1
|
Ai J, Wang Z, Ai S, Li H, Gao H, Shi G, Hu S, Liu L, Zhao L, Wei Y. Development and Validation of a CT-Radiomics Nomogram for the Diagnosis of Small Prevascular Mediastinal Nodules: Reducing Nontherapeutic Surgeries. Acad Radiol 2024:S1076-6332(24)00471-9. [PMID: 39107185 DOI: 10.1016/j.acra.2024.07.037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2024] [Revised: 07/16/2024] [Accepted: 07/19/2024] [Indexed: 08/09/2024]
Abstract
RATIONALE AND OBJECTIVES The preoperative diagnosis of small prevascular mediastinal nodules (SPMNs) presents a challenge, often leading to unnecessary surgical interventions. Our objective was to develop a nomogram based on preoperative CT-radiomics features, serving as a non-invasive diagnostic tool for SPMNs. MATERIALS AND METHODS Patients with surgically resected SPMNs from two medical centers between January 2018 and December 2022 were retrospectively reviewed. Radiomics features were extracted and screened from preoperative CT images. Logistic regression was employed to establish clinical, radiomics, and hybrid models for differentiating thymic epithelial tumors (TETs) from cysts. The performance of these models was validated in both internal and external test sets by area under the receiver operating characteristic curve (AUC), while also comparing their diagnostic capability with human experts. RESULTS The study enrolled a total of 363 patients (median age, 53 years [IQR:45-59 years]; 175 [48.2%] males) for model development and validation, including 136 TETs and 227 cysts. Lesions' enhancement status, shape, calcification, and rad-score were identified as independent factors for distinction. The hybrid model demonstrated superior diagnostic performance compared to other models and human experts, with an AUC of 0.95 (95% CI:0.92-0.98), 0.94 (95% CI:0.89-0.99), and 0.93 (95% CI:0.83-1.00) in the training set, internal test set, and external test set respectively. The calibration curve of the model demonstrated excellent fit, while decision curve analysis underscored its clinical value. CONCLUSION The radiomics-based nomogram effectively discriminates between the most prevalent types of SPMNs, namely TETs and cysts, thus presenting a promising tool for treatment guidance.
Collapse
Affiliation(s)
- Jiangshan Ai
- Department of Thoracic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Zhaofeng Wang
- Department of Thoracic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Shiwen Ai
- Department of Thoracic Surgery, Affiliated Hospital of Jining Medical University, Jining, China
| | - Hengyan Li
- Department of Radiology, Affiliated Hospital of Jining Medical University, Jining, China
| | - Huijiang Gao
- Department of Thoracic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Guodong Shi
- Department of Thoracic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Shiyu Hu
- Department of Thoracic Surgery, Qilu Hospital of Shandong University (Qingdao), Qingdao, China
| | - Lin Liu
- Department of Thoracic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Lianzheng Zhao
- Department of Thoracic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Yucheng Wei
- Department of Thoracic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China.
| |
Collapse
|
2
|
Tan XZ, Ma R, Liu P, Xiao CH, Zhang HH, Yang F, Liang CH, Liu ZY. Decoding tumor stage by peritumoral and intratumoral radiomics in resectable esophageal squamous cell carcinoma. Abdom Radiol (NY) 2024; 49:301-311. [PMID: 37831168 PMCID: PMC10789665 DOI: 10.1007/s00261-023-04061-2] [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: 07/03/2023] [Revised: 09/10/2023] [Accepted: 09/11/2023] [Indexed: 10/14/2023]
Abstract
PURPOSE To evaluate the potential application of radiomics in predicting Tumor-Node-Metastasis (TNM) stage in patients with resectable esophageal squamous cell carcinoma (ESCC). METHODS This retrospective study included 122 consecutive patients (mean age, 57 years; 27 women). Corresponding tumor of interest was identified on axial arterial-phase CT images with manual annotation. Radiomics features were extracted from intra- and peritumoral regions. Features were pruned to train LASSO regression model with 93 patients to construct a radiomics signature, whose performance was validated in a test set of 29 patients. Prognostic value of radiomics-predicted TNM stage was estimated by survival analysis in the entire cohort. RESULTS The radiomics signature incorporating one intratumoral and four peritumoral features was significantly associated with TNM stage. This signature discriminated tumor stage with an area under curve (AUC) of 0.823 in the training set, with similar performance in the test set (AUC 0.813). Recurrence-free survival (RFS) was significantly different between different radiomics-predicted TNM stage groups (Low-risk vs high-risk, log-rank P = 0.004). Univariate and multivariate Cox regression analyses revealed that radiomics-predicted TNM stage was an independent preoperative factor for RFS. CONCLUSIONS The proposed radiomics signature combing intratumoral and peritumoral features was predictive of TNM stage and associated with prognostication in ESCC.
Collapse
Affiliation(s)
- Xian-Zheng Tan
- Department of Radiology, Hunan Provincial People's Hospital (The First Affiliated Hospital of Hunan Normal University), Changsha, 410005, Hunan, China.
| | - Rong Ma
- Department of Radiology, Hunan Provincial People's Hospital (The First Affiliated Hospital of Hunan Normal University), Changsha, 410005, Hunan, China
| | - Peng Liu
- Department of Radiology, Hunan Provincial People's Hospital (The First Affiliated Hospital of Hunan Normal University), Changsha, 410005, Hunan, China
| | - Chang-Hui Xiao
- Department of Radiology, The First People's Hospital of Changde City, Changde, 415000, Hunan, China
| | - Hui-Hui Zhang
- Department of Radiology, Hunan Provincial People's Hospital (The First Affiliated Hospital of Hunan Normal University), Changsha, 410005, Hunan, China
| | - Fan Yang
- Department of Radiology, Hunan Provincial People's Hospital (The First Affiliated Hospital of Hunan Normal University), Changsha, 410005, Hunan, China
| | - Chang-Hong Liang
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, 510180, Guangdong, China.
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, 510180, Guangdong, China.
| | - Zai-Yi Liu
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, 510180, Guangdong, China.
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, 510180, Guangdong, China.
| |
Collapse
|
3
|
Akamine T, Nakagawa K, Ito K, Watanabe H, Yotsukura M, Yoshida Y, Yatabe Y, Kusumoto M, Watanabe SI. Impact of 18F-FDG PET on TNM Staging and Prognosis in Thymic Epithelial Tumors. Ann Surg Oncol 2024; 31:192-200. [PMID: 37743455 DOI: 10.1245/s10434-023-14328-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2023] [Accepted: 09/01/2023] [Indexed: 09/26/2023]
Abstract
BACKGROUND Preoperative fluorine-18-fluorodeoxyglucose positron emission tomography (18F-FDG PET) of thymic epithelial tumors (TETs) is well known for identifying malignant-grade TETs; however, its predictive power for determining locally advanced tumors, lymph node (LN) metastasis, and prognosis remains unknown. PATIENTS AND METHODS We retrospectively evaluated patients with resectable TETs who were preoperatively assessed using 18F-FDG PET from January 2012 to January 2023. The receiver operating characteristic curve was used to evaluate the cutoff value of the maximum standardized uptake value (SUVmax) to predict advanced-stage disease. Recurrence/progression-free survival (RFS/PFS) was analyzed using the Kaplan-Meier method. The staging was classified according to the tumor-node-metastasis system. RESULTS Our study included 177 patients; 145 (81.9%) had pathological early-stage TET (stage I or II), and 32 (19.1%) had advanced stage (stage III or IV). The area under the curve value for predicting the advanced stage was 0.903, and the cutoff value was 5.6 (sensitivity 81.3%, specificity 84.8%). SUVmax > 5.6 was associated with worse prognosis for RFS/PFS. LN metastasis was preoperatively detected by FDG uptake in 30.8% of patients with pathological LN positivity, whereas LN metastasis was not pathologically detected in patients with SUVmax < 5.9. In patients with advanced-stage TETs, LN recurrence was more frequent in patients who were preoperatively detected by 18F-FDG PET than those who were not (75.0% versus 7.1%). CONCLUSIONS 18F-FDG PET is a potentially valuable tool for predicting advanced stage and poor prognosis of recurrence in patients with TETs. SUVmax can help thoracic surgeons to guide them in selecting appropriate therapeutic strategies for TETs.
Collapse
Affiliation(s)
- Takaki Akamine
- Departments of Thoracic Surgery, National Cancer Center Hospital, Tokyo, Japan
| | - Kazuo Nakagawa
- Departments of Thoracic Surgery, National Cancer Center Hospital, Tokyo, Japan.
| | - Kimiteru Ito
- Departments of Diagnostic Radiology, National Cancer Center Hospital, Tokyo, Japan
| | - Hirokazu Watanabe
- Departments of Diagnostic Radiology, National Cancer Center Hospital, Tokyo, Japan
| | - Masaya Yotsukura
- Departments of Thoracic Surgery, National Cancer Center Hospital, Tokyo, Japan
| | - Yukihiro Yoshida
- Departments of Thoracic Surgery, National Cancer Center Hospital, Tokyo, Japan
| | - Yasushi Yatabe
- Departments of Diagnostic Pathology, National Cancer Center Hospital, Tokyo, Japan
| | - Masahiko Kusumoto
- Departments of Diagnostic Radiology, National Cancer Center Hospital, Tokyo, Japan
| | - Shun-Ichi Watanabe
- Departments of Thoracic Surgery, National Cancer Center Hospital, Tokyo, Japan
| |
Collapse
|
4
|
Lu XF, Zhu TY. Diagnostic performance of radiomics model for preoperative risk categorization in thymic epithelial tumors: a systematic review and meta-analysis. BMC Med Imaging 2023; 23:115. [PMID: 37644397 PMCID: PMC10466844 DOI: 10.1186/s12880-023-01083-6] [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: 03/15/2023] [Accepted: 08/21/2023] [Indexed: 08/31/2023] Open
Abstract
BACKGROUND Incidental thymus region masses during thoracic examinations are not uncommon. The clinician's decision-making for treatment largely depends on imaging findings. Due to the lack of specific indicators, it may be of great value to explore the role of radiomics in risk categorization of the thymic epithelial tumors (TETs). METHODS Four databases (PubMed, Web of Science, EMBASE and the Cochrane Library) were screened to identify eligible articles reporting radiomics models of diagnostic performance for risk categorization in TETs patients. The quality assessment of diagnostic accuracy studies 2 (QUADAS-2) and radiomics quality score (RQS) were used for methodological quality assessment. The pooled area under the receiver operating characteristic curve (AUC), sensitivity and specificity with their 95% confidence intervals were calculated. RESULTS A total of 2134 patients in 13 studies were included in this meta-analysis. The pooled AUC of 11 studies reporting high/low-risk histologic subtypes was 0.855 (95% CI, 0.817-0.893), while the pooled AUC of 4 studies differentiating stage classification was 0.826 (95% CI, 0.817-0.893). Meta-regression revealed no source of significant heterogeneity. Subgroup analysis demonstrated that the best diagnostic imaging was contrast enhanced computer tomography (CECT) with largest pooled AUC (0.873, 95% CI 0.832-0.914). Publication bias was found to be no significance by Deeks' funnel plot. CONCLUSIONS This present study shows promise for preoperative selection of high-risk TETs patients based on radiomics signatures with current available evidence. However, methodological quality in further studies still needs to be improved for feasibility confirmation and clinical application of radiomics-based models in predicting risk categorization of the thymic epithelial tumors.
Collapse
Affiliation(s)
- Xue-Fang Lu
- Dept. of Radiology, Renmin Hospital of Wuhan University, Wuhan, 430060, Hubei, P.R. China
| | - Tie-Yuan Zhu
- Dept. of Thoracic Surgery, Renmin Hospital of Wuhan University, No. 238 Jiefang Road, Wuchang District, Wuhan, 430060, Hubei, P.R. China.
| |
Collapse
|
5
|
Tartarone A, Lerose R, Lettini AR, Tartarone M. Current Treatment Approaches for Thymic Epithelial Tumors. Life (Basel) 2023; 13:life13051170. [PMID: 37240815 DOI: 10.3390/life13051170] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Revised: 05/07/2023] [Accepted: 05/09/2023] [Indexed: 05/28/2023] Open
Abstract
Thymic epithelial tumors (TETs), including thymoma, thymic carcinoma and neuroendocrine tumors, are uncommon tumors that originate from the epithelial cells of the thymus. Nevertheless, despite their rarity, they represent the most common tumor type located in the anterior mediastinum. Therapeutic choices based on staging and histology may include surgery with or without neoadjuvant or adjuvant therapy represented by chemotherapy, radiotherapy or chemo-radiotherapy. For patients with advanced or metastatic TETs, platinum-based chemotherapy remains the standard first-line treatment; however, some new drugs and combinations are currently under evaluation. In any case, proper management of patients with TETs requires a multidisciplinary team approach to personalize care for each patient.
Collapse
Affiliation(s)
- Alfredo Tartarone
- Department of Onco-Hematology, Division of Medical Oncology, IRCCS-CROB Referral Cancer Center of Basilicata, 85028 Rionero in Vulture, Italy
| | - Rosa Lerose
- Hospital Pharmacy, IRCCS-CROB Referral Cancer Center of Basilicata, 85028 Rionero in Vulture, Italy
| | - Alessandro Rocco Lettini
- Unit of Clinical Psychology, IRCCS-CROB Referral Cancer Center of Basilicata, 85028 Rionero in Vulture, Italy
| | | |
Collapse
|
6
|
Mayoral M, Pagano AM, Araujo-Filho JAB, Zheng J, Perez-Johnston R, Tan KS, Gibbs P, Fernandes Shepherd A, Rimner A, Simone II CB, Riely G, Huang J, Ginsberg MS. Conventional and radiomic features to predict pathology in the preoperative assessment of anterior mediastinal masses. Lung Cancer 2023; 178:206-212. [PMID: 36871345 PMCID: PMC10544811 DOI: 10.1016/j.lungcan.2023.02.014] [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: 10/04/2022] [Revised: 01/14/2023] [Accepted: 02/19/2023] [Indexed: 02/23/2023]
Abstract
OBJECTIVES The aim of this study was to differentiate benign from malignant tumors in the anterior mediastinum based on computed tomography (CT) imaging characteristics, which could be useful in preoperative planning. Additionally, our secondary aim was to differentiate thymoma from thymic carcinoma, which could guide the use of neoadjuvant therapy. MATERIALS AND METHODS Patients referred for thymectomy were retrospectively selected from our database. Twenty-five conventional characteristics were evaluated by visual analysis, and 101 radiomic features were extracted from each CT. In the step of model training, we applied support vector machines to train classification models. Model performance was assessed using the area under the receiver operating curves (AUC). RESULTS Our final study sample comprised 239 patients, 59 (24.7 %) with benign mediastinal lesions and 180 (75.3 %) with malignant thymic tumors. Among the malignant masses, there were 140 (58.6 %) thymomas, 23 (9.6 %) thymic carcinomas, and 17 (7.1 %) non-thymic lesions. For the benign versus malignant differentiation, the model that integrated both conventional and radiomic features achieved the highest diagnostic performance (AUC = 0.715), in comparison to the conventional (AUC = 0.605) and radiomic-only (AUC = 0.678) models. Similarly, regarding thymoma versus thymic carcinoma differentiation, the model that integrated both conventional and radiomic features also achieved the highest diagnostic performance (AUC = 0.810), in comparison to the conventional (AUC = 0.558) and radiomic-only (AUC = 0.774) models. CONCLUSION CT-based conventional and radiomic features with machine learning analysis could be useful for predicting pathologic diagnoses of anterior mediastinal masses. The diagnostic performance was moderate for differentiating benign from malignant lesions and good for differentiating thymomas from thymic carcinomas. The best diagnostic performance was achieved when both conventional and radiomic features were integrated in the machine learning algorithms.
Collapse
Affiliation(s)
- Maria Mayoral
- Department of Radiology. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA; Medical Imaging Department. Hospital Clinic of Barcelona, 170 Villarroel street, Barcelona 08036, Spain.
| | - Andrew M Pagano
- Department of Radiology. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| | - Jose Arimateia Batista Araujo-Filho
- Department of Radiology. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA; Department of Radiology. Hospital Sirio-Libanes, 91 Dona Adma Jafet street, São Paulo 01308-050, Brazil
| | - Junting Zheng
- Department of Epidemiology and Biostatistics. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| | - Rocio Perez-Johnston
- Department of Radiology. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| | - Kay See Tan
- Department of Epidemiology and Biostatistics. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| | - Peter Gibbs
- Department of Radiology. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| | - Annemarie Fernandes Shepherd
- Department of Radiation Oncology. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| | - Andreas Rimner
- Department of Radiation Oncology. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| | - Charles B Simone II
- Department of Radiation Oncology. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| | - Gregory Riely
- Department of Surgery. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| | - James Huang
- Department of Surgery. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| | - Michelle S Ginsberg
- Department of Radiology. Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065, USA
| |
Collapse
|
7
|
Zheng SJ, Zheng CP, Zhai TT, Xu XE, Zheng YQ, Li ZM, Li EM, Liu W, Xu LY. Development and Validation of a New Staging System for Esophageal Squamous Cell Carcinoma Patients Based on Combined Pathological TNM, Radiomics, and Proteomics. Ann Surg Oncol 2023; 30:2227-2241. [PMID: 36587172 DOI: 10.1245/s10434-022-13026-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2022] [Accepted: 12/06/2022] [Indexed: 01/02/2023]
Abstract
OBJECTIVE This study aimed to construct a new staging system for patients with esophageal squamous cell carcinoma (ESCC) based on combined pathological TNM (pTNM) stage, radiomics, and proteomics. METHODS This study collected patients with radiomics and pTNM stage (Cohort 1, n = 786), among whom 103 patients also had proteomic data (Cohort 2, n = 103). The Cox regression model with the least absolute shrinkage and selection operator, and the Cox proportional hazards model were used to construct a nomogram and predictive models. Concordance index (C-index) and the integrated area under the time-dependent receiver operating characteristic (ROC) curve (IAUC) were used to evaluate the predictive models. The corresponding staging systems were further assessed using Kaplan-Meier survival curves. RESULTS For Cohort 1, the RadpTNM4c staging systems, constructed based on combined pTNM stage and radiomic features, outperformed the pTNM4c stage in both the training dataset 1 (Train1; IAUC 0.711 vs. 0.706, p < 0.001) and the validation dataset 1 (Valid1; IAUC 0.695 vs. 0.659, p < 0.001; C-index 0.703 vs. 0.674, p = 0.029). For Cohort 2, the ProtRadpTNM2c staging system, constructed based on combined pTNM stage, radiomics, and proteomics, outperformed the pTNM2c stage in both the Train2 (IAUC 0.777 vs. 0.610, p < 0.001; C-index 0.898 vs. 0.608, p < 0.001) and Valid2 (IAUC 0.746 vs. 0.608, p < 0.001; C-index 0.889 vs. 0.641, p = 0.009) datasets. CONCLUSIONS The ProtRadpTNM2c staging system, based on combined pTNM stage, radiomic, and proteomic features, improves the predictive performance of the classical pTNM staging system.
Collapse
Affiliation(s)
- Shao-Jun Zheng
- Guangdong Provincial Key Laboratory of Infectious Diseases and Molecular Immunopathology, Institute of Oncologic Pathology, Cancer Research Center, Shantou University Medical College, Shantou, 515041, Guangdong, China
- Department of Surgical Oncology, Shantou Central Hospital, Shantou, 515041, Guangdong, China
| | - Chun-Peng Zheng
- Department of Surgical Oncology, Shantou Central Hospital, Shantou, 515041, Guangdong, China.
| | - Tian-Tian Zhai
- Department of Radiation Oncology, Cancer Hospital of Shantou University Medical College, Shantou, 515041, Guangdong, China
| | - Xiu-E Xu
- Guangdong Provincial Key Laboratory of Infectious Diseases and Molecular Immunopathology, Institute of Oncologic Pathology, Cancer Research Center, Shantou University Medical College, Shantou, 515041, Guangdong, China
| | - Ya-Qi Zheng
- Guangdong Provincial Key Laboratory of Infectious Diseases and Molecular Immunopathology, Institute of Oncologic Pathology, Cancer Research Center, Shantou University Medical College, Shantou, 515041, Guangdong, China
| | - Zhi-Mao Li
- Guangdong Provincial Key Laboratory of Infectious Diseases and Molecular Immunopathology, Institute of Oncologic Pathology, Cancer Research Center, Shantou University Medical College, Shantou, 515041, Guangdong, China
| | - En-Min Li
- The Key Laboratory of Molecular Biology for High Cancer Incidence Coastal Chaoshan Area, Department of Biochemistry and Molecular Biology, Shantou University Medical College, Shantou, 515041, Guangdong, China
| | - Wei Liu
- College of Science, Heilongjiang Institute of Technology, Harbin, Heilongjiang, China
| | - Li-Yan Xu
- Guangdong Provincial Key Laboratory of Infectious Diseases and Molecular Immunopathology, Institute of Oncologic Pathology, Cancer Research Center, Shantou University Medical College, Shantou, 515041, Guangdong, China
| |
Collapse
|
8
|
Machine learning-based radiomic computed tomography phenotyping of thymic epithelial tumors: Predicting pathological and survival outcomes. J Thorac Cardiovasc Surg 2023; 165:502-516.e9. [PMID: 36038386 DOI: 10.1016/j.jtcvs.2022.05.046] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/07/2022] [Revised: 05/01/2022] [Accepted: 05/09/2022] [Indexed: 01/18/2023]
Abstract
OBJECTIVE For patients with thymic epithelial tumors, accurately predicting clinicopathological outcomes remains challenging. We aimed to investigate the performance of machine learning-based radiomic computed tomography phenotyping for predicting pathological (World Health Organization [WHO] type and TNM stage) and survival outcomes (overall and progression-free survival) in patients with thymic epithelial tumors. METHODS This retrospective study included patients with thymic epithelial tumors between January 2001 and January 2022. The radiomic features were extracted from preoperative unenhanced computed tomography images. After strict feature selection, random forest and random survival forest models were fitted to predict pathological and survival outcomes, respectively. The model performance was assessed by the area under the curve (AUC) and validated internally by the bootstrap method. RESULTS In total, 124 patients with a median age of 61 years were included. The radiomics random forest models of WHO type and TNM stage showed satisfactory performance with an AUCWHO of 0.898 (95% CI, 0.753-1.000) and an AUCTNM of 0.766 (95% CI, 0.642-0.886). For overall survival and progression-free survival prediction, the radiomics random survival forest models showed good performance (integrated AUCs, 0.923; 95% CI, 0.691-1.000 and 0.702; 95% CI, 0.513-0.875, respectively), and the integrated AUCs increased to 0.935 (95% CI, 0.705-1.000) and 0.811 (95% CI, 0.647-0.942), respectively, when combined with clinicopathological features. CONCLUSIONS Machine learning-based radiomic computed tomography phenotyping might allow for the satisfactory prediction of pathological and survival outcomes and further improve prognostic performance when integrated with clinicopathological features in patients with thymic epithelial tumors.
Collapse
|
9
|
Yu K, Ying J, Zhao T, Lei L, Zhong L, Hu J, Zhou JW, Huang C, Zhang X. Prediction model for knee osteoarthritis using magnetic resonance-based radiomic features from the infrapatellar fat pad: data from the osteoarthritis initiative. Quant Imaging Med Surg 2023; 13:352-369. [PMID: 36620171 PMCID: PMC9816749 DOI: 10.21037/qims-22-368] [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: 04/16/2022] [Accepted: 10/31/2022] [Indexed: 11/21/2022]
Abstract
Background The infrapatellar fat pad (IPFP) plays an important role in the incidence of knee osteoarthritis (OA). Magnetic resonance (MR) signal heterogeneity of the IPFP is related to pathologic changes. In this study, we aimed to investigate whether the IPFP radiomic features have predictive value for incident radiographic knee OA (iROA) 1 year prior to iROA diagnosis. Methods Data used in this work were obtained from the osteoarthritis initiative (OAI). In this study, iROA was defined as a knee with a baseline Kellgren-Lawrence grade (KLG) of 0 or 1 that further progressed to KLG ≥2 during the follow-up visit. Intermediate-weighted turbo spin-echo knee MR images at the time of iROA diagnosis and 1 year prior were obtained. Five clinical characteristics-age, sex, body mass index, knee injury history, and knee surgery history-were obtained. A total of 604 knees were selected and matched (302 cases and 302 controls). A U-Net segmentation model was independently trained to automatically segment the IPFP. The prediction models were established in the training set (60%). Three main models were generated using (I) clinical characteristics; (II) radiomic features; (III) combined (clinical plus radiomic) features. Model performance was evaluated in an independent testing set (remaining 40%) using the area under the curve (AUC). Two secondary models were also generated using Hoffa-synovitis scores and clinical characteristics. Results The comparison between the automated and manual segmentations of the IPFP achieved a Dice coefficient of 0.900 (95% CI: 0.891-0.908), which was comparable to that of experienced radiologists. The radiomic features model and the combined model yielded superior AUCs of 0.700 (95% CI: 0.630-0.763) and 0.702 (95% CI: 0.635-0.763), respectively. The DeLong test found no statistically significant difference between the receiver operating curves of the radiomic and combined models (P=0.831); however, both models outperformed the clinical model (P=0.014 and 0.004, respectively). Conclusions Our results demonstrated that radiomic features of the IPFP are predictive of iROA 1 year prior to the diagnosis, suggesting that IPFP radiomic features can serve as an early quantitative prediction biomarker of iROA.
Collapse
Affiliation(s)
- Keyan Yu
- Department of Medical Imaging, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics Guangdong Province), Guangzhou, China;,Department of Radiology, Peking University Shenzhen Hospital, Shenzhen, China
| | - Jia Ying
- Department of Biomedical Engineering, Stony Brook University, Stony Brook, NY, USA
| | - Tianyun Zhao
- Department of Biomedical Engineering, Stony Brook University, Stony Brook, NY, USA
| | - Lan Lei
- Program in Public Health, Stony Brook Medicine, Stony Brook, NY, USA;,Department of Medicine, Northside Hospital Gwinnett, Lawrenceville, GA, USA
| | - Lijie Zhong
- Department of Medical Imaging, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics Guangdong Province), Guangzhou, China
| | - Jiaping Hu
- Department of Medical Imaging, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics Guangdong Province), Guangzhou, China
| | - Juin W. Zhou
- Department of Biomedical Engineering, Stony Brook University, Stony Brook, NY, USA
| | - Chuan Huang
- Department of Biomedical Engineering, Stony Brook University, Stony Brook, NY, USA;,Department of Radiology, Stony Brook Medicine, Stony Brook, NY, USA;,Department of Psychiatry, Stony Brook Medicine, Stony Brook, NY, USA
| | - Xiaodong Zhang
- Department of Medical Imaging, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics Guangdong Province), Guangzhou, China
| |
Collapse
|
10
|
Shang L, Wang F, Gao Y, Zhou C, Wang J, Chen X, Chughtai AR, Pu H, Zhang G, Kong W. Machine-learning classifiers based on non-enhanced computed tomography radiomics to differentiate anterior mediastinal cysts from thymomas and low-risk from high-risk thymomas: A multi-center study. Front Oncol 2022; 12:1043163. [PMID: 36505817 PMCID: PMC9731806 DOI: 10.3389/fonc.2022.1043163] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2022] [Accepted: 11/03/2022] [Indexed: 11/25/2022] Open
Abstract
Background This study aimed to investigate the diagnostic value of machine-learning (ML) models with multiple classifiers based on non-enhanced CT Radiomics features for differentiating anterior mediastinal cysts (AMCs) from thymomas, and high-risk from low risk thymomas. Methods In total, 201 patients with AMCs and thymomas from three centers were included and divided into two groups: AMCs vs. thymomas, and high-risk vs low-risk thymomas. A radiomics model (RM) was built with 73 radiomics features that were extracted from the three-dimensional images of each patient. A combined model (CM) was built with clinical features and subjective CT finding features combined with radiomics features. For the RM and CM in each group, five selection methods were adopted to select suitable features for the classifier, and seven ML classifiers were employed to build discriminative models. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic performance of each combination. Results Several classifiers combined with suitable selection methods demonstrated good diagnostic performance with areas under the curves (AUCs) of 0.876 and 0.922 for the RM and CM in group 1 and 0.747 and 0.783 for the RM and CM in group 2, respectively. The combination of support vector machine (SVM) as the feature-selection method and Gradient Boosting Decision Tree (GBDT) as the classification algorithm represented the best comprehensive discriminative ability in both group. Comparatively, assessments by radiologists achieved a middle AUCs of 0.656 and 0.626 in the two groups, which were lower than the AUCs of the RM and CM. Most CMs exhibited higher AUC value compared to RMs in both groups, among them only a few CMs demonstrated better performance with significant difference in group 1. Conclusion Our ML models demonstrated good performance for differentiation of AMCs from thymomas and low-risk from high-risk thymomas. ML based on non-enhanced CT radiomics may serve as a novel preoperative tool.
Collapse
Affiliation(s)
- Lan Shang
- Department of Radiology, Sichuan Academy of Medical Sciences and Sichuan Provincial People’s Hospital, Affiliated Hospital of University of Electronic Science and Technology of China, Chengdu, China,Department of Radiology, Chinese Academy of Sciences Sichuan Translational Medicine Research Hospital, Chengdu, China
| | - Fang Wang
- Department of Radiology, Ningxia Hui Autonomous Region People’s Hospital, Yinchuan, China
| | - Yan Gao
- Department of Radiology, The First People’s Hospital of Liangshan Yi Autonomous Prefecture, Xichang, China
| | - Chaoxin Zhou
- Department of Radiology, The First People’s Hospital of Liangshan Yi Autonomous Prefecture, Xichang, China
| | - Jian Wang
- Department of diagnostic imaging School of Computer Science, Nanjing University of Science and Technology, Nanjing, China
| | - Xinyue Chen
- Department of Diagnostic Imaging, Computed Tomography (CT) Collaboration, Siemens Healthineers, Chengdu, China
| | - Aamer Rasheed Chughtai
- Section of Thoracic Imaging, Cleveland Clinic Health System, Cleveland, OH, United States
| | - Hong Pu
- Department of Radiology, Sichuan Academy of Medical Sciences and Sichuan Provincial People’s Hospital, Affiliated Hospital of University of Electronic Science and Technology of China, Chengdu, China,Department of Radiology, Chinese Academy of Sciences Sichuan Translational Medicine Research Hospital, Chengdu, China,*Correspondence: Weifang Kong, ; Guojin Zhang, ; Hong Pu,
| | - Guojin Zhang
- Department of Radiology, Sichuan Academy of Medical Sciences and Sichuan Provincial People’s Hospital, Affiliated Hospital of University of Electronic Science and Technology of China, Chengdu, China,Department of Radiology, Chinese Academy of Sciences Sichuan Translational Medicine Research Hospital, Chengdu, China,*Correspondence: Weifang Kong, ; Guojin Zhang, ; Hong Pu,
| | - Weifang Kong
- Department of Radiology, Sichuan Academy of Medical Sciences and Sichuan Provincial People’s Hospital, Affiliated Hospital of University of Electronic Science and Technology of China, Chengdu, China,Department of Radiology, Chinese Academy of Sciences Sichuan Translational Medicine Research Hospital, Chengdu, China,*Correspondence: Weifang Kong, ; Guojin Zhang, ; Hong Pu,
| |
Collapse
|
11
|
Feng XL, Wang SZ, Chen HH, Huang YX, Xin YK, Zhang T, Cheng DL, Mao L, Li XL, Liu CX, Hu YC, Wang W, Cui GB, Nan HY. Optimizing the radiomics-machine-learning model based on non-contrast enhanced CT for the simplified risk categorization of thymic epithelial tumors: A large cohort retrospective study. Lung Cancer 2022; 166:150-160. [DOI: 10.1016/j.lungcan.2022.03.007] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2021] [Revised: 02/16/2022] [Accepted: 03/04/2022] [Indexed: 11/29/2022]
|
12
|
Rossi G, Altabella L, Simoni N, Benetti G, Rossi R, Venezia M, Paiella S, Malleo G, Salvia R, Guariglia S, Bassi C, Cavedon C, Mazzarotto R. Computed tomography-based radiomic to predict resectability in locally advanced pancreatic cancer treated with chemotherapy and radiotherapy. World J Gastrointest Oncol 2022; 14:703-715. [PMID: 35321278 PMCID: PMC8919018 DOI: 10.4251/wjgo.v14.i3.703] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/17/2021] [Revised: 08/06/2021] [Accepted: 02/13/2022] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND Surgical resection after neoadjuvant treatment is the main driver for improved survival in locally advanced pancreatic cancer (LAPC). However, the diagnostic performance of computed tomography (CT) imaging to evaluate the residual tumour burden at restaging after neoadjuvant therapy is low due to the difficulty in distinguishing neoplastic tissue from fibrous scar or inflammation. In this context, radiomics has gained popularity over conventional imaging as a complementary clinical tool capable of providing additional, unprecedented information regarding the intratumor heterogeneity and the residual neoplastic tissue, potentially serving in the therapeutic decision-making process.
AIM To assess the capability of radiomic features to predict surgical resection in LAPC treated with neoadjuvant chemotherapy and radiotherapy.
METHODS Patients with LAPC treated with intensive chemotherapy followed by ablative radiation therapy were retrospectively reviewed. One thousand six hundred and fifty-five radiomic features were extracted from planning CT inside the gross tumour volume. Both extracted features and clinical data contribute to create and validate the predictive model of resectability status. Patients were repeatedly divided into training and validation sets. The discriminating performance of each model, obtained applying a LASSO regression analysis, was assessed with the area under the receiver operating characteristic curve (AUC). The validated model was applied to the entire dataset to obtain the most significant features.
RESULTS Seventy-one patients were included in the analysis. Median age was 65 years and 57.8% of patients were male. All patients underwent induction chemotherapy followed by ablative radiotherapy, and 19 (26.8%) ultimately received surgical resection. After the first step of variable selections, a predictive model of resectability was developed with a median AUC for training and validation sets of 0.862 (95%CI: 0.792-0.921) and 0.853 (95%CI: 0.706-0.960), respectively. The validated model was applied to the entire dataset and 4 features were selected to build the model with predictive performance as measured using AUC of 0.944 (95%CI: 0.892-0.996).
CONCLUSION The present radiomic model could help predict resectability in LAPC after neoadjuvant chemotherapy and radiotherapy, potentially integrating clinical and morphological parameters in predicting surgical resection.
Collapse
Affiliation(s)
- Gabriella Rossi
- Department of Radiation Oncology, University of Verona Hospital Trust, Verona 37126, Italy
| | - Luisa Altabella
- Department of Medical Physics, University of Verona Hospital Trust, Verona 37126, Italy
| | - Nicola Simoni
- Department of Radiation Oncology, University of Verona Hospital Trust, Verona 37126, Italy
| | - Giulio Benetti
- Department of Medical Physics, University of Verona Hospital Trust, Verona 37126, Italy
| | - Roberto Rossi
- Department of Radiation Oncology, University of Verona Hospital Trust, Verona 37126, Italy
| | - Martina Venezia
- Department of Radiation Oncology, University of Verona Hospital Trust, Verona 37126, Italy
| | - Salvatore Paiella
- Department of General and Pancreatic Surgery, Pancreas Institute, University of Verona Hospital Trust, Verona 37126, Italy
| | - Giuseppe Malleo
- Department of General and Pancreatic Surgery, Pancreas Institute, University of Verona Hospital Trust, Verona 37126, Italy
| | - Roberto Salvia
- Department of General and Pancreatic Surgery, Pancreas Institute, University of Verona Hospital Trust, Verona 37126, Italy
| | - Stefania Guariglia
- Department of Medical Physics, University of Verona Hospital Trust, Verona 37126, Italy
| | - Claudio Bassi
- Department of General and Pancreatic Surgery, Pancreas Institute, University of Verona Hospital Trust, Verona 37126, Italy
| | - Carlo Cavedon
- Department of Medical Physics, University of Verona Hospital Trust, Verona 37126, Italy
| | - Renzo Mazzarotto
- Department of Radiation Oncology, University of Verona Hospital Trust, Verona 37126, Italy
| |
Collapse
|
13
|
Blüthgen C, Patella M, Euler A, Baessler B, Martini K, von Spiczak J, Schneiter D, Opitz I, Frauenfelder T. Computed tomography radiomics for the prediction of thymic epithelial tumor histology, TNM stage and myasthenia gravis. PLoS One 2021; 16:e0261401. [PMID: 34928978 PMCID: PMC8687592 DOI: 10.1371/journal.pone.0261401] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2021] [Accepted: 12/01/2021] [Indexed: 12/21/2022] Open
Abstract
Objectives To evaluate CT-derived radiomics for machine learning-based classification of thymic epithelial tumor (TET) stage (TNM classification), histology (WHO classification) and the presence of myasthenia gravis (MG). Methods Patients with histologically confirmed TET in the years 2000–2018 were retrospectively included, excluding patients with incompatible imaging or other tumors. CT scans were reformatted uniformly, gray values were normalized and discretized. Tumors were segmented manually; 15 scans were re-segmented after 2 weeks by two readers. 1316 radiomic features were calculated (pyRadiomics). Features with low intra-/inter-reader agreement (ICC<0.75) were excluded. Repeated nested cross-validation was used for feature selection (Boruta algorithm), model training, and evaluation (out-of-fold predictions). Shapley additive explanation (SHAP) values were calculated to assess feature importance. Results 105 patients undergoing surgery for TET were identified. After applying exclusion criteria, 62 patients (28 female; mean age, 57±14 years; range, 22–82 years) with 34 low-risk TET (LRT; WHO types A/AB/B1), 28 high-risk TET (HRT; WHO B2/B3/C) in early stage (49, TNM stage I-II) or advanced stage (13, TNM III-IV) were included. 14(23%) of the patients had MG. 334(25%) features were excluded after intra-/inter-reader analysis. Discriminatory performance of the random forest classifiers was good for histology(AUC, 87.6%; 95% confidence interval, 76.3–94.3) and TNM stage(AUC, 83.8%; 95%CI, 66.9–93.4) but poor for the prediction of MG (AUC, 63.9%; 95%CI, 44.8–79.5). Conclusions CT-derived radiomic features may be a useful imaging biomarker for TET histology and TNM stage.
Collapse
Affiliation(s)
- Christian Blüthgen
- Institute of Diagnostic and Interventional Radiology, University Hospital of Zurich, Zurich, Switzerland
- * E-mail:
| | - Miriam Patella
- Department of Thoracic Surgery, University Hospital of Zurich, Zurich, Switzerland
| | - André Euler
- Institute of Diagnostic and Interventional Radiology, University Hospital of Zurich, Zurich, Switzerland
| | - Bettina Baessler
- Institute of Diagnostic and Interventional Radiology, University Hospital of Zurich, Zurich, Switzerland
| | - Katharina Martini
- Institute of Diagnostic and Interventional Radiology, University Hospital of Zurich, Zurich, Switzerland
| | - Jochen von Spiczak
- Institute of Diagnostic and Interventional Radiology, University Hospital of Zurich, Zurich, Switzerland
| | - Didier Schneiter
- Department of Thoracic Surgery, University Hospital of Zurich, Zurich, Switzerland
| | - Isabelle Opitz
- Department of Thoracic Surgery, University Hospital of Zurich, Zurich, Switzerland
| | - Thomas Frauenfelder
- Institute of Diagnostic and Interventional Radiology, University Hospital of Zurich, Zurich, Switzerland
| |
Collapse
|