1
|
Ou DX, Lu CW, Chen LW, Lee WY, Hu HW, Chuang JH, Lin MW, Chen KY, Chiu LY, Chen JS, Chen CM, Hsieh MS. Deep Learning Analysis for Predicting Tumor Spread through Air Space in Early-Stage Lung Adenocarcinoma Pathology Images. Cancers (Basel) 2024; 16:2132. [PMID: 38893251 PMCID: PMC11172106 DOI: 10.3390/cancers16112132] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2024] [Revised: 05/25/2024] [Accepted: 06/01/2024] [Indexed: 06/21/2024] Open
Abstract
The presence of spread through air spaces (STASs) in early-stage lung adenocarcinoma is a significant prognostic factor associated with disease recurrence and poor outcomes. Although current STAS detection methods rely on pathological examinations, the advent of artificial intelligence (AI) offers opportunities for automated histopathological image analysis. This study developed a deep learning (DL) model for STAS prediction and investigated the correlation between the prediction results and patient outcomes. To develop the DL-based STAS prediction model, 1053 digital pathology whole-slide images (WSIs) from the competition dataset were enrolled in the training set, and 227 WSIs from the National Taiwan University Hospital were enrolled for external validation. A YOLOv5-based framework comprising preprocessing, candidate detection, false-positive reduction, and patient-based prediction was proposed for STAS prediction. The model achieved an area under the curve (AUC) of 0.83 in predicting STAS presence, with 72% accuracy, 81% sensitivity, and 63% specificity. Additionally, the DL model demonstrated a prognostic value in disease-free survival compared to that of pathological evaluation. These findings suggest that DL-based STAS prediction could serve as an adjunctive screening tool and facilitate clinical decision-making in patients with early-stage lung adenocarcinoma.
Collapse
Affiliation(s)
- De-Xiang Ou
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei 10617, Taiwan; (D.-X.O.); (L.-W.C.); (K.-Y.C.)
| | - Chao-Wen Lu
- Division of Thoracic Surgery, Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan; (C.-W.L.); (J.-H.C.)
- Graduate Institute of Pathology, National Taiwan University College of Medicine, Taipei 100, Taiwan
| | - Li-Wei Chen
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei 10617, Taiwan; (D.-X.O.); (L.-W.C.); (K.-Y.C.)
| | - Wen-Yao Lee
- Division of Thoracic Surgery, Department of Surgery, Fu Jen Catholic University Hospital, No. 69, Guizi Road, Taishan District, New Taipei City 24352, Taiwan;
| | - Hsiang-Wei Hu
- Department of Pathology, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan;
| | - Jen-Hao Chuang
- Division of Thoracic Surgery, Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan; (C.-W.L.); (J.-H.C.)
| | - Mong-Wei Lin
- Division of Thoracic Surgery, Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan; (C.-W.L.); (J.-H.C.)
| | - Kuan-Yu Chen
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei 10617, Taiwan; (D.-X.O.); (L.-W.C.); (K.-Y.C.)
| | - Ling-Ying Chiu
- Institute of Medicine, Chung Shan Medical University, Taichung 40201, Taiwan;
| | - Jin-Shing Chen
- Division of Thoracic Surgery, Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan; (C.-W.L.); (J.-H.C.)
| | - Chung-Ming Chen
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei 10617, Taiwan; (D.-X.O.); (L.-W.C.); (K.-Y.C.)
| | - Min-Shu Hsieh
- Graduate Institute of Pathology, National Taiwan University College of Medicine, Taipei 100, Taiwan
- Department of Pathology, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei 100, Taiwan;
| |
Collapse
|
2
|
Liu BC, Ma HY, Huang J, Luo YW, Zhang WB, Deng WW, Liao YT, Xie CM, Li Q. Does dual-layer spectral detector CT provide added value in predicting spread through air spaces in lung adenocarcinoma? A preliminary study. Eur Radiol 2024; 34:4176-4186. [PMID: 37973632 DOI: 10.1007/s00330-023-10440-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2023] [Revised: 08/29/2023] [Accepted: 10/03/2023] [Indexed: 11/19/2023]
Abstract
OBJECTIVES To examine the predictive value of dual-layer spectral detector CT (DLCT) for spread through air spaces (STAS) in clinical lung adenocarcinoma. METHODS A total of 225 lung adenocarcinoma cases were retrospectively reviewed for demographic, clinical, pathological, traditional CT, and spectral parameters. Multivariable logistic regression analysis was carried out based on three logistic models, including a model using traditional CT features (traditional model), a model using spectral parameters (spectral model), and an integrated model combining traditional CT and spectral parameters (integrated model). Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were performed to assess these models. RESULTS Univariable analysis showed significant differences between the STAS and non-STAS groups in traditional CT features, including nodule density (p < 0.001), pleural indentation types (p = 0.006), air-bronchogram sign (p = 0.031), the presence of spiculation (p < 0.001), long-axis diameter of the entire nodule (LD) (p < 0.001), and consolidation/tumor ratio (CTR) (p < 0.001). Multivariable analysis revealed that LD > 20 mm (odds ratio [OR] = 2.271, p = 0.025) and CTR (OR = 24.208, p < 0.001) were independent predictors in the traditional model, while electronic density (ED) in the venous phase was an independent predictor in the spectral (OR = 1.062, p < 0.001) and integrated (OR = 1.055, p < 0.001) models. The area under the curve (AUC) for the integrated model (0.84) was the highest (spectral model, 0.83; traditional model, 0.80), and the difference between the integrated and traditional models was statistically significant (p = 0.015). DCA showed that the integrated model had superior clinical value versus the traditional model. CONCLUSIONS DLCT has added value for STAS prediction in lung adenocarcinoma. CLINICAL RELEVANCE STATEMENT Spectral CT has added value for spread through air spaces prediction in lung adenocarcinoma so may impact treatment planning in the future. KEY POINTS • Electronic density may be a potential spectral index for predicting spread through air spaces in lung adenocarcinoma. • A combination of spectral and traditional CT features enhances the performance of traditional CT for predicting spread through air spaces.
Collapse
Affiliation(s)
- Bao-Cong Liu
- State Key Laboratory of Oncology in South China, Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, People's Republic of China
| | - Hui-Yun Ma
- State Key Laboratory of Oncology in South China, Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, People's Republic of China
| | - Jin Huang
- State Key Laboratory of Oncology in South China, Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, People's Republic of China
| | - Ying-Wei Luo
- State Key Laboratory of Oncology in South China, Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, People's Republic of China
| | - Wen-Biao Zhang
- State Key Laboratory of Oncology in South China, Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, People's Republic of China
| | - Wei-Wei Deng
- Clinical & Technical Support, Philips Healthcare, Shanghai, People's Republic of China
| | - Yu-Ting Liao
- Clinical & Technical Support, Philips Healthcare, Shanghai, People's Republic of China
| | - Chuan-Miao Xie
- State Key Laboratory of Oncology in South China, Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, People's Republic of China.
| | - Qiong Li
- State Key Laboratory of Oncology in South China, Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou, People's Republic of China.
| |
Collapse
|
3
|
Zheng Y, Han X, Li H, Luo Q, Ding C, Zhang K, Fan J, Zeng W, Shi H. A validated model to predict spread through air space in lung adenocarcinoma. J Thorac Dis 2024; 16:2296-2313. [PMID: 38738222 PMCID: PMC11087620 DOI: 10.21037/jtd-23-1871] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Accepted: 03/01/2024] [Indexed: 05/14/2024]
Abstract
Background Spread through air space (STAS) is currently considered to be a significant predictor of a poor outcome of pulmonary adenocarcinoma. Preoperative prediction of STAS is of great importance for treatment planning. The aim of the present study was to establish a nomogram based on computed tomography (CT) features for predicting STAS in lung adenocarcinoma and to assess the prognosis of the patients with STAS. Methods A retrospective cohort study was performed in Wuhan Union Hospital from December 2015 to March 2021. The sample was divided into training and testing cohorts. Clinicopathologic and radiologic variables were recorded. The independent risk factors for STAS were determined by stepwise regression and then incorporated into the nomogram. Receiver operating characteristic (ROC) curves and calibration curves analysed by the Hosmer-Lemeshow test were used to evaluate the performance of the model. Decision curve analysis (DCA) was conducted to determine the clinical value of the nomogram. The Kaplan-Meier method was used for survival analysis and the multivariable Cox proportional hazards regression model was used to identify independent predictors for recurrence-free survival (RFS) and overall survival (OS). Results The sample included 244 patients who underwent surgical resection for primary lung adenocarcinoma. The training cohort included 199 patients (68 STAS-positive and 131 STAS-negative patients), and the testing cohort included 45 patients (15 STAS-positive and 30 STAS-negative patients). The preoperative CT features associated with STAS were shape, ground-glass opacity (GGO) ratio and spicules. The nomogram including these three factors had good discriminative power, and the areas under the ROC curve were 0.875 and 0.922 for the training and testing data sets, respectively, with well-fitted calibration curves. DCA showed that the nomogram was clinically useful. STAS-positive patients had significantly worse OS and RFS than STAS-negative patients (both P<0.01). OS and RFS at 5-year for STAS-positive patients were 63.1% and 59.5%, respectively. Multivariate analysis showed that age [hazard ratio (HR), 1.1; 95% confidence interval (CI): 1.035-1.169; P=0.002], diameter (HR, 1.06; 95% CI: 1.04-1.11; P=0.03) and surgical margin (HR, 32.8; 95% CI: 6.8-158.3; P<0.001) were independent risk factors for OS. Adjuvant therapy (HR, 7.345; 95% CI: 2.52-21.41; P<0.001), N stage (N2) (HR, 0.239; 95% CI: 0.069-0.828; P=0.02) and surgical margin (HR, 15.6; 95% CI: 5.9-41.1; P<0.001) were found to be independent risk factors for RFS. Conclusions The outcome of STAS-positive patients was worse. The nomogram incorporating the identified CT features could be applied to facilitate individualized preoperative prediction of STAS and selection of rational therapy.
Collapse
Affiliation(s)
- Yuting Zheng
- Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China
| | - Xiaoyu Han
- Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China
| | - Hanting Li
- Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China
| | - Qinyue Luo
- Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China
| | | | - Kailu Zhang
- Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China
| | - Jun Fan
- Department of Pathology, Union Hospital, Tongji Medical Collage, Huazhong University of Science and Technology, Wuhan, China
| | - Wenjuan Zeng
- Department of Clinical Laboratory, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Heshui Shi
- Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Hubei Province Key Laboratory of Molecular Imaging, Wuhan, China
| |
Collapse
|
4
|
Lin MW, Chen LW, Yang SM, Hsieh MS, Ou DX, Lee YH, Chen JS, Chang YC, Chen CM. CT-Based Deep-Learning Model for Spread-Through-Air-Spaces Prediction in Ground Glass-Predominant Lung Adenocarcinoma. Ann Surg Oncol 2024; 31:1536-1545. [PMID: 37957504 DOI: 10.1245/s10434-023-14565-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2023] [Accepted: 10/22/2023] [Indexed: 11/15/2023]
Abstract
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.
Collapse
Affiliation(s)
- Mong-Wei Lin
- Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan
| | - Li-Wei Chen
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei, Taiwan
| | - Shun-Mao Yang
- Department of Surgery, National Taiwan University Hospital Biomedical Park Hospital, Zhubei City, Hsinchu County, Taiwan
| | - Min-Shu Hsieh
- Department of Pathology, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan
| | - De-Xiang Ou
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei, Taiwan
| | - Yi-Hsuan Lee
- Department of Surgery, National Taiwan University Hospital Biomedical Park Hospital, Zhubei City, Hsinchu County, Taiwan
| | - Jin-Shing Chen
- Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan
- Department of Surgical Oncology, National Taiwan University Cancer Center, Taipei, Taiwan
| | - Yeun-Chung Chang
- Department of Radiology, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan
| | - Chung-Ming Chen
- Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei, Taiwan.
| |
Collapse
|
5
|
Suh YJ, Han K, Kwon Y, Kim H, Lee S, Hwang SH, Kim MH, Shin HJ, Lee CY, Shim HS. Computed Tomography Radiomics for Preoperative Prediction of Spread Through Air Spaces in the Early Stage of Surgically Resected Lung Adenocarcinomas. Yonsei Med J 2024; 65:163-173. [PMID: 38373836 PMCID: PMC10896671 DOI: 10.3349/ymj.2023.0368] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/11/2023] [Revised: 10/19/2023] [Accepted: 10/25/2023] [Indexed: 02/21/2024] Open
Abstract
PURPOSE To assess the added value of radiomics models from preoperative chest CT in predicting the presence of spread through air spaces (STAS) in the early stage of surgically resected lung adenocarcinomas using multiple validation datasets. MATERIALS AND METHODS This retrospective study included 550 early-stage surgically resected lung adenocarcinomas in 521 patients, classified into training, test, internal validation, and temporal validation sets (n=211, 90, 91, and 158, respectively). Radiomics features were extracted from the segmented tumors on preoperative chest CT, and a radiomics score (Rad-score) was calculated to predict the presence of STAS. Diagnostic performance of the conventional model and the combined model, based on a combination of conventional and radiomics features, for the diagnosis of the presence of STAS were compared using the area under the curve (AUC) of the receiver operating characteristic curve. RESULTS Rad-score was significantly higher in the STAS-positive group compared to the STAS-negative group in the training, test, internal, and temporal validation sets. The performance of the combined model was significantly higher than that of the conventional model in the training set {AUC: 0.784 [95% confidence interval (CI): 0.722-0.846] vs. AUC: 0.815 (95% CI: 0.759-0.872), p=0.042}. In the temporal validation set, the combined model showed a significantly higher AUC than that of the conventional model (p=0.001). The combined model showed a higher AUC than the conventional model in the test and internal validation sets, albeit with no statistical significance. CONCLUSION A quantitative CT radiomics model can assist in the non-invasive prediction of the presence of STAS in the early stage of lung adenocarcinomas.
Collapse
Affiliation(s)
- Young Joo Suh
- Department of Radiology, Research Institute of Radiological Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea.
| | - Kyunghwa Han
- Department of Radiology, Research Institute of Radiological Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
| | - Yonghan Kwon
- Department of Biostatistics and Computing, Yonsei University Graduate School, Seoul, Korea
| | - Hwiyoung Kim
- Department of Biomedical System Informatics, Yonsei University College of Medicine, Seoul, Korea
| | - Suji Lee
- Department of Radiology, Research Institute of Radiological Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
| | - Sung Ho Hwang
- Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul, Korea
| | - Myung Hyun Kim
- Department of Radiology, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Korea
| | - Hyun Joo Shin
- Department of Radiology, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Korea
| | - Chang Young Lee
- Thoracic and Cardiovascular Surgery, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
| | - Hyo Sup Shim
- Department of Pathology, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea
| |
Collapse
|
6
|
Jin W, Shen L, Tian Y, Zhu H, Zou N, Zhang M, Chen Q, Dong C, Yang Q, Jiang L, Huang J, Yuan Z, Ye X, Luo Q. Improving the prediction of Spreading Through Air Spaces (STAS) in primary lung cancer with a dynamic dual-delta hybrid machine learning model: a multicenter cohort study. Biomark Res 2023; 11:102. [PMID: 37996894 PMCID: PMC10668492 DOI: 10.1186/s40364-023-00539-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Accepted: 11/05/2023] [Indexed: 11/25/2023] Open
Abstract
BACKGROUND Reliable pre-surgical prediction of spreading through air spaces (STAS) in primary lung cancer is essential for precision treatment and surgical decision-making. We aimed to develop and validate a dual-delta deep-learning and radiomics model based on pretreatment computed tomography (CT) image series to predict the STAS in patients with lung cancer. METHOD Six hundred seventy-four patients with pre-surgery CT follow-up scans (with a minimum interval of two weeks) and primary lung cancer diagnosed by surgery were retrospectively recruited from three Chinese hospitals. The training cohort and internal validation cohort, comprising 509 and 76 patients respectively, were selected from Shanghai Chest Hospital; the external validation cohorts comprised 36 and 53 patients from two other centers, respectively. Four imaging signatures (classic radiomics features and deep learning [DL] features, delta-radiomics and delta-DL features) reflecting the STAS status were constructed from the pretreatment CT images by comprehensive methods including handcrafting, 3D views extraction, image registration and subtraction. A stepwise optimized three-step procedure, including feature extraction (by DL and time-base radiomics slope), feature selection (by reproducibility check and 45 selection algorithms), and classification (32 classifiers considered), was applied for signature building and methodology optimization. The interpretability of the proposed model was further assessed with Grad-CAM for DL-features and feature ranking for radiomics features. RESULTS The dual-delta model showed satisfactory discrimination between STAS and non-STAS and yielded the areas under the receiver operating curve (AUCs) of 0.94 (95% CI, 0.92-0.96), 0.84 (95% CI, 0.82-0.86), and 0.84 (95% CI, 0.83-0.85) in the internal and two external validation cohorts, respectively, with interpretable core feature sets and feature maps. CONCLUSION The coupling of delta-DL model with delta-radiomics features enriches information such as anisotropy of tumor growth and heterogeneous changes within the tumor during the radiological follow-up, which could provide valuable information for STAS prediction in primary lung cancer.
Collapse
Affiliation(s)
- Weiqiu Jin
- Shanghai Lung Cancer Center, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China
| | - Leilei Shen
- Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, 200032, China
- Shanghai Institute of Medical Imaging, Shanghai, 200032, China
- Department of Cancer Center, Zhongshan Hospital, Fudan University, Shanghai, 200032, China
| | - Yu Tian
- Shanghai Lung Cancer Center, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China
| | - Hongda Zhu
- Shanghai Lung Cancer Center, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China
| | - Ningyuan Zou
- Shanghai Lung Cancer Center, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China
| | - Mengwei Zhang
- School of Medicine, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Qian Chen
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Changzi Dong
- Department of Bioengineering, School of Engineering and Science, University of Pennsylvania, Philadelphia, 19104, USA
| | - Qisheng Yang
- School of Integrated Circuits & Beijing National Research On Information Science and Technology (BNRist), Tsinghua University, Beijing, 100084, China
| | - Long Jiang
- Shanghai Lung Cancer Center, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China
| | - Jia Huang
- Shanghai Lung Cancer Center, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China.
| | - Zheng Yuan
- Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200011, China.
| | - Xiaodan Ye
- Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, 200032, China.
- Shanghai Institute of Medical Imaging, Shanghai, 200032, China.
- Department of Cancer Center, Zhongshan Hospital, Fudan University, Shanghai, 200032, China.
- Department of Radiology, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, 200030, China.
| | - Qingquan Luo
- Shanghai Lung Cancer Center, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China.
| |
Collapse
|
7
|
Onozato Y, Iwata T, Uematsu Y, Shimizu D, Yamamoto T, Matsui Y, Ogawa K, Kuyama J, Sakairi Y, Kawakami E, Iizasa T, Yoshino I. Predicting pathological highly invasive lung cancer from preoperative [ 18F]FDG PET/CT with multiple machine learning models. Eur J Nucl Med Mol Imaging 2023; 50:715-726. [PMID: 36385219 PMCID: PMC9852187 DOI: 10.1007/s00259-022-06038-7] [Citation(s) in RCA: 12] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2022] [Accepted: 11/08/2022] [Indexed: 11/18/2022]
Abstract
PURPOSE The efficacy of sublobar resection of primary lung cancer have been proven in recent years. However, sublobar resection for highly invasive lung cancer increases local recurrence. We developed and validated multiple machine learning models predicting pathological invasiveness of lung cancer based on preoperative [18F]fluorodeoxyglucose (FDG) positron emission tomography (PET) and computed tomography (CT) radiomic features. METHODS Overall, 873 patients who underwent lobectomy or segmentectomy for primary lung cancer were enrolled. Radiomics features were extracted from preoperative PET/CT images with the PyRadiomics package. Seven machine learning models and an ensemble of all models (ENS) were evaluated after 100 iterations. In addition, the probability of highly invasive lung cancer was calculated in a nested cross-validation to assess the calibration plot and clinical usefulness and to compare to consolidation tumour ratio (CTR) on CT images, one of the generally used diagnostic criteria. RESULTS In the training set, when PET and CT features were combined, all models achieved an area under the curve (AUC) of ≥ 0.880. In the test set, ENS showed the highest mean AUC of 0.880 and smallest standard deviation of 0.0165, and when the cutoff was 0.5, accuracy of 0.804, F1 of 0.851, precision of 0.821, and recall of 0.885. In the nested cross-validation, the AUC of 0.882 (95% CI: 0.860-0.905) showed a high discriminative ability, and the calibration plot indicated consistency with a Brier score of 0.131. A decision curve analysis showed that the ENS was valid with a threshold probability ranging from 3 to 98%. Accuracy showed an improvement of more than 8% over the CTR. CONCLUSION The machine learning model based on preoperative [18F]FDG PET/CT images was able to predict pathological highly invasive lung cancer with high discriminative ability and stability. The calibration plot showed good consistency, suggesting its usefulness in quantitative risk assessment.
Collapse
Affiliation(s)
- Yuki Onozato
- Division of Thoracic Surgery, Chiba Cancer Centre, 666-2, Nitona-Cho, Chuo-Ku, Chiba, 260-8717 Japan
| | - Takekazu Iwata
- Division of Thoracic Surgery, Chiba Cancer Centre, 666-2, Nitona-Cho, Chuo-Ku, Chiba, 260-8717 Japan
| | - Yasufumi Uematsu
- Division of Thoracic Surgery, Chiba Cancer Centre, 666-2, Nitona-Cho, Chuo-Ku, Chiba, 260-8717 Japan
| | - Daiki Shimizu
- Division of Thoracic Surgery, Chiba Cancer Centre, 666-2, Nitona-Cho, Chuo-Ku, Chiba, 260-8717 Japan
| | - Takayoshi Yamamoto
- Division of Thoracic Surgery, Chiba Cancer Centre, 666-2, Nitona-Cho, Chuo-Ku, Chiba, 260-8717 Japan
| | - Yukiko Matsui
- Division of Thoracic Surgery, Chiba Cancer Centre, 666-2, Nitona-Cho, Chuo-Ku, Chiba, 260-8717 Japan
| | - Kazuyuki Ogawa
- Division of Nuclear Medicine, Chiba Cancer Centre, 666-2, Nitona-Cho, Chuo-Ku, Chiba, 260-8717 Japan
| | - Junpei Kuyama
- Division of Nuclear Medicine, Chiba Cancer Centre, 666-2, Nitona-Cho, Chuo-Ku, Chiba, 260-8717 Japan
| | - Yuichi Sakairi
- Department of General Thoracic Surgery, Chiba University Graduate School of Medicine, Chiba, Japan
| | - Eiryo Kawakami
- Department of Artificial Intelligence Medicine, Chiba University Graduate School of Medicine, Chiba, Japan
| | - Toshihiko Iizasa
- Division of Thoracic Surgery, Chiba Cancer Centre, 666-2, Nitona-Cho, Chuo-Ku, Chiba, 260-8717 Japan
| | - Ichiro Yoshino
- Department of General Thoracic Surgery, Chiba University Graduate School of Medicine, Chiba, Japan
| |
Collapse
|
8
|
Zeng Y, Zhou L, Jia D, Pan B, Li X, Yu Y. Comprehensive analysis for clarifying transcriptomics landscapes of spread through air spaces in lung adenocarcinoma. Front Genet 2022; 13:900864. [PMID: 36072669 PMCID: PMC9441605 DOI: 10.3389/fgene.2022.900864] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2022] [Accepted: 07/19/2022] [Indexed: 11/19/2022] Open
Abstract
Patients with spread through air spaces (STAS) have worse postoperative survival and a higher recurrence rate in lung adenocarcinoma, even in the earliest phases of the disease. At present, the molecular pathogenesis of STAS is not well understood. Therefore, to illustrate the underlying pathogenic mechanism of STAS, we accomplished a comprehensive analysis of a microarray dataset of STAS. Differential expression analysis revealed 841 differentially expressed genes (DEGs) between STAS_positive and STAS_negative groups. Additionally, we acquired two hub genes associated with survival. Gene set variation analysis (GSVA) confirmed that the main differential signaling pathways between the two groups were hypoxia VHL targets, PKC, and pyrimidine metabolism pathways. Analysis of immune activity showed that the increased expression of MHC-class-Ⅰ was observed in the STAS_positive group. These findings provided novel insights for a better knowledge of pathogenic mechanisms and potential therapeutic markers for STAS treatment.
Collapse
Affiliation(s)
- Yuan Zeng
- Department of Medical Oncology, Harbin Medical University Cancer Hospital, Harbin, China
| | - Lingli Zhou
- Department of Respiratory Medicine, Suizhou Hospital, Hubei University of Medicine, Hubei, China
| | - Dexin Jia
- Department of Medical Oncology, Harbin Medical University Cancer Hospital, Harbin, China
| | - Bo Pan
- Department of Medical Oncology, Harbin Medical University Cancer Hospital, Harbin, China
| | - Xiaomei Li
- Department of Pathology, Harbin Medical University Cancer Hospital, Harbin, China
| | - Yan Yu
- Department of Medical Oncology, Harbin Medical University Cancer Hospital, Harbin, China
| |
Collapse
|
9
|
Study on the Relationship between Lung Cancer Stromal Cells and Air Cavity Diffusion Based on an Image Acquisition System. CONTRAST MEDIA & MOLECULAR IMAGING 2022; 2022:2492124. [PMID: 35909590 PMCID: PMC9303510 DOI: 10.1155/2022/2492124] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/20/2022] [Revised: 06/14/2022] [Accepted: 06/17/2022] [Indexed: 11/17/2022]
Abstract
Objective. The study aimed to investigate the role of tumor stromal cells in the pathogenesis of STAS, the relationship between air diffusion (STAS) and tumor stromal cells (TSCs) was studied, and the prognostic significance of TSC and STAS in patients with lung adenocarcinoma was evaluated. Methods. A total of 150 patients with lung cancer diagnosed in the Affiliated Hospital of Jiangsu Province were selected. From the perspective of pathology, medical information technology was used to assist the diagnosis. The data of multiple magnetic resonance images were analyzed by three-dimensional space convolution (CNN), fuzzy neural network (FNN), transfinite learning machine (ELM), and binarization. Result. After data fusion, the specificity and sensitivity of multiple magnetic resonance (MRI) data are significantly higher than those of single MRI data, and the more fusion times, the better the sensitivity and specificity. With the increase in the number of information and data fusion, the proportion of the significant effect and the comprehensive effective rate of patients are on the rise. Multiple MRI data fusion examination and analysis under medical information technology can improve the cure rate of patients, and the 1-year survival rate and the 3-year survival rate of patients have also gradually improved. Conclusion. The MRI data fusion diagnosis method under the application of information technology can improve the sensitivity and specificity of the diagnosis results and comprehensively improve the clinical cure rate and the survival rate at different times of prognosis. In the context of the current big data information age, this multifeature fusion analysis technology is playing a more and more important role in medical treatment. The application of this method and technology not only improves the quality of life of patients but also processes multiple types of data at one time only by using the proposed medical assistant diagnosis model, which can save the diagnosis time to a certain extent. It has effectively realized the medical management and medical service quality and has important promotion significance.
Collapse
|
10
|
Prediction of Nodal Metastasis in Lung Cancer Using Deep Learning of Endobronchial Ultrasound Images. Cancers (Basel) 2022; 14:cancers14143334. [PMID: 35884395 PMCID: PMC9321716 DOI: 10.3390/cancers14143334] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Revised: 06/25/2022] [Accepted: 07/05/2022] [Indexed: 11/16/2022] Open
Abstract
Simple Summary Endobronchial ultrasound-guided transbronchial aspiration is a minimally invasive and highly accurate modality for the diagnosis of lymph node metastasis and is useful for pre-treatment biomarker test sampling in patients with lung cancer. Endobronchial ultrasound image analysis is useful for predicting nodal metastasis; however, it can only be used as a supplemental method to tissue sampling. In recent years, deep learning-based computer-aided diagnosis using artificial intelligence technology has been introduced in research and clinical medicine. This study investigated the feasibility of computer-aided diagnosis for the prediction of nodal metastasis in lung cancer using endobronchial ultrasound images. The outcome of this study may help improve diagnostic efficiency and reduce invasiveness of the procedure. Abstract Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a valid modality for nodal lung cancer staging. The sonographic features of EBUS helps determine suspicious lymph nodes (LNs). To facilitate this use of this method, machine-learning-based computer-aided diagnosis (CAD) of medical imaging has been introduced in clinical practice. This study investigated the feasibility of CAD for the prediction of nodal metastasis in lung cancer using endobronchial ultrasound images. Image data of patients who underwent EBUS-TBNA were collected from a video clip. Xception was used as a convolutional neural network to predict the nodal metastasis of lung cancer. The prediction accuracy of nodal metastasis through deep learning (DL) was evaluated using both the five-fold cross-validation and hold-out methods. Eighty percent of the collected images were used in five-fold cross-validation, and all the images were used for the hold-out method. Ninety-one patients (166 LNs) were enrolled in this study. A total of 5255 and 6444 extracted images from the video clip were analyzed using the five-fold cross-validation and hold-out methods, respectively. The prediction of LN metastasis by CAD using EBUS images showed high diagnostic accuracy with high specificity. CAD during EBUS-TBNA may help improve the diagnostic efficiency and reduce invasiveness of the procedure.
Collapse
|
11
|
Huang L, Tang L, Dai L, Shi Y. The prognostic significance of tumor spread through air space in stage I lung adenocarcinoma. Thorac Cancer 2022; 13:997-1005. [PMID: 35174646 PMCID: PMC8977166 DOI: 10.1111/1759-7714.14348] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2021] [Revised: 01/24/2022] [Accepted: 01/25/2022] [Indexed: 12/25/2022] Open
Abstract
AIM There are still patients of stage I lung adenocarcinoma (ADC) suffering from local or distant recurrence. Herein we conducted a meta-analysis to investigate the prognostic value of tumor spread through air space (STAS), a new form of invasion pattern, in patients with pathologically confirmed stage I lung ADC. METHODS Related literature was searched using PubMed, Embase, Cochrane Library, and Web of Science databases from the inception dates to September 4, 2021. Recurrence-free survival (RFS) and overall survival (OS) were set as primary outcome endpoints. In addition, subgroup analyses on operation mode, edition of the American Joint Committee on Cancer TNM staging, sample size, and research regions were also investigated. RESULTS A total of 17 studies involving 9785 patients were included. The presence of STAS was detected in 31.2% of patients and was associated with poor RFS (adjusted hazard ratio [HR] = 1.93, p < 0.001) and OS (HR = 2.02, p < 0.001). In subgroup analysis on operation mode, the prognostic value of STAS was prominently shown in patients who underwent limited resection (RFS: HR = 3.58, p < 0.001; OS: HR = 3.37, p < 0.001), while for patients who underwent lobectomy, adverse impact of STAS on RFS was observed (HR = 1.60, p = 0.019), but no significant difference was observed on OS (HR = 1.56, p = 0.061). The results fluctuated in different regions while other factors did not alter the independent predictive value of STAS. CONCLUSION Tumor STAS should be considered as an adverse prognostic indicator for patients with stage I lung ADC, especially for those under limited resection. More intensive medical care for those patients needs to be investigated in further studies.
Collapse
Affiliation(s)
- Liling Huang
- Department of Medical OncologyNational Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing Key Laboratory of Clinical Study on Anticancer Molecular Targeted DrugsBeijingChina
| | - Le Tang
- Department of Medical OncologyNational Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing Key Laboratory of Clinical Study on Anticancer Molecular Targeted DrugsBeijingChina
| | - Liyuan Dai
- Department of Clinical LaboratoryNational Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing Key Laboratory of Clinical Study on Anticancer Molecular Targeted DrugsBeijingChina
| | - Yuankai Shi
- Department of Medical OncologyNational Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing Key Laboratory of Clinical Study on Anticancer Molecular Targeted DrugsBeijingChina
| |
Collapse
|
12
|
Fan L, He P. [Research Progress on Spread Through Air Spaces of Lung Cancer]. ZHONGGUO FEI AI ZA ZHI = CHINESE JOURNAL OF LUNG CANCER 2022; 25:54-60. [PMID: 34937151 PMCID: PMC8796127 DOI: 10.3779/j.issn.1009-3419.2021.101.49] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 01/01/2023]
Abstract
The concept of spread through air spaces (STAS) was first proposed in the World Health Organization (WHO) Classification of Tumors of the Lung, Pleura, Thymus and Heart (version 2015). STAS is defined as the micropapillary clusters, solid nests or single cells of tumor that exist in the air spaces of the surrounding lung parenchyma beyond the edge of the main tumor. Meanwhile, apart from the traditional invasion modes of lung adenocarcinoma (interstitial, visceral pleura and lym-phovascular invasion), STAS has been identified as the fourth invasion mode of lung adenocarcinoma. In recent years, the research on STAS has been a hot spot in the field of lung adenocarcinoma. The existence of STAS is related to lung cancer histopathology, gene mutation and other factors, and many studies have also confirmed that it can be used as an independent factor for tumor recurrence and prognosis. However, according to some studies, human factors can cause morphological artifacts of STAS, which still needs to be distinguished in clinical work. This paper reviews the research progress of STAS classification, related pathological features, genetic status changes, and human factors that may cause STAS artifacts.
.
Collapse
Affiliation(s)
- Lei Fan
- Department of Pathology, First Affiliated Hospital of Guangzhou Medical University, Guangzhou 510120, China
| | - Ping He
- Department of Pathology, First Affiliated Hospital of Guangzhou Medical University, Guangzhou 510120, China
| |
Collapse
|
13
|
Bompoti A, Papazoglou AS, Moysidis DV, Otountzidis N, Karagiannidis E, Stalikas N, Panteris E, Ganesh V, Sanctuary T, Arvanitidis C, Sianos G, Michaelson JS, Herrmann MD. Volumetric Imaging of Lung Tissue at Micrometer Resolution: Clinical Applications of Micro-CT for the Diagnosis of Pulmonary Diseases. Diagnostics (Basel) 2021; 11:diagnostics11112075. [PMID: 34829422 PMCID: PMC8625264 DOI: 10.3390/diagnostics11112075] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2021] [Revised: 11/04/2021] [Accepted: 11/05/2021] [Indexed: 11/16/2022] Open
Abstract
Micro-computed tomography (micro-CT) is a promising novel medical imaging modality that allows for non-destructive volumetric imaging of surgical tissue specimens at high spatial resolution. The aim of this study is to provide a comprehensive assessment of the clinical applications of micro-CT for the tissue-based diagnosis of lung diseases. This scoping review was conducted in accordance with the PRISMA Extension for Scoping Reviews, aiming to include every clinical study reporting on micro-CT imaging of human lung tissues. A literature search yielded 570 candidate articles, out of which 37 were finally included in the review. Of the selected studies, 9 studies explored via micro-CT imaging the morphology and anatomy of normal human lung tissue; 21 studies investigated microanatomic pulmonary alterations due to obstructive or restrictive lung diseases, such as chronic obstructive pulmonary disease, idiopathic pulmonary fibrosis, and cystic fibrosis; and 7 studies examined the utility of micro-CT imaging in assessing lung cancer lesions (n = 4) or in transplantation-related pulmonary alterations (n = 3). The selected studies reported that micro-CT could successfully detect several lung diseases providing three-dimensional images of greater detail and resolution than routine optical slide microscopy, and could additionally provide valuable volumetric insight in both restrictive and obstructive lung diseases. In conclusion, micro-CT-based volumetric measurements and qualitative evaluations of pulmonary tissue structures can be utilized for the clinical management of a variety of lung diseases. With micro-CT devices becoming more accessible, the technology has the potential to establish itself as a core diagnostic imaging modality in pathology and to enable integrated histopathologic and radiologic assessment of lung cancer and other lung diseases.
Collapse
Affiliation(s)
- Andreana Bompoti
- Department of Radiology, Peterborough City Hospital, Northwest Anglia NHS Foundation Trust, Peterborough PE3 9GZ, UK;
| | - Andreas S. Papazoglou
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, Greece; (A.S.P.); (D.V.M.); (N.O.); (E.K.); (N.S.); (G.S.)
| | - Dimitrios V. Moysidis
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, Greece; (A.S.P.); (D.V.M.); (N.O.); (E.K.); (N.S.); (G.S.)
| | - Nikolaos Otountzidis
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, Greece; (A.S.P.); (D.V.M.); (N.O.); (E.K.); (N.S.); (G.S.)
| | - Efstratios Karagiannidis
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, Greece; (A.S.P.); (D.V.M.); (N.O.); (E.K.); (N.S.); (G.S.)
| | - Nikolaos Stalikas
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, Greece; (A.S.P.); (D.V.M.); (N.O.); (E.K.); (N.S.); (G.S.)
| | - Eleftherios Panteris
- Biomic_AUTh, Center for Interdisciplinary Research and Innovation (CIRI-AUTH), Balkan Center B1.4, 10th km Thessaloniki-Thermi Rd., P.O. Box 8318, GR 57001 Thessaloniki, Greece;
| | | | - Thomas Sanctuary
- Respiratory Department, Medway NHS Foundation Trust, Kent ME7 5NY, UK;
| | - Christos Arvanitidis
- Hellenic Centre for Marine Research (HCMR), Institute of Marine Biology, Biotechnology and Aquaculture (IMBBC), 70013 Heraklion, Greece;
- LifeWatch ERIC, Sector II-II, Plaza de España, 41071 Seville, Spain
| | - Georgios Sianos
- First Department of Cardiology, AHEPA University Hospital, Aristotle University of Thessaloniki, St. Kiriakidi 1, 54636 Thessaloniki, Greece; (A.S.P.); (D.V.M.); (N.O.); (E.K.); (N.S.); (G.S.)
| | - James S. Michaelson
- Department of Pathology, Massachusetts General Hospital, Boston, MA 02114, USA;
| | - Markus D. Herrmann
- Department of Pathology, Massachusetts General Hospital, Boston, MA 02114, USA;
- Correspondence: ; Tel.: +6-17-724-1896
| |
Collapse
|