Your browser doesn't support javascript.
loading
CT-Based Deep-Learning Model for Spread-Through-Air-Spaces Prediction in Ground Glass-Predominant Lung Adenocarcinoma.
Lin, Mong-Wei; Chen, Li-Wei; Yang, Shun-Mao; Hsieh, Min-Shu; Ou, De-Xiang; Lee, Yi-Hsuan; Chen, Jin-Shing; Chang, Yeun-Chung; Chen, Chung-Ming.
Afiliación
  • Lin MW; Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan.
  • Chen LW; Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei, Taiwan.
  • Yang SM; Department of Surgery, National Taiwan University Hospital Biomedical Park Hospital, Zhubei City, Hsinchu County, Taiwan.
  • Hsieh MS; Department of Pathology, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan.
  • Ou DX; Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei, Taiwan.
  • Lee YH; Department of Surgery, National Taiwan University Hospital Biomedical Park Hospital, Zhubei City, Hsinchu County, Taiwan.
  • Chen JS; Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan.
  • Chang YC; Department of Surgical Oncology, National Taiwan University Cancer Center, Taipei, Taiwan.
  • Chen CM; Department of Radiology, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan.
Ann Surg Oncol ; 31(3): 1536-1545, 2024 Mar.
Article en En | MEDLINE | ID: mdl-37957504
BACKGROUND: Sublobar resection is strongly associated with poor prognosis in early-stage lung adenocarcinoma, with the presence of tumor spread through air spaces (STAS). Thus, preoperative prediction of STAS is important for surgical planning. This study aimed to develop a STAS deep-learning (STAS-DL) prediction model in lung adenocarcinoma with tumor smaller than 3 cm and a consolidation-to-tumor (C/T) ratio less than 0.5. METHODS: The study retrospectively enrolled of 581 patients from two institutions between 2015 and 2019. The STAS-DL model was developed to extract the feature of solid components through solid components gated (SCG) for predicting STAS. The STAS-DL model was assessed with external validation in the testing sets and compared with the deep-learning model without SCG (STAS-DLwoSCG), the radiomics-based model, the C/T ratio, and five thoracic surgeons. The performance of the models was evaluated using area under the curve (AUC), accuracy and standardized net benefit of the decision curve analysis. RESULTS: The study evaluated 458 patients (institute 1) in the training set and 123 patients (institute 2) in the testing set. The proposed STAS-DL yielded the best performance compared with the other methods in the testing set, with an AUC of 0.82 and an accuracy of 74%, outperformed the STAS-DLwoSCG with an accuracy of 70%, and was superior to the physicians with an AUC of 0.68. Moreover, STAS-DL achieved the highest standardized net benefit compared with the other methods. CONCLUSION: The proposed STAS-DL model has great potential for the preoperative prediction of STAS and may support decision-making for surgical planning in early-stage, ground glass-predominant lung adenocarcinoma.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Adenocarcinoma del Pulmón / Aprendizaje Profundo / Neoplasias Pulmonares Límite: Humans Idioma: En Revista: Ann Surg Oncol Asunto de la revista: NEOPLASIAS Año: 2024 Tipo del documento: Article País de afiliación: Taiwán Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Adenocarcinoma del Pulmón / Aprendizaje Profundo / Neoplasias Pulmonares Límite: Humans Idioma: En Revista: Ann Surg Oncol Asunto de la revista: NEOPLASIAS Año: 2024 Tipo del documento: Article País de afiliación: Taiwán Pais de publicación: Estados Unidos