1
|
Cheng J, Su W, Wang Y, Zhan Y, Wang Y, Yan S, Yuan Y, Chen L, Wei Z, Zhang S, Gao X, Tang Z. Magnetic resonance imaging based on radiomics for differentiating T1-category nasopharyngeal carcinoma from nasopharyngeal lymphoid hyperplasia: a multicenter study. Jpn J Radiol 2024; 42:709-719. [PMID: 38409300 DOI: 10.1007/s11604-024-01544-0] [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: 10/21/2023] [Accepted: 01/29/2024] [Indexed: 02/28/2024]
Abstract
PURPOSE To investigate the role of magnetic resonance imaging (MRI) based on radiomics using T2-weighted imaging fat suppression (T2WI-FS) and contrast enhanced T1-weighted imaging (CE-T1WI) sequences in differentiating T1-category nasopharyngeal carcinoma (NPC) from nasopharyngeal lymphoid hyperplasia (NPH). MATERIALS AND METHODS This study enrolled 614 patients (training dataset: n = 390, internal validation dataset: n = 98, and external validation dataset: n = 126) of T1-category NPC and NPH. Three feature selection methods were used, including analysis of variance, recursive feature elimination, and relief. The logistic regression classifier was performed to construct the radiomics signatures of T2WI-FS, CE-T1WI, and T2WI-FS + CE-T1WI to differentiate T1-category NPC from NPH. The performance of the optimal radiomics signature (T2WI-FS + CE-T1WI) was compared with those of three radiologists in the internal and external validation datasets. RESULTS Twelve, 15, and 15 radiomics features were selected from T2WI-FS, CE-T1WI, and T2WI-FS + CE-T1WI to develop the three radiomics signatures, respectively. The area under the curve (AUC) values for radiomics signatures of T2WI-FS + CE-T1WI and CE-T1WI were significantly higher than that of T2WI-FS (AUCs = 0.940, 0.935, and 0.905, respectively) for distinguishing T1-category NPC and NPH in the training dataset (Ps all < 0.05). In the internal and external validation datasets, the radiomics signatures based on T2WI-FS + CE-T1WI and CE-T1WI outperformed T2WI-FS with no significant difference (AUCs = 0.938, 0.925, and 0.874 for internal validation dataset and 0.932, 0.918, and 0.882 for external validation dataset; Ps > 0.05). The radiomics signature of T2WI-FS + CE-T1WI significantly performed better than three radiologists in the internal and external validation datasets. CONCLUSION The MRI-based radiomics signature is meaningful in differentiating T1-category NPC from NPH and potentially helps clinicians select suitable therapy strategies.
Collapse
Affiliation(s)
- Jingfeng Cheng
- Department of Radiology, Eye & ENT Hospital of Fudan University, Shanghai Medical School, Fudan University, 83 Fenyang Road, Shanghai, 200031, China
| | - Wenzhe Su
- Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China
| | - Yuzhe Wang
- Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, 200032, China
| | - Yang Zhan
- Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, 200032, China
| | - Yin Wang
- Department of Radiology, Eye & ENT Hospital of Fudan University, Shanghai Medical School, Fudan University, 83 Fenyang Road, Shanghai, 200031, China
| | - Shuyu Yan
- Fudan University, Shanghai, 200032, China
| | - Yuan Yuan
- Fudan University, Shanghai, 200032, China
| | | | - Zixun Wei
- Fudan University, Shanghai, 200032, China
| | - Shengjian Zhang
- Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China
| | - Xin Gao
- Shanghai Universal Medical Imaging Diagnostic Center, Shanghai, 200233, China.
| | - Zuohua Tang
- Department of Radiology, Eye & ENT Hospital of Fudan University, Shanghai Medical School, Fudan University, 83 Fenyang Road, Shanghai, 200031, China.
| |
Collapse
|
2
|
Mao K, Wong LM, Zhang R, So TY, Shan Z, Hung KF, Ai QYH. Radiomics Analysis in Characterization of Salivary Gland Tumors on MRI: A Systematic Review. Cancers (Basel) 2023; 15:4918. [PMID: 37894285 PMCID: PMC10605883 DOI: 10.3390/cancers15204918] [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: 09/12/2023] [Revised: 10/06/2023] [Accepted: 10/08/2023] [Indexed: 10/29/2023] Open
Abstract
Radiomics analysis can potentially characterize salivary gland tumors (SGTs) on magnetic resonance imaging (MRI). The procedures for radiomics analysis were various, and no consistent performances were reported. This review evaluated the methodologies and performances of studies using radiomics analysis to characterize SGTs on MRI. We systematically reviewed studies published until July 2023, which employed radiomics analysis to characterize SGTs on MRI. In total, 14 of 98 studies were eligible. Each study examined 23-334 benign and 8-56 malignant SGTs. Least absolute shrinkage and selection operator (LASSO) was the most common feature selection method (in eight studies). Eleven studies confirmed the stability of selected features using cross-validation or bootstrap. Nine classifiers were used to build models that achieved area under the curves (AUCs) of 0.74 to 1.00 for characterizing benign and malignant SGTs and 0.80 to 0.96 for characterizing pleomorphic adenomas and Warthin's tumors. Performances were validated using cross-validation, internal, and external datasets in four, six, and two studies, respectively. No single feature consistently appeared in the final models across the studies. No standardized procedure was used for radiomics analysis in characterizing SGTs on MRIs, and various models were proposed. The need for a standard procedure for radiomics analysis is emphasized.
Collapse
Affiliation(s)
- Kaijing Mao
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China
| | - Lun M. Wong
- Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China
| | - Rongli Zhang
- Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China
| | - Tiffany Y. So
- Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, China
| | - Zhiyi Shan
- Paediatric Dentistry & Orthodontics, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China
| | - Kuo Feng Hung
- Applied Oral Sciences & Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China
| | - Qi Yong H. Ai
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China
| |
Collapse
|
3
|
Huynh BN, Groendahl AR, Tomic O, Liland KH, Knudtsen IS, Hoebers F, van Elmpt W, Malinen E, Dale E, Futsaether CM. Head and neck cancer treatment outcome prediction: a comparison between machine learning with conventional radiomics features and deep learning radiomics. Front Med (Lausanne) 2023; 10:1217037. [PMID: 37711738 PMCID: PMC10498924 DOI: 10.3389/fmed.2023.1217037] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2023] [Accepted: 07/07/2023] [Indexed: 09/16/2023] Open
Abstract
Background Radiomics can provide in-depth characterization of cancers for treatment outcome prediction. Conventional radiomics rely on extraction of image features within a pre-defined image region of interest (ROI) which are typically fed to a classification algorithm for prediction of a clinical endpoint. Deep learning radiomics allows for a simpler workflow where images can be used directly as input to a convolutional neural network (CNN) with or without a pre-defined ROI. Purpose The purpose of this study was to evaluate (i) conventional radiomics and (ii) deep learning radiomics for predicting overall survival (OS) and disease-free survival (DFS) for patients with head and neck squamous cell carcinoma (HNSCC) using pre-treatment 18F-fluorodeoxuglucose positron emission tomography (FDG PET) and computed tomography (CT) images. Materials and methods FDG PET/CT images and clinical data of patients with HNSCC treated with radio(chemo)therapy at Oslo University Hospital (OUS; n = 139) and Maastricht University Medical Center (MAASTRO; n = 99) were collected retrospectively. OUS data was used for model training and initial evaluation. MAASTRO data was used for external testing to assess cross-institutional generalizability. Models trained on clinical and/or conventional radiomics features, with or without feature selection, were compared to CNNs trained on PET/CT images without or with the gross tumor volume (GTV) included. Model performance was measured using accuracy, area under the receiver operating characteristic curve (AUC), Matthew's correlation coefficient (MCC), and the F1 score calculated for both classes separately. Results CNNs trained directly on images achieved the highest performance on external data for both endpoints. Adding both clinical and radiomics features to these image-based models increased performance further. Conventional radiomics including clinical data could achieve competitive performance. However, feature selection on clinical and radiomics data lead to overfitting and poor cross-institutional generalizability. CNNs without tumor and node contours achieved close to on-par performance with CNNs including contours. Conclusion High performance and cross-institutional generalizability can be achieved by combining clinical data, radiomics features and medical images together with deep learning models. However, deep learning models trained on images without contours can achieve competitive performance and could see potential use as an initial screening tool for high-risk patients.
Collapse
Affiliation(s)
- Bao Ngoc Huynh
- Faculty of Science and Technology, Norwegian University of Life Sciences, Ås, Norway
| | | | - Oliver Tomic
- Faculty of Science and Technology, Norwegian University of Life Sciences, Ås, Norway
| | - Kristian Hovde Liland
- Faculty of Science and Technology, Norwegian University of Life Sciences, Ås, Norway
| | - Ingerid Skjei Knudtsen
- Department of Circulation and Medical Imaging, Norwegian University of Science and Technology, Trondheim, Norway
- Department of Medical Physics, Oslo University Hospital, Oslo, Norway
| | - Frank Hoebers
- Department of Radiation Oncology (MAASTRO), Maastricht University Medical Center, Maastricht, Netherlands
- GROW School for Oncology and Reproduction, Maastricht University Medical Center, Maastricht, Netherlands
| | - Wouter van Elmpt
- Department of Radiation Oncology (MAASTRO), Maastricht University Medical Center, Maastricht, Netherlands
- GROW School for Oncology and Reproduction, Maastricht University Medical Center, Maastricht, Netherlands
| | - Eirik Malinen
- Department of Medical Physics, Oslo University Hospital, Oslo, Norway
- Department of Physics, University of Oslo, Oslo, Norway
| | - Einar Dale
- Department of Oncology, Oslo University Hospital, Oslo, Norway
| | | |
Collapse
|
4
|
Yang F, Wei H, Li X, Yu X, Zhao Y, Li L, Li Y, Xie L, Wang S, Lin M. Pretreatment synthetic magnetic resonance imaging predicts disease progression in nonmetastatic nasopharyngeal carcinoma after intensity modulation radiation therapy. Insights Imaging 2023; 14:59. [PMID: 37016104 PMCID: PMC10073373 DOI: 10.1186/s13244-023-01411-y] [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: 11/03/2022] [Accepted: 03/22/2023] [Indexed: 04/06/2023] Open
Abstract
BACKGROUND To investigate the potential of synthetic MRI (SyMRI) in the prognostic assessment of patients with nonmetastatic nasopharyngeal carcinoma (NPC), and the predictive value when combined with diffusion-weighted imaging (DWI) as well as clinical factors. METHODS Fifty-three NPC patients who underwent SyMRI were prospectively included. 10th Percentile, Mean, Kurtosis, and Skewness of T1, T2, and PD maps and ADC value were obtained from the primary tumor. Cox regression analysis was used for analyzing the association between SyMRI and DWI parameters and progression-free survival (PFS), and then age, sex, staging, and treatment as confounding factors were also included. C-index was obtained by bootstrap. Moreover, significant parameters were used to construct models in predicting 3-year disease progression. ROC curves and leave-one-out cross-validation were used to evaluate the performance and stability. RESULTS Disease progression occurred in 16 (30.2%) patients at a follow-up of 39.6 (3.5, 48.2) months. T1_Kurtosis, T1_Skewness, T2_10th, PD_Mean, and ADC were correlated with PFS, and T1_Kurtosis (HR: 1.093) and ADC (HR: 1.009) were independent predictors of PFS. The C-index of SyMRI and SyMRI + DWI + Clinic models was 0.687 and 0.779. Moreover, the SyMRI + DWI + Clinic model predicted 3-year disease progression better than DWI or Clinic model (p ≤ 0.008). Interestingly, there was no significant difference between the SyMRI model (AUC: 0.748) and SyMRI + DWI + Clinic model (AUC: 0.846, p = 0.092). CONCLUSION SyMRI combined with histogram analysis could predict disease progression in NPC patients, and SyMRI + DWI + Clinic model further improved the predictive performance.
Collapse
Affiliation(s)
- Fan Yang
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Haoran Wei
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Xiaolu Li
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Xiaoduo Yu
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Yanfeng Zhao
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Lin Li
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Yujie Li
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China
| | - Lizhi Xie
- MR Research China, GE Healthcare, Beijing, China
| | - Sicong Wang
- MR Research China, GE Healthcare, Beijing, China
| | - Meng Lin
- Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China.
| |
Collapse
|
5
|
Yang F, Li Y, Li X, Yu X, Zhao Y, Li L, Xie L, Lin M. The utility of texture analysis based on quantitative synthetic magnetic resonance imaging in nasopharyngeal carcinoma: a preliminary study. BMC Med Imaging 2023; 23:15. [PMID: 36698156 PMCID: PMC9875491 DOI: 10.1186/s12880-023-00968-w] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2022] [Accepted: 01/13/2023] [Indexed: 01/27/2023] Open
Abstract
BACKGROUND Magnetic resonance imaging (MRI) is commonly used for the diagnosis of nasopharyngeal carcinoma (NPC) and occipital clivus (OC) invasion, but a proportion of lesions may be missed using non-enhanced MRI. The purpose of this study is to investigate the diagnostic performance of synthetic magnetic resonance imaging (SyMRI) in differentiating NPC from nasopharyngeal hyperplasia (NPH), as well as evaluating OC invasion. METHODS Fifty-nine patients with NPC and 48 volunteers who underwent SyMRI examination were prospectively enrolled. Eighteen first-order features were extracted from VOIs (primary tumours, benign mucosa, and OC). Statistical comparisons were conducted between groups using the independent-samples t-test and the Mann-Whitney U test to select significant parameters. Multiple diagnostic models were then constructed using multivariate logistic analysis. The diagnostic performance of the models was calculated by receiver operating characteristics (ROC) curve analysis and compared using the DeLong test. Bootstrap and 5-folds cross-validation were applied to avoid overfitting. RESULTS The T1, T2 and PD map-derived models had excellent diagnostic performance in the discrimination between NPC and NPH in volunteers, with area under the curves (AUCs) of 0.975, 0.972 and 0.986, respectively. Besides, SyMRI models also showed excellent performance in distinguishing OC invasion from non-invasion (AUC: 0.913-0.997). Notably, the T1 map-derived model showed the highest diagnostic performance with an AUC, sensitivity, specificity, and accuracy of 0.997, 96.9%, 97.9% and 97.5%, respectively. By using 5-folds cross-validation, the bias-corrected AUCs were 0.965-0.984 in discriminating NPC from NPH and 0.889-0.975 in discriminating OC invasion from OC non-invasion. CONCLUSIONS SyMRI combined with first-order parameters showed excellent performance in differentiating NPC from NPH, as well as discriminating OC invasion from non-invasion.
Collapse
Affiliation(s)
- Fan Yang
- grid.506261.60000 0001 0706 7839Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021 China
| | - Yujie Li
- grid.506261.60000 0001 0706 7839Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021 China
| | - Xiaolu Li
- grid.506261.60000 0001 0706 7839Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021 China
| | - Xiaoduo Yu
- grid.506261.60000 0001 0706 7839Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021 China
| | - Yanfeng Zhao
- grid.506261.60000 0001 0706 7839Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021 China
| | - Lin Li
- grid.506261.60000 0001 0706 7839Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021 China
| | - Lizhi Xie
- MR Research China, GE Healthcare, Beijing, China
| | - Meng Lin
- grid.506261.60000 0001 0706 7839Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021 China
| |
Collapse
|
6
|
Hung KF, Ai QYH, Wong LM, Yeung AWK, Li DTS, Leung YY. Current Applications of Deep Learning and Radiomics on CT and CBCT for Maxillofacial Diseases. Diagnostics (Basel) 2022; 13:diagnostics13010110. [PMID: 36611402 PMCID: PMC9818323 DOI: 10.3390/diagnostics13010110] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2022] [Revised: 12/23/2022] [Accepted: 12/24/2022] [Indexed: 12/31/2022] Open
Abstract
The increasing use of computed tomography (CT) and cone beam computed tomography (CBCT) in oral and maxillofacial imaging has driven the development of deep learning and radiomics applications to assist clinicians in early diagnosis, accurate prognosis prediction, and efficient treatment planning of maxillofacial diseases. This narrative review aimed to provide an up-to-date overview of the current applications of deep learning and radiomics on CT and CBCT for the diagnosis and management of maxillofacial diseases. Based on current evidence, a wide range of deep learning models on CT/CBCT images have been developed for automatic diagnosis, segmentation, and classification of jaw cysts and tumors, cervical lymph node metastasis, salivary gland diseases, temporomandibular (TMJ) disorders, maxillary sinus pathologies, mandibular fractures, and dentomaxillofacial deformities, while CT-/CBCT-derived radiomics applications mainly focused on occult lymph node metastasis in patients with oral cancer, malignant salivary gland tumors, and TMJ osteoarthritis. Most of these models showed high performance, and some of them even outperformed human experts. The models with performance on par with human experts have the potential to serve as clinically practicable tools to achieve the earliest possible diagnosis and treatment, leading to a more precise and personalized approach for the management of maxillofacial diseases. Challenges and issues, including the lack of the generalizability and explainability of deep learning models and the uncertainty in the reproducibility and stability of radiomic features, should be overcome to gain the trust of patients, providers, and healthcare organizers for daily clinical use of these models.
Collapse
Affiliation(s)
- Kuo Feng Hung
- Oral and Maxillofacial Surgery, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China
| | - Qi Yong H. Ai
- Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Lun M. Wong
- Imaging and Interventional Radiology, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Andy Wai Kan Yeung
- Oral and Maxillofacial Radiology, Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China
| | - Dion Tik Shun Li
- Oral and Maxillofacial Surgery, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China
| | - Yiu Yan Leung
- Oral and Maxillofacial Surgery, Faculty of Dentistry, The University of Hong Kong, Hong Kong SAR, China
- Correspondence:
| |
Collapse
|
7
|
Radiomics for Discriminating Benign and Malignant Salivary Gland Tumors; Which Radiomic Feature Categories and MRI Sequences Should Be Used? Cancers (Basel) 2022; 14:cancers14235804. [PMID: 36497285 PMCID: PMC9740105 DOI: 10.3390/cancers14235804] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2022] [Revised: 11/12/2022] [Accepted: 11/22/2022] [Indexed: 11/26/2022] Open
Abstract
The lack of a consistent MRI radiomic signature, partly due to the multitude of initial feature analyses, limits the widespread clinical application of radiomics for the discrimination of salivary gland tumors (SGTs). This study aimed to identify the optimal radiomics feature category and MRI sequence for characterizing SGTs, which could serve as a step towards obtaining a consensus on a radiomics signature. Preliminary radiomics models were built to discriminate malignant SGTs (n = 34) from benign SGTs (n = 57) on T1-weighted (T1WI), fat-suppressed (FS)-T2WI and contrast-enhanced (CE)-T1WI images using six feature categories. The discrimination performances of these preliminary models were evaluated using 5-fold-cross-validation with 100 repetitions and the area under the receiver operating characteristic curve (AUC). The differences between models’ performances were identified using one-way ANOVA. Results show that the best feature categories were logarithm for T1WI and CE-T1WI and exponential for FS-T2WI, with AUCs of 0.828, 0.754 and 0.819, respectively. These AUCs were higher than the AUCs obtained using all feature categories combined, which were 0.750, 0.707 and 0.774, respectively (p < 0.001). The highest AUC (0.846) was obtained using a combination of T1WI + logarithm and FS-T2WI + exponential features, which reduced the initial features by 94.0% (from 1015 × 3 to 91 × 2). CE-T1WI did not improve performance. Using one feature category rather than all feature categories combined reduced the number of initial features without compromising radiomic performance.
Collapse
|