In 2016 a total of 224,390 patients in the US were diagnosed with non-small cell lung cancer (NSCLC) and 16% of these patients (35,902) were diagnosed as early stage (I and II) and eligible for adjuvant cytotoxic chemotherapy (adj chemo). However, more than 50% of these patients may have low risk disease and hence may not receive added benefit from adj chemo, while suffering its side-effects. From an economic standpoint, unnecessary adj chemo for early stage NSCLC results in a loss of over $35,000 for each quality- adjusted life year lost. With increased lung cancer screening, we can expect an increase in diagnosis of early stage NSCLC. Two large completed randomized clinical trials of NSCLC (International Adjuvant Lung Cancer Trial (IALT) and JBR10) involving surgery with and without adj chemo, only found survival benefit in higher stage patients (>=Stage III). Unfortunately there are currently no validated predictive companion diagnostic (CDx) tools to identify (1) which stage II NSCLC are at a lower risk for disease recurrence and hence will not receive additional benefit from adj chemo and (2) which stage 1A, 1B patients are at elevated risk and hence will benefit? Extant genomic assays have only been shown to be prognostic (i.e. they predict mortality or recurrence) in early stage NSCLC, 1?5, but this does not imply they are predictive (i.e. they do not predict treatment response). Recently, our group validated the computerized histologic risk predictor (CHiRP), an approach that relies solely on computer extracted morphologic measurements (e.g. cellular orientation, texture, shape, architecture) from standard H&E tissue slide images to predict early recurrence in early stage NSCLC. CHiRP has been shown to be prognostic with an accuracy>85% in three independent clinical cohorts (N=290); higher compared to what has been previously reported for molecular based prognostic tests. However, to show that CHiRP is predictive, we need access to randomized clinical trial data involving early stage NSCLC patients treated with surgery and surgery+ adj chemo. The only two trials that fit these criteria are IALT and JBR10. Since molecular tests are tissue destructive, validation is more difficult compared to a tissue non-destructive approach like CHiRP; clinical trial groups are often reluctant to share tissue blocks since it is a valuable resource. For this study we have obtained preliminary approval for use of the slide images from IALT and JBR10 to establish CHiRP as a predictive Affordable Precision Medicine (APM) solution. This Academic-Industry partnership will leverage long-standing collaborations between (1) the Madabhushi group at Case Western who bring expertise in computational histomorphometric imaging, (2) the Velcheti group at the Cleveland Clinic (CCF) with clinical expertise in treatment and management of early stage NSCLC, and (3) Inspirata Inc., a cancer diagnostics company which has recently licensed a number of histomorphometry based technologies from the Madabhushi group and who will bring quality management systems and production software standards to help create a pre-commercial CHiRP test.

Public Health Relevance

Even though many early stage non-small cell lung cancer (NSCLC) patients will be treated with chemotherapy following surgical resection of the tumor, the vast majority of these early stage NSCLC patients will not receive additional benefit from this adjuvant chemotherapy, thus unnecessarily suffering the deleterious effects of treatment. We aim to develop and validate the first predictive companion diagnostic assay - computerized histologic risk predictor (CHiRP) - to identify which early stage NSCLC patients, following surgery, will receive additional benefit from adjuvant chemotherapy.

Agency
National Institute of Health (NIH)
Institute
National Cancer Institute (NCI)
Type
Research Project (R01)
Project #
5R01CA216579-03
Application #
9841917
Study Section
Special Emphasis Panel (ZRG1)
Program Officer
Ossandon, Miguel
Project Start
2018-01-01
Project End
2022-12-31
Budget Start
2020-01-01
Budget End
2020-12-31
Support Year
3
Fiscal Year
2020
Total Cost
Indirect Cost
Name
Case Western Reserve University
Department
Biomedical Engineering
Type
Biomed Engr/Col Engr/Engr Sta
DUNS #
077758407
City
Cleveland
State
OH
Country
United States
Zip Code
44106
Lu, Cheng; Romo-Bucheli, David; Wang, Xiangxue et al. (2018) Nuclear shape and orientation features from H&E images predict survival in early-stage estrogen receptor-positive breast cancers. Lab Invest 98:1438-1448
Beig, Niha; Patel, Jay; Prasanna, Prateek et al. (2018) Radiogenomic analysis of hypoxia pathway is predictive of overall survival in Glioblastoma. Sci Rep 8:7
Bera, Kaustav; Velcheti, Vamsidhar; Madabhushi, Anant (2018) Novel Quantitative Imaging for Predicting Response to Therapy: Techniques and Clinical Applications. Am Soc Clin Oncol Educ Book :1008-1018
Algohary, Ahmad; Viswanath, Satish; Shiradkar, Rakesh et al. (2018) Radiomic features on MRI enable risk categorization of prostate cancer patients on active surveillance: Preliminary findings. J Magn Reson Imaging :
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

Showing the most recent 10 out of 17 publications