{"id":{"repo_id":"milano","oai_identifier":"oai:air.unimi.it:2434/932853"},"canonical_url":"https://search.dev.ndltd.org/etd/milano/oai:air.unimi.it:2434/932853","repository":{"repo_id":"milano","name":"Università degli Studi di Milano","base_url":"https://air.unimi.it/oai/request"},"display":{"title":"NEW ADVANCES IN QUANTITATIVE RADIOLOGY: RADIOMICS IN NEURORADIOLOGY APPLIED TO PRIMARY BRAIN TUMORS USING A MACHINE LEARNING APPROACH","abstract":"Arterial spin labelling (ASL) radiomics analysis to predict IDH mutation and MGMT methylation status in gliomas Fabio M. Doniselli1,2, Riccardo Pascuzzo1, Eleonora Bruno3, Domenico Aquino1, Mattia Verri, Alberto Redolfi, Valeria Cuccarini1, Marco Moscatelli1,2, Maria Grazia Bruzzone1, Luca Maria Sconfienza2,4 Abstract Objectives: To evaluate the strength and ability of radiomics features extracted from multiple tumor subregions on MR brain images to predict MGMT promoter (MGMT) methylation status and isocitrate dehydrogenase (IDH) mutation in glioma patients through a multiparametric MRI-based radiomics model, using arterial-spin labelling (ASL) perfusion imaging. Methods: Retrospective single-institution study in a cohort of 52 glioma patients. Radiomics-based models with a minimal set of relevant features and clinical parameters were built for MGMT methylation and IDH-mutation prediction from a training cohort (31 patients) and tested on an validation cohort (13 patients). Results: Feature selection methods (Boruta, RFE and LR-EL) identified age and 3 radiomics features for MGMT prediction and 3 features for IDH prediction. For IDH prediction, SVM classifier achieved average 96.8% accuracy and 0.929 AUC during the training phase, and 84.6% accuracy and 0.60 AUC on the test set. For MGMT methylation prediction, SVM classifier achieved average 67.7% accuracy and 0.765 AUC during the training phase, and 38.5% accuracy and 0.429 AUC on the test set. Conclusions: The classification model based on both demographic (age) and radiomic ASL perfusion characteristics had the best performance in predicting the IDH mutational status of gliomas. This result suggests that the proposed method has promising efficacy in predicting IDH mutational status. We have not obtained a sufficient result trying to correlate radiomics with the MGMT mutational pattern.","abstract_html":"Arterial spin labelling (ASL) radiomics analysis to predict IDH mutation and MGMT methylation status in gliomas Fabio M. Doniselli1,2, Riccardo Pascuzzo1, Eleonora Bruno3, Domenico Aquino1, Mattia Verri, Alberto Redolfi, Valeria Cuccarini1, Marco Moscatelli1,2, Maria Grazia Bruzzone1, Luca Maria Sconfienza2,4 Abstract Objectives: To evaluate the strength and ability of radiomics features extracted from multiple tumor subregions on MR brain images to predict MGMT promoter (MGMT) methylation status and isocitrate dehydrogenase (IDH) mutation in glioma patients through a multiparametric MRI-based radiomics model, using arterial-spin labelling (ASL) perfusion imaging. Methods: Retrospective single-institution study in a cohort of 52 glioma patients. Radiomics-based models with a minimal set of relevant features and clinical parameters were built for MGMT methylation and IDH-mutation prediction from a training cohort (31 patients) and tested on an validation cohort (13 patients). Results: Feature selection methods (Boruta, RFE and LR-EL) identified age and 3 radiomics features for MGMT prediction and 3 features for IDH prediction. For IDH prediction, SVM classifier achieved average 96.8% accuracy and 0.929 AUC during the training phase, and 84.6% accuracy and 0.60 AUC on the test set. For MGMT methylation prediction, SVM classifier achieved average 67.7% accuracy and 0.765 AUC during the training phase, and 38.5% accuracy and 0.429 AUC on the test set. Conclusions: The classification model based on both demographic (age) and radiomic ASL perfusion characteristics had the best performance in predicting the IDH mutational status of gliomas. This result suggests that the proposed method has promising efficacy in predicting IDH mutational status. We have not obtained a sufficient result trying to correlate radiomics with the MGMT mutational pattern.","abstract_has_math":false,"creators":["DONISELLI, FABIO MARTINO"],"institution":"Università degli Studi di Milano","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["tutor: L.M. Sconfienza ; coordinatore: M. Del Fabbro","F.M. Doniselli","SCONFIENZA, LUCA MARIA","DEL FABBRO, MASSIMO"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-07-05","date_published":"2022-07-05","updated_at":"2026-07-27T20:18:53Z","subjects":["glioma","radiomic","machine learning","neuroradiology","MGMT","IDH","RQS","ASL","Settore MED/36 - Diagnostica per Immagini e Radioterapia","Settore MED/37 - Neuroradiologia"],"languages":["eng"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["http://dx.doi.org/10.13130/doniselli-fabio-martino_phd2022-07-05","10.13130/doniselli-fabio-martino_phd2022-07-05"],"render_values":[{"text":"http://dx.doi.org/10.13130/doniselli-fabio-martino_phd2022-07-05","href":"http://dx.doi.org/10.13130/doniselli-fabio-martino_phd2022-07-05","code":true},{"text":"10.13130/doniselli-fabio-martino_phd2022-07-05","href":"https://doi.org/10.13130/doniselli-fabio-martino_phd2022-07-05","code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2434/932853","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["tutor: L.M. Sconfienza ; coordinatore: M. Del Fabbro","F.M. Doniselli","SCONFIENZA, LUCA MARIA","DEL FABBRO, MASSIMO"]},{"key":"dc:creator","label":"Author","values":["DONISELLI, FABIO MARTINO"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-07-05"]},{"key":"dc:publisher","label":"Institution","values":["Università degli Studi di Milano"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/doctoralThesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["glioma","radiomic","machine learning","neuroradiology","MGMT","IDH","RQS","ASL","Settore MED/36 - Diagnostica per Immagini e Radioterapia","Settore MED/37 - Neuroradiologia"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2434/932853","http://dx.doi.org/10.13130/doniselli-fabio-martino_phd2022-07-05","10.13130/doniselli-fabio-martino_phd2022-07-05"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Arterial spin labelling (ASL) radiomics analysis to predict IDH mutation and MGMT methylation status in gliomas Fabio M. Doniselli1,2, Riccardo Pascuzzo1, Eleonora Bruno3, Domenico Aquino1, Mattia Verri, Alberto Redolfi, Valeria Cuccarini1, Marco Moscatelli1,2, Maria Grazia Bruzzone1, Luca Maria Sconfienza2,4 Abstract Objectives: To evaluate the strength and ability of radiomics features extracted from multiple tumor subregions on MR brain images to predict MGMT promoter (MGMT) methylation status and isocitrate dehydrogenase (IDH) mutation in glioma patients through a multiparametric MRI-based radiomics model, using arterial-spin labelling (ASL) perfusion imaging. Methods: Retrospective single-institution study in a cohort of 52 glioma patients. Radiomics-based models with a minimal set of relevant features and clinical parameters were built for MGMT methylation and IDH-mutation prediction from a training cohort (31 patients) and tested on an validation cohort (13 patients). Results: Feature selection methods (Boruta, RFE and LR-EL) identified age and 3 radiomics features for MGMT prediction and 3 features for IDH prediction. For IDH prediction, SVM classifier achieved average 96.8% accuracy and 0.929 AUC during the training phase, and 84.6% accuracy and 0.60 AUC on the test set. For MGMT methylation prediction, SVM classifier achieved average 67.7% accuracy and 0.765 AUC during the training phase, and 38.5% accuracy and 0.429 AUC on the test set. Conclusions: The classification model based on both demographic (age) and radiomic ASL perfusion characteristics had the best performance in predicting the IDH mutational status of gliomas. This result suggests that the proposed method has promising efficacy in predicting IDH mutational status. We have not obtained a sufficient result trying to correlate radiomics with the MGMT mutational pattern.","Assessment of quality and classification performances of MRI-based radiomics studies on MGMT methylation in gliomas: a systematic review Fabio M. Doniselli1,2*, Riccardo Pascuzzo1*, Massimiliano Agrò3, Domenico Aquino1, Federica Mazzi1, Francesco Padelli1, Marco Moscatelli1, Maria Grazia Bruzzone1, Luca M. Sconfienza2,4 Objectives To evaluate the quality of MRI-based radiomics studies predicting the O6-methylguanine-DNA methyltransferase (MGMT) methylation status in gliomas, using radiomics quality score (RQS) and Image Biomarkers Standardization Initiative (IBSI) guidelines, and examine their classification performance. Methods PubMed Medline and EMBASE were searched to identify MRI-based radiomics studies on MGMT methylation in gliomas until January 31, 2022. Included studies were scored according to RQS (16 components) and IBSI (six items) scales by two raters. Results We included 20 out of 62 identified studies. The median RQS total score was 32% of the maximum (11.5 out of 36), ranging between 8% and 44%. Eleven studies performed external validation; only three studies performed decision curve analysis to report potential clinical utility. All studies reported area under the curve (AUC) or accuracy, and 14 computed these statistics using resampling methods (e.g., cross-validation). No study performed phantom study, cost-effectiveness analysis, and prospective validation. Regarding IBSI items, 14 studies (70%) performed signal intensity normalization, while few performed N4 bias-field correction (4, 20%) and skull stripping (3, 15%). Good classification performance (AUC>0.75) was obtained by 11 (55%) studies, but only four of them performed external validation (on sets with 20-60 patients). On the contrary, seven out of the nine studies with lower classification results performed external validation (on sets with 27-126 patients). Conclusions Adherence to RQS and IBSI guidelines was generally low. MGMT methylation status appears to be correlated with radiomic features, but with great heterogeneity of results. To confirm this trend, strict implementation of RQS and IBSI criteria is needed.","Radiomics for MGMT methylation detection in GBM using conventional pre-operative MRI Fabio M. Doniselli1,2, Riccardo Pascuzzo1, Massimiliano Agrò3, Domenico Aquino1, Elena Anghileri, Bianca Pollo, Valeria Cuccarini1, Marco Moscatelli1, Francesco DiMeco, Maria Grazia Bruzzone1, Luca M. Sconfienza2,4 Abstract Objectives: To evaluate the strength and ability of radiomics features extracted from multiple tumor subregions on MR brain images to predict MGMT promoter (MGMT) methylation status in GBM patients through a multiparametric MRI-based radiomics model. Methods: Retrospective single-institution study in a cohort of 277 GBM patients. Radiomics-based models with a minimal set of relevant features and clinical parameters were built for MGMT methylation prediction from a training cohort (196 patients) and tested on an validation cohort (81 patients). Radiomic Quality Score (RQS) was equal to 15. Results: Feature selection methods (Boruta, RFE and LR-EL) identified age and 218 radiomics features. SVM classifier achieved average 73.6% (standard deviation: 6.5%) accuracy and 0.836 (0.054) AUC during the training phase, and 59.3% (95% confidence interval: 47.8%-70.0%) accuracy and 0.553 (0.412-0.686) AUC on the test set. Conclusions: We agree on the probable presence of subtle association between imaging characteristics and MGMT methylation status. However, further verification on the strength of this association is needed, as the low diagnostic performance in the validation cohort is still not sufficiently robust to allow clinically meaningful predictions."]},{"key":"dc:title","label":"Title","values":["NEW ADVANCES IN QUANTITATIVE RADIOLOGY: RADIOMICS IN NEURORADIOLOGY APPLIED TO PRIMARY BRAIN TUMORS USING A MACHINE LEARNING APPROACH"]}]}],"canonical_facts":{"dc:contributor":["tutor: L.M. Sconfienza ; coordinatore: M. Del Fabbro","F.M. Doniselli","SCONFIENZA, LUCA MARIA","DEL FABBRO, MASSIMO"],"dc:creator":["DONISELLI, FABIO MARTINO"],"dc:date":["2022-07-05"],"dc:description":["Arterial spin labelling (ASL) radiomics analysis to predict IDH mutation and MGMT methylation status in gliomas Fabio M. Doniselli1,2, Riccardo Pascuzzo1, Eleonora Bruno3, Domenico Aquino1, Mattia Verri, Alberto Redolfi, Valeria Cuccarini1, Marco Moscatelli1,2, Maria Grazia Bruzzone1, Luca Maria Sconfienza2,4 Abstract Objectives: To evaluate the strength and ability of radiomics features extracted from multiple tumor subregions on MR brain images to predict MGMT promoter (MGMT) methylation status and isocitrate dehydrogenase (IDH) mutation in glioma patients through a multiparametric MRI-based radiomics model, using arterial-spin labelling (ASL) perfusion imaging. Methods: Retrospective single-institution study in a cohort of 52 glioma patients. Radiomics-based models with a minimal set of relevant features and clinical parameters were built for MGMT methylation and IDH-mutation prediction from a training cohort (31 patients) and tested on an validation cohort (13 patients). Results: Feature selection methods (Boruta, RFE and LR-EL) identified age and 3 radiomics features for MGMT prediction and 3 features for IDH prediction. For IDH prediction, SVM classifier achieved average 96.8% accuracy and 0.929 AUC during the training phase, and 84.6% accuracy and 0.60 AUC on the test set. For MGMT methylation prediction, SVM classifier achieved average 67.7% accuracy and 0.765 AUC during the training phase, and 38.5% accuracy and 0.429 AUC on the test set. Conclusions: The classification model based on both demographic (age) and radiomic ASL perfusion characteristics had the best performance in predicting the IDH mutational status of gliomas. This result suggests that the proposed method has promising efficacy in predicting IDH mutational status. We have not obtained a sufficient result trying to correlate radiomics with the MGMT mutational pattern.","Assessment of quality and classification performances of MRI-based radiomics studies on MGMT methylation in gliomas: a systematic review Fabio M. Doniselli1,2*, Riccardo Pascuzzo1*, Massimiliano Agrò3, Domenico Aquino1, Federica Mazzi1, Francesco Padelli1, Marco Moscatelli1, Maria Grazia Bruzzone1, Luca M. Sconfienza2,4 Objectives To evaluate the quality of MRI-based radiomics studies predicting the O6-methylguanine-DNA methyltransferase (MGMT) methylation status in gliomas, using radiomics quality score (RQS) and Image Biomarkers Standardization Initiative (IBSI) guidelines, and examine their classification performance. Methods PubMed Medline and EMBASE were searched to identify MRI-based radiomics studies on MGMT methylation in gliomas until January 31, 2022. Included studies were scored according to RQS (16 components) and IBSI (six items) scales by two raters. Results We included 20 out of 62 identified studies. The median RQS total score was 32% of the maximum (11.5 out of 36), ranging between 8% and 44%. Eleven studies performed external validation; only three studies performed decision curve analysis to report potential clinical utility. All studies reported area under the curve (AUC) or accuracy, and 14 computed these statistics using resampling methods (e.g., cross-validation). No study performed phantom study, cost-effectiveness analysis, and prospective validation. Regarding IBSI items, 14 studies (70%) performed signal intensity normalization, while few performed N4 bias-field correction (4, 20%) and skull stripping (3, 15%). Good classification performance (AUC>0.75) was obtained by 11 (55%) studies, but only four of them performed external validation (on sets with 20-60 patients). On the contrary, seven out of the nine studies with lower classification results performed external validation (on sets with 27-126 patients). Conclusions Adherence to RQS and IBSI guidelines was generally low. MGMT methylation status appears to be correlated with radiomic features, but with great heterogeneity of results. To confirm this trend, strict implementation of RQS and IBSI criteria is needed.","Radiomics for MGMT methylation detection in GBM using conventional pre-operative MRI Fabio M. Doniselli1,2, Riccardo Pascuzzo1, Massimiliano Agrò3, Domenico Aquino1, Elena Anghileri, Bianca Pollo, Valeria Cuccarini1, Marco Moscatelli1, Francesco DiMeco, Maria Grazia Bruzzone1, Luca M. Sconfienza2,4 Abstract Objectives: To evaluate the strength and ability of radiomics features extracted from multiple tumor subregions on MR brain images to predict MGMT promoter (MGMT) methylation status in GBM patients through a multiparametric MRI-based radiomics model. Methods: Retrospective single-institution study in a cohort of 277 GBM patients. Radiomics-based models with a minimal set of relevant features and clinical parameters were built for MGMT methylation prediction from a training cohort (196 patients) and tested on an validation cohort (81 patients). Radiomic Quality Score (RQS) was equal to 15. Results: Feature selection methods (Boruta, RFE and LR-EL) identified age and 218 radiomics features. SVM classifier achieved average 73.6% (standard deviation: 6.5%) accuracy and 0.836 (0.054) AUC during the training phase, and 59.3% (95% confidence interval: 47.8%-70.0%) accuracy and 0.553 (0.412-0.686) AUC on the test set. Conclusions: We agree on the probable presence of subtle association between imaging characteristics and MGMT methylation status. However, further verification on the strength of this association is needed, as the low diagnostic performance in the validation cohort is still not sufficiently robust to allow clinically meaningful predictions."],"dc:identifier":["http://hdl.handle.net/2434/932853","http://dx.doi.org/10.13130/doniselli-fabio-martino_phd2022-07-05","10.13130/doniselli-fabio-martino_phd2022-07-05"],"dc:language":["eng"],"dc:publisher":["Università degli Studi di Milano"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:subject":["glioma","radiomic","machine learning","neuroradiology","MGMT","IDH","RQS","ASL","Settore MED/36 - Diagnostica per Immagini e Radioterapia","Settore MED/37 - Neuroradiologia"],"dc:title":["NEW ADVANCES IN QUANTITATIVE RADIOLOGY: RADIOMICS IN NEURORADIOLOGY APPLIED TO PRIMARY BRAIN TUMORS USING A MACHINE LEARNING APPROACH"],"dc:type":["info:eu-repo/semantics/doctoralThesis"]},"updated_at":"2026-07-27T20:18:53Z"}