1
|
Zhu C, Sun W, Chen C, Qiu Q, Wang S, Song Y, Ma X. Prediction of malignant esophageal fistula in esophageal cancer using a radiomics-clinical nomogram. Eur J Med Res 2024; 29:217. [PMID: 38570887 PMCID: PMC10993504 DOI: 10.1186/s40001-024-01746-2] [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: 04/22/2023] [Accepted: 02/25/2024] [Indexed: 04/05/2024] Open
Abstract
BACKGROUND Malignant esophageal fistula (MEF), which occurs in 5% to 15% of esophageal cancer (EC) patients, has a poor prognosis. Accurate identification of esophageal cancer patients at high risk of MEF is challenging. The goal of this study was to build and validate a model to predict the occurrence of esophageal fistula in EC patients. METHODS This study retrospectively enrolled 122 esophageal cancer patients treated by chemotherapy or chemoradiotherapy (53 with fistula, 69 without), and all patients were randomly assigned to a training (n = 86) and a validation (n = 36) cohort. Radiomic features were extracted from pre-treatment CTs, clinically predictors were identified by logistic regression analysis. Lasso regression model was used for feature selection, and radiomics signature building. Multivariable logistic regression analysis was used to develop the clinical nomogram, radiomics-clinical nomogram and radiomics prediction model. The models were validated and compared by discrimination, calibration, reclassification, and clinical benefit. RESULTS The radiomic signature consisting of ten selected features, was significantly associated with esophageal fistula (P = 0.001). Radiomics-clinical nomogram was created by two predictors including radiomics signature and stenosis, which was identified by logistic regression analysis. The model showed good discrimination with an AUC = 0.782 (95% CI 0.684-0.8796) in the training set and 0.867 (95% CI 0.7461-0.987) in the validation set, with an AIC = 101.1, and good calibration. When compared to the clinical prediction model, the radiomics-clinical nomogram improved NRI by 0.236 (95% CI 0.153, 0.614) and IDI by 0.125 (95% CI 0.040, 0.210), P = 0.004. CONCLUSION We developed and validated the first radiomics-clinical nomogram for malignant esophageal fistula, which could assist clinicians in identifying patients at high risk of MEF.
Collapse
Affiliation(s)
- Chao Zhu
- School of Basic Medicine, Qingdao University, Qingdao, 266000, China
- Department of Oncology, Affiliated Qingdao Central Hospital of Qingdao University, Qingdao Cancer Hospital, Qingdao, 266042, China
- Department of Radiation Oncology, Shandong Cancer Hospital, Jinan, 250117, China
| | - Wenju Sun
- Department of Oncology, Affiliated Qingdao Central Hospital of Qingdao University, Qingdao Cancer Hospital, Qingdao, 266042, China
| | - Cunhai Chen
- Department of Oncology, Affiliated Qingdao Central Hospital of Qingdao University, Qingdao Cancer Hospital, Qingdao, 266042, China
| | - Qingtao Qiu
- Department of Radiation Oncology, Shandong Cancer Hospital, Jinan, 250117, China
| | - Shuai Wang
- Department of Radiation Oncology, Affiliated Hospital of Weifang Medical University, Weifang, 261000, China
| | - Yang Song
- School of Basic Medicine, Qingdao University, Qingdao, 266000, China.
| | - Xuezhen Ma
- Department of Oncology, Affiliated Qingdao Central Hospital of Qingdao University, Qingdao Cancer Hospital, Qingdao, 266042, China.
| |
Collapse
|
2
|
Guo W, Li B, Xu W, Cheng C, Qiu C, Sam SK, Zhang J, Teng X, Meng L, Zheng X, Wang Y, Lou Z, Mao R, Lei H, Zhang Y, Zhou T, Li A, Cai J, Ge H. Multi-omics and Multi-VOIs to predict esophageal fistula in esophageal cancer patients treated with radiotherapy. J Cancer Res Clin Oncol 2024; 150:39. [PMID: 38280037 PMCID: PMC10821966 DOI: 10.1007/s00432-023-05520-5] [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: 08/10/2023] [Accepted: 11/20/2023] [Indexed: 01/29/2024]
Abstract
OBJECTIVE This study aimed to develop a prediction model for esophageal fistula (EF) in esophageal cancer (EC) patients treated with intensity-modulated radiation therapy (IMRT), by integrating multi-omics features from multiple volumes of interest (VOIs). METHODS We retrospectively analyzed pretreatment planning computed tomographic (CT) images, three-dimensional dose distributions, and clinical factors of 287 EC patients. Nine groups of features from different combination of omics [Radiomics (R), Dosiomics (D), and RD (the combination of R and D)], and VOIs [esophagus (ESO), gross tumor volume (GTV), and EG (the combination of ESO and GTV)] were extracted and separately selected by unsupervised (analysis of variance (ANOVA) and Pearson correlation test) and supervised (Student T test) approaches. The final model performance was evaluated using five metrics: average area under the receiver-operator-characteristics curve (AUC), accuracy, precision, recall, and F1 score. RESULTS For multi-omics using RD features, the model performance in EG model shows: AUC, 0.817 ± 0.031; 95% CI 0.805, 0.825; p < 0.001, which is better than single VOI (ESO or GTV). CONCLUSION Integrating multi-omics features from multi-VOIs enables better prediction of EF in EC patients treated with IMRT. The incorporation of dosiomics features can enhance the model performance of the prediction.
Collapse
Affiliation(s)
- Wei Guo
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China
| | - Bing Li
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China
| | - Wencai Xu
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China
| | - Chen Cheng
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China
| | - Chengyu Qiu
- Department of Medical Informatics, Nantong University, Nantong, China
| | - Sai-Kit Sam
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Jiang Zhang
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Xinzhi Teng
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Lingguang Meng
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China
| | - Xiaoli Zheng
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China
| | - Yuan Wang
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China
| | - Zhaoyang Lou
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China
| | - Ronghu Mao
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China
| | - Hongchang Lei
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China
| | - Yuanpeng Zhang
- Department of Medical Informatics, Nantong University, Nantong, China
| | - Ta Zhou
- School of Electrical and Information Engineering, Jiangsu University of Science and Technology, Zhenjiang, China
| | - Aijia Li
- Zhengzhou University School of Medicine, Zhengzhou, China
| | - Jing Cai
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Hong Ge
- Department of Radiation Oncology, The Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital, 127 Dong Ming Rd, Zhengzhou, Henan Province, China.
| |
Collapse
|
3
|
Wu YP, Wu L, Ou J, Cao JM, Fu MY, Chen TW, Ouchi E, Hu J. Preoperative CT radiomics of esophageal squamous cell carcinoma and lymph node to predict nodal disease with a high diagnostic capability. Eur J Radiol 2024; 170:111197. [PMID: 37992611 DOI: 10.1016/j.ejrad.2023.111197] [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: 09/25/2023] [Revised: 10/12/2023] [Accepted: 11/13/2023] [Indexed: 11/24/2023]
Abstract
PURPOSE To develop CT radiomics models of resectable esophageal squamous cell carcinoma (ESCC) and lymph node (LN) to preoperatively identify LN+. MATERIALS AND METHODS 299 consecutive patients with ESCC were enrolled in the study, 140 of whom were LN+ and 159 were LN-. Of the 299 patients, 249 (from the same hospital) were randomly divided into a training cohort (n = 174) and a test cohort (n = 75). The remaining 50 patients, from a second hospital, were assigned to an external validation cohort. In the training cohort, preoperative contrast-enhanced CT radiomics features of ESCC and LN were extracted, then integrated with clinical features to develop three models: ESCC, LN and combined. The performance of these models was assessed using area under receiver operating characteristic curve (AUC), and F-1 score, which were validated in both the test cohort and external validation cohort. RESULTS An ESCC model was developed for the training cohort utilizing the 8 tumor radiomics features, and an LN model was constructed using 9 nodal radiomics features. A combined model was constructed using both ESCC and LN extracted features, in addition to cT stage and LN+ distribution. This combined model had the highest predictive ability among the three models in the training cohort (AUC = 0.948, F1-score = 0.878). The predictive ability was validated in both the test and external validation cohorts (AUC = 0.885 and 0.867, F1-score = 0.816 and 0.773, respectively). CONCLUSION To preoperatively determine LN+, the combined model is superior to models of ESCC and LN alone.
Collapse
Affiliation(s)
- Yu-Ping Wu
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China; Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China
| | - Lan Wu
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Jing Ou
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China
| | - Jin-Ming Cao
- Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China; Department of Radiology, Nanchong Central Hospital, The Second Clinical Medical College, North Sichuan Medical College, Nanchong, China
| | - Mao-Yong Fu
- Department of Thoracic Surgery, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Tian-Wu Chen
- Department of Radiology, the Second Affiliated Hospital of Chongqing Medical University, Chongqing, China; Medical Imaging Key Laboratory of Sichuan Province, and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China.
| | - Erika Ouchi
- Department of Radiology, Wayne State University, Detroit, MI, USA
| | - Jiani Hu
- Department of Radiology, Wayne State University, Detroit, MI, USA
| |
Collapse
|
4
|
Hirohata R, Hamai Y, Murakami Y, Emi M, Nishibuchi I, Kurokawa T, Yoshikawa T, Ohsawa M, Kitasaki N, Okada M. Risk factors for aortoesophageal fistula in cT4b esophageal squamous cell carcinoma after definitive radiation therapy. J Thorac Dis 2023; 15:5319-5329. [PMID: 37969281 PMCID: PMC10636439 DOI: 10.21037/jtd-23-848] [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: 07/17/2023] [Accepted: 08/18/2023] [Indexed: 11/17/2023]
Abstract
Background Esophageal fistula (EF) is a serious complication in patients with cT4b esophageal squamous cell carcinoma (ESCC) with adjacent organ involvement. Among EFs, aortoesophageal fistula (AEF), forming a fistula with the aorta, could be fatal. This study aimed to identify the risk factors for AEF in patients with cT4b ESCC with obvious or suspected aortic invasion who underwent definitive radiotherapy (DRT). Methods Forty-four patients with cT4b ESCC with obvious or suspected invasion to the aorta who underwent DRT were included. Blood tests and computed tomography (CT) findings before and after DRT were compared between the patients with and without AEF to identify the potential risk factors for AEF. Results Nine patients (20.5%) developed AEF after DRT. Comparing between patients with and without AEF, pre-DRT white blood cell counts and post-DRT C-reactive protein (CRP) levels were significantly higher in patients with AEF. Furthermore, pre-DRT CT findings were similar between the two groups. However, post-DRT CT findings demonstrated significantly larger picus angle and lower esophageal wall thickness on the aortic side in patients with AEF. Multivariate analysis identified elevated post-DRT CRP levels [<3.3 versus ≥3.3 mg/dL; odds ratio (OR): 30.7; 95% confidence interval (CI): 2.92-323.2; P=0.004] and esophageal wall thinning on post-DRT CT scans (>6 versus ≤6 mm; OR: 13.2; 95% CI: 1.24-140.1; P=0.033) as risk factors for AEF. Conclusions We found that post-DRT esophageal wall thinning on the aortic side, as observed on CT scans, and elevated CRP levels were predictive factors for AEF in patients with cT4b ESCC with obvious or suspected invasion to the aorta.
Collapse
Affiliation(s)
- Ryosuke Hirohata
- Department of Surgical Oncology, Hiroshima University, Hiroshima, Japan
| | - Yoichi Hamai
- Department of Surgical Oncology, Hiroshima University, Hiroshima, Japan
| | - Yuji Murakami
- Department of Radiation Oncology, Hiroshima University, Hiroshima, Japan
| | - Manabu Emi
- Department of Surgical Oncology, Hiroshima University, Hiroshima, Japan
| | - Ikuno Nishibuchi
- Department of Radiation Oncology, Hiroshima University, Hiroshima, Japan
| | - Tomoaki Kurokawa
- Department of Surgical Oncology, Hiroshima University, Hiroshima, Japan
| | - Toru Yoshikawa
- Department of Surgical Oncology, Hiroshima University, Hiroshima, Japan
| | - Manato Ohsawa
- Department of Surgical Oncology, Hiroshima University, Hiroshima, Japan
| | - Nao Kitasaki
- Department of Surgical Oncology, Hiroshima University, Hiroshima, Japan
| | - Morihito Okada
- Department of Surgical Oncology, Hiroshima University, Hiroshima, Japan
| |
Collapse
|