1
|
Zhou S, Tsui P, Lin M, Chen G, Chen W, Cai X. A diagnostic model based on 18F-FDG PET/CT parameters in improving the differential diagnosis of invasive thymic epithelial tumors and anterior mediastinal lymphomas. BMC Med Imaging 2024; 24:14. [PMID: 38191331 PMCID: PMC10773031 DOI: 10.1186/s12880-023-01185-1] [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: 04/18/2023] [Accepted: 12/22/2023] [Indexed: 01/10/2024] Open
Abstract
BACKGROUND Accurately distinguishing between invasive thymic epithelial tumors (TETs) and anterior mediastinal lymphoma before surgery is crucial for subsequent treatment choices. But currently, the diagnosis of invasive TET is sometimes difficult to distinguish from anterior mediastinal lymphoma. OBJECTIVE To assess the application of fluorine-18-fluorodeoxyglucose (18F-FDG) positron emission tomography/computer tomography (PET/CT) in the differential diagnosis of TETs and anterior mediastinal lymphomas. METHODS 18F-FDG PET/CT images of 133 invasive TETs and anterior mediastinal lymphomas patients were retrospectively analyzed. In particular, the tumor's longest diameter and maximum standardized uptake value (SUVmax) were evaluated. The SUVmax and longest diameter values of the two groups were analyzed by using the receiver operating characteristic (ROC) curve to determine the optimal threshold and diagnostic efficiency. RESULTS Age, myasthenia gravis, SUVmax and tumor longest diameter differed significantly between invasive TETs and anterior mediastinal lymphomas patients. The tumor location, calcification, relationship with adjacent vessels and distant metastasis differed significantly between the groups. The ROC analysis showed an AUC for SUVmax and tumor longest diameter of 0.841 and 0.737. Respectively, the cutoff values with the best diagnostic performance were 9.65 (sensitivity: 77.78%, specificity: 81.97%) and 6.65 (sensitivity: 80.56%, specificity: 62.30%) for SUVmax and tumor longest diameter. The diagnostic model of SUVmax, calcification, relationship with surrounding blood vessels, lymph node metastasis and lung metastasis in the highest AUC of 0.935 (sensitivity: 90.16%, specificity: 88.89%). In addition, we incorporated splenic involvement and metastatic sub-diaphragmatic lymph node into Model 2 as a new predictive model 3 for differential diagnosis and found a significant improvement in the diagnostic performance of Model 3. CONCLUSION The diagnostic model composed of 18F-FDG PET parameters is improving the differential diagnosis of invasive TETs and anterior mediastinal lymphomas.
Collapse
Affiliation(s)
- Shuo Zhou
- Department of Nuclear Medicine, Shengli Clinical Medical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou City, Fujian Province, China
| | - Pokwan Tsui
- Medical Imaging Center, First Affiliated Hospital of Jinan University, No. 613 West Huangpu Avenue, Tianhe District, Guangzhou, 510630, Guangdong, China
| | - Meifu Lin
- Department of Nuclear Medicine, Shengli Clinical Medical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou City, Fujian Province, China
| | - Guobao Chen
- Department of Nuclear Medicine, Shengli Clinical Medical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou City, Fujian Province, China
| | - Wenxin Chen
- Department of Nuclear Medicine, Shengli Clinical Medical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou City, Fujian Province, China.
| | - Xiangran Cai
- Medical Imaging Center, First Affiliated Hospital of Jinan University, No. 613 West Huangpu Avenue, Tianhe District, Guangzhou, 510630, Guangdong, China.
| |
Collapse
|
2
|
Li J, Cui N, Jiang Z, Li W, Liu W, Wang S, Wang K. Differentiating thymic epithelial tumors from mediastinal lymphomas: preoperative nomograms based on PET/CT radiomic features to minimize unnecessary anterior mediastinal surgery. J Cancer Res Clin Oncol 2023; 149:14101-14112. [PMID: 37552308 DOI: 10.1007/s00432-023-05054-w] [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: 05/17/2023] [Accepted: 06/28/2023] [Indexed: 08/09/2023]
Abstract
PURPOSE Clinical feasibility nomograms were developed to facilitate the differentiation between thymic epithelial tumors (TETs) and mediastinal lymphomas (MLs), aiming to minimize the occurrence of non-therapeutic thymectomy. METHODS A total of 255 patients diagnosed with TETs or MLs underwent pre-treatment 18F-FDG PET/CT. Comprehensive clinical and imaging data were collected, including age, gender, lactate dehydrogenase (LDH) level, pathological results, presence of myasthenia gravis symptoms, B symptoms, mass size, location, morphology, margins, density, and metabolic parameters derived from PET/CT. Radiomic features were extracted from the region of interest (ROI) of the primary lesion. Feature selection techniques were employed to identify the most discriminative subset of features. Machine learning methods were utilized to build candidate models, which were subsequently evaluated based on their area under the curve (AUC). Finally, nomograms were constructed using the optimal model to provide a clinical tool for improved diagnostic accuracy. The performance of the radiomic models was evaluated by their calibration, discrimination, and clinical utility. RESULTS Several independent risk factors were identified for distinguishing TETs from MLs, including average standardized uptake value (SUVavg), LDH, age, mass size, and radiomic score (rad-score). Significance was observed in differentiating the two types of tumors based on these factors. The best clinical efficacy was demonstrated by the combined model, with an impressive AUC of 0.954. Decision curve analysis and calibration curves indicated that the combined model was clinically advantageous for discriminating TETs from MLs. Besides, the results of external validation showed a sensitivity of 0.8 and a specificity of 0.78. CONCLUSION Preoperatively, the differentiation of TETs from MLs can be facilitated by the utilization of the combined clinical information and radiomics model. This approach holds promise in minimizing the occurrence of unnecessary anterior mediastinal surgeries.
Collapse
Affiliation(s)
- Jiatong Li
- PET-CT/MRI Department, Harbin Medical University Cancer Hospital, Harbin Medical University, 150 Haping Road, Harbin, 150081, Heilongjiang, China
| | - Nan Cui
- PET-CT/MRI Department, Harbin Medical University Cancer Hospital, Harbin Medical University, 150 Haping Road, Harbin, 150081, Heilongjiang, China
| | - Zhiyun Jiang
- Radiology Department, Harbin Medical University Cancer Hospital, Harbin Medical University, 150 Haping Road, Harbin, 150081, Heilongjiang, China
| | - Wei Li
- Interventional Vascular Surgery Department, The 4th Affiliated Hospital of Harbin Medical University, Harbin Medical University, 37 Yiyuan Road, Harbin, 150001, Heilongjiang, China
| | - Wei Liu
- PET-CT/MRI Department, Harbin Medical University Cancer Hospital, Harbin Medical University, 150 Haping Road, Harbin, 150081, Heilongjiang, China
| | - Shuai Wang
- Department of Thoracic Surgery, Zhongshan Hospital, Fudan University, No. 180, Fenglin Road, Shanghai, 200032, China.
| | - Kezheng Wang
- PET-CT/MRI Department, Harbin Medical University Cancer Hospital, Harbin Medical University, 150 Haping Road, Harbin, 150081, Heilongjiang, China.
| |
Collapse
|
3
|
Zhang G, Bao C, Liu Y, Wang Z, Du L, Zhang Y, Wang F, Xu B, Zhou SK, Liu R. 18F-FDG-PET/CT-based deep learning model for fully automated prediction of pathological grading for pancreatic ductal adenocarcinoma before surgery. EJNMMI Res 2023; 13:49. [PMID: 37231321 DOI: 10.1186/s13550-023-00985-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Accepted: 04/17/2023] [Indexed: 05/27/2023] Open
Abstract
BACKGROUND The determination of pathological grading has a guiding significance for the treatment of pancreatic ductal adenocarcinoma (PDAC) patients. However, there is a lack of an accurate and safe method to obtain pathological grading before surgery. The aim of this study is to develop a deep learning (DL) model based on 18F-fluorodeoxyglucose-positron emission tomography/computed tomography (18F-FDG-PET/CT) for a fully automatic prediction of preoperative pathological grading of pancreatic cancer. METHODS A total of 370 PDAC patients from January 2016 to September 2021 were collected retrospectively. All patients underwent 18F-FDG-PET/CT examination before surgery and obtained pathological results after surgery. A DL model for pancreatic cancer lesion segmentation was first developed using 100 of these cases and applied to the remaining cases to obtain lesion regions. After that, all patients were divided into training set, validation set, and test set according to the ratio of 5:1:1. A predictive model of pancreatic cancer pathological grade was developed using the features computed from the lesion regions obtained by the lesion segmentation model and key clinical characteristics of the patients. Finally, the stability of the model was verified by sevenfold cross-validation. RESULTS The Dice score of the developed PET/CT-based tumor segmentation model for PDAC was 0.89. The area under curve (AUC) of the PET/CT-based DL model developed on the basis of the segmentation model was 0.74, with an accuracy, sensitivity, and specificity of 0.72, 0.73, and 0.72, respectively. After integrating key clinical data, the AUC of the model improved to 0.77, with its accuracy, sensitivity, and specificity boosted to 0.75, 0.77, and 0.73, respectively. CONCLUSION To the best of our knowledge, this is the first deep learning model to end-to-end predict the pathological grading of PDAC in a fully automatic manner, which is expected to improve clinical decision-making.
Collapse
Affiliation(s)
- Gong Zhang
- Medical School of Chinese PLA, Beijing, China
- Faculty of Hepato-Biliary-Pancreatic Surgery, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, 28 Fuxing Road, Beijing, 100853, China
| | - Chengkai Bao
- School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China
- Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, Jiangsu, China
| | - Yanzhe Liu
- Faculty of Hepato-Biliary-Pancreatic Surgery, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, 28 Fuxing Road, Beijing, 100853, China
| | - Zizheng Wang
- Senior Department of Hepatology, The Fifth Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China
| | - Lei Du
- Department of Nuclear Medicine, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China
| | - Yue Zhang
- School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China
- Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, Jiangsu, China
| | - Fei Wang
- Faculty of Hepato-Biliary-Pancreatic Surgery, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, 28 Fuxing Road, Beijing, 100853, China
| | - Baixuan Xu
- Department of Nuclear Medicine, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, Beijing, China.
| | - S Kevin Zhou
- School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China.
- Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, Jiangsu, China.
| | - Rong Liu
- Faculty of Hepato-Biliary-Pancreatic Surgery, The First Medical Center of Chinese People's Liberation Army (PLA) General Hospital, 28 Fuxing Road, Beijing, 100853, China.
| |
Collapse
|
4
|
Takumi K, Nagano H, Oose A, Gohara M, Kamimura K, Nakajo M, Harada-Takeda A, Ueda K, Tabata K, Yoshiura T. Extracellular volume fraction derived from equilibrium contrast-enhanced CT as a diagnostic parameter in anterior mediastinal tumors. Eur J Radiol 2023; 165:110891. [PMID: 37245341 DOI: 10.1016/j.ejrad.2023.110891] [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: 04/10/2023] [Revised: 05/08/2023] [Accepted: 05/22/2023] [Indexed: 05/30/2023]
Abstract
PURPOSE To assess the usefulness of extracellular volume (ECV) fraction derived from equilibrium contrast-enhanced CT (CECT) for diagnosing anterior mediastinal tumors. METHOD This study included 161 histologically confirmed anterior mediastinal tumors (55 low-risk thymomas, 57 high-risk thymomas, 32 thymic carcinomas, and 17 malignant lymphomas) that were assessed by pretreatment CECT. ECV fraction was calculated using measurements obtained within the lesion and the aorta on unenhanced and equilibrium phase CECT. ECV fraction was compared among anterior mediastinal tumors using one-way ANOVA or t-test. Receiver-operating characteristic (ROC) curve analysis was performed to evaluate the ability of ECV fraction to differentiate thymic carcinomas/lymphomas from thymomas. RESULTS ECV fraction differed significantly among the anterior mediastinal tumors (p < 0.001). ECV fraction of thymic carcinomas was significantly higher than those of low-risk thymomas, high-risk thymomas, and lymphomas (p < 0.001, p < 0.001, and p = 0.006, respectively). ECV fraction of lymphomas was significantly higher than that of low-risk thymomas (p < 0.001). ECV fraction was significantly higher in thymic carcinomas/lymphomas than in thymomas (40.1 % vs. 27.7 %, p < 0.001). The optimal cutoff value to differentiate thymic carcinomas/lymphomas from thymomas was 38.5 % (AUC, 0.805; 95 %CI, 0.736-0.863). CONCLUSIONS ECV fraction derived from equilibrium CECT is helpful in diagnosing anterior mediastinal tumors. High ECV fraction is indicative of thymic carcinomas/lymphomas, particularly thymic carcinomas.
Collapse
Affiliation(s)
- Koji Takumi
- Departments of Radiology Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima City 890-8544, Japan.
| | - Hiroaki Nagano
- Departments of Radiology Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima City 890-8544, Japan
| | - Arata Oose
- Departments of Radiology Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima City 890-8544, Japan
| | - Misaki Gohara
- Departments of Radiology Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima City 890-8544, Japan
| | - Kiyohisa Kamimura
- Departments of Radiology Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima City 890-8544, Japan
| | - Masatoyo Nakajo
- Departments of Radiology Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima City 890-8544, Japan
| | - Aya Harada-Takeda
- General Thoracic Surgery Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima City 890-8544, Japan
| | - Kazuhiro Ueda
- General Thoracic Surgery Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima City 890-8544, Japan
| | - Kazuhiro Tabata
- Human Pathology Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima City 890-8544, Japan
| | - Takashi Yoshiura
- Departments of Radiology Kagoshima University Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima City 890-8544, Japan
| |
Collapse
|