CT-Based Super-Resolution Deep Learning Models with Attention Mechanisms for Predicting Spread Through Air Spaces of Solid or Part-Solid Lung Adenocarcinoma

Wang, Shuxing1; Liu, Xiaowen1; Jiang, Changsi2; Kang, Wenyan3; Pan, Yudie1; Tang, Xue2; Luo, Yan2; Gong, Jingshan1,2

2024-06-01

10.1016/j.acra.2023.12.034

ACADEMIC RADIOLOGY   影响因子和分区

1076-6332

1878-4046

Rationale and Objectives: Spread through air space (STAS) is a novel invasive pattern of lung adenocarcinoma (LUAD), and preoperative knowledge of STAS status is helpful in choosing an appropriate surgical approach. Materials and Methods: This retrospective study collected and analyzed 602 patients diagnosed with LUAD from two medical centers: center 1 was randomly partitioned into training ( n = 358) and validation cohorts ( n = 154) at a 7:3 ratio; and center 2 was the external test cohort ( n = 90). Super resolution was performed on all images to acquire high-resolution images, which were used to train the SEResNet50 model, before creating an equivalent parameter ResNet50 model. Disparities were compared between the two models using receiver operating characteristic curves, area under the curve, accuracy, precision, sensitivity, and specificity. Results: In this study, 512 and 90 patients with LUAD were enrolled from centers 1 and 2, respectively. The curve values of the SEResNet50 and ResNet50 models were compared for training, validation, and test cohorts, resulting in values of 0.933 vs 0.909, 0.783 vs 0.728, and 0.806 vs 0.695, respectively. In the external test cohort, the accuracy of the SE-ResNet50 model demonstrated a 10% improvement over the ResNet50 model (82.2% vs 72.2%). Conclusion: The SE-ResNet50 model based on computed tomography super-resolution has great potential for predicting STAS status in patients with solid or partially solid LUAD, with superior predictive performance compared to traditional deep learning models.

Deep learning Lung cancer Spread through air spaces Computer tomography

SCI

英语

通讯

National Natural Science Foundation of China[82172026]

Radiology, Nuclear Medicine & Medical Imaging

Radiology, Nuclear Medicine & Medical Imaging

WOS:001266509800001

ELSEVIER SCIENCE INC

CLINICAL MEDICINE

Web of Science

1.Jinan Univ, Clin Med Coll 2, Shenzhen, Guangdong, Peoples R China
2.Jinan Univ, Southern Univ Sci & Technol, Shenzhen Peoples Hosp, Dept Radiol,Clin Med Coll 2,Affiliated Hosp 1, Floor 1,Bldg 4,Dongbeilu 1017, Shenzhen 518020, Guangdong, Peoples R China
3.Chinese Acad Med Sci, Shenzhen Ctr, Dept Radiol, Canc Hosp, Shenzhen, Peoples R China

Wang, Shuxing,Liu, Xiaowen,Jiang, Changsi,et al. CT-Based Super-Resolution Deep Learning Models with Attention Mechanisms for Predicting Spread Through Air Spaces of Solid or Part-Solid Lung Adenocarcinoma[J]. ACADEMIC RADIOLOGY,2024,31(6).

Wang, Shuxing.,Liu, Xiaowen.,Jiang, Changsi.,Kang, Wenyan.,Pan, Yudie.,...&Gong, Jingshan.(2024).CT-Based Super-Resolution Deep Learning Models with Attention Mechanisms for Predicting Spread Through Air Spaces of Solid or Part-Solid Lung Adenocarcinoma.ACADEMIC RADIOLOGY,31(6).

Wang, Shuxing,et al."CT-Based Super-Resolution Deep Learning Models with Attention Mechanisms for Predicting Spread Through Air Spaces of Solid or Part-Solid Lung Adenocarcinoma".ACADEMIC RADIOLOGY 31.6(2024).