Overview

Schema Version

https://atlas.rsna.org/schemas/2025-11/dataset.json

Name

Cleveland Clinic NSCLC baseline non-contrast CT cohort for chemotherapy response prediction (1998–2010)

Link

https://doi.org/10.1148/ryai.2019180012

Indexing

Keywords: NSCLC, lung adenocarcinoma, chemotherapy response, pemetrexed-based platinum doublet, radiomics, peritumoral, intratumoral, time to progression, overall survival, baseline non-contrast CT

Content: CH, CT, OI

RadLex: RID50134, RID10341, RID4226

SNOMED: 254637007

Author(s)

Mohammadhadi Khorrami

Monica Khunger

Alexia Zagouras

Pradnya Patil

Rajat Thawani

Kaustav Bera

Prabhakar Rajiah

Pingfu Fu

Vamsidhar Velcheti

Anant Madabhushi

Organization(s)

Cleveland Clinic

Case Western Reserve University

UT Southwestern Medical Center

Maimonides Medical Center

New York University

Louis Stokes Cleveland Veterans Administration Medical Center

Funding

Supported by the U.S. Department of Defense, the National Cancer Institute, the National Institute of Diabetes and Digestive and Kidney Diseases, the National Center for Research Resources, the Ohio Third Frontier Technology Validation Fund, the Wallace H. Coulter Foundation Program in the Department of Biomedical Engineering, and the Clinical and Translational Science Award Program at Case Western Reserve University.

Ethical review

HIPAA-compliant; Cleveland Clinic Institutional Review Board approval (IRB #14-562); informed consent waived.

Comments

Retrospective single-institution cohort used to develop and validate radiomics models predicting response to pemetrexed-based platinum doublet chemotherapy and association with time to progression and overall survival in NSCLC.

Date

Published: 2019-03-20

References

[1] Khorrami M, Khunger M, Zagouras A, Patil P, Thawani R, Bera K, Rajiah P, Fu P, Velcheti V, Madabhushi A. "Combination of Peri- and Intratumoral Radiomic Features on Baseline CT Scans Predicts Response to Chemotherapy in Lung Adenocarcinoma". Radiology: Artificial Intelligence. 2019. doi:10.1148/ryai.2019180012. PMID: 32076657. PMCID: PMC6515986.

Dataset

Motivation

To evaluate whether peri- and intratumoral radiomic features on baseline CT predict chemotherapy response and are associated with TTP and OS in NSCLC.

Sampling

Retrospective identification of lung adenocarcinoma stage IIIb/IV patients treated with front-line platinum-based chemotherapy between Jan 1, 1998 and Dec 21, 2010; inclusion required baseline CT <30 days prior to chemotherapy and availability of response data after four cycles.

Partitioning scheme

Patients randomly split into training (n=53) and validation (n=72) with equal numbers of responders and nonresponders in the training set.

Missing information

Image file formats, scanner vendors/protocols, exact patient demographics by partition, and complete acquisition parameters beyond section thickness were not detailed.

Relationships between instances

Each patient contributed a baseline non–contrast-enhanced thoracic CT with an annotated index lesion; features extracted from intra- and peritumoral regions.

External data

RIDER lung CT dataset used solely for test-retest feature reproducibility assessment (intraclass correlation).

Confidentiality

Retrospective HIPAA-compliant study with IRB approval and consent waiver.

Sensitive data

Clinical imaging and outcomes (response, TTP, OS) from oncology patients.