Yoon Seong Choi1,2, Sung Soo Ahn3, Jong Hee Chang4, Seok-Gu Kang4, Eui Hyun Kim4, Se Hoon Kim5, Rajan Jain6,7, Seung-Koo Lee1. 1. Department of Radiology and Research Institute of Radiological Science, College of Medicine, Yonsei University College of Medicine, 50 Yonsei-ro, Seodaemun-gu, Seoul, 120-752, South Korea. 2. Department of Diagnostic Radiology, Singapore General Hospital, Singapore, Singapore. 3. Department of Radiology and Research Institute of Radiological Science, College of Medicine, Yonsei University College of Medicine, 50 Yonsei-ro, Seodaemun-gu, Seoul, 120-752, South Korea. SUNGSOO@yuhs.ac. 4. Department of Neurosurgery, Yonsei University College of Medicine, Seoul, South Korea. 5. Department of Pathology, Yonsei University College of Medicine, Seoul, South Korea. 6. Department of Radiology, Langone Medical Center, New York University School of Medicine, New York, NY, USA. 7. Department of Neurosurgery, Langone Medical Center, New York University School of Medicine, New York, NY, USA.
Abstract
BACKGROUND AND PURPOSE: Recent studies have highlighted the importance of isocitrate dehydrogenase (IDH) mutational status in stratifying biologically distinct subgroups of gliomas. This study aimed to evaluate whether MRI-based radiomic features could improve the accuracy of survival predictions for lower grade gliomas over clinical and IDH status. MATERIALS AND METHODS: Radiomic features (n = 250) were extracted from preoperative MRI data of 296 lower grade glioma patients from databases at our institutional (n = 205) and The Cancer Genome Atlas (TCGA)/The Cancer Imaging Archive (TCIA) (n = 91) datasets. For predicting overall survival, random survival forest models were trained with radiomic features; non-imaging prognostic factors including age, resection extent, WHO grade, and IDH status on the institutional dataset, and validated on the TCGA/TCIA dataset. The performance of the random survival forest (RSF) model and incremental value of radiomic features were assessed by time-dependent receiver operating characteristics. RESULTS: The radiomics RSF model identified 71 radiomic features to predict overall survival, which were successfully validated on TCGA/TCIA dataset (iAUC, 0.620; 95% CI, 0.501-0.756). Relative to the RSF model from the non-imaging prognostic parameters, the addition of radiomic features significantly improved the overall survival prediction accuracy of the random survival forest model (iAUC, 0.627 vs. 0.709; difference, 0.097; 95% CI, 0.003-0.209). CONCLUSION: Radiomic phenotyping with machine learning can improve survival prediction over clinical profile and genomic data for lower grade gliomas. KEY POINTS: • Radiomics analysis with machine learning can improve survival prediction over the non-imaging factors (clinical and molecular profiles) for lower grade gliomas, across different institutions.
BACKGROUND AND PURPOSE: Recent studies have highlighted the importance of isocitrate dehydrogenase (IDH) mutational status in stratifying biologically distinct subgroups of gliomas. This study aimed to evaluate whether MRI-based radiomic features could improve the accuracy of survival predictions for lower grade gliomas over clinical and IDH status. MATERIALS AND METHODS: Radiomic features (n = 250) were extracted from preoperative MRI data of 296 lower grade gliomapatients from databases at our institutional (n = 205) and The Cancer Genome Atlas (TCGA)/The Cancer Imaging Archive (TCIA) (n = 91) datasets. For predicting overall survival, random survival forest models were trained with radiomic features; non-imaging prognostic factors including age, resection extent, WHO grade, and IDH status on the institutional dataset, and validated on the TCGA/TCIA dataset. The performance of the random survival forest (RSF) model and incremental value of radiomic features were assessed by time-dependent receiver operating characteristics. RESULTS: The radiomics RSF model identified 71 radiomic features to predict overall survival, which were successfully validated on TCGA/TCIA dataset (iAUC, 0.620; 95% CI, 0.501-0.756). Relative to the RSF model from the non-imaging prognostic parameters, the addition of radiomic features significantly improved the overall survival prediction accuracy of the random survival forest model (iAUC, 0.627 vs. 0.709; difference, 0.097; 95% CI, 0.003-0.209). CONCLUSION: Radiomic phenotyping with machine learning can improve survival prediction over clinical profile and genomic data for lower grade gliomas. KEY POINTS: • Radiomics analysis with machine learning can improve survival prediction over the non-imaging factors (clinical and molecular profiles) for lower grade gliomas, across different institutions.
Authors: Zaid Abdi Alkareem Alyasseri; Mohammed Azmi Al-Betar; Iyad Abu Doush; Mohammed A Awadallah; Ammar Kamal Abasi; Sharif Naser Makhadmeh; Osama Ahmad Alomari; Karrar Hameed Abdulkareem; Afzan Adam; Robertas Damasevicius; Mazin Abed Mohammed; Raed Abu Zitar Journal: Expert Syst Date: 2021-07-28 Impact factor: 2.812
Authors: Arshad A Pandith; Iqbal Qasim; Shahid M Baba; Aabid Koul; Wani Zahoor; Dil Afroze; Adil Lateef; Usma Manzoor; Ina A Bhat; Dheera Sanadhya; Abdul R Bhat; Altaf U Ramzan; Fozia Mohammad; Iqra Anwar Journal: Future Sci OA Date: 2020-12-09
Authors: Simon Williams; Hugo Layard Horsfall; Jonathan P Funnell; John G Hanrahan; Danyal Z Khan; William Muirhead; Danail Stoyanov; Hani J Marcus Journal: Cancers (Basel) Date: 2021-10-07 Impact factor: 6.639