1
|
Azizova A, Prysiazhniuk Y, Wamelink IJHG, Petr J, Barkhof F, Keil VC. Ten Years of VASARI Glioma Features: Systematic Review and Meta-Analysis of Their Impact and Performance. AJNR Am J Neuroradiol 2024:ajnr.A8274. [PMID: 38937115 DOI: 10.3174/ajnr.a8274] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2024] [Accepted: 03/01/2024] [Indexed: 06/29/2024]
Abstract
BACKGROUND Visually Accessible Rembrandt (Repository for Molecular Brain Neoplasia Data) Images (VASARI) features, a vocabulary to establish reproducible terminology for glioma reporting, have been applied for a decade, but a systematic performance evaluation is lacking. PURPOSE Our aim was to conduct a systematic review and meta-analysis of the performance of the VASARI features set for glioma assessment. DATA SOURCES MEDLINE, Web of Science, EMBASE, and the Cochrane Library were systematically searched until September 26, 2023. STUDY SELECTION Original articles predicting diagnosis, progression, and survival in patients with glioma were included. DATA ANALYSIS The modified Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was applied to evaluate the risk-of-bias. The meta-analysis used a random effects model and forest plot visualizations, if ≥5 comparable studies with a low or medium risk of bias were provided. DATA SYNTHESIS Thirty-five studies (3304 patients) were included. Risk-of-bias scores were medium (n = 33) and low (n = 2). Recurring objectives were overall survival (n = 18) and isocitrate dehydrogenase mutation (IDH; n = 12) prediction. Progression-free survival was examined in 7 studies. In 4 studies (glioblastoma n = 2, grade 2/3 glioma n = 1, grade 3 glioma n = 1), a significant association was found between progression-free survival and single VASARI features. The single features predicting overall survival with the highest pooled hazard ratios were multifocality (hazard ratio = 1.80; 95%-CI, 1.21-2.67; I2 = 53%), ependymal invasion (hazard ratio = 1.73; 95% CI, 1.45-2.05; I2 = 0%), and enhancing tumor crossing the midline (hazard ratio = 2.08; 95% CI, 1.35-3.18; I2 = 52%). IDH mutation-predicting models combining VASARI features rendered a pooled area under the receiver operating characteristic curve of 0.82 (95% CI, 0.76-0.88) at considerable heterogeneity (I2 = 100%). Combined input models using VASARI plus clinical and/or radiomics features outperformed single data-type models in all relevant studies (n = 17). LIMITATIONS Studies were heterogeneously designed and often with a small sample size. Several studies used The Cancer Imaging Archive database, with likely overlapping cohorts. The meta-analysis for IDH was limited due to a high study heterogeneity. CONCLUSIONS Some VASARI features perform well in predicting overall survival and IDH mutation status, but combined models outperform single features. More studies with less heterogeneity are needed to increase the evidence level.
Collapse
Affiliation(s)
- Aynur Azizova
- From the Radiology and Nuclear Medicine Department (A.A., I.J.H.G.W., J.P., F.B., V.C.K.), Amsterdam UMC location Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
- Imaging and Biomarkers (A.A., I.J.H.G.W., V.C.K.), Cancer Center Amsterdam, Amsterdam, the Netherlands
| | - Yeva Prysiazhniuk
- The Second Faculty of Medicine (Y.P.), Department of Pathophysiology, Charles University, Prague, Czech Republic
| | - Ivar J H G Wamelink
- From the Radiology and Nuclear Medicine Department (A.A., I.J.H.G.W., J.P., F.B., V.C.K.), Amsterdam UMC location Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
- Imaging and Biomarkers (A.A., I.J.H.G.W., V.C.K.), Cancer Center Amsterdam, Amsterdam, the Netherlands
| | - Jan Petr
- From the Radiology and Nuclear Medicine Department (A.A., I.J.H.G.W., J.P., F.B., V.C.K.), Amsterdam UMC location Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
- Institute of Radiopharmaceutical Cancer Research (J.P.), Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany
| | - Frederik Barkhof
- From the Radiology and Nuclear Medicine Department (A.A., I.J.H.G.W., J.P., F.B., V.C.K.), Amsterdam UMC location Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
- Brain Imaging (F.B., V.C.K.), Amsterdam Neuroscience, Amsterdam, the Netherlands
- Queen Square Institute of Neurology and Center for Medical Image Computing (F.B.), University College London, London, United Kingdom
| | - Vera C Keil
- From the Radiology and Nuclear Medicine Department (A.A., I.J.H.G.W., J.P., F.B., V.C.K.), Amsterdam UMC location Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
- Imaging and Biomarkers (A.A., I.J.H.G.W., V.C.K.), Cancer Center Amsterdam, Amsterdam, the Netherlands
- Brain Imaging (F.B., V.C.K.), Amsterdam Neuroscience, Amsterdam, the Netherlands
| |
Collapse
|
2
|
Li A, Hu Y, Cui XW, Ye XH, Peng XJ, Lv WZ, Zhao CK. Predicting the malignancy of extremity soft-tissue tumors by an ultrasound-based radiomics signature. Acta Radiol 2024; 65:470-481. [PMID: 38321752 DOI: 10.1177/02841851231217227] [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] [Indexed: 02/08/2024]
Abstract
BACKGROUND Accurate differentiation of extremity soft-tissue tumors (ESTTs) is important for treatment planning. PURPOSE To develop and validate an ultrasound (US) image-based radiomics signature to predict ESTTs malignancy. MATERIAL AND METHODS A dataset of US images from 108 ESTTs were retrospectively enrolled and divided into the training cohort (78 ESTTs) and validation cohort (30 ESTTs). A total of 1037 radiomics features were extracted from each US image. The most useful predictive radiomics features were selected by the maximum relevance and minimum redundancy method, least absolute shrinkage, and selection operator algorithm in the training cohort. A US-based radiomics signature was built based on these selected radiomics features. In addition, a conventional radiologic model based on the US features from the interpretation of two experienced radiologists was developed by a multivariate logistic regression algorithm. The diagnostic performances of the selected radiomics features, the US-based radiomics signature, and the conventional radiologic model for differentiating ESTTs were evaluated and compared in the validation cohort. RESULTS In the validation cohort, the area under the curve (AUC), sensitivity, and specificity of the US-based radiomics signature for predicting ESTTs malignancy were 0.866, 84.2%, and 81.8%, respectively. The US-based radiomics signature had better diagnostic predictability for predicting ESTT malignancy than the best single radiomics feature and the conventional radiologic model (AUC = 0.866 vs. 0.719 vs. 0.681 for the validation cohort, all P <0.05). CONCLUSION The US-based radiomics signature could provide a potential imaging biomarker to accurately predict ESTT malignancy.
Collapse
Affiliation(s)
- Ao Li
- Department of Medical Ultrasound, First Affiliated Hospital of Nanjing Medical University, Nanjing, PR China
| | - Yu Hu
- Department of Medical Ultrasound, First Affiliated Hospital of Nanjing Medical University, Nanjing, PR China
| | - Xin-Wu Cui
- Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, PR China
| | - Xin-Hua Ye
- Department of Medical Ultrasound, First Affiliated Hospital of Nanjing Medical University, Nanjing, PR China
| | - Xiao-Jing Peng
- Department of Medical Ultrasound, First Affiliated Hospital of Nanjing Medical University, Nanjing, PR China
| | - Wen-Zhi Lv
- Department of Artificial Intelligence, Julei Technology, Wuhan, PR China
| | - Chong-Ke Zhao
- Department of Ultrasound, Zhongshan Hospital, Institute of Ultrasound in Medicine and Engineering, Fudan University, Shanghai, PR China
| |
Collapse
|
3
|
Fatania K, Frood R, Mistry H, Short SC, O’Connor J, Scarsbrook AF, Currie S. Tumour Size and Overall Survival in a Cohort of Patients with Unifocal Glioblastoma: A Uni- and Multivariable Prognostic Modelling and Resampling Study. Cancers (Basel) 2024; 16:1301. [PMID: 38610979 PMCID: PMC11011077 DOI: 10.3390/cancers16071301] [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: 02/15/2024] [Revised: 03/15/2024] [Accepted: 03/20/2024] [Indexed: 04/14/2024] Open
Abstract
Published models inconsistently associate glioblastoma size with overall survival (OS). This study aimed to investigate the prognostic effect of tumour size in a large cohort of patients diagnosed with GBM and interrogate how sample size and non-linear transformations may impact on the likelihood of finding a prognostic effect. In total, 279 patients with a IDH-wildtype unifocal WHO grade 4 GBM between 2014 and 2020 from a retrospective cohort were included. Uni-/multivariable association between core volume, whole volume (CV and WV), and diameter with OS was assessed with (1) Cox proportional hazard models +/- log transformation and (2) resampling with 1,000,000 repetitions and varying sample size to identify the percentage of models, which showed a significant effect of tumour size. Models adjusted for operation type and a diameter model adjusted for all clinical variables remained significant (p = 0.03). Multivariable resampling increased the significant effects (p < 0.05) of all size variables as sample size increased. Log transformation also had a large effect on the chances of a prognostic effect of WV. For models adjusted for operation type, 19.5% of WV vs. 26.3% log-WV (n = 50) and 69.9% WV and 89.9% log-WV (n = 279) were significant. In this large well-curated cohort, multivariable modelling and resampling suggest tumour volume is prognostic at larger sample sizes and with log transformation for WV.
Collapse
Affiliation(s)
- Kavi Fatania
- Department of Radiology, Leeds Teaching Hospitals NHS Trust, Leeds General Infirmary, Leeds LS1 3EX, UK (A.F.S.); (S.C.)
- Leeds Institute of Medical Research, University of Leeds, Leeds LS2 9TJ, UK;
| | - Russell Frood
- Department of Radiology, Leeds Teaching Hospitals NHS Trust, Leeds General Infirmary, Leeds LS1 3EX, UK (A.F.S.); (S.C.)
- Leeds Institute of Medical Research, University of Leeds, Leeds LS2 9TJ, UK;
| | - Hitesh Mistry
- Division of Cancer Sciences, The University of Manchester, Manchester M13 9PL, UK; (H.M.)
| | - Susan C. Short
- Leeds Institute of Medical Research, University of Leeds, Leeds LS2 9TJ, UK;
- Department of Oncology, Leeds Teaching Hospitals NHS Trust, St James’s University Hospital, Leeds LS9 7TF, UK
| | - James O’Connor
- Division of Cancer Sciences, The University of Manchester, Manchester M13 9PL, UK; (H.M.)
- Department of Radiology, The Christie Hospital, Manchester M20 4BX, UK
- Division of Radiotherapy and Imaging, Institute of Cancer Research, London SM2 5NG, UK
| | - Andrew F. Scarsbrook
- Department of Radiology, Leeds Teaching Hospitals NHS Trust, Leeds General Infirmary, Leeds LS1 3EX, UK (A.F.S.); (S.C.)
- Leeds Institute of Medical Research, University of Leeds, Leeds LS2 9TJ, UK;
| | - Stuart Currie
- Department of Radiology, Leeds Teaching Hospitals NHS Trust, Leeds General Infirmary, Leeds LS1 3EX, UK (A.F.S.); (S.C.)
- Leeds Institute of Medical Research, University of Leeds, Leeds LS2 9TJ, UK;
| |
Collapse
|
4
|
Fan H, Luo Y, Gu F, Tian B, Xiong Y, Wu G, Nie X, Yu J, Tong J, Liao X. Artificial intelligence-based MRI radiomics and radiogenomics in glioma. Cancer Imaging 2024; 24:36. [PMID: 38486342 PMCID: PMC10938723 DOI: 10.1186/s40644-024-00682-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Accepted: 03/03/2024] [Indexed: 03/18/2024] Open
Abstract
The specific genetic subtypes that gliomas exhibit result in variable clinical courses and the need to involve multidisciplinary teams of neurologists, epileptologists, neurooncologists and neurosurgeons. Currently, the diagnosis of gliomas pivots mainly around the preliminary radiological findings and the subsequent definitive surgical diagnosis (via surgical sampling). Radiomics and radiogenomics present a potential to precisely diagnose and predict survival and treatment responses, via morphological, textural, and functional features derived from MRI data, as well as genomic data. In spite of their advantages, it is still lacking standardized processes of feature extraction and analysis methodology among different research groups, which have made external validations infeasible. Radiomics and radiogenomics can be used to better understand the genomic basis of gliomas, such as tumor spatial heterogeneity, treatment response, molecular classifications and tumor microenvironment immune infiltration. These novel techniques have also been used to predict histological features, grade or even overall survival in gliomas. In this review, workflows of radiomics and radiogenomics are elucidated, with recent research on machine learning or artificial intelligence in glioma.
Collapse
Affiliation(s)
- Haiqing Fan
- Department of Medical Imaging, The Affiliated Hospital of Guizhou Medical University, 550000, Guizhou, Guiyang, China
| | - Yilin Luo
- Department of Medical Imaging, The Affiliated Hospital of Guizhou Medical University, 550000, Guizhou, Guiyang, China
| | - Fang Gu
- Department of Medical Imaging, The Affiliated Hospital of Guizhou Medical University, 550000, Guizhou, Guiyang, China
| | - Bin Tian
- Department of Medical Imaging, The Affiliated Hospital of Guizhou Medical University, 550000, Guizhou, Guiyang, China
| | - Yongqin Xiong
- Department of Medical Imaging, The Affiliated Hospital of Guizhou Medical University, 550000, Guizhou, Guiyang, China
| | - Guipeng Wu
- Department of Medical Imaging, The Affiliated Hospital of Guizhou Medical University, 550000, Guizhou, Guiyang, China
| | - Xin Nie
- Department of Medical Imaging, The Affiliated Hospital of Guizhou Medical University, 550000, Guizhou, Guiyang, China
| | - Jing Yu
- Department of Medical Imaging, The Affiliated Hospital of Guizhou Medical University, 550000, Guizhou, Guiyang, China
| | - Juan Tong
- Department of Medical Imaging, The Affiliated Hospital of Guizhou Medical University, 550000, Guizhou, Guiyang, China
| | - Xin Liao
- Department of Medical Imaging, The Affiliated Hospital of Guizhou Medical University, 550000, Guizhou, Guiyang, China.
| |
Collapse
|
5
|
Dono A, Torres J, Nunez L, Arevalo O, Rodriguez-Quinteros JC, Riascos RF, Kamali A, Tandon N, Ballester LY, Esquenazi Y. Imaging predictors of 4q12 amplified and RB1 mutated glioblastoma IDH-wildtype. J Neurooncol 2024; 167:99-109. [PMID: 38351343 PMCID: PMC11227885 DOI: 10.1007/s11060-024-04575-9] [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: 11/07/2023] [Accepted: 01/16/2024] [Indexed: 07/04/2024]
Abstract
INTRODUCTION Recent studies have identified that glioblastoma IDH-wildtype consists of different molecular subgroups with distinct prognoses. In order to accurately describe and classify gliomas, the Visually AcceSAble Rembrandt Images (VASARI) system was developed. The goal of this study was to evaluate the VASARI characteristics in molecular subgroups of IDH-wildtype glioblastoma. METHODS A retrospective analysis of glioblastoma IDH- wildtype with comprehensive next-generation sequencing and pre-operative and post-operative MRI was performed. VASARI characteristics and 205 genes were evaluated. Multiple comparison adjustment by the Bejamin-Hochberg false discovery rate (BH-FDR) was performed. A 1:3 propensity score match (PSM) with a Caliper of 0.2 was done. RESULTS 178 patients with GBM IDH-WT met the inclusion criteria. 4q12 amplified patients (n = 20) were associated with cyst presence (30% vs. 12%, p = 0.042), decreased hemorrhage (35% vs. 62%, p = 0.028), and non-restricting/mixed (35%/60%) rather than restricting diffusion pattern (5%), meanwhile, 4q12 non-amplified patients had mostly restricting (47.4%) rather than a non-restricting/mixed diffusion pattern (28.4%/23.4%). This remained statistically significant after BH-FDR adjustment (p = 0.002). PSM by 4q12 amplification showed that diffusion characteristics continued to be significantly different. Among RB1-mutant patients, 96% had well-defined enhancing margins vs. 70.6% of RB1-WT (p = 0.018), however, this was not significant after BH-FDR or PSM. CONCLUSIONS Patients with glioblastoma IDH-wildtype harboring 4q12 amplification rarely have restricting DWI patterns compared to their wildtype counterparts, in which this DWI pattern is present in ~ 50% of patients. This suggests that some phenotypic imaging characteristics can be identified among molecular subtypes of IDH-wildtype glioblastoma.
Collapse
Affiliation(s)
- Antonio Dono
- Vivian L. Smith Department of Neurosurgery, McGovern Medical School, The University of Texas Health Science Center at Houston, 77030, Houston, TX, USA
| | - Jose Torres
- Vivian L. Smith Department of Neurosurgery, McGovern Medical School, The University of Texas Health Science Center at Houston, 77030, Houston, TX, USA
| | - Luis Nunez
- Department of Diagnostic and Interventional Imaging, McGovern Medical School, The University of Texas Health Science Center at Houston, 77030, Houston, TX, USA
| | - Octavio Arevalo
- Department of Diagnostic and Interventional Imaging, McGovern Medical School, The University of Texas Health Science Center at Houston, 77030, Houston, TX, USA
- Department of Radiology, LSU Health Shreveport, 71103, Shreveport, LA, USA
| | - Juan Carlos Rodriguez-Quinteros
- Department of Neurology, McGovern Medical School, The University of Texas Health Science Center at Houston, 77030, Houston, TX, USA
| | - Roy F Riascos
- Department of Diagnostic and Interventional Imaging, McGovern Medical School, The University of Texas Health Science Center at Houston, 77030, Houston, TX, USA
- Memorial Hermann Hospital-TMC, 77030, Houston, TX, USA
| | - Arash Kamali
- Department of Diagnostic and Interventional Imaging, McGovern Medical School, The University of Texas Health Science Center at Houston, 77030, Houston, TX, USA
- Memorial Hermann Hospital-TMC, 77030, Houston, TX, USA
| | - Nitin Tandon
- Vivian L. Smith Department of Neurosurgery, McGovern Medical School, The University of Texas Health Science Center at Houston, 77030, Houston, TX, USA
- Memorial Hermann Hospital-TMC, 77030, Houston, TX, USA
| | - Leomar Y Ballester
- Department of Pathology, The University of Texas MD Anderson Cancer Center, 77030, Houston, TX, USA
- Department of Translational Molecular Pathology, The University of Texas MD Anderson Cancer Center, 77030, Houston, TX, USA
| | - Yoshua Esquenazi
- Vivian L. Smith Department of Neurosurgery, McGovern Medical School, The University of Texas Health Science Center at Houston, 77030, Houston, TX, USA.
- Memorial Hermann Hospital-TMC, 77030, Houston, TX, USA.
- Center for Precision Health, School of Biomedical Informatics, the University of Texas Health Science Center at Houston, 77030, Houston, TX, USA.
| |
Collapse
|
6
|
Ren L, Chen J, Deng J, Qing X, Cheng H, Wang D, Ji J, Chen H, Juratli TA, Wakimoto H, Gong Y, Hua L. The development of a combined clinico-radiomics model for predicting post-operative recurrence in atypical meningiomas: a multicenter study. J Neurooncol 2024; 166:59-71. [PMID: 38146046 DOI: 10.1007/s11060-023-04511-3] [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: 10/27/2023] [Accepted: 11/14/2023] [Indexed: 12/27/2023]
Abstract
PURPOSE Atypical meningiomas could manifest early recurrence after surgery and even adjuvant radiotherapy. We aimed to construct a clinico-radiomics model to predict post-operative recurrence of atypical meningiomas based on clinicopathological and radiomics features. MATERIALS AND METHODS The study cohort was comprised of 224 patients from two neurosurgical centers. 164 patients from center I were divided to the training cohort for model development and the testing cohort for internal validation. 60 patients from center II were used for external validation. Clinicopathological characteristics, radiological semantic, and radiomics features were collected. A radiomic signature was comprised of four radiomics features. A clinico-radiomics model combining the radiomics signature and clinical characteristics was constructed to predict the recurrence of atypical meningiomas. RESULTS 1920 radiomics features were extracted from the T1 Contrast and T2-FLAIR sequences of patients in center I. The radiomics signature was able to differentiate post-operative patients into low-risk and high-risk groups based on tumor recurrence (P < 0.001). A clinic-radiomics model was established by combining age, extent of resection, Ki-67 index, surgical history and the radiomics signature for recurrence prediction in atypical meningiomas. The model achieved a good prediction performance with the integrated AUC of 0.858 (0.802-0.915), 0.781 (0.649-0.912) and 0.840 (0.747-0.933) in the training, internal validation and external validation cohort, respectively. CONCLUSIONS The present study established a radiomics signature and a clinico-radiomics model with a favorable performance in predicting tumor recurrence for atypical meningiomas.
Collapse
Affiliation(s)
- Leihao Ren
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
- Institute of Neurosurgery, Fudan University, Shanghai, China
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Fudan University, Shanghai, China
| | - Jiawei Chen
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
- Institute of Neurosurgery, Fudan University, Shanghai, China
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Fudan University, Shanghai, China
| | - Jiaojiao Deng
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
- Institute of Neurosurgery, Fudan University, Shanghai, China
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Fudan University, Shanghai, China
| | - Xie Qing
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
- Institute of Neurosurgery, Fudan University, Shanghai, China
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Fudan University, Shanghai, China
| | - Haixia Cheng
- Department of Pathology, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
| | - Daijun Wang
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
- Institute of Neurosurgery, Fudan University, Shanghai, China
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Fudan University, Shanghai, China
| | - Jing Ji
- Department of Neurosurgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China
| | - Hong Chen
- Department of Pathology, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
| | - Tareq A Juratli
- Department of Neurosurgery, University Hospital Carl Gustav Carus, Technische Universität Dresden, Fetscherstr. 74, 01307, Dresden, Germany
| | - Hiroaki Wakimoto
- Department of Neurosurgery, Harvard Medical School, Massachusetts General Hospital, Boston, MA, USA
| | - Ye Gong
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China.
- Institute of Neurosurgery, Fudan University, Shanghai, China.
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Fudan University, Shanghai, China.
- Department of Critical Care Medicine, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China.
| | - Lingyang Hua
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China.
- Institute of Neurosurgery, Fudan University, Shanghai, China.
- Shanghai Key Laboratory of Brain Function Restoration and Neural Regeneration, Fudan University, Shanghai, China.
| |
Collapse
|
7
|
Llorián-Salvador Ó, Akhgar J, Pigorsch S, Borm K, Münch S, Bernhardt D, Rost B, Andrade-Navarro MA, Combs SE, Peeken JC. The importance of planning CT-based imaging features for machine learning-based prediction of pain response. Sci Rep 2023; 13:17427. [PMID: 37833283 PMCID: PMC10576053 DOI: 10.1038/s41598-023-43768-6] [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: 02/06/2023] [Accepted: 09/28/2023] [Indexed: 10/15/2023] Open
Abstract
Patients suffering from painful spinal bone metastases (PSBMs) often undergo palliative radiation therapy (RT), with an efficacy of approximately two thirds of patients. In this exploratory investigation, we assessed the effectiveness of machine learning (ML) models trained on radiomics, semantic and clinical features to estimate complete pain response. Gross tumour volumes (GTV) and clinical target volumes (CTV) of 261 PSBMs were segmented on planning computed tomography (CT) scans. Radiomics, semantic and clinical features were collected for all patients. Random forest (RFC) and support vector machine (SVM) classifiers were compared using repeated nested cross-validation. The best radiomics classifier was trained on CTV with an area under the receiver-operator curve (AUROC) of 0.62 ± 0.01 (RFC; 95% confidence interval). The semantic model achieved a comparable AUROC of 0.63 ± 0.01 (RFC), significantly below the clinical model (SVM, AUROC: 0.80 ± 0.01); and slightly lower than the spinal instability neoplastic score (SINS; LR, AUROC: 0.65 ± 0.01). A combined model did not improve performance (AUROC: 0,74 ± 0,01). We could demonstrate that radiomics and semantic analyses of planning CTs allowed for limited prediction of therapy response to palliative RT. ML predictions based on established clinical parameters achieved the best results.
Collapse
Affiliation(s)
- Óscar Llorián-Salvador
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675, Munich, Germany
- Department for Bioinformatics and Computational Biology, Informatik 12, Technical University of Munich (TUM), Boltzmannstraße 3, 85748, Garching, Germany
- Institute of Organismic and Molecular Evolution, Johannes Gutenberg University Mainz, Hanns-Dieter-Hüsch-Weg 15, 55128, Mainz, Germany
| | - Joachim Akhgar
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675, Munich, Germany
| | - Steffi Pigorsch
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675, Munich, Germany
| | - Kai Borm
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675, Munich, Germany
| | - Stefan Münch
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675, Munich, Germany
| | - Denise Bernhardt
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675, Munich, Germany
- Department of Radiation Sciences (DRS), Institute of Radiation Medicine (IRM), Helmholtz Zentrum, 85764, München, Germany
- Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, 69120, Heidelberg, Germany
| | - Burkhard Rost
- Department for Bioinformatics and Computational Biology, Informatik 12, Technical University of Munich (TUM), Boltzmannstraße 3, 85748, Garching, Germany
| | - Miguel A Andrade-Navarro
- Institute of Organismic and Molecular Evolution, Johannes Gutenberg University Mainz, Hanns-Dieter-Hüsch-Weg 15, 55128, Mainz, Germany
| | - Stephanie E Combs
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675, Munich, Germany
- Department of Radiation Sciences (DRS), Institute of Radiation Medicine (IRM), Helmholtz Zentrum, 85764, München, Germany
- Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, 69120, Heidelberg, Germany
| | - Jan C Peeken
- Department of Radiation Oncology, Klinikum Rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675, Munich, Germany.
- Department of Radiation Sciences (DRS), Institute of Radiation Medicine (IRM), Helmholtz Zentrum, 85764, München, Germany.
- Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, 69120, Heidelberg, Germany.
| |
Collapse
|
8
|
Li L, Fu Y, Zhang Y, Mao Y, Huang D, Yi X, Wang J, Tan Z, Jiang M, Chen BT. Magnetic resonance imaging findings of intracranial extraventricular ependymoma: A retrospective multi-center cohort study of 114 cases. Cancer Med 2023; 12:16195-16206. [PMID: 37376821 PMCID: PMC10469843 DOI: 10.1002/cam4.6279] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2023] [Revised: 06/07/2023] [Accepted: 06/09/2023] [Indexed: 06/29/2023] Open
Abstract
BACKGROUND Intracranial extraventricular ependymoma (IEE) is an ependymoma located in the brain parenchyma outside the ventricles. IEE has overlapping clinical and imaging characteristics with glioblastoma multiforme (GBM) but different treatment strategy and prognosis. Therefore, an accurate preoperative diagnosis is necessary for optimizing therapy for IEE. METHODS A retrospective multicenter cohort of IEE and GBM was identified. MR imaging characteristics assessed with the Visually Accessible Rembrandt Images (VASARI) feature set and clinicopathological findings were recorded. Independent predictors for IEE were identified using multivariate logistic regression, which was used to construct a diagnostic score for differentiating IEE from GBM. RESULTS Compared to GBM, IEE tended to occur in younger patients. Multivariate logistic regression analysis identified seven independent predictors for IEE. Among them, 3 predictors including tumor necrosis rate (F7), age, and tumor-enhancing margin thickness (F11), demonstrated higher diagnostic performance with an Area Under Curve (AUC) of more than 70% in distinguishing IEE from GBM. The AUC was 0.85, 0.78, and 0.70, with sensitivity of 92.98%, 72.81%, and 96.49%, and specificity of 65.50%, 73.64%, and 43.41%, for F7, age, and F11, respectively. CONCLUSION We identified specific MR imaging features such as tumor necrosis and thickness of enhancing tumor margins that could help to differentiate IEE from GBM. Our study results should be helpful to assist in diagnosis and clinical management of this rare brain tumor.
Collapse
Affiliation(s)
- Liyan Li
- Department of RadiologyFirst Affiliated Hospital of Guangxi Medical UniversityNanningP. R. China
| | - Yan Fu
- Department of RadiologyXiangya Hospital, Central South UniversityChangshaP. R. China
| | - Yinping Zhang
- Department of RadiologyXiangya Hospital, Central South UniversityChangshaP. R. China
| | - Yipu Mao
- Department of RadiologyNanning First People's HospitalNanningP. R. China
| | - Deyou Huang
- Department of RadiologyAffiliated Hospital of Youjiang Medical University for NationalitiesBaiseP. R. China
| | - Xiaoping Yi
- Department of RadiologyXiangya Hospital, Central South UniversityChangshaP. R. China
- National Engineering Research Center of Personalized Diagnostic and Therapeutic TechnologyXiangya HospitalChangshaP. R. China
- National Clinical Research Center for Geriatric DisordersXiangya Hospital, Central South UniversityChangshaP. R. China
- Hunan Key Laboratory of Skin Cancer and Psoriasis, Xiangya HospitalCentral South UniversityChangshaP. R. China
- Hunan Engineering Research Center of Skin Health and DiseaseXiangya Hospital, Central South UniversityChangshaP. R. China
- Department of DermatologyXiangya Hospital, Central South UniversityChangshaP. R. China
| | - Jing Wang
- Department of NeurologyXiangya Hospital, Central South UniversityChangshaP. R. China
| | - Zeming Tan
- Department of NeurosurgeryXiangya Hospital, Central South UniversityChangshaP. R. China
| | - Muliang Jiang
- Department of RadiologyFirst Affiliated Hospital of Guangxi Medical UniversityNanningP. R. China
| | - Bihong T. Chen
- Department of Diagnostic RadiologyCity of Hope National Medical CenterDuarteCaliforniaUSA
| |
Collapse
|
9
|
Perillo T, de Giorgi M, Papace UM, Serino A, Cuocolo R, Manto A. Current role of machine learning and radiogenomics in precision neuro-oncology. EXPLORATION OF TARGETED ANTI-TUMOR THERAPY 2023; 4:545-555. [PMID: 37720347 PMCID: PMC10501892 DOI: 10.37349/etat.2023.00151] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2022] [Accepted: 04/20/2023] [Indexed: 09/19/2023] Open
Abstract
In the past few years, artificial intelligence (AI) has been increasingly used to create tools that can enhance workflow in medicine. In particular, neuro-oncology has benefited from the use of AI and especially machine learning (ML) and radiogenomics, which are subfields of AI. ML can be used to develop algorithms that dynamically learn from available medical data in order to automatically do specific tasks. On the other hand, radiogenomics can identify relationships between tumor genetics and imaging features, thus possibly giving new insights into the pathophysiology of tumors. Therefore, ML and radiogenomics could help treatment tailoring, which is crucial in personalized neuro-oncology. The aim of this review is to illustrate current and possible future applications of ML and radiomics in neuro-oncology.
Collapse
Affiliation(s)
- Teresa Perillo
- Department of Neuroradiology, “Umberto I” Hospital, 84014 Norcera Inferiore, Italy
| | - Marco de Giorgi
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, 80138 Naples, Italy
| | - Umberto Maria Papace
- Department of Advanced Biomedical Sciences, University of Naples “Federico II”, 80138 Naples, Italy
| | - Antonietta Serino
- Department of Neuroradiology, “Umberto I” Hospital, 84014 Norcera Inferiore, Italy
| | - Renato Cuocolo
- Department of Medicine, Surgery, and Dentistry, University of Salerno, 84084 Fisciano, Italy
| | - Andrea Manto
- Department of Neuroradiology, “Umberto I” Hospital, 84014 Norcera Inferiore, Italy
| |
Collapse
|
10
|
Kim Y, Kim KH, Park J, Yoon HI, Sung W. Prognosis prediction for glioblastoma multiforme patients using machine learning approaches: Development of the clinically applicable model. Radiother Oncol 2023; 183:109617. [PMID: 36921767 DOI: 10.1016/j.radonc.2023.109617] [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: 09/20/2022] [Revised: 02/28/2023] [Accepted: 03/04/2023] [Indexed: 03/16/2023]
Abstract
BACKGROUND AND PURPOSE We aimed to develop a clinically applicable prognosis prediction model predicting overall survival (OS) and progression-free survival (PFS) for glioblastoma multiforme (GBM) patients. MATERIALS AND METHODS All 467 patients treated with concurrent chemoradiotherapy at Yonsei Cancer Center from 2016 to 2020 were included in this study. We developed a conventional linear regression, Cox proportional hazards (COX), and non-linear machine learning algorithms, random survival forest (RSF) and survival support vector machine (SVM) based on 16 clinical variables. After backward feature selection and hyperparameter tuning using grid search, we repeated 100 times of cross-validations to combat overfitting and enhance the model performance. Harrell's concordance index (C-index) and integrated brier score (IBS) were employed as quantitative performance metrics. RESULTS In both predictions, RSF performed much better than COX and SVM. (For OS prediction: RSF C-index = 0.72 90%CI [0.71-0.72] and IBS = 0.12 90%CI [0.10-0.13]; For PFS prediction: RSF C-index = 0.70 90%CI [0.70-0.71] and IBS = 0.12 90%CI [0.10-0.14]). Permutation feature importance confirmed that MGMT promoter methylation, extent of resection, age, cone down planning target volume, and subventricular zone involvement are significant prognostic factors for OS. The importance of the extent of resection and MGMT promoter methylation was much higher than other selected input factors in PFS. Our final models accurately stratified two risk groups with root mean square errors less than 0.07. The sensitivity analysis revealed that our final models are highly applicable to newly diagnosed GBM patients. CONCLUSION Our final models can provide a reliable outcome prediction for individual GBM. The final OS and PFS predicting models we developed accurately stratify high-risk groups up to 5-years, and the sensitivity analysis confirmed that both final models are clinically applicable.
Collapse
Affiliation(s)
- Yeseul Kim
- Department of Biomedical Engineering and of Biomedicine & Health Science, College of Medicine, The Catholic University of Korea, Seoul 137-70, South Korea
| | - Kyung Hwan Kim
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, South Korea
| | - Junyoung Park
- Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea
| | - Hong In Yoon
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, South Korea.
| | - Wonmo Sung
- Department of Biomedical Engineering and of Biomedicine & Health Science, College of Medicine, The Catholic University of Korea, Seoul 137-70, South Korea.
| |
Collapse
|
11
|
García-García S, García-Galindo M, Arrese I, Sarabia R, Cepeda S. Current Evidence, Limitations and Future Challenges of Survival Prediction for Glioblastoma Based on Advanced Noninvasive Methods: A Narrative Review. MEDICINA (KAUNAS, LITHUANIA) 2022; 58:medicina58121746. [PMID: 36556948 PMCID: PMC9786785 DOI: 10.3390/medicina58121746] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/17/2022] [Revised: 11/16/2022] [Accepted: 11/28/2022] [Indexed: 12/03/2022]
Abstract
Background and Objectives: Survival estimation for patients diagnosed with Glioblastoma (GBM) is an important information to consider in patient management and communication. Despite some known risk factors, survival estimation remains a major challenge. Novel non-invasive technologies such as radiomics and artificial intelligence (AI) have been implemented to increase the accuracy of these predictions. In this article, we reviewed and discussed the most significant available research on survival estimation for GBM through advanced non-invasive methods. Materials and Methods: PubMed database was queried for articles reporting on survival prognosis for GBM through advanced image and data management methods. Articles including in their title or abstract the following terms were initially screened: ((glioma) AND (survival)) AND ((artificial intelligence) OR (radiomics)). Exclusively English full-text articles, reporting on humans, published as of 1 September 2022 were considered. Articles not reporting on overall survival, evaluating the effects of new therapies or including other tumors were excluded. Research with a radiomics-based methodology were evaluated using the radiomics quality score (RQS). Results: 382 articles were identified. After applying the inclusion criteria, 46 articles remained for further analysis. These articles were thoroughly assessed, summarized and discussed. The results of the RQS revealed some of the limitations of current radiomics investigation on this field. Limitations of analyzed studies included data availability, patient selection and heterogeneity of methodologies. Future challenges on this field are increasing data availability, improving the general understanding of how AI handles data and establishing solid correlations between image features and tumor's biology. Conclusions: Radiomics and AI methods of data processing offer a new paradigm of possibilities to tackle the question of survival prognosis in GBM.
Collapse
Affiliation(s)
- Sergio García-García
- Department of Neurosurgery, University Hospital Río Hortega, Dulzaina 2, 47012 Valladolid, Spain
- Correspondence:
| | - Manuel García-Galindo
- Faculty of Medicine, University of Valladolid, Avenida Ramón y Cajal 7, 47003 Valladolid, Spain
| | - Ignacio Arrese
- Department of Neurosurgery, University Hospital Río Hortega, Dulzaina 2, 47012 Valladolid, Spain
| | - Rosario Sarabia
- Department of Neurosurgery, University Hospital Río Hortega, Dulzaina 2, 47012 Valladolid, Spain
| | - Santiago Cepeda
- Department of Neurosurgery, University Hospital Río Hortega, Dulzaina 2, 47012 Valladolid, Spain
| |
Collapse
|
12
|
Bilmez BS, Firat Z, Topcuoglu OM, Yaltirik K, Ture U, Ozturk-Isik E. Identifying overall survival in 98 glioblastomas using VASARI features at 3T. Clin Imaging 2022; 93:86-92. [DOI: 10.1016/j.clinimag.2022.10.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2022] [Revised: 10/04/2022] [Accepted: 10/16/2022] [Indexed: 11/27/2022]
|
13
|
Li Y, Qin Q, Zhang Y, Cao Y. Noninvasive Determination of the IDH Status of Gliomas Using MRI and MRI-Based Radiomics: Impact on Diagnosis and Prognosis. Curr Oncol 2022; 29:6893-6907. [PMID: 36290819 PMCID: PMC9600456 DOI: 10.3390/curroncol29100542] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Revised: 09/18/2022] [Accepted: 09/19/2022] [Indexed: 01/13/2023] Open
Abstract
Gliomas are the most common primary malignant brain tumors in adults. The fifth edition of the WHO Classification of Tumors of the Central Nervous System, published in 2021, provided molecular and practical approaches to CNS tumor taxonomy. Currently, molecular features are essential for differentiating the histological subtypes of gliomas, and recent studies have emphasized the importance of isocitrate dehydrogenase (IDH) mutations in stratifying biologically distinct subgroups of gliomas. IDH plays a significant role in gliomagenesis, and the association of IDH status with prognosis is very clear. Recently, there has been much progress in conventional MR imaging (cMRI), advanced MR imaging (aMRI), and radiomics, which are widely used in the study of gliomas. These advances have resulted in an improved correlation between MR signs and IDH mutation status, which will complement the prediction of the IDH phenotype. Although imaging cannot currently substitute for genetic tests, imaging findings have shown promising signs of diagnosing glioma subtypes and evaluating the efficacy and prognosis of individualized molecular targeted therapy. This review focuses on the correlation between MRI and MRI-based radiomics and IDH gene-phenotype prediction, discussing the value and application of these techniques in the diagnosis and evaluation of the prognosis of gliomas.
Collapse
Affiliation(s)
- Yurong Li
- Department of Radiation Oncology, Nanjing Medical University First Affiliated Hospital, Nanjing 210029, China
- The First School of Clinical Medicine, Nanjing Medical University, Nanjing 210029, China
| | - Qin Qin
- Department of Radiation Oncology, Nanjing Medical University First Affiliated Hospital, Nanjing 210029, China
| | - Yumeng Zhang
- Department of Radiation Oncology, Nanjing Medical University First Affiliated Hospital, Nanjing 210029, China
| | - Yuandong Cao
- Department of Radiation Oncology, Nanjing Medical University First Affiliated Hospital, Nanjing 210029, China
- Correspondence:
| |
Collapse
|
14
|
Wu C, Yu S, Zhang Y, Zhu L, Chen S, Liu Y. CT-Based Radiomics Nomogram Improves Risk Stratification and Prediction of Early Recurrence in Hepatocellular Carcinoma After Partial Hepatectomy. Front Oncol 2022; 12:896002. [PMID: 35875140 PMCID: PMC9302642 DOI: 10.3389/fonc.2022.896002] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Accepted: 06/17/2022] [Indexed: 01/27/2023] Open
Abstract
Objectives To develop and validate an intuitive computed tomography (CT)-based radiomics nomogram for the prediction and risk stratification of early recurrence (ER) in hepatocellular carcinoma (HCC) patients after partial hepatectomy. Methods A total of 132 HCC patients treated with partial hepatectomy were retrospectively enrolled and assigned to training and test sets. Least absolute shrinkage and selection operator and gradient boosting decision tree were used to extract quantitative radiomics features from preoperative contrast-enhanced CT images of the HCC patients. The radiomics features with predictive value for ER were used, either alone or in combination with other predictive features, to construct predictive models. The best performing model was then selected to develop an intuitive, simple-to-use nomogram, and its performance in the prediction and risk stratification of ER was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA). Results The radiomics model based on the radiomics score (Rad-score) achieved AUCs of 0.870 and 0.890 in the training and test sets, respectively. Among the six predictive models, the combined model based on the Rad-score, Edmondson grade, and tumor size had the highest AUCs of 0.907 in the training set and 0.948 in the test set and was used to develop an intuitive nomogram. Notably, the calibration curve and DCA for the nomogram showed good calibration and clinical application. Moreover, the risk of ER was significantly different between the high- and low-risk groups stratified by the nomogram (p <0.001). Conclusions The CT-based radiomics nomogram developed in this study exhibits outstanding performance for ER prediction and risk stratification. As such, this intuitive nomogram holds promise as a more effective and user-friendly tool in predicting ER for HCC patients after partial hepatectomy.
Collapse
Affiliation(s)
- Cuiyun Wu
- Cancer Center, Department of Radiology, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital, Hangzhou Medical College), Hangzhou, China
| | - Shufeng Yu
- Cancer Center, Department of Radiology, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital, Hangzhou Medical College), Hangzhou, China
| | - Yang Zhang
- Cancer Center, Department of Radiology, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital, Hangzhou Medical College), Hangzhou, China
| | - Li Zhu
- Cancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital, Hangzhou Medical College), Hangzhou, China
| | - Shuangxi Chen
- Cancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital, Hangzhou Medical College), Hangzhou, China
| | - Yang Liu
- Cancer Center, Department of Ultrasound Medicine, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital, Hangzhou Medical College), Hangzhou, China
- Key Laboratory of Gastroenterology of Zhejiang Province, Zhejiang Provincial People's Hospital (Affiliated People's Hospital, Hangzhou Medical College), Hangzhou, China
- *Correspondence: Yang Liu,
| |
Collapse
|
15
|
A Comparative and Summative Study of Radiomics-based Overall Survival Prediction in Glioblastoma Patients. J Comput Assist Tomogr 2022; 46:470-479. [PMID: 35405713 DOI: 10.1097/rct.0000000000001300] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
PURPOSE This study aimed to assess different machine learning models based on radiomic features, Visually Accessible Rembrandt Images features and clinical characteristics in overall survival prediction of glioblastoma and to identify the reproducible features. MATERIALS AND METHODS Patients with preoperative magnetic resonance scans were allocated into 3 data sets. The Least Absolute Shrinkage and Selection Operator was used for feature selection. The prediction models were built by random survival forest (RSF) and Cox regression. C-index and integrated Brier scores were calculated to compare model performances. RESULTS Patients with cortical involvement had shorter survival times in the training set (P = 0.006). Random survival forest showed higher C-index than Cox, and the RSF model based on the radiomic features was the best one (testing set: C-index = 0.935 ± 0.023). Ten reproducible radiomic features were summarized. CONCLUSIONS The RSF model based on radiomic features had promising potential in predicting overall survival of glioblastoma. Ten reproducible features were identified.
Collapse
|
16
|
Gore S, Chougule T, Jagtap J, Saini J, Ingalhalikar M. A Review of Radiomics and Deep Predictive Modeling in Glioma Characterization. Acad Radiol 2021; 28:1599-1621. [PMID: 32660755 DOI: 10.1016/j.acra.2020.06.016] [Citation(s) in RCA: 25] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2020] [Revised: 06/11/2020] [Accepted: 06/11/2020] [Indexed: 12/22/2022]
Abstract
Recent developments in glioma categorization based on biological genotypes and application of computational machine learning or deep learning based predictive models using multi-modal MRI biomarkers to assess these genotypes provides potential assurance for optimal and personalized treatment plans and efficacy. Artificial intelligence based quantified assessment of glioma using MRI derived hand-crafted or auto-extracted features have become crucial as genomic alterations can be associated with MRI based phenotypes. This survey integrates all the recent work carried out in state-of-the-art radiomics, and Artificial Intelligence based learning solutions related to molecular diagnosis, prognosis, and treatment monitoring with the aim to create a structured resource on radiogenomic analysis of glioma. Challenges such as inter-scanner variability, requirement of benchmark datasets, prospective validations for clinical applicability are discussed with further scope for designing optimal solutions for glioma stratification with immediate recommendations for further diagnostic decisions and personalized treatment plans for glioma patients.
Collapse
|
17
|
Fleischmann DF, Schön R, Corradini S, Bodensohn R, Hadi I, Hofmaier J, Forbrig R, Thon N, Dorostkar M, Belka C, Niyazi M. Multifocal high-grade glioma radiotherapy safety and efficacy. Radiat Oncol 2021; 16:165. [PMID: 34454558 PMCID: PMC8400399 DOI: 10.1186/s13014-021-01886-3] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2021] [Accepted: 08/13/2021] [Indexed: 11/20/2022] Open
Abstract
Background Multifocal manifestation of high-grade glioma is a rare disease with very unfavourable prognosis. The pathogenesis of multifocal glioma and pathophysiological differences to unifocal glioma are not fully understood. The optimal treatment of patients suffering from multifocal high-grade glioma is not defined in the current guidelines, therefore individual case series may be helpful as guidance for clinical decision-making. Methods Patients with multifocal high-grade glioma treated with conventionally fractionated radiation therapy (RT) in our institution with or without concomitant chemotherapy between April 2011 and April 2019 were retrospectively analysed. Multifocality was neuroradiologically assessed and defined as at least two independent contrast-enhancing foci in the MRI T1 contrast-enhanced sequence. IDH mutational status and MGMT methylation status were assessed from histopathology records. GTV, PTV as well as the V30Gy, V45Gy and D2% volumes of the brain were analysed. Overall and progression-free survival were calculated from the diagnosis until death and from start of radiation therapy until diagnosis of progression of disease in MRI for all patients. Results 20 multifocal glioma cases (18 IDH wild-type glioblastoma cases, one diffuse astrocytic glioma, IDH wild-type case with molecular features of glioblastoma and one anaplastic astrocytoma, IDH wild-type case) were included into the analysis. Resection was performed in two cases and stereotactic biopsy only in 18 cases before the start of radiation therapy. At the start of radiation therapy patients were 61 years old in median (range 42–84 years). Histopathological examination showed IDH wild-type in all cases and MGMT promotor methylation in 11 cases (55%). Prescription schedules were 60 Gy (2 Gy × 30), 59.4 Gy (1.8 Gy × 33), 55 Gy (2.2 Gy × 25) and 50 Gy (2.5 Gy × 20) in 15, three, one and one cases, respectively. Concomitant temozolomide chemotherapy was applied in 16 cases, combined temozolomide/lomustine chemotherapy was applied in one case and concomitant bevacizumab therapy in one case. Median number of GTVs was three. Median volume of the sum of the GTVs was 26 cm3. Median volume of the PTV was 425.7 cm3 and median PTV to brain ratio 32.8 percent. Median D2% of the brain was 61.5 Gy (range 51.2–62.7) and median V30Gy and V45 of the brain were 59.9 percent (range 33–79.7) and 40.7 percent (range 14.9–64.1), respectively. Median survival was eight months (95% KI 3.6–12.4 months) and median progression free survival after initiation of RT five months (95% CI 2.8–7.2 months). Grade 2 toxicities were detected in eight cases and grade 3 toxicities in four cases consisting of increasing edema in three cases and one new-onset seizure. One grade 4 toxicity was detected, which was febrile neutropenia related to concomitant chemotherapy. Conclusion Conventionally fractionated RT with concomitant chemotherapy could safely be applied in multifocal high-grade glioma in this case series despite large irradiation treatment fields.
Collapse
Affiliation(s)
- Daniel Felix Fleischmann
- Department of Radiation Oncology, University Hospital, LMU Munich, Munich, Germany.,German Cancer Consortium (DKTK), partner site, Munich, Germany.,German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Rudolph Schön
- Department of Radiation Oncology, University Hospital, LMU Munich, Munich, Germany
| | - Stefanie Corradini
- Department of Radiation Oncology, University Hospital, LMU Munich, Munich, Germany
| | - Raphael Bodensohn
- Department of Radiation Oncology, University Hospital, LMU Munich, Munich, Germany
| | - Indrawati Hadi
- Department of Radiation Oncology, University Hospital, LMU Munich, Munich, Germany
| | - Jan Hofmaier
- Department of Radiation Oncology, University Hospital, LMU Munich, Munich, Germany
| | - Robert Forbrig
- Institute of Neuroradiology, University Hospital, LMU Munich, Munich, Germany
| | - Niklas Thon
- Department of Neurosurgery, University Hospital, LMU Munich, Munich, Germany
| | - Mario Dorostkar
- Institute of Neuropathology, Faculty of Medicine, LMU Munich, Munich, Germany
| | - Claus Belka
- Department of Radiation Oncology, University Hospital, LMU Munich, Munich, Germany.,German Cancer Consortium (DKTK), partner site, Munich, Germany
| | - Maximilian Niyazi
- Department of Radiation Oncology, University Hospital, LMU Munich, Munich, Germany. .,German Cancer Consortium (DKTK), partner site, Munich, Germany.
| |
Collapse
|
18
|
Patel M, Zhan J, Natarajan K, Flintham R, Davies N, Sanghera P, Grist J, Duddalwar V, Peet A, Sawlani V. Machine learning-based radiomic evaluation of treatment response prediction in glioblastoma. Clin Radiol 2021; 76:628.e17-628.e27. [PMID: 33941364 DOI: 10.1016/j.crad.2021.03.019] [Citation(s) in RCA: 24] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2020] [Accepted: 03/29/2021] [Indexed: 11/16/2022]
Abstract
AIM To investigate machine learning based models combining clinical, radiomic, and molecular information to distinguish between early true progression (tPD) and pseudoprogression (psPD) in patients with glioblastoma. MATERIALS AND METHODS A retrospective analysis was undertaken of 76 patients (46 tPD, 30 psPD) with early enhancing disease following chemoradiotherapy for glioblastoma. Outcome was determined on follow-up until 6 months post-chemoradiotherapy. Models comprised clinical characteristics, O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status, and 307 quantitative imaging features extracted from enhancing disease and perilesional oedema masks on early post-chemoradiotherapy contrast-enhanced T1-weighted imaging, T2-weighted imaging (T2WI), and apparent diffusion coefficient (ADC) maps. Feature selection was performed within bootstrapped cross-validated recursive feature elimination with a random forest algorithm. Naive Bayes five-fold cross-validation was used to validate the final model. RESULTS Top selected features included age, MGMT promoter methylation status, two shape-based features from the enhancing disease mask, three radiomic features from the enhancing disease mask on ADC, and one radiomic feature from the perilesional oedema mask on T2WI. The final model had an area under the receiver operating characteristics curve (AUC) of 0.80, sensitivity 78.2%, specificity 66.7%, and accuracy of 73.7%. CONCLUSION Incorporating a machine learning-based approach using quantitative radiomic features from standard-of-care magnetic resonance imaging (MRI), in combination with clinical characteristics and MGMT promoter methylation status has a complementary effect and improves model performance for early prediction of glioblastoma treatment response.
Collapse
Affiliation(s)
- M Patel
- University of Birmingham, Birmingham, UK; Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| | - J Zhan
- Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK; The Affiliated Hospital of Qingdao University, Qingdao Shi, Shandong Sheng, China
| | - K Natarajan
- Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| | - R Flintham
- Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| | - N Davies
- Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| | - P Sanghera
- University of Birmingham, Birmingham, UK; Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| | - J Grist
- University of Birmingham, Birmingham, UK
| | - V Duddalwar
- Departments of Radiology, Urology and Biomedical Engineering, University of Southern California, USA
| | - A Peet
- University of Birmingham, Birmingham, UK; Birmingham Children's Hospital, Birmingham Women's and Children's NHS Foundation Trust, Birmingham, UK
| | - V Sawlani
- University of Birmingham, Birmingham, UK; Queen Elizabeth Hospital Birmingham, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK.
| |
Collapse
|
19
|
Peeken JC, Neumann J, Asadpour R, Leonhardt Y, Moreira JR, Hippe DS, Klymenko O, Foreman SC, von Schacky CE, Spraker MB, Schaub SK, Dapper H, Knebel C, Mayr NA, Woodruff HC, Lambin P, Nyflot MJ, Gersing AS, Combs SE. Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics. Cancers (Basel) 2021; 13:1929. [PMID: 33923697 PMCID: PMC8073388 DOI: 10.3390/cancers13081929] [Citation(s) in RCA: 26] [Impact Index Per Article: 8.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2021] [Revised: 04/13/2021] [Accepted: 04/13/2021] [Indexed: 12/12/2022] Open
Abstract
BACKGROUND In patients with soft-tissue sarcomas of the extremities, the treatment decision is currently regularly based on tumor grading and size. The imaging-based analysis may pose an alternative way to stratify patients' risk. In this work, we compared the value of MRI-based radiomics with expert-derived semantic imaging features for the prediction of overall survival (OS). METHODS Fat-saturated T2-weighted sequences (T2FS) and contrast-enhanced T1-weighted fat-saturated (T1FSGd) sequences were collected from two independent retrospective cohorts (training: 108 patients; testing: 71 patients). After preprocessing, 105 radiomic features were extracted. Semantic imaging features were determined by three independent radiologists. Three machine learning techniques (elastic net regression (ENR), least absolute shrinkage and selection operator, and random survival forest) were compared to predict OS. RESULTS ENR models achieved the best predictive performance. Histologies and clinical staging differed significantly between both cohorts. The semantic prognostic model achieved a predictive performance with a C-index of 0.58 within the test set. This was worse compared to a clinical staging system (C-index: 0.61) and the radiomic models (C-indices: T1FSGd: 0.64, T2FS: 0.63). Both radiomic models achieved significant patient stratification. CONCLUSIONS T2FS and T1FSGd-based radiomic models outperformed semantic imaging features for prognostic assessment.
Collapse
Affiliation(s)
- Jan C. Peeken
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; (R.A.); (O.K.); (H.D.); (S.E.C.)
- Institute of Radiation Medicine (IRM), Department of Radiation Sciences (DRS), Helmholtz Zentrum München, 85764 München, Germany
- Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany
- Department of Precision Medicine, GROW—School for Oncology and Developmental Biology, Maastricht University, 6200 MD Maastricht, The Netherlands; (H.C.W.); (P.L.)
| | - Jan Neumann
- Department of Radiology, Klinikum rechts der Isar, Technical University of Munich (TUM), 81675 Munich, Germany; (J.N.); (Y.L.); (J.R.M.); (S.C.F.); (C.E.v.S.); (A.S.G.)
| | - Rebecca Asadpour
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; (R.A.); (O.K.); (H.D.); (S.E.C.)
| | - Yannik Leonhardt
- Department of Radiology, Klinikum rechts der Isar, Technical University of Munich (TUM), 81675 Munich, Germany; (J.N.); (Y.L.); (J.R.M.); (S.C.F.); (C.E.v.S.); (A.S.G.)
| | - Joao R. Moreira
- Department of Radiology, Klinikum rechts der Isar, Technical University of Munich (TUM), 81675 Munich, Germany; (J.N.); (Y.L.); (J.R.M.); (S.C.F.); (C.E.v.S.); (A.S.G.)
| | - Daniel S. Hippe
- Department of Radiation Oncology, University of Washington, Seattle, WA 98195, USA; (D.S.H.); (S.K.S.); (N.A.M.); (M.J.N.)
| | - Olena Klymenko
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; (R.A.); (O.K.); (H.D.); (S.E.C.)
| | - Sarah C. Foreman
- Department of Radiology, Klinikum rechts der Isar, Technical University of Munich (TUM), 81675 Munich, Germany; (J.N.); (Y.L.); (J.R.M.); (S.C.F.); (C.E.v.S.); (A.S.G.)
| | - Claudio E. von Schacky
- Department of Radiology, Klinikum rechts der Isar, Technical University of Munich (TUM), 81675 Munich, Germany; (J.N.); (Y.L.); (J.R.M.); (S.C.F.); (C.E.v.S.); (A.S.G.)
| | - Matthew B. Spraker
- Department of Radiation Oncology, Washington University in St. Louis, St. Louis, MO 63110, USA;
| | - Stephanie K. Schaub
- Department of Radiation Oncology, University of Washington, Seattle, WA 98195, USA; (D.S.H.); (S.K.S.); (N.A.M.); (M.J.N.)
| | - Hendrik Dapper
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; (R.A.); (O.K.); (H.D.); (S.E.C.)
| | - Carolin Knebel
- Department of Orthopedics and Sports Orthopedics, Klinikum rechts der Isar, Technical University of Munich (TUM), 81675 Munich, Germany;
| | - Nina A. Mayr
- Department of Radiation Oncology, University of Washington, Seattle, WA 98195, USA; (D.S.H.); (S.K.S.); (N.A.M.); (M.J.N.)
| | - Henry C. Woodruff
- Department of Precision Medicine, GROW—School for Oncology and Developmental Biology, Maastricht University, 6200 MD Maastricht, The Netherlands; (H.C.W.); (P.L.)
- Department of Radiology and Nuclear Imaging, GROW—School for Oncology and Developmental Biology, Maastricht University Medical Centre, 6229 HX Maastricht, The Netherlands
| | - Philippe Lambin
- Department of Precision Medicine, GROW—School for Oncology and Developmental Biology, Maastricht University, 6200 MD Maastricht, The Netherlands; (H.C.W.); (P.L.)
- Department of Radiology and Nuclear Imaging, GROW—School for Oncology and Developmental Biology, Maastricht University Medical Centre, 6229 HX Maastricht, The Netherlands
| | - Matthew J. Nyflot
- Department of Radiation Oncology, University of Washington, Seattle, WA 98195, USA; (D.S.H.); (S.K.S.); (N.A.M.); (M.J.N.)
- Department of Radiology, University of Washington, Seattle, WA 98195, USA
| | - Alexandra S. Gersing
- Department of Radiology, Klinikum rechts der Isar, Technical University of Munich (TUM), 81675 Munich, Germany; (J.N.); (Y.L.); (J.R.M.); (S.C.F.); (C.E.v.S.); (A.S.G.)
| | - Stephanie E. Combs
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; (R.A.); (O.K.); (H.D.); (S.E.C.)
- Institute of Radiation Medicine (IRM), Department of Radiation Sciences (DRS), Helmholtz Zentrum München, 85764 München, Germany
- Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany
| |
Collapse
|
20
|
Zheng L, Zhou ZR, Shi M, Chen H, Yu QQ, Yang Y, Liu L, Zhang L, Guo Y, Zhou X, Li C, Wei Q. Nomograms for predicting progression-free survival and overall survival after surgery and concurrent chemoradiotherapy for glioblastoma: a retrospective cohort study. ANNALS OF TRANSLATIONAL MEDICINE 2021; 9:571. [PMID: 33987269 DOI: 10.21037/atm-21-673] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
Background Glioblastoma (GBM) is the most common malignant brain tumor in adults. The prognosis of GBM patients is poor. Even with active standard treatment, the median overall survival is only 14.6 months. It is therefore critical to ascertain recurrence and search for factors that influence the prognosis of GBM. This study aimed to screen the variables related to the progression-free survival (PFS) and overall survival (OS) of GBM patients undergoing surgery and concurrent chemoradiotherapy, as well as propose a nomogram for individual risk prediction based on preoperative imaging parameters and clinicopathological variables readily available in clinical practice. Methods We retrospectively analyzed 114 consecutive patients with GBM who underwent surgery and concurrent chemoradiotherapy at the Second Affiliated Hospital, Zhejiang University School of Medicine from January 1st, 2015, to June 1st, 2018. Twenty-four preoperative magnetic resonance imaging (MRI) parameters were extracted manually from the Picture Archiving and Communication System (PACS). Clinicopathological factors were extracted from the electronic medical record system (EMRS). Least absolute shrinkage and selection operator (LASSO) regression and Cox regression were used for feature selection and model prediction, respectively. The models were presented using nomograms, which were applied to identify the risk of recurrence and survival according to the score. The performance of the nomograms to predict PFS and OS was tested with C-statistics, calibration plots, and Kaplan-Meier curves. Results The results revealed that sex, Karnofsky performance score (KPS), O6-methylglucamine-DNA methyltransferase (MGMT) protein expression, number of adjuvant chemotherapy cycles with temozolomide (TMZ), and the MRI signature effectively predicted PFS; and sex, KPS, extent of surgery, number of TMZ cycles, and MRI signature effectively predicted OS. The nomogram revealed good discriminative ability (C-statistics: 0.81 for PFS and 0.79 for OS). In the nomogram of PFS, patients with a score greater than 122 were considered to have a high risk of recurrence. In the nomogram of OS, the cutoff score were 115 and 145, and then patients were classified as low, medium, and high risk. Conclusions In conclusion, our nomograms can effectively predict the risk of recurrence and survival of GBM patients and thus can be a good guide for clinical practice.
Collapse
Affiliation(s)
- Lin Zheng
- Department of Radiation Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.,Department of Radiation Oncology, Taizhou Cancer Hospital, Taizhou, China
| | - Zhi-Rui Zhou
- Radiation Oncology Center, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China
| | - Minghan Shi
- Département de l'éducation aux adultes, Cégep Saint-Jean-sur-Richelieu, Brossard, QC, Canada
| | - Haiyan Chen
- Department of Radiation Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Qian-Qian Yu
- Department of Radiation Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Yang Yang
- Department of Radiation Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Lihong Liu
- Department of Radiation Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Lili Zhang
- Department of Radiation Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Yinglu Guo
- Department of Radiation Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Xiaofeng Zhou
- Department of Radiation Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Chao Li
- Department of Radiation Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Qichun Wei
- Department of Radiation Oncology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| |
Collapse
|
21
|
Yan R, Hao D, Li J, Liu J, Hou F, Chen H, Duan L, Huang C, Wang H, Yu T. Magnetic Resonance Imaging-Based Radiomics Nomogram for Prediction of the Histopathological Grade of Soft Tissue Sarcomas: A Two-Center Study. J Magn Reson Imaging 2021; 53:1683-1696. [PMID: 33604955 DOI: 10.1002/jmri.27532] [Citation(s) in RCA: 38] [Impact Index Per Article: 12.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2020] [Revised: 01/13/2021] [Accepted: 01/15/2021] [Indexed: 12/26/2022] Open
Abstract
BACKGROUND Preoperative prediction of soft tissue sarcoma (STS) grade is important for treatment decisions. Therefore, formulation an STS grade model is strongly needed. PURPOSE To develop and test an magnetic resonance imaging (MRI)-based radiomics nomogram for predicting the grade of STS (low-grade vs. high grade). STUDY TYPE Retrospective POPULATION: One hundred and eighty patients with STS confirmed by pathologic results at two independent institutions were enrolled (training set, N = 109; external validation set, N = 71). FIELD STRENGTH/SEQUENCE Unenhanced T1-weighted (T1WI) and fat-suppressed T2-weighted images (FS-T2WI) were acquired at 1.5 T and 3.0 T. ASSESSMENT Clinical-MRI characteristics included age, gender, tumor-node-metastasis (TNM) stage, American Joint Committee on Cancer (AJCC) stage, progression-free survival (PFS), and MRI morphological features (ie, margin). Radiomics feature extraction were performed on T1WI and FS-T2WI images by minimum redundancy maximum relevance (MRMR) method and least absolute shrinkage and selection operator (LASSO) algorithm. The selected features constructed three radiomics signatures models (RS-T1, RS-FST2, and RS-Combined). Univariate and multivariate logistic regression analysis were applied for screening significant risk factors. Radiomics nomogram was constructed by incorporating the radiomics signature and risk factors. STATISTICAL TESTS Clinical-MRI characteristics were performed by a univariate analysis. Model performances (discrimination, calibration, and clinical usefulness) were validated in the external validation set. The RS-T1 model, RS-FST2 model, and RS-Combined model had an area under curves (AUCs) of 0.645, 0.641, and 0.829, respectively, in the external validation set. The radiomics nomogram, incorporating significant risk factors and the RS-Combined model had AUCs of 0.916 (95%CI, 0.866-0.966, training set) and 0.879 (95%CI, 0.791-0.967, external validation set), and demonstrated good calibration and good clinical utility. DATA CONCLUSION The proposed noninvasive MRI-based radiomics models showed good performance in differentiating low-grade from high-grade STSs. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY STAGE: 2.
Collapse
Affiliation(s)
- Ruixin Yan
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, 266003, China
| | - Dapeng Hao
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, 266003, China
| | - Jie Li
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, 266003, China
| | - Jihua Liu
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, 266003, China
| | - Feng Hou
- Department of Pathology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, 266003, China
| | - Haisong Chen
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, 266003, China
| | - Lisha Duan
- Department of CT/MRI, The Third Hospital of Hebei Medical University, Shi jiazhuang, Hebei, 050051, China
| | - Chencui Huang
- Department of Research Collaboration, R&D center, Beijing Deepwise & League of PHD Technology Co., Ltd, Beijing, 100080, China
| | - Hexiang Wang
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, 266003, China
| | - Tengbo Yu
- Department of Sports Medicine, the Affiliated Hospital of Qingdao University, QingDao, Shandong, 266003, China
| |
Collapse
|
22
|
Prognostic and Predictive Value of Integrated Qualitative and Quantitative Magnetic Resonance Imaging Analysis in Glioblastoma. Cancers (Basel) 2021; 13:cancers13040722. [PMID: 33578746 PMCID: PMC7916478 DOI: 10.3390/cancers13040722] [Citation(s) in RCA: 23] [Impact Index Per Article: 7.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2020] [Revised: 02/01/2021] [Accepted: 02/06/2021] [Indexed: 02/07/2023] Open
Abstract
Simple Summary Glioblastoma (GBM) is the most malignant primary brain tumor, for which improving patient outcome is limited by a substantial amount of tumor heterogeneity. Magnetic resonance imaging (MRI) in combination with machine learning offers the possibility to collect qualitative and quantitative imaging features which can be used to predict patient prognosis and relevant tumor markers which can aid in selecting the right treatment. This study showed that combining these MRI features with clinical features has the highest prognostic value for GBM patients; this model performed similarly in an independent GBM cohort, showing its reproducibility. The prediction of tumor markers showed promising results in the training set but not could be validated in the independent dataset. This study shows the potential of using MRI to predict prognosis and tumor markers, but further optimization and prospective studies are warranted. Abstract Glioblastoma (GBM) is the most malignant primary brain tumor for which no curative treatment options exist. Non-invasive qualitative (Visually Accessible Rembrandt Images (VASARI)) and quantitative (radiomics) imaging features to predict prognosis and clinically relevant markers for GBM patients are needed to guide clinicians. A retrospective analysis of GBM patients in two neuro-oncology centers was conducted. The multimodal Cox-regression model to predict overall survival (OS) was developed using clinical features with VASARI and radiomics features in isocitrate dehydrogenase (IDH)-wild type GBM. Predictive models for IDH-mutation, 06-methylguanine-DNA-methyltransferase (MGMT)-methylation and epidermal growth factor receptor (EGFR) amplification using imaging features were developed using machine learning. The performance of the prognostic model improved upon addition of clinical, VASARI and radiomics features, for which the combined model performed best. This could be reproduced after external validation (C-index 0.711 95% CI 0.64–0.78) and used to stratify Kaplan–Meijer curves in two survival groups (p-value < 0.001). The predictive models performed significantly in the external validation for EGFR amplification (area-under-the-curve (AUC) 0.707, 95% CI 0.582–8.25) and MGMT-methylation (AUC 0.667, 95% CI 0.522–0.82) but not for IDH-mutation (AUC 0.695, 95% CI 0.436–0.927). The integrated clinical and imaging prognostic model was shown to be robust and of potential clinical relevance. The prediction of molecular markers showed promising results in the training set but could not be validated after external validation in a clinically relevant manner. Overall, these results show the potential of combining clinical features with imaging features for prognostic and predictive models in GBM, but further optimization and larger prospective studies are warranted.
Collapse
|
23
|
Meier R, Pahud de Mortanges A, Wiest R, Knecht U. Exploratory Analysis of Qualitative MR Imaging Features for the Differentiation of Glioblastoma and Brain Metastases. Front Oncol 2020; 10:581037. [PMID: 33425734 PMCID: PMC7793795 DOI: 10.3389/fonc.2020.581037] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2020] [Accepted: 11/09/2020] [Indexed: 12/12/2022] Open
Abstract
OBJECTIVES To identify qualitative VASARI (Visually AcceSIble Rembrandt Images) Magnetic Resonance (MR) Imaging features for differentiation of glioblastoma (GBM) and brain metastasis (BM) of different primary tumors. MATERIALS AND METHODS T1-weighted pre- and post-contrast, T2-weighted, and T2-weighted, fluid attenuated inversion recovery (FLAIR) MR images of a total of 239 lesions from 109 patients with either GBM or BM (breast cancer, non-small cell (NSCLC) adenocarcinoma, NSCLC squamous cell carcinoma, small-cell lung cancer (SCLC)) were included. A set of adapted, qualitative VASARI MR features describing tumor appearance and location was scored (binary; 1 = presence of feature, 0 = absence of feature). Exploratory data analysis was performed on binary scores using a combination of descriptive statistics (proportions with 95% binomial confidence intervals), unsupervised methods and supervised methods including multivariate feature ranking using either repeated fitting or recursive feature elimination with Support Vector Machines (SVMs). RESULTS GBMs were found to involve all lobes of the cerebrum with a fronto-occipital gradient, often affected the corpus callosum (32.4%, 95% CI 19.1-49.2), and showed a strong preference for the right hemisphere (79.4%, 95% CI 63.2-89.7). BMs occurred most frequently in the frontal lobe (35.1%, 95% CI 28.9-41.9) and cerebellum (28.3%, 95% CI 22.6-34.8). The appearance of GBMs was characterized by preference for well-defined non-enhancing tumor margin (100%, 89.8-100), ependymal extension (52.9%, 36.7-68.5) and substantially less enhancing foci than BMs (44.1%, 28.9-60.6 vs. 75.1%, 68.8-80.5). Unsupervised and supervised analyses showed that GBMs are distinctively different from BMs and that this difference is driven by definition of non-enhancing tumor margin, ependymal extension and features describing laterality. Differentiation of histological subtypes of BMs was driven by the presence of well-defined enhancing and non-enhancing tumor margins and localization in the vision center. SVM models with optimal hyperparameters led to weighted F1-score of 0.865 for differentiation of GBMs from BMs and weighted F1-score of 0.326 for differentiation of BM subtypes. CONCLUSION VASARI MR imaging features related to definition of non-enhancing margin, ependymal extension, and tumor localization may serve as potential imaging biomarkers to differentiate GBMs from BMs.
Collapse
Affiliation(s)
- Raphael Meier
- University Institute of Diagnostic and Interventional Neuroradiology, University Hospital Bern, Inselspital, University of Bern, Bern, Switzerland
- Support Center for Advanced Neuroimaging, University Hospital Bern, Inselspital, University of Bern, Bern, Switzerland
| | - Aurélie Pahud de Mortanges
- University Institute of Diagnostic and Interventional Neuroradiology, University Hospital Bern, Inselspital, University of Bern, Bern, Switzerland
| | - Roland Wiest
- University Institute of Diagnostic and Interventional Neuroradiology, University Hospital Bern, Inselspital, University of Bern, Bern, Switzerland
- Support Center for Advanced Neuroimaging, University Hospital Bern, Inselspital, University of Bern, Bern, Switzerland
| | - Urspeter Knecht
- ARTORG Center for Biomedical Research, University of Bern, Bern, Switzerland
- Department of Diagnostic Radiology and Neuroradiology, Regional Hospital Emmental, Burgdorf, Switzerland
| |
Collapse
|
24
|
Tewarie IA, Senders JT, Kremer S, Devi S, Gormley WB, Arnaout O, Smith TR, Broekman MLD. Survival prediction of glioblastoma patients-are we there yet? A systematic review of prognostic modeling for glioblastoma and its clinical potential. Neurosurg Rev 2020; 44:2047-2057. [PMID: 33156423 PMCID: PMC8338817 DOI: 10.1007/s10143-020-01430-z] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2020] [Revised: 09/28/2020] [Accepted: 10/27/2020] [Indexed: 02/07/2023]
Abstract
Glioblastoma is associated with a poor prognosis. Even though survival statistics are well-described at the population level, it remains challenging to predict the prognosis of an individual patient despite the increasing number of prognostic models. The aim of this study is to systematically review the literature on prognostic modeling in glioblastoma patients. A systematic literature search was performed to identify all relevant studies that developed a prognostic model for predicting overall survival in glioblastoma patients following the PRISMA guidelines. Participants, type of input, algorithm type, validation, and testing procedures were reviewed per prognostic model. Among 595 citations, 27 studies were included for qualitative review. The included studies developed and evaluated a total of 59 models, of which only seven were externally validated in a different patient cohort. The predictive performance among these studies varied widely according to the AUC (0.58-0.98), accuracy (0.69-0.98), and C-index (0.66-0.70). Three studies deployed their model as an online prediction tool, all of which were based on a statistical algorithm. The increasing performance of survival prediction models will aid personalized clinical decision-making in glioblastoma patients. The scientific realm is gravitating towards the use of machine learning models developed on high-dimensional data, often with promising results. However, none of these models has been implemented into clinical care. To facilitate the clinical implementation of high-performing survival prediction models, future efforts should focus on harmonizing data acquisition methods, improving model interpretability, and externally validating these models in multicentered, prospective fashion.
Collapse
Affiliation(s)
- Ishaan Ashwini Tewarie
- Department of Neurosurgery, Haaglanden Medical Center, Lijnbaan 32, 2512 VA, The Hague, The Netherlands
- Faculty of Medicine, Erasmus University Rotterdam, Rotterdam, The Netherlands
- Computational Neurosciences Outcomes Center, Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - Joeky T Senders
- Department of Neurosurgery, Haaglanden Medical Center, Lijnbaan 32, 2512 VA, The Hague, The Netherlands
- Computational Neurosciences Outcomes Center, Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - Stijn Kremer
- Department of Neurosurgery, Haaglanden Medical Center, Lijnbaan 32, 2512 VA, The Hague, The Netherlands
| | - Sharmila Devi
- Computational Neurosciences Outcomes Center, Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
- King's College, London, UK
| | - William B Gormley
- Computational Neurosciences Outcomes Center, Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - Omar Arnaout
- Computational Neurosciences Outcomes Center, Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - Timothy R Smith
- Computational Neurosciences Outcomes Center, Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - Marike L D Broekman
- Department of Neurosurgery, Haaglanden Medical Center, Lijnbaan 32, 2512 VA, The Hague, The Netherlands.
- Computational Neurosciences Outcomes Center, Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
- Department of Neurosurgery, Leiden University Medical Center, Leiden, The Netherlands.
| |
Collapse
|
25
|
Goerig NL, Frey B, Korn K, Fleckenstein B, Überla K, Schmidt MA, Dörfler A, Engelhorn T, Eyüpoglu I, Rühle PF, Putz F, Semrau S, Gaipl US, Fietkau R. Early Mortality of Brain Cancer Patients and its Connection to Cytomegalovirus Reactivation During Radiochemotherapy. Clin Cancer Res 2020; 26:3259-3270. [PMID: 32060103 DOI: 10.1158/1078-0432.ccr-19-3195] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2019] [Revised: 01/15/2020] [Accepted: 02/11/2020] [Indexed: 11/16/2022]
Abstract
PURPOSE If routine diagnostics are inconclusive, neurologic deterioration and death of patients with brain cancer are attributed to tumor or therapy. Therefore, diagnosing symptoms of encephalopathy caused by human cytomegalovirus (HCMV) reactivation remains uncommon. We investigated the role of HCMV reactivation in neurologic decline and clinical outcome after the start of radiochemotherapy. EXPERIMENTAL DESIGN HCMV analyses and extended MRI studies including additional independent retrospective neuroradiologic evaluation were performed at predetermined intervals and in case of sudden neurologic decline for 118 adult patients: 63 histologically proven high-grade gliomas, 55 with brain metastases. Immunophenotyping from simultaneously taken whole-blood samples was carried out to detect immune cells serving as prognostic marker for HCMV-associated complications. Symptomatic viremia and overall survival (OS) were the endpoints. RESULTS Twenty-four percent (28/118) of all patients (12/44 glioblastoma, 3/13 anaplastic astrocytoma; 8/31 non-small cell lung cancer (NSCLC), 13/24 other brain metastases) developed HCMV-viremia during or within 4 weeks after radiotherapy; 21 of 28 patients experienced concurrent major neurologic decline, reversible by antiviral treatment. Identified by immunophenotyping, pretherapeutically low basophil counts predicted a high-risk for HCMV-associated encephalopathy (glioblastoma: P = 0.002, NSCLC: P = 0.02). Median OS was substantially reduced after HCMV-associated encephalopathy without MRI signs of tumor progression [glioblastoma: 99 vs. 570 days (calculated 1-year OS: 22% vs. 69%; P = 0.01) and NSCLC: 47 vs. 219 days (calculated 1-year OS: 0% vs. 32%; P = 0.02)]. CONCLUSIONS For patients with brain cancer, HCMV reactivation after the start of radiochemotherapy is a frequent risk for cognitively detrimental but treatable encephalopathy and premature death. Routinely performed HCMV diagnostics, assessing basophil counts and study-based anti-viral regimens, are necessary to combat this hidden threat.See related commentary by Lawler et al., p. 3077.
Collapse
Affiliation(s)
- Nicole L Goerig
- Department of Radiation Oncology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany.
| | - Benjamin Frey
- Department of Radiation Oncology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Klaus Korn
- Institute of Clinical and Molecular Virology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Bernhard Fleckenstein
- Institute of Clinical and Molecular Virology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Klaus Überla
- Institute of Clinical and Molecular Virology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Manuel A Schmidt
- Institute of Neuroradiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Arnd Dörfler
- Institute of Neuroradiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Tobias Engelhorn
- Institute of Neuroradiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Ilker Eyüpoglu
- Department of Neurosurgery, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Paul F Rühle
- Department of Radiation Oncology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Florian Putz
- Department of Radiation Oncology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Sabine Semrau
- Department of Radiation Oncology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Udo S Gaipl
- Department of Radiation Oncology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Rainer Fietkau
- Department of Radiation Oncology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| |
Collapse
|
26
|
Wang XH, Long LH, Cui Y, Jia AY, Zhu XG, Wang HZ, Wang Z, Zhan CM, Wang ZH, Wang WH. MRI-based radiomics model for preoperative prediction of 5-year survival in patients with hepatocellular carcinoma. Br J Cancer 2020; 122:978-985. [PMID: 31937925 PMCID: PMC7109104 DOI: 10.1038/s41416-019-0706-0] [Citation(s) in RCA: 69] [Impact Index Per Article: 17.3] [Reference Citation Analysis] [Abstract] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2019] [Revised: 09/10/2019] [Accepted: 10/08/2019] [Indexed: 12/17/2022] Open
Abstract
Background Recurrence is the major cause of mortality in patients with resected HCC. However, without a standard approach to evaluate prognosis, it is difficult to select candidates for additional therapy. Methods A total of 201 patients with HCC who were followed up for at least 5 years after curative hepatectomy were enrolled in this retrospective, multicentre study. A total of 3144 radiomics features were extracted from preoperative MRI. The random forest method was used for radiomics signature building, and five-fold cross-validation was applied. A radiomics model incorporating the radiomics signature and clinical risk factors was developed. Results Patients were divided into survivor (n = 97) and non-survivor (n = 104) groups based on the 5-year survival after surgery. The 30 most survival-related radiomics features were selected for the radiomics signature. Preoperative AFP and AST were integrated into the model as independent clinical risk factors. The model demonstrated good calibration and satisfactory discrimination, with a mean AUC of 0.9804 and 0.7578 in the training and validation sets, respectively. Conclusions This radiomics model is a valid method to predict 5-year survival in patients with HCC and may be used to identify patients for clinical trials of perioperative therapies and for additional surveillance.
Collapse
Affiliation(s)
- Xiao-Hang Wang
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital and Institute, Beijing, China
| | - Liu-Hua Long
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital and Institute, Beijing, China
| | - Yong Cui
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiology, Peking University Cancer Hospital and Institute, Beijing, China
| | - Angela Y Jia
- Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Xiang-Gao Zhu
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital and Institute, Beijing, China
| | - Hong-Zhi Wang
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital and Institute, Beijing, China
| | - Zhi Wang
- Blot Info & Tech (Beijing) Co. Ltd, Beijing, China
| | | | - Zhao-Hai Wang
- Department of Hepatobiliary Surgery, The Fifth Medical Center of Chinese PLA General Hospital, Beijing Institute of Infectious Diseases, Beijing, China.
| | - Wei-Hu Wang
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital and Institute, Beijing, China.
| |
Collapse
|
27
|
Booth TC, Williams M, Luis A, Cardoso J, Ashkan K, Shuaib H. Machine learning and glioma imaging biomarkers. Clin Radiol 2020; 75:20-32. [PMID: 31371027 PMCID: PMC6927796 DOI: 10.1016/j.crad.2019.07.001] [Citation(s) in RCA: 50] [Impact Index Per Article: 12.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/24/2018] [Accepted: 07/04/2019] [Indexed: 12/14/2022]
Abstract
AIM To review how machine learning (ML) is applied to imaging biomarkers in neuro-oncology, in particular for diagnosis, prognosis, and treatment response monitoring. MATERIALS AND METHODS The PubMed and MEDLINE databases were searched for articles published before September 2018 using relevant search terms. The search strategy focused on articles applying ML to high-grade glioma biomarkers for treatment response monitoring, prognosis, and prediction. RESULTS Magnetic resonance imaging (MRI) is typically used throughout the patient pathway because routine structural imaging provides detailed anatomical and pathological information and advanced techniques provide additional physiological detail. Using carefully chosen image features, ML is frequently used to allow accurate classification in a variety of scenarios. Rather than being chosen by human selection, ML also enables image features to be identified by an algorithm. Much research is applied to determining molecular profiles, histological tumour grade, and prognosis using MRI images acquired at the time that patients first present with a brain tumour. Differentiating a treatment response from a post-treatment-related effect using imaging is clinically important and also an area of active study (described here in one of two Special Issue publications dedicated to the application of ML in glioma imaging). CONCLUSION Although pioneering, most of the evidence is of a low level, having been obtained retrospectively and in single centres. Studies applying ML to build neuro-oncology monitoring biomarker models have yet to show an overall advantage over those using traditional statistical methods. Development and validation of ML models applied to neuro-oncology require large, well-annotated datasets, and therefore multidisciplinary and multi-centre collaborations are necessary.
Collapse
Affiliation(s)
- T C Booth
- School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London SE1 7EH, UK; Department of Neuroradiology, King's College Hospital NHS Foundation Trust, London SE5 9RS, UK.
| | - M Williams
- Department of Neuro-oncology, Imperial College Healthcare NHS Trust, Fulham Palace Rd, London W6 8RF, UK
| | - A Luis
- School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London SE1 7EH, UK; Department of Radiology, St George's University Hospitals NHS Foundation Trust, Blackshaw Road, London SW17 0QT, UK
| | - J Cardoso
- School of Biomedical Engineering & Imaging Sciences, King's College London, St Thomas' Hospital, London SE1 7EH, UK
| | - K Ashkan
- Department of Neurosurgery, King's College Hospital NHS Foundation Trust, London SE5 9RS, UK
| | - H Shuaib
- Department of Medical Physics, Guy's & St. Thomas' NHS Foundation Trust, London SE1 7EH, UK; Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, SE5 8AF, UK
| |
Collapse
|
28
|
Chen X, Fang M, Dong D, Liu L, Xu X, Wei X, Jiang X, Qin L, Liu Z. Development and Validation of a MRI-Based Radiomics Prognostic Classifier in Patients with Primary Glioblastoma Multiforme. Acad Radiol 2019; 26:1292-1300. [PMID: 30660472 DOI: 10.1016/j.acra.2018.12.016] [Citation(s) in RCA: 21] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2018] [Revised: 12/06/2018] [Accepted: 12/19/2018] [Indexed: 12/15/2022]
Abstract
RATIONALE AND OBJECTIVES Glioblastoma multiforme (GBM) is the most common and deadly type of primary malignant tumor of the central nervous system. Accurate risk stratification is vital for a more personalized approach in GBM management. The purpose of this study is to develop and validate a MRI-based prognostic quantitative radiomics classifier in patients with newly diagnosed GBM and to evaluate whether the classifier allows stratification with improved accuracy over the clinical and qualitative imaging features risk models. METHODS Clinical and MR imaging data of 127 GBM patients were obtained from the Cancer Genome Atlas and the Cancer Imaging Archive. Regions of interest corresponding to high signal intensity portions of tumor were drawn on postcontrast T1-weighted imaging (post-T1WI) on the 127 patients (allocated in a 2:1 ratio into a training [n = 85] or validation [n = 42] set), then 3824 radiomics features per patient were extracted. The dimension of these radiomics features were reduced using the minimum redundancy maximum relevance algorithm, then Cox proportional hazard regression model was used to build a radiomics classifier for predicting overall survival (OS). The value of the radiomics classifier beyond clinical (gender, age, Karnofsky performance status, radiation therapy, chemotherapy, and type of resection) and VASARI features for OS was assessed with multivariate Cox proportional hazards model. Time-dependent receiver operating characteristic curve analysis was used to assess the predictive accuracy. RESULTS A classifier using four post-T1WI-MRI radiomics features built on the training dataset could successfully separate GBM patients into low- or high-risk group with a significantly different OS in training (HR, 6.307 [95% CI, 3.475-11.446]; p < 0.001) and validation set (HR, 3.646 [95% CI, 1.709-7.779]; p < 0.001). The area under receiver operating characteristic curve of radiomics classifier (training, 0.799; validation, 0.815 for 12-month) was higher compared to that of the clinical risk model (Karnofsky performance status, radiation therapy; training, 0.749; validation, 0.670 for 12-month), and none of the qualitative imaging features was associated with OS. The predictive accuracy was further improved when combined the radiomics classifier with clinical data (training, 0.819; validation: 0.851 for 12-month). CONCLUSION A classifier using radiomics features allows preoperative prediction of survival and risk stratification of patients with GBM, and it shows improved performance compared to that of clinical and qualitative imaging features models.
Collapse
Affiliation(s)
- Xin Chen
- Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou 510080, China; Department of Radiology, Guangzhou First People's Hospital, School of Medicine, South China University of Technology, Guangzhou, China; Department of Radiology, Harvard Medical School, Boston 02115, Massachusetts
| | - Mengjie Fang
- Key Laboratory of Molecular Imaging, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China
| | - Di Dong
- Key Laboratory of Molecular Imaging, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China
| | - Lingling Liu
- Department of Radiology, Guangzhou First People's Hospital, School of Medicine, South China University of Technology, Guangzhou, China
| | - Xiangdong Xu
- Department of Radiology, Guangzhou First People's Hospital, School of Medicine, South China University of Technology, Guangzhou, China
| | - Xinhua Wei
- Department of Radiology, Guangzhou First People's Hospital, School of Medicine, South China University of Technology, Guangzhou, China
| | - Xinqing Jiang
- Department of Radiology, Guangzhou First People's Hospital, School of Medicine, South China University of Technology, Guangzhou, China
| | - Lei Qin
- Department of Imaging, Dana-Farber Cancer Institute, Boston 02115, Massachusetts; Department of Radiology, Harvard Medical School, Boston 02115, Massachusetts.
| | - Zaiyi Liu
- Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou 510080, China.
| |
Collapse
|
29
|
Peeken JC, Spraker MB, Knebel C, Dapper H, Pfeiffer D, Devecka M, Thamer A, Shouman MA, Ott A, von Eisenhart-Rothe R, Nüsslin F, Mayr NA, Nyflot MJ, Combs SE. Tumor grading of soft tissue sarcomas using MRI-based radiomics. EBioMedicine 2019; 48:332-340. [PMID: 31522983 PMCID: PMC6838361 DOI: 10.1016/j.ebiom.2019.08.059] [Citation(s) in RCA: 74] [Impact Index Per Article: 14.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2019] [Revised: 08/13/2019] [Accepted: 08/24/2019] [Indexed: 12/13/2022] Open
Abstract
Background Treatment decisions for multimodal therapy in soft tissue sarcoma (STS) patients greatly depend on the differentiation between low-grade and high-grade tumors. We developed MRI-based radiomics grading models for the differentiation between low-grade (G1) and high-grade (G2/G3) STS. Methods The study was registered at ClinicalTrials.gov (number NCT03798795). Contrast-enhanced T1-weighted fat saturated (T1FSGd), fat-saturated T2-weighted (T2FS) MRI sequences, and tumor grading following the French Federation of Cancer Centers Sarcoma Group obtained from pre-therapeutic biopsies were gathered from two independent retrospective patient cohorts. Volumes of interest were manually segmented. After preprocessing, 1394 radiomics features were extracted from each sequence. Features unstable in 21 independent multiple-segmentations were excluded. Least absolute shrinkage and selection operator models were developed using nested cross-validation on a training patient cohort (122 patients). The influence of ComBatHarmonization was assessed for correction of batch effects. Findings Three radiomic models based on T2FS, T1FSGd and a combined model achieved predictive performances with an area under the receiver operator characteristic curve (AUC) of 0.78, 0.69, and 0.76 on the independent validation set (103 patients), respectively. The T2FS-based model showed the best reproducibility. The radiomics model involving T1FSGd-based features achieved significant patient stratification. Combining the T2FS radiomic model into a nomogram with clinical staging improved prognostic performance and the clinical net benefit above clinical staging alone. Interpretation MRI-based radiomics tumor grading models effectively classify low-grade and high-grade soft tissue sarcomas. Fund The authors received support by the medical faculty of the Technical University of Munich and the German Cancer Consortium.
Collapse
Affiliation(s)
- Jan C Peeken
- Department of Radiation Oncology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; Institute of Radiation Medicine (IRM), Department of Radiation Sciences (DRS), Helmholtz Zentrum München, Ingolstaedter Landstrasse 1, 85764 Neuherberg, Germany; Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany.
| | - Matthew B Spraker
- Department of Radiation Oncology, University of Washington, 1959 NE Pacific St, Box 356043, Seattle, WA 98195, United States of America
| | - Carolin Knebel
- Department of Orthopaedic Surgery, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 München, Germany
| | - Hendrik Dapper
- Department of Radiation Oncology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany
| | - Daniela Pfeiffer
- Department of Radiology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany
| | - Michal Devecka
- Department of Radiation Oncology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany
| | - Ahmed Thamer
- Department of Radiation Oncology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany
| | - Mohamed A Shouman
- Department of Radiation Oncology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany
| | - Armin Ott
- Institute of Medical Informatics, Statistics and Epidemiology, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany
| | - Rüdiger von Eisenhart-Rothe
- Department of Orthopaedic Surgery, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 München, Germany
| | - Fridtjof Nüsslin
- Department of Radiation Oncology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany
| | - Nina A Mayr
- Department of Radiation Oncology, University of Washington, 1959 NE Pacific St, Box 356043, Seattle, WA 98195, United States of America
| | - Matthew J Nyflot
- Department of Radiation Oncology, University of Washington, 1959 NE Pacific St, Box 356043, Seattle, WA 98195, United States of America; Department of Radiology, University of Washington, Seattle, WA, United States of America
| | - Stephanie E Combs
- Department of Radiation Oncology, Klinikum Rechts der Isar, School of Medicine, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; Institute of Radiation Medicine (IRM), Department of Radiation Sciences (DRS), Helmholtz Zentrum München, Ingolstaedter Landstrasse 1, 85764 Neuherberg, Germany; Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany
| |
Collapse
|
30
|
Bousabarah K, Temming S, Hoevels M, Borggrefe J, Baus WW, Ruess D, Visser-Vandewalle V, Ruge M, Kocher M, Treuer H. Radiomic analysis of planning computed tomograms for predicting radiation-induced lung injury and outcome in lung cancer patients treated with robotic stereotactic body radiation therapy. Strahlenther Onkol 2019; 195:830-842. [PMID: 30874846 DOI: 10.1007/s00066-019-01452-7] [Citation(s) in RCA: 23] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2018] [Accepted: 03/02/2019] [Indexed: 12/11/2022]
Abstract
OBJECTIVES To predict radiation-induced lung injury and outcome in non-small cell lung cancer (NSCLC) patients treated with robotic stereotactic body radiation therapy (SBRT) from radiomic features of the primary tumor. METHODS In all, 110 patients with primary stage I/IIa NSCLC were analyzed for local control (LC), disease-free survival (DFS), overall survival (OS) and development of local lung injury up to fibrosis (LF). First-order (histogram), second-order (GLCM, Gray Level Co-occurrence Matrix) and shape-related radiomic features were determined from the unprocessed or filtered planning CT images of the gross tumor volume (GTV), subjected to LASSO (Least Absolute Shrinkage and Selection Operator) regularization and used to construct continuous and dichotomous risk scores for each endpoint. RESULTS Continuous scores comprising 1-5 histogram or GLCM features had a significant (p = 0.0001-0.032) impact on all endpoints that was preserved in a multifactorial Cox regression analysis comprising additional clinical and dosimetric factors. At 36 months, LC did not differ between the dichotomous risk groups (93% vs. 85%, HR 0.892, 95%CI 0.222-3.590), while DFS (45% vs. 17%, p < 0.05, HR 0.457, 95%CI 0.240-0.868) and OS (80% vs. 37%, p < 0.001, HR 0.190, 95%CI 0.065-0.556) were significantly lower in the high-risk groups. Also, the frequency of LF differed significantly between the two risk groups (63% vs. 20% at 24 months, p < 0.001, HR 0.158, 95%CI 0.054-0.458). CONCLUSION Radiomic analysis of the gross tumor volume may help to predict DFS and OS and the development of local lung fibrosis in early stage NSCLC patients treated with stereotactic radiotherapy.
Collapse
Affiliation(s)
- Khaled Bousabarah
- Department of Stereotactic and Functional Neurosurgery, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Susanne Temming
- Department of Radiation Oncology, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Mauritius Hoevels
- Department of Stereotactic and Functional Neurosurgery, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Jan Borggrefe
- Institute of Diagnostic and Interventional Radiology, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Wolfgang W Baus
- Department of Radiation Oncology, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Daniel Ruess
- Department of Stereotactic and Functional Neurosurgery, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Veerle Visser-Vandewalle
- Department of Stereotactic and Functional Neurosurgery, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Maximilian Ruge
- Department of Stereotactic and Functional Neurosurgery, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| | - Martin Kocher
- Department of Stereotactic and Functional Neurosurgery, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany.
- Department of Radiation Oncology, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany.
| | - Harald Treuer
- Department of Stereotactic and Functional Neurosurgery, University Hospital of Cologne, Kerpener Str. 62, 50937, Cologne, Germany
| |
Collapse
|
31
|
Incidence of Dural Venous Sinus Thrombosis in Patients with Glioblastoma and Its Implications. World Neurosurg 2019; 125:e189-e197. [PMID: 30684707 DOI: 10.1016/j.wneu.2019.01.039] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2018] [Revised: 01/10/2019] [Accepted: 01/14/2019] [Indexed: 11/22/2022]
Abstract
OBJECTIVE Glioblastoma (GBM) is associated with increased risk of developing dural venous sinus thrombosis (DVST), which often goes undiagnosed as symptoms are readily attributed to tumor. The purpose of this study was to investigate the incidence of DVST, potential predictive features on imaging, complications, its effect on survival, and time of greatest risk for developing DVST. METHODS A retrospective search of patients with GBM who had surgery followed by chemotherapy and/or radiation therapy between 2009 and 2015 at our institution was performed. Magnetic resonance imaging studies of the brain were reviewed on volumetric postgadolinium T1-weighted sequences for DVST. Tumors were characterized using the Visually Accessible REMBRANDT (Repository for Molecular Brain Neoplasia Data) Images classification, and identified thromboses were tracked for propagation, regression, or resolution. Statistical analyses were directed at identifying clinical predictors and survival differences between the DVST and no-DVST groups. RESULTS In total, 163 cases totaling 1637 scans, were reviewed; 12 patients (7.4%) developed DVST, of whom 11 presented with thrombus before any treatment. Tumor invasion of dural sinuses and greater T1/fluid-attenuated inversion recovery ratios were significantly associated with thrombus development (P = 0.02 and P = 0.02, respectively). In patients who developed DVST, thrombosis was more likely to develop ipsilateral to tumor side (P = 0.01) and was associated with a greater likelihood of developing extracranial venous thromboembolism (P = 0.012). There were no venous infarcts and no significant difference in survival between groups (P = 0.83). CONCLUSIONS Patients with GBM have increased risk of developing DVST, independent of surgical treatment or chemoradiation. DVST presence does not affect survival. Tumor invasion of dural sinuses and greater T1/fluid-attenuated inversion recovery ratio on preoperative imaging were the most significant predictors of DVST development.
Collapse
|
32
|
Tixier F, Um H, Bermudez D, Iyer A, Apte A, Graham MS, Nevel KS, Deasy JO, Young RJ, Veeraraghavan H. Preoperative MRI-radiomics features improve prediction of survival in glioblastoma patients over MGMT methylation status alone. Oncotarget 2019; 10:660-672. [PMID: 30774763 PMCID: PMC6363013 DOI: 10.18632/oncotarget.26578] [Citation(s) in RCA: 31] [Impact Index Per Article: 6.2] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2018] [Accepted: 12/22/2018] [Indexed: 12/14/2022] Open
Abstract
BACKGROUND Glioblastoma (GBM) is the most common malignant central nervous system tumor, and MGMT promoter hypermethylation in this tumor has been shown to be associated with better prognosis. We evaluated the capacity of radiomics features to add complementary information to MGMT status, to improve the ability to predict prognosis. METHODS 159 patients with untreated GBM were included in this study and divided into training and independent test sets. 286 radiomics features were extracted from the magnetic resonance images acquired prior to any treatments. A least absolute shrinkage selection operator (LASSO) selection followed by Kaplan-Meier analysis was used to determine the prognostic value of radiomics features to predict overall survival (OS). The combination of MGMT status with radiomics was also investigated and all results were validated on the independent test set. RESULTS LASSO analysis identified 8 out of the 286 radiomic features to be relevant which were then used for determining association to OS. One feature (edge descriptor) remained significant on the external validation cohort after multiple testing (p=0.04) and the combination with MGMT identified a group of patients with the best prognosis with a survival probability of 0.61 after 43 months (p=0.0005). CONCLUSION Our results suggest that combining radiomics with MGMT is more accurate in stratifying patients into groups of different survival risks when compared to with using these predictors in isolation. We identified two subgroups within patients who have methylated MGMT: one with a similar survival to unmethylated MGMT patients and the other with a significantly longer OS.
Collapse
Affiliation(s)
- Florent Tixier
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Hyemin Um
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Dalton Bermudez
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Aditi Iyer
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Aditya Apte
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Maya S. Graham
- Department of Neurology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Kathryn S. Nevel
- Department of Neurology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
- Department of Neurology, Indiana University School of Medicine, Indianapolis, Indiana, USA
| | - Joseph O. Deasy
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Robert J. Young
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
- Brain Tumor Center, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Harini Veeraraghavan
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| |
Collapse
|
33
|
Peeken JC, Bernhofer M, Wiestler B, Goldberg T, Cremers D, Rost B, Wilkens JJ, Combs SE, Nüsslin F. Radiomics in radiooncology - Challenging the medical physicist. Phys Med 2018; 48:27-36. [PMID: 29728226 DOI: 10.1016/j.ejmp.2018.03.012] [Citation(s) in RCA: 56] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/11/2018] [Revised: 03/07/2018] [Accepted: 03/20/2018] [Indexed: 02/06/2023] Open
Abstract
PURPOSE Noticing the fast growing translation of artificial intelligence (AI) technologies to medical image analysis this paper emphasizes the future role of the medical physicist in this evolving field. Specific challenges are addressed when implementing big data concepts with high-throughput image data processing like radiomics and machine learning in a radiooncology environment to support clinical decisions. METHODS Based on the experience of our interdisciplinary radiomics working group, techniques for processing minable data, extracting radiomics features and associating this information with clinical, physical and biological data for the development of prediction models are described. A special emphasis was placed on the potential clinical significance of such an approach. RESULTS Clinical studies demonstrate the role of radiomics analysis as an additional independent source of information with the potential to influence the radiooncology practice, i.e. to predict patient prognosis, treatment response and underlying genetic changes. Extending the radiomics approach to integrate imaging, clinical, genetic and dosimetric data ('panomics') challenges the medical physicist as member of the radiooncology team. CONCLUSIONS The new field of big data processing in radiooncology offers opportunities to support clinical decisions, to improve predicting treatment outcome and to stimulate fundamental research on radiation response both of tumor and normal tissue. The integration of physical data (e.g. treatment planning, dosimetric, image guidance data) demands an involvement of the medical physicist in the radiomics approach of radiooncology. To cope with this challenge national and international organizations for medical physics should organize more training opportunities in artificial intelligence technologies in radiooncology.
Collapse
Affiliation(s)
- Jan C Peeken
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany
| | - Michael Bernhofer
- Department of Informatics, Technical University of Munich (TUM), Boltzmannstraße 3, 85748 Garching, Germany
| | - Benedikt Wiestler
- Department of Neuroradiology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany
| | | | - Daniel Cremers
- Department of Informatics, Technical University of Munich (TUM), Boltzmannstraße 3, 85748 Garching, Germany
| | - Burkhard Rost
- Department of Informatics, Technical University of Munich (TUM), Boltzmannstraße 3, 85748 Garching, Germany
| | - Jan J Wilkens
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany
| | - Stephanie E Combs
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany; Institute of Innovative Radiotherapy (iRT), Department of Radiation Sciences (DRS), Helmholtz Zentrum München, Ingolstaedter Landstrasse 1, 85764 Neuherberg, Germany; Deutsches Konsortium für Translationale Krebsforschung (DKTK), Partner Site Munich, Germany
| | - Fridtjof Nüsslin
- Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich (TUM), Ismaninger Straße 22, 81675 Munich, Germany.
| |
Collapse
|