In 2016, nearly 50,000 adults in the US were diagnosed with oral and pharyngeal squamous cell carcinoma (SCC), and nearly 10,000 died from the disease. Human papillomavirus (HPV) is now recognized as the most common cause of oropharyngeal (OP) SCC in the US. Although concomitant chemo- and radio-therapy is the most common treatment choice in patients with advanced OP-SCC, they have substantial short- and long- term morbidity and result in increased health care costs in patients who are cured of their cancers. These patients live with sometimes disabling morbidity for many years post-treatment. For these reasons, it has been suggested that therapy in lower risk patients might be de-escalated. There is also a higher risk cohort of patients in whom treatment with chemo-radiation may be insufficient, often resulting in distant metastatic failure. As such, these patients may require intensified therapies to improve outcomes. This is an agonizing choice for patients and their doctors, however. While patients do not want to be sickened by morbid treatments, they are obviously concerned about having the best chance at cure. Unfortunately, there currently are no companion diagnostic tools to identify which HPV + OPSCC patients are at (1) low risk of recurrence such that they can be treated safely to high cure rates with de-escalated therapy; (2) higher risk of failure despite aggressive high dose chemoradiation in whom treatment intensification strategies should be studied. Recently, we developed a quantitative histomorphometric based image risk classifier (QuHbIC) that uses computerized measurements of tumor morphology (e.g. nuclear orientation, texture, shape, architecture) from digital images of H&E-stained tumor sections to predict progression in HPV+ OP-SCC patients; the current version of QuHbIC has already been validated in >400 patients and found to be superior to clinical variables in outcome prediction. In this Academic-Industry Partnership we seek to further improve predictive accuracy of QuHbIC by incorporating new classes of image features relating to stromal morphology, density and patterns of tumor infiltrating lymphocytes, and tumor cell multi-nucleation, features now recognized as promising markers of unfavorable prognosis in HPV+ OP-SCC. We also seek to create a pre-commercial QuHbIC companion diagnostic test that is ready for clinical use in risk stratification in p16+ OP-SCC. QuHbIC will be trained on >700 retrospectively identified HPV + OP-SCC whole tissue slide images with associated long term outcome data and then validated on 440 cases from randomized, controlled, multi-institutional RTOG 0129 and 0522 clinical trials. This partnership will leverage long-standing collaborations in (1) computational histomorphometry from the Madabhushi group at Case Western Reserve University, (2) surgical pathology and oncology expertise in HPV+ OPSCC from Vanderbilt University and the Cleveland Clinic and, (3) Inspirata Inc., a cancer diagnostics company that will bring quality management systems and production software standards to establish QuHbIC as an Affordable Precision Medicine (APM) solution for oropharyngeal cancers.
Project Relevance: In this project we propose to optimize and validate a quantitative histomorphometric-based image classifier (QuHbIC) to better risk stratify survival among p16+ (Human papillomavirus (HPV)-related) OPSCC patients. The successful validation of QuHbIC could pave the way for its adoption as an Affordable Precision Medicine (APM) companion diagnostic tool, allowing for the identification of patients for whom therapies could be either 'de-escalated?, left as standard, or even potentially escalated, depending on risk status.
|Corredor, Germán; Wang, Xiangxue; Zhou, Yu et al. (2018) Spatial architecture and arrangement of tumor-infiltrating lymphocytes for predicting likelihood of recurrence in early-stage non-small cell lung cancer. Clin Cancer Res :|
|Beig, Niha; Khorrami, Mohammadhadi; Alilou, Mehdi et al. (2018) Perinodular and Intranodular Radiomic Features on Lung CT Images Distinguish Adenocarcinomas from Granulomas. Radiology :180910|
|Orooji, Mahdi; Alilou, Mehdi; Rakshit, Sagar et al. (2018) Combination of computer extracted shape and texture features enables discrimination of granulomas from adenocarcinoma on chest computed tomography. J Med Imaging (Bellingham) 5:024501|
|Cruz-Roa, Angel; Gilmore, Hannah; Basavanhally, Ajay et al. (2018) High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection. PLoS One 13:e0196828|
|Shiradkar, Rakesh; Ghose, Soumya; Jambor, Ivan et al. (2018) Radiomic features from pretreatment biparametric MRI predict prostate cancer biochemical recurrence: Preliminary findings. J Magn Reson Imaging 48:1626-1636|
|Nirschl, Jeffrey J; Janowczyk, Andrew; Peyster, Eliot G et al. (2018) A deep-learning classifier identifies patients with clinical heart failure using whole-slide images of H&E tissue. PLoS One 13:e0192726|
|Penzias, Gregory; Singanamalli, Asha; Elliott, Robin et al. (2018) Identifying the morphologic basis for radiomic features in distinguishing different Gleason grades of prostate cancer on MRI: Preliminary findings. PLoS One 13:e0200730|
|Whitney, Jon; Corredor, German; Janowczyk, Andrew et al. (2018) Quantitative nuclear histomorphometry predicts oncotype DX risk categories for early stage ER+ breast cancer. BMC Cancer 18:610|
|Carleton, Neil M; Lee, George; Madabhushi, Anant et al. (2018) Advances in the computational and molecular understanding of the prostate cancer cell nucleus. J Cell Biochem 119:7127-7142|
|Leo, Patrick; Elliott, Robin; Shih, Natalie N C et al. (2018) Stable and discriminating features are predictive of cancer presence and Gleason grade in radical prostatectomy specimens: a multi-site study. Sci Rep 8:14918|
Showing the most recent 10 out of 12 publications