Multimodal integration to identify the invasion status of lung adenocarcinoma intraoperatively

Xueyun Tan; Feng Pan; Na Zhan; Sufei Wang; Zegang Dong; Yan Li; Guanghai Yang; Bo Huang; Yanran Duan; Hui Xia; Yaqi Cao; Min Zhou; Zhilei Lv; Qi Huang; Shan Tian; Liang Zhang; Mengmeng Zhou; Lian Yang; Yang Jin

doi:10.1016/j.isci.2024.111421

Multimodal integration to identify the invasion status of lung adenocarcinoma intraoperatively

iScience. 2024 Nov 19;27(12):111421. doi: 10.1016/j.isci.2024.111421. eCollection 2024 Dec 20.

Authors

Xueyun Tan^{1

2

3}, Feng Pan⁴, Na Zhan⁵, Sufei Wang^{1

2

3}, Zegang Dong⁶, Yan Li⁷, Guanghai Yang⁸, Bo Huang⁷, Yanran Duan⁹, Hui Xia^{1

2

3}, Yaqi Cao^{1

2

3}, Min Zhou^{1

2

3}, Zhilei Lv^{1

2

3}, Qi Huang^{1

2

3}, Shan Tian¹⁰, Liang Zhang¹¹, Mengmeng Zhou^{1

2

3}, Lian Yang⁴, Yang Jin^{1

2

3}

Affiliations

¹ Department of Respiratory and Critical Care Medicine, Hubei Province Clinical Research Center for Major Respiratory Disease, NHC Key Laboratory of Pulmonary Diseases, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
² Hubei Province Key Laboratory of Biological Targeted Therapy, MOE Key Laboratory of Biological Targeted Therapy, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
³ Hubei Province Engineering Research Center for Tumor-Targeted Biochemotherapy, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
⁴ Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
⁵ Department of Pathology, Renmin Hospital of Wuhan University, Wuhan 430060, China.
⁶ Sino-US Telemed (Wuhan) Co., Ltd, Wuhan 430064, China.
⁷ Department of Pathology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
⁸ Department of Thoracic Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
⁹ Department of Epidemiology and Biostatistics, School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430030, China.
¹⁰ Department of Infectious Diseases, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
¹¹ Department of Radiology, Renmin Hospital of Wuhan University, Wuhan 430060, China.

Abstract

Evaluating the invasiveness of lung adenocarcinoma is crucial for determining the appropriate surgical strategy, impacting postoperative outcomes. This study developed a multimodality model combining radiomics, intraoperative frozen section (FS) pathology, and clinical indicators to predict invasion status. The study enrolled 1,424 patients from two hospitals, divided into multimodal training, radiology testing, and pathology testing cohorts. A prospective validation cohort of 114 patients was selected between March and May 2023. The radiomics + pathology + clinical indicators multimodality model (multi-RPC model) achieved an area under the curve (AUC) of 0.921 (95% confidence interval [CI] 0.899-0.939) in the multimodal training cohort and 0.939 (95% CI 0.878-0.975) in the validation cohort, outperforming single- and dual-modality models. The multi-RPC model's predictive accuracy of 0.860 (95% CI 0.782-0.918) suggests that it could significantly reduce inappropriate surgical procedures, enhancing precision oncology by integrating multimodal information to guide surgical decisions.

Keywords: Artificial intelligence applications; Medical imaging; Oncology.