriptor which considers patient’s geometry and the relationship of plan dose distributions between different patients for retrieving similar patient for prostate cancer radiotherapy treatment planning.
- 2015.09 - 2018.05, Imaging Method Based on Field Emission X-ray Source Array, IIPPR, XJTU
.
- Participated in the design and manufacture of the field emission x-ray source array imaging and lateral Compton scattering imaging verification platform.
- Designed a stationary CT scheme based on x-ray source array.
- Proposed a nonlinear constrain based method to address the overlapping projection problem due to simultaneous scanning of the x-ray source array for source-array-based radiographic imaging.
📝 Publications
📓 Journal Paper
Towards reliable head and neck cancers locoregional recurrence prediction using delta-radiomics and learning with rejection option
Kai Wang, Michael Dohopolski, Qiongwen Zhang, David Sher, Jing Wang, Medical physics, 2022.
Project |
- Delta-radiomcis features calculated based on Pre- and Post-Therapy PET/CT.
- Multi-modality model for early-stage locoregional recurrence prediction.
- We performed patient-specific prediction uncertainty estimation for learning with rejection option to improve the model reliability (higher performance on high-confidence group).
![sym](images/VS-MultiTask.png)
Joint Vestibular Schwannoma Enlargement Prediction and Segmentation Using a Deep Multi-task Model
Kai Wang, Nicholas George-Jones, Liyuan Chen, Jacob Hunter, Jing Wang, The Laryngoscope, 2022.
Project |
- We presented a deep multi-task (DMT) model to predict vestibular schwannoma enlargement and tumor segmentation mask simultaneously using the initial diagnostic ceT1 MRI.
- The proposed DMT model is of higher learning efficiency and prediction accuracy than single-task prediction model.
A multi‐objective radiomics model for the prediction of locoregional recurrence in head and neck squamous cell cancer
Kai Wang, Zhiguo Zhou, Rongfang Wang, Liyuan Chen, Qiongwen Zhang, David Sher, Jing Wang, Medical physics 47.10 (2020): 5392-5400.
- We built a multi-classifier, multi-objective, and multi-modality (mCOM) model for HNSCC LRR prediction.
- Our study shows fusing multiple classifiers and multiple modalities can improve the robustness of the predictive model. Additionally, the multi-objective model could help to build a predictive model that can be flexibly adapted to different clinical preferences.
- Predicting local persistence/recurrence after radiation therapy for head and neck cancer from PET/CT using a multi-objective, multi-classifier radiomics model, Qiongwen Zhang, Kai Wang, Zhiguo Wang, et al., Frontiers in oncology 12 (2022). (The first two authors contributed to this work equally)
- Preliminary Evaluation of PTV Margins for Online Adaptive Radiotherapy of the Prostatic Fossa, Howard Morgan, Kai Wang, Yulong Yan, et al., Practical Radiation Oncology, 2022.
- Use of deep learning to predict the need for aggressive nutritional supplementation during head and neck radiotherapy, Michael Dohopolski, Kai Wang, Howard Morgan, David Sher, Jing Wang, Radiotherapy and Oncology, 2022, 171, 129-138.
- Exploratory ensemble interpretable model for predicting local failure in head and neck cancer: The additive benefit of CT and intra-treatment cone-beam computed tomography features, Howard E Morgan, Kai Wang, Michael Dohopolski, Xiao Liang, Michael R Folkert, David J Sher, Jing Wang, Quantitative Imaging in Medicine and Surgery, 2021, 11(12), 4781-4796.
- Prediction of vestibular schwannoma enlargement after radiosurgery using tumor shape and MRI texture features, Nicholas A George-Jones, Kai Wang, Jing Wang, Jacob B Hunter, Otology & Neurotology, 2021, 42(3), e348-e354.
- Automated Detection of Vestibular Schwannoma Growth Using a Two‐Dimensional U‐Net Convolutional Neural Network, Nicholas A George-Jones, Kai Wang, Jing Wang, Jacob B Hunter, The Laryngoscope, 2021, 131(2), E619-E624.
- Multifaceted radiomics for distant metastasis prediction in head & neck cancer, Zhiguo Zhou, Kai Wang, Michael Folkert, Hui Liu, Steve Jiang, David Sher, Jing Wang, Physics in Medicine & Biology, 2020, 65(15), 155009.
- A Novel Stationary CT Scheme Based on High-Density X-Ray Sources Device, Yiting Duan, Haitao Cheng, Kai Wang, Xuanqin Mou, IEEE Access, 2020, 8, 112910-112921.
- Locoregional recurrence prediction in head and neck cancer based on multi-modality and multi-view feature expansion, Rongfang Wang, Jinkun Guo, Zhiguo Zhou, Kai Wang, Shuiping Gou, Rongbin Xu, David Sher, Jing Wang, Physics in Medicine & Biology, 2022, 67(12), 125004.
- Attention Guided Lymph Node Malignancy Prediction in Head and Neck Cancer, Liyuan Chen, Michael Dohopolski, Zhiguo Zhou, Kai Wang, Rongfang Wang, David Sher, Jing Wang, International Journal of Radiation Oncology* Biology* Physics, 2021, 110(4), pp.1171-1179.
- Real-time MRI motion estimation through an unsupervised k-space-driven deformable registration network (KS-RegNet), Hua-Chieh Shao, Tian Li, Michael J Dohopolski, Jing Wang, Jing Cai, Jun Tan, Kai Wang, You Zhang, Physics in Medicine & Biology, 2022, 67(13), p.135012.
📑 Conference Proceeding
Recurrence-free Survival Prediction under the Guidance of Automatic Gross Tumor Volume Segmentation for Head and Neck Cancers
Kai Wang, Yunxiang Li, Michael Dohopolski, Tao Peng, Weiguo Lu, You Zhang, Jing Wang (The first two authors contributed to this work equally, Oral 🎤)
- Ranked No.3 in the recurrece-free survival (RFS) prediction task of the head and neck tumor segmentation and outcome prediction challenge (HECKTOR 2022).
- nnUNet for GTVp and GTVn segmentation on a multi-institution dataset.
- Extract radiomics feature from the AI-based auto-segmentated ROI for radiomics-based HNC RFS prediction.
- Ensemble multi-modality model for more robust prediction.
- Gas Bubble Motion Artifact Reduction through Simultaneous Motion Estimation and Image Reconstruction, Kai Wang, Hua-Chieh Shao, You Zhang, Chunjoo Park, Steve Jiang, Jing Wang, CT Meeting 2021
- Enabling High-Resolution (~2 mm or better) Brain Imaging with a Standard Clinical Whole-Body PET: A Simulation Study, Kai Wang, Jing Wang, Yiping Shao, NSS MIC 2021
- Compton scatter tomography with photon-counting detector: a preliminary study, Kai Wang, Haitao Cheng, Xi Chen, Xuanqin Mou, SPIE Medical Imaging 2018
- Image Restoration for Field Emission X-ray Source Array Based Radiographic Imaging, Kai Wang, Xi Chen, Haitao Cheng, Qinrong Qian, Xuanqin Mou, Fully 3D 2017
- A Stationary CT Scheme Based on Field Emission Flat-panel X-ray Source Array, Haitao Cheng, Kai Wang, Xuanqin Mou, Fully 3D 2017
- Multi-Modality and Multi-View 2D CNN to Predict Locoregional Recurrence in Head & Neck Cancer, Jinkun Guo, Rongfang Wang, Zhiguo Zhou, Kai Wang, Rongbin Xu, Jing Wang, IJCNN 2021
📰 Conference Abstract
- Time Dependence of Coverage of the Prostatic Fossa: Implications for Daily Adaptive Radiotherapy, Kai Wang, Howard Morgan, Yulong Yan, et al., ASTRO 2022 (ePoster)
- Predicting radiotherapy induced anatomic change for head neck cancer patients using vision transformer, Kai Wang, Aixa Andrade, Michael Dohopolski, Jing Wang, AAPM 2022 (ePoster)
- Delta radiomic features predict failure and survival outcomes for surgically resected pancreatic cancer patients treated with neoadjuvant therapy, Kai Wang, Ahmed Elamir, John Karalis, et al., AAPM 2022 (Oral 🎤)
- Attention guided network for vestibular schwannoma growth prediction, Kai Wang, Liyuan Chen, Nicholas George-Jone, Jacob Hunter, Jing Wang, SWAAPM 2021 (Oral 🎤)
- Combining radiomics and convolutional neural network to predict tumor growth of vestibular schwannoma, Kai Wang, Liyuan Chen, Nicholas George-Jone, Jacob Hunter, Jing Wang, AAPM 2020 (Blue Ribbon ePoster)
- Head Neck Squamous Cell Cancer Locoregional Recurrence Prediction Using Delta-radiomics Feature, Kai Wang, Zhiguo Zhou, Jing Wang, SWAAPM 2019 (Oral 🎤)
- A Relational Autoencoder for Retrieving Similar Patients in Radiotherapy Treatment Planning. AAPM Annual Meeting, Kai Wang, Xuejun Gu, Mingli Chen, Weiguo Lu, AAPM 2019 (Oral 🎤)
- Using Radiomics to Improve the Diagnostic Accuracy of Indeterminate Residual Primary Disease on Restaging PET/CT Imaging Following Radiation Therapy for Head and Neck Cancers, Michael Dohopolski, Kai Wang, Howard Morgan, David Sher, Jing Wang, ASTRO 2022
- Using Prediction Uncertainty to Identify Reliable Predictions for a Deep Learning Model that Predicts the Need for Early Feeding Tube Placement, Michael Dohopolski, Kai Wang, Howard Morgan, David Sher, Jing Wang, ASTRO 2022
- Reducing PTV Margins with Daily Adaptive Radiotherapy to the Prostatic Fossa, Howard Morgan, Kai Wang, Yulong Yan, et al., AAPM 2022
- Delta Radiomic Signature from Neoadjuvant Pancreas Cancer Radiation Planning Volume is Superior to Tumor Proper Volume to Predict Surgical Failures, Ahmed Elamir, Kai Wang, John Karalis, et al., AAPM 2022
- Comprehensive Evaluation of a Real-Time 3D MR Imaging Technique Using a Deformation-Driven Deep Convolutional Neural Network (KS-RegNet), Hua-Chieh Shao1, Tian Li, Michael Dohopolski, Jing Wang, Jing Cai, Jun Tan, Kai Wang and You Zhang, AAPM 2022
- Lymph Node Segmentation via Deep Feature Boosting Network in Head and Neck CT Images, Tao Peng, Kai Wang, Hua-Chieh Shao, Michael Dohopolski, You Zhang, Jing Wang,AAPM 2022
- Predicting Feeding Tube Placement in Head and Neck Cancer Patients Receiving Radiation Therapy with Machine Learning, Michael Dohopolski, Kai Wang, Howard Morgan, Liyuan Chen, David Sher, Jing Wang,ASTRO 2021
- Explainable Boosting Machine Model with a Parallel Ensemble Design Predicts Local Failure for Head and Neck Cancer with Clinical, Howard Morgan, Kai Wang, Michael Dohopolski, et al,ASTRO 2021
- Interpretable Machine Learning Model Supported by Parallel Ensemble Learning to Predict Local Recurrence for Patients with Cervical Cancer, Allen Yen, Howard Morgan, Kai Wang, Kevin Albuquerque, Jing Wang, ASTRO 2021
- A Bilateral Neural Network for Loco-Regional Recurrence Prediction in Head and Neck Squamous Cell Cancer Liyuan Chen, Kai Wang, Chenyang Shen, David Sher, Jing Wang,AAPM 2021
- Segmentation Guided Classification Scheme for Lymph Node Malignancy Prediction in Head and Neck Cancer Liyuan Chen, Michael Dohopolski, Kai Wang, Zhiguo Zhou, David Sher, Jing Wang,AAPM 2021
- An automated method for determining vestibular schwannoma size and growth, Nicholas George-Jone, Kai Wang, Jacob Hunter, Jing Wang, Journal of Neurological Surgery Part B: Skull Base, 2020
- Predicting Treatment Outcome After Immunotherapy Based on Delta-Radiomic Model in Metastatic Melanoma, Xi Chen, Zhiguo Zhou, Kai Wang, Zhiguo Zhou, AAPM 2020
- Deciphering Metabolic Features to Target Neuroblastoma Using Machine Learning, Rongfang Wang, Yuanyuan Zhang, Panayotis Pachnis, Hieu Vu, Kai Wang, Ralph DeBerardinis, Jing Wang, AAPM 2020
- Multifaceted Radiomics: towards more reliable radiomics for predicting distant metastasis in head & neck cancer, Zhiguo Zhou, Kai Wang, Hui Liu, David Sher, Jing Wang, AAPM 2019
📰 Patent
- Projection Image Restoration Method for X-ray Source Array Based Radiographic Imaging System, Xuanqin Mou, Kai Wang, Haitao Cheng, Application No. 201611170284.4. China. (Issued)
- Computed Tomography Imaging Methods Based on Array X-ray Source Array and Flat Panel Detector, Xuanqin Mou, Haitao Cheng, Kai Wang, Application No. 201611170283.X, China. (Issued)
- A polygon stationary computed tomography system and imaging methods, Xuanqin Mou, Qinrong Qian, Haitao Cheng, Kai Wang, Application No. 201810167211.2, China. (Issued)
✒️ In Preparation
- Uncertainty estimations methods for a deep learning model to aid in clinical decision-making–a clinician’s perspective, Michael Dohopolski, Kai Wang , Biling Wang, Ti Bai, Dan Nguyen, David Sher, Steve Jiang, Jing Wang, 📃
- Development and Validation of Delta-radiomics based Predictors of Resectability and Prognosis in Pancreatic Ductal Adenocarcinoma after Neoadjuvant, Kai Wang, Ahmed Elamir, John Karalis, et al.
- Recurrence-Free Survival Prediction for Anal Squamous Cell Carcinoma Chemo-radiotherapy using Planning CT based Radiomics Model, Shanshan Tang, Kai Wang, David Hein, Nina N. Sanford, Jing Wang.
🏅 Honors and Awards
- 2022.09 Third place for Recurrence-Free Survival Prediction Task in the Head and Neck Tumor Segmentation and Outcome Prediction Challenge (HECKTOR2022)
- 2016.10 Excellent Graduate Student, XJTU
- 2012-2015 Siyuan Scholarship, XJTU
- 2015.06 Outstanding Undergraduate Student Cadres, XJTU
- 2014.10 Special Award in “TI Cup” Circuit Design Competition, Shaanxi, China
- 2013.10 First Prize in Undergraduate Mathematical Contest in Modeling, Shaanxi, China
💻 Activities
📜 Journal Reviewer
- Medical Physics
- Physics in Medicine and Biology
- International Journal of Radiation Oncology* Biology* Physics
- IEEE Journal of Biomedical and Health Informatics
- IEEE Transactions on Medical Imaging
- The British Journal of Radiology
- Scientific Reports
- Biomedical Physics & Engineering Express
📯 Student Activities
- 2017.06, Student conference coordinator, 14th Fully 3D International Conference, Xi’an, Shaanxi, China.
- 2013.08-2014.06, Vice Chair, Senior Student Group, Wenzhi College, XJTU.
- 2012.08-2013.06, Director, Campus Life Program, Student’s Association, Wenzhi College, XJTU.