1. Full characterization of amyloid-beta plaques in Alzheimer’s disease pathologies (2024-present)

Overview: Charactering the amyloid-beta (Aβ) plaques in a quantitative way such as size, type, shape, location, etc., plays an important role in better understanding Alzheimer’s disease (AD). The existing and our new developed deep learning method such as evidential learning, AutoMO will be used to quantify the Aβ plaques.   

 Team: Kwame Yeboah, Ph.D. student, Mohammad Haeri, Ph.D. (Assistant Professor, Pathology and Laboratory Medicine), Zhiguo Zhou, Ph.D.

2. Pathological complete response prediction in triple negative breast cancer (2023-present)

Overview: Triple negative breast cancer (TNBC) is an aggressive subtype of breast cancer. The standard of care for most TNBC patients is neoadjuvant chemotherapy (NAC), followed by surgery and radiotherapy. Approximately 40-50% of patients will achieve a pathologic complete response (pCR) with NAC. Developing reliable predictors of response and resistance to NAC will enable optimization and its personalization of therapy for TNBC. We will develop tumor detection/segmentation model and deep AutoMO models to predict pCR. This project is funded by University of Kansas Cancer Center Pilot Grant.

Team: Xi Chen, Ph.D. student, Kazi Md Farhad Mahmud, Ph.D. student, Priyanka Sharma, M.D. (Professor, Medical Oncology), Shane Stecklein, M.D. (Assistant Professor, Radiation Oncology), Allison Aripoli, M.D. (Assistant Professor, Radiology), Zhiguo Zhou, Ph.D.

3. Bleeding risk prediction for patients with kidney disease on dialysis (2023-present)

Overview: In the past two decades, the all-age death rate from kidney diseases has nearly doubled. Cardiovascular (CV) diseases account for the majority of deaths in patients with kidney diseases. Patients with end stage kidney disease on dialysis (ESKD) are at a higher risk of dying from CV events than the general population. We are aiming to develop reliable machine learning model for predicting thrombotic and bleeding risks of ESKD patients.

Team: Oluwatobiloba Ige, Ph.D. student, Suzanne Hunt, M.S., Statistician II, Nishank Jain, M.D. (Assistant Professor, Nephrology, University of Arkansas for Medical Sciences), Zhiguo Zhou, Ph.D.

4. Distant metastasis/Locoregional recurrence prediction in head and neck squamous cell cancers (HNSCC) (2019-present)

Overview: Head and neck squamous cell cancers (HNSCC) has become one of most common malignant tumors in the world. Radiotherapy is commonly used as part of managing patients’ disease. However, many patients with HNSCC may occur locoregional recurrence (LRR) within three years after therapy. Meanwhile, distant metastasis (DM) in HNSCC remains one of the leading causes of treatment failure and death, adversely impacting the patient survival. We are aiming to develop multifaceted radiomics model and new delta radiomics model to predict LRR and DM.

Team: Oluwatobiloba Ige, Ph.D. student, Kazi Md Farhad Mahmud, Ph.D. student, Ahmad Qasem, M.S., Andres Bur, M.D. (Associate Professor, Otolaryngology-Head and Neck Surgery), Gregory N. Gan, M.D., Ph.D. (Assistant Professor, Radiation Oncology), Jing Wang, Ph.D. (Professor, Radiation Oncology, UT Southwestern Medical Center), Zhiguo Zhou, Ph.D.

Featured publication:

(1) Qiongwen Zhang, Kai Wang, Zhiguo Zhou, Genggeng Qin, Lei Wang, Ping Li, David Sher, Steve Jiang, Jing Wang, “Predicting local persistence/recurrence after radiation therapy for head and neck cancer from PET/CT using a multi-objective, multi-classifier radiomics model”, Frontiers in oncology, 12: 955712, 2022

(2) Zhiguo Zhou, Kai Wang, Michael Folkert, Hui Liu, Steve Jiang, David Sher, Jing Wang, “Multifaceted radiomics for distant metastasis prediction in head & neck cancer”, Physics in Medicine and Biology, Vol. 65, 155009, 2020  

(3) Kai Wang, Zhiguo Zhou, Rongfang Wang, Liyuan Chen, Qiongwen Zhang, David Sher, Jing Wang, “A multi-objective radiomics model for the prediction of locoregional recurrence in head and neck squamous cell cancers”, Medical Physics, Vol 47, Issue 10, 5392-5400, 2020

5. Immunotherapy response prediction in metastatic melanoma and lung cancer (2020-present)

Overview: Immunotherapy has brought about a revolution in cancer treatment which harnesses the remarkable power of a person’s immune system to discern and eradicate cancer cells. However, it is essential to recognize that its effectiveness is not universal, with only a subset of patients experiencing a positive response to immunotherapy. Consequently, the imperative to accurately identify a patient’s likelihood of responding to immunotherapy cannot be overstated, and the pursuit of more dependable methods to predict a patient's response to immunotherapy emerges as a pivotal object. We are aiming to develop new delta radiomics model to achieve this goal.

Team: Meijuan Zhou, M.S., Gary C. Doolittle, M.D. (Professor, Medical Oncology), Chao Huang M.D., (Professor, Medical Oncology), Xi Chen, Ph.D. (Associate Professor, Electronic and Information Engineering), Zhiguo Zhou, Ph.D.

Featured publication:

(1) Zhiguo Zhou, Meijuan Zhou, Zhilong Wang, Xi Chen, “Predicting treatment outcome in metastatic melanoma through automated multi-objective model with hyperparameter optimization”, SPIE Medical Imaging Conference, 2022

(2) Xi Chen, Meijuan Zhou, Zhilong Wang, Si Lu, Shaojie Chang, Zhiguo Zhou*, “Immunotherapy treatment outcome prediction in metastatic melanoma through automated multi-objective delta-radiomics model”, Computers in Biology and Medicine, 138, 104916, 2021

(3) Zhi-long Wang, Li-li Mao, Zhiguo Zhou, Lu Si, Hai-tao Zhu, Xi Chen, Mei-juan Zhou, Ying-shi Sun, Jun Guo, “Pilot study of CT-based radiomics model for early evaluation of response to immunotherapy in patients with metastatic melanoma”, Frontiers in Oncology, 10, 1524, 2020

6. Lesion malignancy classification in digital breast tomosynthesis (2018-present)

Overview: Predicting lesion malignancy accurately and reliably in digital breast tomosynthesis is critically important for breast cancer screening. We have developed tumor segmentation model as well as prediction model.

Team: Allison Aripoli, M.D. (Assistant Professor, Radiology), Jiahuan Lv, M.S., Xiaoyu Wang, M.S., Ahmad Qasem, M.S., Genggeng Qin, M.D. (Associate Professor, Radiology), Xi Chen, Ph.D. (Associate Professor, Electronic and Information Engineering), Jing Wang, Ph.D. (Professor, Radiation Oncology, UT Southwestern Medical Center), Zhiguo Zhou, Ph.D.

Featured publication:

(1) X. Chen, X. Wang, J. Lv, G. Qin and Z. Zhou, “An integrated network based on 2D/3D feature correlations for benign-malignant tumor classification and uncertainty estimation in digital breast tomosynthesis”, Physics in Medicine and Biology, 68, 175046, 2023

(2) Zhiguo Zhou, Shulong Li, Genggeng Qin, Michael Folkert, Steve Jiang, Jing Wang, “Multi-objective based radiomic feature selection for lesion malignancy classification”, IEEE Journal of Biomedical and Health Informatics, 24 (1), 194-204, 2020

(3) Benjuang Yang, Yingjiang Wu, Zhiguo Zhou, Shulong Li, Genggeng Qin, Liyuan Chen, Jing Wang, “A collection input based support tensor machine for lesion malignancy classification in digital breast tomosynthesis”, Physics in Medicine and Biology, 64, 23, 235007, 2019

7. Lymph node metastasis prediction in head and neck squamous cell cancers (HNSCC) (2018-2023)

Overview: Lymph node metastasis (LNM) plays an important role for accurately diagnosing and treating the patients with head & neck cancer. it is necessary to build a reliable and automatic model for predicting LNM based on PET and CT images. We have developed AutoMO method to predict LNM in a more reliable way.

Team: David Sher, M.D. (Professor, Radiation Oncology, UT Southwestern Medical Center), Jing Wang, Ph.D. (Professor, Radiation Oncology, UT Southwestern Medical Center), Zhiguo Zhou, Ph.D.

Featured publication:

(1) Zhiguo Zhou, Liyuan Chen, Michael Dohopolski, David Sher and Jing Wang, “ARMO:  automated and reliable multi-objective model for lymph node metastasis prediction in head and neck cancer”, Physics in Medicine and Biology, 68, 095012, 2023

(2) Liyuan Chen, Zhiguo Zhou, David Sher, Qiongwen Zhang, Jennifer Shah, Nhat-Long Pham, Steve Jiang, Jing Wang, “Combining Many-objective Radiomics and 3-dimensional Convolutional Neural Network through Evidential Reasoning to Predict Lymph Node Metastasis in Head and Neck Cancer”, Physics in Medicine and Biology, 64 (7), 2019

(3) Zhiguo Zhou, Michael Dohopolski, Liyuan Chen, Xi Chen, Steve Jiang, David Sher, Jing Wang, “Reliable lymph node metastasis prediction in head & neck cancer through automated multi-objective model”, IEEE International Conference on Biomedical and Health Informatics (BHI), 2019

8. Statistical project

(1) Sinonasal Melanoma analysis (2024-present).

9. Lung cancer early screening through image and clinical parameters (2024-present)

Overview: Lung cancer early screening is a critical component of efforts to detect lung cancer in its earliest stages, when it is most treatable. We are aiming to build a general lung cancer screening model by using medical images and clinical parameters.

Team: Md Saiful Islam Saif, Ph.D. student, Chao Huang M.D., (Professor, Medical Oncology), Zhiguo Zhou, Ph.D.