jump to content jump to footer

Structured Reporting Improves TNM Classification Accuracy and Radiologist Satisfaction

In a collaborative, multi-center study, radiology experts developed and validated in mint Lesion a software-assisted structured reporting (SR) framework for non-small cell lung cancer (NSCLC) staging.

Findings revealed that SR significantly improved TNM classification accuracy, reducing common errors in T-, N-, and M-staging compared to traditional free-text reports. Radiologists using SR were more likely to classify cases correctly and rated the tool highly for enhancing report quality, completeness, and interdisciplinary communication. This study suggests that SR may not only improve clinical accuracy but also support data standardization for future lung cancer research.

Read a summary of the study here.

BORN Structured Reporting TNM

Related Resources

Radiologists reviewing oncologic imaging cases during the ESOI–EORTC Workshop on standardized tumor response assessment
The ESOI–EORTC Workshop provides practical training in RECIST 1.1, standardized tumor response assessment, clinical trial imaging, and hands-on oncology case reviews.
ESOI–EORTC Workshop 2026: Experience, Exchange, and Standardized Tumor Response Assessment in Radiology
The ESOI–EORTC Workshop is one of the leading educational formats for radiologists focusing on the standardized assessment of tumor response.This…
From PCWG3 to PCWG4: Evolving Standards in Prostate Cancer Clinical Trials
The Prostate Cancer Working Group 4 (PCWG4) updates and extends the recommendations of PCWG3 to reflect a patient-centric approach, the emergence of…
Participants at the RECIST and Beyond workshop in Cologne during hands-on training with mint Lesion for structured tumor response assessment.
The two-day “RECIST and Beyond” workshop at radCIO Cologne offered intensive hands-on training on RECIST, iRECIST, mRECIST and LI-RADS, with real-case reporting performed directly in mint Lesion.
Successful “RECIST and Beyond” Workshop in Cologne: Advancing Precision in Oncologic Imaging
How can complex tumor findings be assessed accurately, reproducibly, and in line with clinical guidelines?