- Browse by Author
Browsing by Author "Liu, Ziyu"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Optimal transport- and kernel-based early detection of mild cognitive impairment patients based on magnetic resonance and positron emission tomography images(BMC, 2022) Liu, Ziyu; Johnson, Travis S.; Shao, Wei; Zhang, Min; Zhang, Jie; Huang, Kun; Biostatistics and Health Data Science, School of MedicineBackground: To help clinicians provide timely treatment and delay disease progression, it is crucial to identify dementia patients during the mild cognitive impairment (MCI) stage and stratify these MCI patients into early and late MCI stages before they progress to Alzheimer's disease (AD). In the process of diagnosing MCI and AD in living patients, brain scans are collected using neuroimaging technologies such as computed tomography (CT), magnetic resonance imaging (MRI), or positron emission tomography (PET). These brain scans measure the volume and molecular activity within the brain resulting in a very promising avenue to diagnose patients early in a minimally invasive manner. Methods: We have developed an optimal transport based transfer learning model to discriminate between early and late MCI. Combing this transfer learning model with bootstrap aggregation strategy, we overcome the overfitting problem and improve model stability and prediction accuracy. Results: With the transfer learning methods that we have developed, we outperform the current state of the art MCI stage classification frameworks and show that it is crucial to leverage Alzheimer's disease and normal control subjects to accurately predict early and late stage cognitive impairment. Conclusions: Our method is the current state of the art based on benchmark comparisons. This method is a necessary technological stepping stone to widespread clinical usage of MRI-based early detection of AD.Item Predicting melanoma survival and metastasis with interpretable histopathological features and machine learning models(Frontiers Media, 2023-01-06) Couetil, Justin; Liu, Ziyu; Huang, Kun; Zhang, Jie; Alomari, Ahmed K.; Medical and Molecular Genetics, School of MedicineIntroduction: Melanoma is the fifth most common cancer in US, and the incidence is increasing 1.4% annually. The overall survival rate for early-stage disease is 99.4%. However, melanoma can recur years later (in the same region of the body or as distant metastasis), and results in a dramatically lower survival rate. Currently there is no reliable method to predict tumor recurrence and metastasis on early primary tumor histological images. Methods: To identify rapid, accurate, and cost-effective predictors of metastasis and survival, in this work, we applied various interpretable machine learning approaches to analyze melanoma histopathological H&E images. The result is a set of image features that can help clinicians identify high-risk-of-metastasis patients for increased clinical follow-up and precision treatment. We use simple models (i.e., logarithmic classification and KNN) and "human-interpretable" measures of cell morphology and tissue architecture (e.g., cell size, staining intensity, and cell density) to predict the melanoma survival on public and local Stage I-III cohorts as well as the metastasis risk on a local cohort. Results: We use penalized survival regression to limit features available to downstream classifiers and investigate the utility of convolutional neural networks in isolating tumor regions to focus morphology extraction on only the tumor region. This approach allows us to predict survival and metastasis with a maximum F1 score of 0.72 and 0.73, respectively, and to visualize several high-risk cell morphologies. Discussion: This lays the foundation for future work, which will focus on using our interpretable pipeline to predict metastasis in Stage I & II melanoma.