Preoperative evaluation of visceral pleural invasion in peripheral lung cancer utilizing deep learning technology.

IF 1.7 4区医学 Q2 SURGERY

Surgery Today Pub Date : 2025-01-01 Epub Date: 2024-05-23 DOI:10.1007/s00595-024-02869-z

Yujin Kudo, Akira Saito, Tomoaki Horiuchi, Kotaro Murakami, Masaharu Kobayashi, Jun Matsubayashi, Toshitaka Nagao, Tatsuo Ohira, Masahiko Kuroda, Norihiko Ikeda

{"title":"Preoperative evaluation of visceral pleural invasion in peripheral lung cancer utilizing deep learning technology.","authors":"Yujin Kudo, Akira Saito, Tomoaki Horiuchi, Kotaro Murakami, Masaharu Kobayashi, Jun Matsubayashi, Toshitaka Nagao, Tatsuo Ohira, Masahiko Kuroda, Norihiko Ikeda","doi":"10.1007/s00595-024-02869-z","DOIUrl":null,"url":null,"abstract":"Purpose: This study aimed to assess the efficiency of artificial intelligence (AI) in the detection of visceral pleural invasion (VPI) of lung cancer using high-resolution computed tomography (HRCT) images, which is challenging for experts because of its significance in T-classification and lymph node metastasis prediction.Methods: This retrospective analysis was conducted on preoperative HRCT images of 472 patients with stage I non-small cell lung cancer (NSCLC), focusing on lesions adjacent to the pleura to predict VPI. YOLOv4.0 was utilized for tumor localization, and EfficientNetv2 was applied for VPI prediction with HRCT images meticulously annotated for AI model training and validation.Results: Of the 472 lung cancer cases (500 CT images) studied, the AI algorithm successfully identified tumors, with YOLOv4.0 accurately localizing tumors in 98% of the test images. In the EfficientNet v2-M analysis, the receiver operating characteristic curve exhibited an area under the curve of 0.78. It demonstrated powerful diagnostic performance with a sensitivity, specificity, and precision of 76.4% in VPI prediction.Conclusion: AI is a promising tool for improving the diagnostic accuracy of VPI for NSCLC. Furthermore, incorporating AI into the diagnostic workflow is advocated because of its potential to improve the accuracy of preoperative diagnosis and patient outcomes in NSCLC.","PeriodicalId":22163,"journal":{"name":"Surgery Today","volume":" ","pages":"18-28"},"PeriodicalIF":1.7000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Surgery Today","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00595-024-02869-z","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/5/23 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"SURGERY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: This study aimed to assess the efficiency of artificial intelligence (AI) in the detection of visceral pleural invasion (VPI) of lung cancer using high-resolution computed tomography (HRCT) images, which is challenging for experts because of its significance in T-classification and lymph node metastasis prediction.

Methods: This retrospective analysis was conducted on preoperative HRCT images of 472 patients with stage I non-small cell lung cancer (NSCLC), focusing on lesions adjacent to the pleura to predict VPI. YOLOv4.0 was utilized for tumor localization, and EfficientNetv2 was applied for VPI prediction with HRCT images meticulously annotated for AI model training and validation.

Results: Of the 472 lung cancer cases (500 CT images) studied, the AI algorithm successfully identified tumors, with YOLOv4.0 accurately localizing tumors in 98% of the test images. In the EfficientNet v2-M analysis, the receiver operating characteristic curve exhibited an area under the curve of 0.78. It demonstrated powerful diagnostic performance with a sensitivity, specificity, and precision of 76.4% in VPI prediction.

Conclusion: AI is a promising tool for improving the diagnostic accuracy of VPI for NSCLC. Furthermore, incorporating AI into the diagnostic workflow is advocated because of its potential to improve the accuracy of preoperative diagnosis and patient outcomes in NSCLC.

Abstract Image

查看原文本刊更多论文

利用深度学习技术对周围型肺癌的内脏胸膜侵犯进行术前评估。

目的：本研究旨在评估人工智能（AI）在使用高分辨率计算机断层扫描（HRCT）图像检测肺癌内脏胸膜侵犯（VPI）方面的效率：这项回顾性分析是针对 472 例 I 期非小细胞肺癌（NSCLC）患者的术前 HRCT 图像进行的，重点关注胸膜附近的病变，以预测 VPI。YOLOv4.0用于肿瘤定位，EfficientNetv2用于VPI预测，HRCT图像经过精心标注，用于人工智能模型的训练和验证：在研究的 472 例肺癌病例（500 张 CT 图像）中，人工智能算法成功识别了肿瘤，YOLOv4.0 在 98% 的测试图像中准确定位了肿瘤。在 EfficientNet v2-M 分析中，接收器工作特征曲线的曲线下面积为 0.78。在 VPI 预测方面，它的灵敏度、特异度和精确度均达到 76.4%，显示出强大的诊断性能：结论：人工智能是提高 NSCLC VPI 诊断准确性的有效工具。结论：人工智能是提高 NSCLC VPI 诊断准确性的理想工具，此外，将人工智能纳入诊断工作流程还能提高 NSCLC 术前诊断的准确性和患者的预后，因此值得提倡。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Surgery Today 医学-外科

CiteScore

4.90

自引率

4.00%

发文量

208

审稿时长

1 months

期刊介绍： Surgery Today is the official journal of the Japan Surgical Society. The main purpose of the journal is to provide a place for the publication of high-quality papers documenting recent advances and new developments in all fields of surgery, both clinical and experimental. The journal welcomes original papers, review articles, and short communications, as well as short technical reports("How to do it"). The "How to do it" section will includes short articles on methods or techniques recommended for practical surgery. Papers submitted to the journal are reviewed by an international editorial board. Field of interest: All fields of surgery.