We have five research positions available in image analytics and informatics at ASU:
- Assistant/Associate Research Professorship
- Postdoctoral Fellowship
- Research Software Engineer
- PhD Fellowship
- Visiting Scholarship
If you are interested in, please visit www.tinyurl.com/ASUPositions
Associate Professor, Department of Biomedical Informatics, Biomedicine@ASU
Dr. Liang is an Associate Professor of Biomedical Informatics, Computer Science, and Biomedical Engineering. He joined the faculty of Arizona State University in 2009 after six years with Siemens. Drawing upon computer vision, machine learning, visualization, mathematics, and statistics, his research focuses on imaging informatics, developing systems for computer-aided diagnosis, therapy and surgery, addressing a significant challenge facing biomedicine: image data explosion, a manifestation of big data in biomedical imaging, through a multidisciplinary team-based approach, involving informatics, computer science, mathematics, radiology, cardiology, gastroenterology, ontology, pathology, etc. His research is currently supported by an R01 grant and several grants from the ASU-Mayo partnerships. To translate his developed technologies into clinical practice and realize their clinical impact, with the assistance of Arizona Technology Enterprises and Mayo Clinic Ventures, Dr. Liang co-founded IMANIN. In addition to his 70+ peer-reviewed publications, he has been awarded 13 US patents with an additional 31 patents pending. His research has led to FDA-approved products. Dr. Liang received an ASU President’s Award for Innovation.
To help achieve ASU Charter and Goals: “establish, with Mayo Clinic, innovative health solutions pathways capable of . . . enhancing treatment for 2 million patients”, Dr. Liang has established extensive collaborations with Mayo Clinic. Examples of his projects follow:
- Computer-aided diagnosis and prognosis of pulmonary embolism. The US Surgeon General has declared pulmonary embolism (PE) a major national health problem. CT pulmonary angiography (CTPA) is the diagnostic standard for suspected PE. However, incorrect CTPA interpretations are frequent in general clinical practice, and the wealth of CPTA imaging information useful for PE prognostication is barely utilized for the personalized management of PE patients. Therefore, the goal of this project is to integrate diagnosis with prognosis in a single unified framework.
- Personalized cardiovascular disease risk stratification. Cardiovascular disease (CVD) is the #1 killer in the US, but it is largely preventable—the key is to identify at-risk individuals prior to adverse events. For stratifying individual CVD risk, carotid intima-media thickness (CIMT), a noninvasive ultrasound method, has proven to be valuable. However, interpreting CIMT images is tedious, laborious, and time consuming, a serious limitation that hinders widespread utilization of CIMT in clinical practice. To overcome this limitation, we are developing an innovative informatics solution to fully automate CIMT image interpretation process.
- Ensuring high-quality colonoscopy. The primary modality for screening and prevention of colorectal cancer is (optical) colonoscopy. However, during colonoscopy, a significant number of polyps are missed—the pooled miss-rate for all polyps is 22% (95% CI, 19%-26%). To reduce the polyp miss-rate of colonoscopy, we are developing computer algorithms to ensure high-quality colonoscopy procedures, resulted in software systems with “built in” alerts that recognize polyps and distinguish poor video quality.
- Personalized proton therapy for lung cancer . Lung cancer is the leading cause of cancer deaths. Intensity modulated proton therapy (IMPT) is revolutionizing radiotherapy because of its extraordinary capability of precisely depositing maximum cell killing energy in tumors while protecting surrounding healthy tissues. However, the use of IMPT for lung cancer is hindered by a serious limitation: IMPT is highly sensitive to uncertainties caused by patient setup, respiratory motion, anatomic changes, etc. We are aiming to overcome this limitation by developing novel algorithms to achieve personalized proton therapy by explicitly accounting for patient-specific information that can be extracted from the weekly CTs.