1
|
Karakas AB, Govsa F, Ozer MA, Biceroglu H, Eraslan C, Tanir D. From pixels to prognosis: leveraging radiomics and machine learning to predict IDH1 genotype in gliomas. Neurosurg Rev 2025; 48:396. [PMID: 40299088 PMCID: PMC12040993 DOI: 10.1007/s10143-025-03515-z] [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: 12/11/2024] [Revised: 03/17/2025] [Accepted: 04/05/2025] [Indexed: 04/30/2025]
Abstract
Gliomas are the most common primary tumors of the central nervous system, and advances in genetics and molecular medicine have significantly transformed their classification and treatment. This study aims to predict the IDH1 genotype in gliomas using radiomics and machine learning (ML) methods. Retrospective data from 108 glioma patients were analyzed, including MRI data supported by demographic details such as age, sex, and comorbidities. Tumor segmentation was manually performed using 3D Slicer software, and 112 radiomic features were extracted with the PyRadiomics library. Feature selection using the mRMR algorithm identified 17 significant radiomic features. Various ML algorithms, including KNN, Ensemble, DT, LR, Discriminant and SVM, were applied to predict the IDH1 genotype. The KNN and Ensemble models achieved the highest sensitivity (92-100%) and specificity (100%), emerging as the most successful models. Comparative analyses demonstrated that KNN achieved an accuracy of 92.59%, sensitivity of 92.38%, specificity of 100%, precision of 100%, and an F1-score of 95.02%. Similarly, the Ensemble model achieved an accuracy of 90.74%, sensitivity of 90.65%, specificity of 100%, precision of 100%, and an F1-score of 95.13%. To evaluate their effectiveness, KNN and Ensemble models were compared with commonly used machine learning approaches in glioma classification. LR, a conventional statistical approach, exhibited lower predictive performance with an accuracy of 79.63%, while SVM, a frequently utilized ML model for radiomics-based tumor classification, achieved an accuracy of 85.19%. Our findings are consistent with previous research indicating that radiomics-based ML models achieve high accuracy in IDH1 mutation prediction, with reported performances typically exceeding 80%. These findings suggest that KNN and Ensemble models are more effective in capturing the non-linear radiomic patterns associated with IDH1 status, compared to traditional ML approaches. Our findings indicate that radiomic analyses provide comprehensive genotypic classification by assessing the entire tumor and present a safer, faster, and more patient-friendly alternative to traditional biopsies. This study highlights the potential of radiomics and ML techniques, particularly KNN, Ensemble, and SVM, as powerful tools for predicting the molecular characteristics of gliomas and developing personalized treatment strategies.
Collapse
Affiliation(s)
- Asli Beril Karakas
- Department of Anatomy, Faculty of Medicine, Kastamonu University, Kastamonu, 37200, Turkey.
| | - Figen Govsa
- Department of Anatomy, Faculty of Medicine, Ege University, Izmir, Turkey
| | - Mehmet Asim Ozer
- Department of Anatomy, Faculty of Medicine, Ege University, Izmir, Turkey
| | - Huseyin Biceroglu
- Department of Neurosurgery, Faculty of Medicine, Ege University, Izmir, Turkey
| | - Cenk Eraslan
- Department of Radiology, Faculty of Medicine, Ege University, Izmir, Turkey
| | - Deniz Tanir
- Department of Management Information Systems, Faculty of Economics and Administrative Sciences, Kafkas University, Kars, Turkey
| |
Collapse
|
2
|
Gouel P, Callonnec F, Levêque É, Valet C, Blôt A, Cuvelier C, Saï S, Saunier L, Pepin LF, Hapdey S, Libraire J, Vera P, Viard B. Evaluation of the capability and reproducibility of RECIST 1.1. measurements by technologists in breast cancer follow-up: a pilot study. Sci Rep 2023; 13:9148. [PMID: 37277412 DOI: 10.1038/s41598-023-36315-w] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2022] [Accepted: 05/31/2023] [Indexed: 06/07/2023] Open
Abstract
The evaluation of tumor follow-up according to RECIST 1.1 has become essential in clinical practice given its role in therapeutic decision making. At the same time, radiologists are facing an increase in activity while facing a shortage. Radiographic technologists could contribute to the follow-up of these measures, but no studies have evaluated their ability to perform them. Ninety breast cancer patients were performed three CT follow-ups between September 2017 and August 2021. 270 follow-up treatment CT scans were analyzed including 445 target lesions. The rate of agreement of classifications RECIST 1.1 between five technologists and radiologists yielded moderate (k value between 0.47 and 0.52) and substantial (k value = 0.62 and k = 0.67) agreement values. 112 CT were classified as progressive disease (PD) by the radiologists, and 414 new lesions were identified. The analysis showed a percentage of strict agreement of progressive disease classification between reader-technologists and radiologists ranging from substantial to almost perfect agreement (range 73-97%). Analysis of intra-observer agreement was strong at almost perfect (k > 0.78) for 3 technologists. These results are encouraging regarding the ability of selected technologists to perform measurements according to RECIST 1.1 criteria by CT scan with good identification of disease progression.
Collapse
Affiliation(s)
- Pierrick Gouel
- Department of Medical Imaging, Henri Becquerel Cancer Center, Rouen, Normandy, France.
- QuantIF-LITIS EA4108, University of Rouen, Rouen, Normandy, France.
| | - Françoise Callonnec
- Department of Medical Imaging, Henri Becquerel Cancer Center, Rouen, Normandy, France
| | - Émilie Levêque
- Department of Statistics and Clinical Research Unit, Henri Becquerel Cancer Center, Rouen, Normandy, France
| | - Céline Valet
- Department of Medical Imaging, Henri Becquerel Cancer Center, Rouen, Normandy, France
| | - Axelle Blôt
- Department of Medical Imaging, Henri Becquerel Cancer Center, Rouen, Normandy, France
| | - Clémence Cuvelier
- Department of Medical Imaging, Henri Becquerel Cancer Center, Rouen, Normandy, France
| | - Sonia Saï
- Department of Medical Imaging, Henri Becquerel Cancer Center, Rouen, Normandy, France
| | - Lucie Saunier
- Department of Medical Imaging, Henri Becquerel Cancer Center, Rouen, Normandy, France
| | - Louis-Ferdinand Pepin
- Department of Statistics and Clinical Research Unit, Henri Becquerel Cancer Center, Rouen, Normandy, France
| | - Sébastien Hapdey
- Department of Medical Imaging, Henri Becquerel Cancer Center, Rouen, Normandy, France
- QuantIF-LITIS EA4108, University of Rouen, Rouen, Normandy, France
| | - Julie Libraire
- Department of Statistics and Clinical Research Unit, Henri Becquerel Cancer Center, Rouen, Normandy, France
| | - Pierre Vera
- Department of Medical Imaging, Henri Becquerel Cancer Center, Rouen, Normandy, France
- QuantIF-LITIS EA4108, University of Rouen, Rouen, Normandy, France
| | - Benjamin Viard
- Department of Medical Imaging, Henri Becquerel Cancer Center, Rouen, Normandy, France
| |
Collapse
|
3
|
Diao K, Liang HQ, Yin HK, Yuan MJ, Gu M, Yu PX, He S, Sun J, Song B, Li K, He Y. Multi-channel deep learning model-based myocardial spatial-temporal morphology feature on cardiac MRI cine images diagnoses the cause of LVH. Insights Imaging 2023; 14:70. [PMID: 37093501 PMCID: PMC10126185 DOI: 10.1186/s13244-023-01401-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2022] [Accepted: 03/08/2023] [Indexed: 04/25/2023] Open
Abstract
BACKGROUND To develop a fully automatic framework for the diagnosis of cause for left ventricular hypertrophy (LVH) via cardiac cine images. METHODS A total of 302 LVH patients with cine MRI images were recruited as the primary cohort. Another 53 LVH patients prospectively collected or from multi-centers were used as the external test dataset. Different models based on the cardiac regions (Model 1), segmented ventricle (Model 2) and ventricle mask (Model 3) were constructed. The diagnostic performance was accessed by the confusion matrix with respect to overall accuracy. The capability of the predictive models for binary classification of cardiac amyloidosis (CA), hypertrophic cardiomyopathy (HCM) or hypertensive heart disease (HHD) were also evaluated. Additionally, the diagnostic performance of best Model was compared with that of 7 radiologists/cardiologists. RESULTS Model 3 showed the best performance with an overall classification accuracy up to 77.4% in the external test datasets. On the subtasks for identifying CA, HCM or HHD only, Model 3 also achieved the best performance with AUCs yielding 0.895-0.980, 0.879-0.984 and 0.848-0.983 in the validation, internal test and external test datasets, respectively. The deep learning model showed non-inferior diagnostic capability to the cardiovascular imaging expert and outperformed other radiologists/cardiologists. CONCLUSION The combined model based on the mask of left ventricular segmented from multi-sequences cine MR images shows favorable and robust performance in diagnosing the cause of left ventricular hypertrophy, which could be served as a noninvasive tool and help clinical decision.
Collapse
Affiliation(s)
- Kaiyue Diao
- Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China
| | - Hong-Qing Liang
- Department of Radiology, First Affiliated Hospital to Army Medical University (Third Military Medical University Southwest Hospital), Chongqing, China
| | - Hong-Kun Yin
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, China
| | - Ming-Jing Yuan
- Department of Radiology, Yongchuan Hospital, Chongqing Medical University, Chongqing, China
| | - Min Gu
- Department of Radiology, Chongqing General Hospital, University of Chinese Academy of Sciences, Chongqing, China
| | - Peng-Xin Yu
- Institute of Advanced Research, Infervision Medical Technology Co., Ltd, Beijing, China
| | - Sen He
- Department of Cardiology, West China Hospital of Sichuan University, 37 Guo Xue Xiang, Chengdu, 610041, Sichuan, China
| | - Jiayu Sun
- Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China
| | - Bin Song
- Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China
- Department of Radiology, Sanya Municipal People's Hospital, Sanya, Hainan, China
| | - Kang Li
- West China Biomedical Big Data Center, Med-X Center for Informatics, West China Hospital, Sichuan University, 37 Guo Xue Xiang, Chengdu, 610041, Sichuan, China.
- Med-X Center for Informatics, Sichuan University, Chengdu, China.
| | - Yong He
- Department of Cardiology, West China Hospital of Sichuan University, 37 Guo Xue Xiang, Chengdu, 610041, Sichuan, China.
| |
Collapse
|