Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Multicenter Study
. 2024 Dec 31;13(1):2415285.
doi: 10.1080/20450907.2024.2415285. Epub 2024 Nov 13.

Radio-pathomic estimates of cellular growth kinetics predict survival in recurrent glioblastoma

Sonoko Oshima  1   2 , Jingwen Yao  1   2   3 , Samuel Bobholz  4 , Raksha Nagaraj  1   2 , Catalina Raymond  1   2 , Ashley Teraishi  1   2 , Anna-Marie Guenther  1   3 , Asher Kim  1   3 , Francesco Sanvito  1   2 , Nicholas S Cho  1   2   3   5 , Blaine S. C. Eldred  6 , Jennifer M Connelly  7 , Phioanh L Nghiemphu  6   8 , Albert Lai  6   8 , Noriko Salamon  2 , Timothy F Cloughesy  6   8 , Peter S LaViolette  4   9   10 , Benjamin M Ellingson  1   2   3   11   12
Affiliations
Multicenter Study

Radio-pathomic estimates of cellular growth kinetics predict survival in recurrent glioblastoma

Sonoko Oshima et al. CNS Oncol. .

Abstract

Aim: A radio-pathomic machine learning (ML) model has been developed to estimate tumor cell density, cytoplasm density (Cyt) and extracellular fluid density (ECF) from multimodal MR images and autopsy pathology. In this multicenter study, we implemented this model to test its ability to predict survival in patients with recurrent glioblastoma (rGBM) treated with chemotherapy.Methods: Pre- and post-contrast T1-weighted, FLAIR and ADC images were used to generate radio-pathomic maps for 51 patients with longitudinal pre- and post-treatment scans. Univariate and multivariate Cox regression analyses were used to test the influence of contrast-enhancing tumor volume, total cellularity, mean Cyt and mean ECF at baseline, immediately post-treatment and the pre- and post-treatment rate of change in volume and cellularity on overall survival (OS).Results: Smaller Cyt and larger ECF after treatment were significant predictors of OS, independent of tumor volume and other clinical prognostic factors (HR = 3.23 × 10-6, p < 0.001 and HR = 2.39 × 105, p < 0.001, respectively). Both post-treatment volumetric growth rate and the rate of change in cellularity were significantly correlated with OS (HR = 1.17, p = 0.003 and HR = 1.14, p = 0.01, respectively).Conclusion: Changes in histological characteristics estimated from a radio-pathomic ML model are a promising tool for evaluating treatment response and predicting outcome in rGBM.

Keywords: MRI; rad-path; radiopathomic mapping; recurrent glioblastoma; survival; tumor growth rate.

Plain language summary

[Box: see text].

PubMed Disclaimer

Conflict of interest statement

BM Ellingson is a Paid Consultant and Advisor for Voiant, Servier Pharmaceuticals, Siemens, Imaging Endpoints, Chimerix, Sumitomo Dainippon Pharma Oncology, ImmunoGenesis, Ellipses Pharma, Monteris, Neosoma, Alpheus Medical, Sagiment Biosciences, Sapience Therapeutics, the Global Coalition for Adaptive Research, Telix and Third Rock Ventures. BME has received grant funding from Siemens and Neosoma.

TF Cloughesy is cofounder, major stock holder, consultant and board member of Katmai Pharmaceuticals, member of the board for the 501c3 Global Coalition for Adaptive Research, holds stock option of Notable Labs, holds stock in Chimerix and receives milestone payments and possible future royalties, member of the scientific advisory board for Break Through Cancer, member of the scientific advisory board for Cure Brain Cancer Foundation, has provided paid consulting services to GCAR; Gan & Lee; BrainStorm; Katmai; Sapience; Inovio; Vigeo Therapeutics; DNATrix; Tyme; SDP; Novartis; Roche; Kintara; Bayer; Merck; Boehinger Ingelheim; VBL; Amgen; Kiyatec; Odonate Therapeutics QED; Medefield; Pascal Biosciences; Bayer; Tocagen; Karyopharm; GW Pharma; Abbvie; VBI; Deciphera; VBL; Agios; Genocea; Celgene; Puma; Lilly; BMS; Cortice; Wellcome Trust; Novocure; Novogen; Boston Biomedical; Sunovion; Human Longevity; Insys; ProNai; Pfizer; Notable labs; Medqia Trizel; Medscape and has contracts with UCLA for the Brain Tumor Program with Oncovir; Merck; Oncoceutics; Novartis; Amgen; Abbvie; DNAtrix; Beigene; BMS; AstraZeneca; Kazia; Agios; Boston Biomedical; Deciphera; Tocagen; Orbus; AstraZenica; Karyopharm.

PS LaViolette holds a patent protecting portions of the IP used in this study (US18/349,584)

The authors have no other relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript apart from those disclosed.

Figures

Figure 1.
Figure 1.
CONSORT diagram. PFS: Progression free survival; RANO: Response assessment in neuro-oncology; RT: Radiation therapy; PD: Progressive disease.
Figure 2.
Figure 2.
Overview of the methods of this study. (A) Pre- and post-contrast T1-weighted, FLAIR and ADC images were used to train a “radiopathomic” machine learning (ML) model to predict histological characteristics using post-mortem brain tissue. (B) This model was then applied to an independent cohort of patients to testimate cellularity, cytoplasm volume fraction (Cyt) and extracellular volume fraction (ECF) before and after cytotoxic therapy.
Figure 3.
Figure 3.
Representative cases: (A) A 68-year-old female IDH wild-type glioblastoma patient who responded to chemotherapy as evidenced by a reduction in enhancing tumor volume and cellularity after the initiation of chemotherapy. (B) A 64-year-old female IDH wild-type glioblastoma patient who did not respond to chemotherapy and had increasing volume of enhancing tumor and cellularity after treatment.
Figure 4.
Figure 4.
Kaplan-Meier curves for overall survival at baseline and first post-treatment follow-up. Patients with smaller enhancing tumor volume and total cellularity at baseline (A & B) and 1st post-treatment scans (C & D), as well as those with smaller Cyt and larger ECF at the 1st post-treatment scan (E & F), demonstrated significantly longer OS.
Figure 5.
Figure 5.
Kaplan-Meier curves for overall survival stratified by volumetric growth rate or the rate of change in cellularity. Patients with smaller pre-treatment (A & D) growth or cellular rates of change, (B & E) post-treatment growth or cellular rate of change, or (C & F) a larger decrease in growth rate or cellular rate of change had significantly longer OS.
See this image and copyright information in PMC

References

    1. Alexander BM, Cloughesy TF. Adult glioblastoma. J Clin Oncol. 2017;35(21):2402–2409. doi:10.1200/JCO.2017.73.0119 - DOI - PubMed
    1. Mandel JJ, Yust-Katz S, Patel AJ, et al. . Inability of positive phase II clinical trials of investigational treatments to subsequently predict positive Phase III clinical trials in glioblastoma. Neuro Oncol. 2018;20(1):113–122. doi:10.1093/neuonc/nox144 - DOI - PMC - PubMed
    1. Johnson DR, O'Neill BP. Glioblastoma survival in the United States before and during the temozolomide era. J Neurooncol. 2012;107(2):359–364. doi:10.1007/s11060-011-0749-4 - DOI - PubMed
    1. Koshy M, Villano JL, Dolecek TA, et al. . Improved survival time trends for glioblastoma using the SEER 17 population-based registries. J Neurooncol. 2012;107(1):207–212. doi:10.1007/s11060-011-0738-7 - DOI - PMC - PubMed
    1. Ellingson BM, Bendszus M, Boxerman J, et al. . Consensus recommendations for a standardized Brain Tumor Imaging Protocol in clinical trials. Neuro Oncol. 2015;17(9):1188–1198. - PMC - PubMed

Publication types