In 2018, nearly 34,000 adults in the US and over 275,000 worldwide were diagnosed with oral cavity squamous cell carcinoma (OC-SCC). In the US alone >6,600 died from the disease in 2018. In addition to stage, perineural invasion, lymphovascular invasion, depth of invasion, and close or frankly positive resection margins are used to help stratify patients into low-, intermediate-, or high risk categories. Currently, all OC-SCC patients are treated primarily by surgical resection. Post-operative treatment depends on patient risk category. Low-risk patients receive surgery alone and studies have shown the benefit of PORT (Post-operative radiation therapy) in selected patients. A retrospective analysis of 1467 patients with low-risk OC-SCC where 740 (50.4%) received PORT had improved overall survival compared to 727 patients treated with surgery alone. Identifying these patients and better stratifying their risk of progression is critical. Meanwhile, patients with loco-regionally advanced (i.e. intermediate and high risk) disease are treated with PORT as standard. Select high risk patients may be treated with concomitant chemoradiation or subsequent chemotherapy. There is thus an urgent need to develop companion diagnostic tools to better define which patients will benefit from PORT, or, if intermediate or high risk, who will benefit from systemic therapy intensification. Recently, our group has developed a OC-SCC histomorphometric based image risk classifier (OHbIC) that uses computerized measurements of nuclear orientation, texture, shape, architecture from digital images of H&E-stained tumor sections to identify patients who are likely to recur versus those who are not. OHbIC was trained and validated on N=115 OC-SCC patients, and it had a 2 and 7-fold higher-correlation with disease specific survival compared to the 7th edition AJCC N- and T-stage (clinical variables used in patient prognosis). In this NIH R01, we seek to further improve the prognostic and predictive accuracy of OHbIC by incorporating new classes of image features relating to stromal morphology, pattern of invasion at the tumor leading edge, density and patterns of tumor infiltrating lymphocytes, and tumor cell multi-nucleation, features now recognized as potential histopathological markers of prognostic relevance in OC-SCC. Additionally, we seek to 1) validate OHbIC as prognostic of survival in clinically defined low-risk patients and identify those low-risk patients who would benefit from PORT and 2) validate OHbIC as not only prognostic of survival but also predictive of benefit from chemotherapeutic intensification for patients with loco-regionally advanced disease. This partnership will leverage long-standing collaborations in (1) digital pathomics from the Madabhushi group at Case Western Reserve, (2) surgical pathology and oncology expertise in oral cancer from Vanderbilt University, Cleveland Clinic, San Francisco VA, and Tata Memorial Centre, Mumbai to establish OHbIC as a tissue non-destructive and Affordable Precision Medicine (APM) solution for OC-SCC patients.

Public Health Relevance

Project Relevance: In this project, we seek to improve the predictive accuracy of a computerized histomorphometric predictor (OHbIC) for risk stratification, outcome prediction and added benefit of adjuvant chemotherapy for patients with oral cavity squamous cell carcinoma (OC-SCC) from routine H&E tissue slide images. The success of this project will pave the way for its adoption as a tissue non-destructive Affordable Precision Medicine (APM) companion diagnostic tool, allowing for the identification of OC-SCC patients for whom therapies could be either left as standard, or require ?escalation?, depending on the OHbIC risk score.

National Institute of Health (NIH)
National Cancer Institute (NCI)
Research Project (R01)
Project #
Application #
Study Section
Special Emphasis Panel (ZRG1)
Program Officer
Ossandon, Miguel
Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
Case Western Reserve University
Biomedical Engineering
Biomed Engr/Col Engr/Engr Sta
United States
Zip Code