NIMG-66. AI-BASED PROGNOSTIC IMAGING BIOMARKERS FOR PRECISION NEUROONCOLOGY AND THE RESPOND CONSORTIUM. (9th November 2020)

• Record Type: Journal Article
• Authors: Davatzikos, Christos; Badve, Chaitra; Kazerooni, Anahita Fathi; Bashyam, Vishnu; Bakas, Spyridon; Colen, Rivka; Mahajan, Abhishek; Balaña, Carmen; Capellades, Jaume; Puig, Josep; Jain, Rajan; Sloan, Andrew E; Marcus, Daniel S; Choi, Yoon Seong; Lee, Seung-Koo; Chang, Jong Hee; Poisson, Laila M; Griffith, Brent; Dicker, Adam P; Flanders, Adam E; Booth, Thomas C; Rathore, Saima; Akbari, Hamed; Sako, Chiharu; Bilello, Michel; Shukla, Gaurav; Brem, Steven; Lustig, Robert; Mohan, Suyash; Nasrallah, MacLean; O'Rourke, Donald M; Bagley, Stephen; Barnholtz-Sloan, Jill S;
• Is Part Of: Neuro-oncology. Volume 22(2020)Supplement 2
• Page Start: ii162
• Page End: ii163
• Publication Date: 2020-11-09
• Subjects: Brain Neoplasms -- Periodicals; Brain -- Tumors -- Periodicals; Brain -- Cancer -- Periodicals; Nervous system -- Cancer -- Periodicals; 616.99481
• DOI: 10.1093/neuonc/noaa215.679
• Languages: English
• ISSNs: 1522-8517

Abstract

Abstract: AI-based methods have shown great promise in a variety of biomedical research fields, including neurooncologic imaging. For example, machine learning methods have offered informative predictions of overall survival (OS) and progression-free survival (PFS), differentiation between pseudoprogression (PsP) and progressive disease (PD), and estimation of mutational status from imaging data. Despite their promise, AI, and especially the emerging deep learning (DL) methods, are challenged by several factors, including imaging heterogeneity across scanners and lack of sufficiently large and diverse training datasets, which limits their reproducibility and general acceptance. These challenges prompted the development of the ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium on glioblastoma, a growing effort to bring together a community of researchers sharing imaging, demographic, clinical and (currently) limited molecular data in order to address the following aims: 1) pool and harmonize data across diverse hospitals and patient populations worldwide; 2) derive robust and generalizable AI models for prediction of (initially) OS, PFS, PsP vs. PD, and recurrence; 3) test these predictive models across multiple sites. In its first phase, ReSPOND aims to pool together approximately 3, 000MRI scans (from 10institutions plus TCIA), along with demographics, KPS, and (for a subset) MGMT/IDH1 status. We present initial results testing the generalization of a previously trained model of OS on 505Penn datasets to 2independent cohorts from Case Western Reserve University and University Hospitals (N=44), and Penn (N=67). The results indicate good generalization, with correlation coefficients between OS/predicted-OS between 0.25 to 0.5, depending on variable availability, which is comparable to cross-validated accuracy previously obtained from the training set itself (N=505). Additional preliminary studies evaluating prediction of future recurrence from baseline pre-operative scans in de novo patients (Penn model applied to CWR) indicated potential for guiding targeted dose escalation and supra-total resection (excellent predictions in 6/12 patients, modest in 1/12, and poor in 5/12).