What question did this study set out to answer?

This research aims to advance automated lung cancer staging using radiology reports through natural language processing.

April 1, 2026Open Access

NTCIR-17 MedNLP-SC Radiology Report Subtask Overview: Dataset and Solutions for Automated Lung Cancer Staging

Key Points

This research aims to advance automated lung cancer staging using radiology reports through natural language processing.
Created a dataset of 243 Japanese radiology reports without personal information.
Conducted the RR-TNM subtask as part of NTCIR-17 MedNLP-SC.
Three teams with 16 members submitted seven solutions focusing on lung cancer staging.
Achieved accuracy scores of 67% for T category, 80% for N category, and 93% for M category.
Provided a valuable open clinical corpus for Japanese radiology reports and insights on NLP applications.

Abstract

This paper describes the Radiology Report TNM staging (RR-TNM) subtask as a part of NTCIR-17 Medical Natural Language Processing for Social Media and Clinical Texts (MedNLP-SC) shared task in 2023. This subtask focused on automated lung cancer staging based on radiology reports. We created a dataset of 243 Japanese radiology reports containing no personal health information. A total of three teams with 16 members participated and submitted seven solutions. The best accuracy scores for the T, N, and M categories reached 67%, 80%, and 93%, respectively. Through the RR- TNM subtask, we have provided a valuable open Japanese clinical corpus and useful insights to apply natural language processing for secondary usage of staging information.

Read Full Paperexternally

Perguntar à IA

Bookmark

View Full Paper