Development of a clinical prediction model for benign and malignant pulmonary nodules with a CTR ≥ 50% utilizing artificial intelligence-driven radiomics analysis
Abstract Objective In clinical practice, diagnosing the benignity and malignancy of solid-component-predominant pulmonary nodules is challenging, especially when 3D consolidation-to-tumor ratio (CTR) ≥ 50%, as malignant ones are more invasive. This study aims to develop and validate an AI-driven rad...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-024-01533-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594351168946176 |
|---|---|
| author | Wensong Shi Yuzhui Hu Guotao Chang He Qian Yulun Yang Yinsen Song Zhengpan Wei Liang Gao Hang Yi Sikai Wu Kun Wang Huandong Huo Shuaibo Wang Yousheng Mao Siyuan Ai Liang Zhao Xiangnan Li Huiyu Zheng |
| author_facet | Wensong Shi Yuzhui Hu Guotao Chang He Qian Yulun Yang Yinsen Song Zhengpan Wei Liang Gao Hang Yi Sikai Wu Kun Wang Huandong Huo Shuaibo Wang Yousheng Mao Siyuan Ai Liang Zhao Xiangnan Li Huiyu Zheng |
| author_sort | Wensong Shi |
| collection | DOAJ |
| description | Abstract Objective In clinical practice, diagnosing the benignity and malignancy of solid-component-predominant pulmonary nodules is challenging, especially when 3D consolidation-to-tumor ratio (CTR) ≥ 50%, as malignant ones are more invasive. This study aims to develop and validate an AI-driven radiomics prediction model for such nodules to enhance diagnostic accuracy. Methods Data of 2,591 pulmonary nodules from five medical centers (Zhengzhou People’s Hospital, etc.) were collected. Applying exclusion criteria, 370 nodules (78 benign, 292 malignant) with 3D CTR ≥ 50% were selected and randomly split 7:3 into training and validation cohorts. Using R programming, Lasso regression with 10-fold cross-validation filtered features, followed by univariate and multivariate logistic regression to construct the model. Its efficacy was evaluated by ROC, DCA curves and calibration plots. Results Lasso regression picked 18 non-zero coefficients from 108 features. Three significant factors—patient age, solid component volume and mean CT value—were identified. The logistic regression equation was formulated. In the training set, the ROC AUC was 0.721 (95%CI: 0.642–0.801); in the validation set, AUC was 0.757 (95%CI: 0.632–0.881), showing the model’s stability and predictive ability. Conclusion The model has moderate accuracy in differentiating benign from malignant 3D CTR ≥ 50% nodules, holding clinical potential. Future efforts could explore more to improve its precision and value. Clinical trial number Not applicable. |
| format | Article |
| id | doaj-art-89ff0de65e414fb8a69ce1c69b65ddae |
| institution | Kabale University |
| issn | 1471-2342 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj-art-89ff0de65e414fb8a69ce1c69b65ddae2025-01-19T12:43:24ZengBMCBMC Medical Imaging1471-23422025-01-0125111110.1186/s12880-024-01533-9Development of a clinical prediction model for benign and malignant pulmonary nodules with a CTR ≥ 50% utilizing artificial intelligence-driven radiomics analysisWensong Shi0Yuzhui Hu1Guotao Chang2He Qian3Yulun Yang4Yinsen Song5Zhengpan Wei6Liang Gao7Hang Yi8Sikai Wu9Kun Wang10Huandong Huo11Shuaibo Wang12Yousheng Mao13Siyuan Ai14Liang Zhao15Xiangnan Li16Huiyu Zheng17Department of Thoracic Surgery, The Fifth Clinical Medical College of Henan, University of Chinese Medicine (Zhengzhou People’s Hospital)Department of Geratology, Ninth People’s Hospital of ZhengzhouDepartment of Thoracic Surgery, The Fifth Clinical Medical College of Henan, University of Chinese Medicine (Zhengzhou People’s Hospital)Department of Thoracic Surgery, The Fifth Clinical Medical College of Henan, University of Chinese Medicine (Zhengzhou People’s Hospital)Department of Thoracic Surgery, The Fifth Clinical Medical College of Henan, University of Chinese Medicine (Zhengzhou People’s Hospital)Translational Medicine Research Center (Key Laboratory of Organ Transplantation of Henan Province), The Fifth Clinical Medical College of Henan University of Chinese Medicine (Zhengzhou People’s Hospital)Department of Thoracic Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Radiology, Ninth People’s Hospital of ZhengzhouDepartment of Thoracic Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Thoracic Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Thoracic Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Thoracic Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Thoracic Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Thoracic Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Thoracic Surgery, Liangxiang HospitalShukun (Beijing) Technology CoDepartment of Thoracic Surgery, The First Affiliated Hospital of Zhengzhou UniversityDepartment of Thoracic Surgery, The Fifth Clinical Medical College of Henan, University of Chinese Medicine (Zhengzhou People’s Hospital)Abstract Objective In clinical practice, diagnosing the benignity and malignancy of solid-component-predominant pulmonary nodules is challenging, especially when 3D consolidation-to-tumor ratio (CTR) ≥ 50%, as malignant ones are more invasive. This study aims to develop and validate an AI-driven radiomics prediction model for such nodules to enhance diagnostic accuracy. Methods Data of 2,591 pulmonary nodules from five medical centers (Zhengzhou People’s Hospital, etc.) were collected. Applying exclusion criteria, 370 nodules (78 benign, 292 malignant) with 3D CTR ≥ 50% were selected and randomly split 7:3 into training and validation cohorts. Using R programming, Lasso regression with 10-fold cross-validation filtered features, followed by univariate and multivariate logistic regression to construct the model. Its efficacy was evaluated by ROC, DCA curves and calibration plots. Results Lasso regression picked 18 non-zero coefficients from 108 features. Three significant factors—patient age, solid component volume and mean CT value—were identified. The logistic regression equation was formulated. In the training set, the ROC AUC was 0.721 (95%CI: 0.642–0.801); in the validation set, AUC was 0.757 (95%CI: 0.632–0.881), showing the model’s stability and predictive ability. Conclusion The model has moderate accuracy in differentiating benign from malignant 3D CTR ≥ 50% nodules, holding clinical potential. Future efforts could explore more to improve its precision and value. Clinical trial number Not applicable.https://doi.org/10.1186/s12880-024-01533-9Artificial intelligenceRadiomics3D CTR ≥ 50%Benign and malignantClinical prediction model |
| spellingShingle | Wensong Shi Yuzhui Hu Guotao Chang He Qian Yulun Yang Yinsen Song Zhengpan Wei Liang Gao Hang Yi Sikai Wu Kun Wang Huandong Huo Shuaibo Wang Yousheng Mao Siyuan Ai Liang Zhao Xiangnan Li Huiyu Zheng Development of a clinical prediction model for benign and malignant pulmonary nodules with a CTR ≥ 50% utilizing artificial intelligence-driven radiomics analysis BMC Medical Imaging Artificial intelligence Radiomics 3D CTR ≥ 50% Benign and malignant Clinical prediction model |
| title | Development of a clinical prediction model for benign and malignant pulmonary nodules with a CTR ≥ 50% utilizing artificial intelligence-driven radiomics analysis |
| title_full | Development of a clinical prediction model for benign and malignant pulmonary nodules with a CTR ≥ 50% utilizing artificial intelligence-driven radiomics analysis |
| title_fullStr | Development of a clinical prediction model for benign and malignant pulmonary nodules with a CTR ≥ 50% utilizing artificial intelligence-driven radiomics analysis |
| title_full_unstemmed | Development of a clinical prediction model for benign and malignant pulmonary nodules with a CTR ≥ 50% utilizing artificial intelligence-driven radiomics analysis |
| title_short | Development of a clinical prediction model for benign and malignant pulmonary nodules with a CTR ≥ 50% utilizing artificial intelligence-driven radiomics analysis |
| title_sort | development of a clinical prediction model for benign and malignant pulmonary nodules with a ctr ≥ 50 utilizing artificial intelligence driven radiomics analysis |
| topic | Artificial intelligence Radiomics 3D CTR ≥ 50% Benign and malignant Clinical prediction model |
| url | https://doi.org/10.1186/s12880-024-01533-9 |
| work_keys_str_mv | AT wensongshi developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT yuzhuihu developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT guotaochang developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT heqian developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT yulunyang developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT yinsensong developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT zhengpanwei developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT lianggao developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT hangyi developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT sikaiwu developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT kunwang developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT huandonghuo developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT shuaibowang developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT youshengmao developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT siyuanai developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT liangzhao developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT xiangnanli developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis AT huiyuzheng developmentofaclinicalpredictionmodelforbenignandmalignantpulmonarynoduleswithactr50utilizingartificialintelligencedrivenradiomicsanalysis |