A CT-based deep learning model for preoperative prediction of spread through air spaces in clinical stage I lung adenocarcinoma
ObjectiveTo develop and validate a deep learning signature for noninvasive prediction of spread through air spaces (STAS) in clinical stage I lung adenocarcinoma and compare its predictive performance with conventional clinical-semantic model.MethodsA total of 513 patients with pathologically-confir...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2024.1482965/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555083837308928 |
|---|---|
| author | Xiaoling Ma Weiheng He Chong Chen Fengmei Tan Jun Chen Lili Yang Dazhi Chen Liming Xia |
| author_facet | Xiaoling Ma Weiheng He Chong Chen Fengmei Tan Jun Chen Lili Yang Dazhi Chen Liming Xia |
| author_sort | Xiaoling Ma |
| collection | DOAJ |
| description | ObjectiveTo develop and validate a deep learning signature for noninvasive prediction of spread through air spaces (STAS) in clinical stage I lung adenocarcinoma and compare its predictive performance with conventional clinical-semantic model.MethodsA total of 513 patients with pathologically-confirmed stage I lung adenocarcinoma were retrospectively enrolled and were divided into training cohort (n = 386) and independent validation cohort (n = 127) according to different center. Clinicopathological data were collected and CT semantic features were evaluated. Multivariate logistic regression analyses were conducted to construct a clinical-semantic model predictive of STAS. The Swin Transformer architecture was adopted to develop a deep learning signature predictive of STAS. Model performance was assessed using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive and negative predictive value, and calibration curve. AUC comparisons were performed by the DeLong test.ResultsThe proposed deep learning signature achieved an AUC of 0.869 (95% CI: 0.831, 0.901) in training cohort and 0.837 (95% CI: 0.831, 0.901) in validation cohort, surpassing clinical-semantic model both in training and validation cohort (all P<0.01). Calibration curves demonstrated good agreement between STAS predicted probabilities using deep learning signature and actual observed probabilities in both cohorts. The inclusion of all clinical-semantic risk predictors failed to show an incremental value with respect to deep learning signature.ConclusionsThe proposed deep learning signature based on Swin Transformer achieved a promising performance in predicting STAS in clinical stage I lung adenocarcinoma, thereby offering information in directing surgical strategy and facilitating adjuvant therapeutic scheduling. |
| format | Article |
| id | doaj-art-53dbcaee04cb4fe08a1163fcf63f00c2 |
| institution | Kabale University |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-53dbcaee04cb4fe08a1163fcf63f00c22025-01-08T06:12:02ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-01-011410.3389/fonc.2024.14829651482965A CT-based deep learning model for preoperative prediction of spread through air spaces in clinical stage I lung adenocarcinomaXiaoling Ma0Weiheng He1Chong Chen2Fengmei Tan3Jun Chen4Lili Yang5Dazhi Chen6Liming Xia7Medical imaging center, People’s Hospital of Ningxia Hui Autonomous Region, Yinchuan, ChinaMedical imaging center, People’s Hospital of Ningxia Hui Autonomous Region, Yinchuan, ChinaDepartment of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaDepartment of Pathology, People’s Hospital of Ningxia Hui Autonomous Region, Yinchuan, ChinaDepartment of Radiology, Bayer Healthcare, Wuhan, ChinaMedical imaging center, People’s Hospital of Ningxia Hui Autonomous Region, Yinchuan, ChinaMedical imaging center, People’s Hospital of Ningxia Hui Autonomous Region, Yinchuan, ChinaDepartment of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaObjectiveTo develop and validate a deep learning signature for noninvasive prediction of spread through air spaces (STAS) in clinical stage I lung adenocarcinoma and compare its predictive performance with conventional clinical-semantic model.MethodsA total of 513 patients with pathologically-confirmed stage I lung adenocarcinoma were retrospectively enrolled and were divided into training cohort (n = 386) and independent validation cohort (n = 127) according to different center. Clinicopathological data were collected and CT semantic features were evaluated. Multivariate logistic regression analyses were conducted to construct a clinical-semantic model predictive of STAS. The Swin Transformer architecture was adopted to develop a deep learning signature predictive of STAS. Model performance was assessed using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive and negative predictive value, and calibration curve. AUC comparisons were performed by the DeLong test.ResultsThe proposed deep learning signature achieved an AUC of 0.869 (95% CI: 0.831, 0.901) in training cohort and 0.837 (95% CI: 0.831, 0.901) in validation cohort, surpassing clinical-semantic model both in training and validation cohort (all P<0.01). Calibration curves demonstrated good agreement between STAS predicted probabilities using deep learning signature and actual observed probabilities in both cohorts. The inclusion of all clinical-semantic risk predictors failed to show an incremental value with respect to deep learning signature.ConclusionsThe proposed deep learning signature based on Swin Transformer achieved a promising performance in predicting STAS in clinical stage I lung adenocarcinoma, thereby offering information in directing surgical strategy and facilitating adjuvant therapeutic scheduling.https://www.frontiersin.org/articles/10.3389/fonc.2024.1482965/fulldeep learninglung adenocarcinomaspread though air spacecomputer tomographyprediction |
| spellingShingle | Xiaoling Ma Weiheng He Chong Chen Fengmei Tan Jun Chen Lili Yang Dazhi Chen Liming Xia A CT-based deep learning model for preoperative prediction of spread through air spaces in clinical stage I lung adenocarcinoma Frontiers in Oncology deep learning lung adenocarcinoma spread though air space computer tomography prediction |
| title | A CT-based deep learning model for preoperative prediction of spread through air spaces in clinical stage I lung adenocarcinoma |
| title_full | A CT-based deep learning model for preoperative prediction of spread through air spaces in clinical stage I lung adenocarcinoma |
| title_fullStr | A CT-based deep learning model for preoperative prediction of spread through air spaces in clinical stage I lung adenocarcinoma |
| title_full_unstemmed | A CT-based deep learning model for preoperative prediction of spread through air spaces in clinical stage I lung adenocarcinoma |
| title_short | A CT-based deep learning model for preoperative prediction of spread through air spaces in clinical stage I lung adenocarcinoma |
| title_sort | ct based deep learning model for preoperative prediction of spread through air spaces in clinical stage i lung adenocarcinoma |
| topic | deep learning lung adenocarcinoma spread though air space computer tomography prediction |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2024.1482965/full |
| work_keys_str_mv | AT xiaolingma actbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT weihenghe actbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT chongchen actbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT fengmeitan actbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT junchen actbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT liliyang actbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT dazhichen actbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT limingxia actbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT xiaolingma ctbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT weihenghe ctbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT chongchen ctbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT fengmeitan ctbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT junchen ctbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT liliyang ctbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT dazhichen ctbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma AT limingxia ctbaseddeeplearningmodelforpreoperativepredictionofspreadthroughairspacesinclinicalstageilungadenocarcinoma |