Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain Metastases
<b>Background</b>: The accurate and early distinction of glioblastomas (GBMs) from single brain metastases (BMs) provides a window of opportunity for reframing treatment strategies enabling optimal and timely therapeutic interventions. We sought to leverage physiologically sensitive para...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/1/38 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549242550714368 |
|---|---|
| author | Seyyed Ali Hosseini Stijn Servaes Brandon Hall Sourav Bhaduri Archith Rajan Pedro Rosa-Neto Steven Brem Laurie A. Loevner Suyash Mohan Sanjeev Chawla |
| author_facet | Seyyed Ali Hosseini Stijn Servaes Brandon Hall Sourav Bhaduri Archith Rajan Pedro Rosa-Neto Steven Brem Laurie A. Loevner Suyash Mohan Sanjeev Chawla |
| author_sort | Seyyed Ali Hosseini |
| collection | DOAJ |
| description | <b>Background</b>: The accurate and early distinction of glioblastomas (GBMs) from single brain metastases (BMs) provides a window of opportunity for reframing treatment strategies enabling optimal and timely therapeutic interventions. We sought to leverage physiologically sensitive parameters derived from diffusion tensor imaging (DTI) and dynamic susceptibility contrast (DSC)–perfusion-weighted imaging (PWI) along with machine learning-based methods to distinguish GBMs from single BMs. <b>Methods</b>: Patients with histopathology-confirmed GBMs (<i>n</i> = 62) and BMs (<i>n</i> = 26) and exhibiting contrast-enhancing regions (CERs) underwent 3T anatomical imaging, DTI and DSC-PWI prior to treatment. Median values of mean diffusivity (MD), fractional anisotropy, linear, planar and spheric anisotropic coefficients, and relative cerebral blood volume (rCBV) and maximum rCBV values were measured from CERs and immediate peritumor regions. Data normalization and scaling were performed. In the next step, most relevant features were extracted (non-interacting features), which were subsequently used to generate a set of new, innovative, high-order features (interacting features) using a feature engineering method. Finally, 10 machine learning classifiers were employed in distinguishing GBMs and BMs. Cross-validation and receiver operating characteristic (ROC) curve analyses were performed to determine the diagnostic performance. <b>Results</b>: A random forest classifier with ANOVA F-value feature selection algorithm using both interacting and non-interacting features provided the best diagnostic performance in distinguishing GBMs from BMs with an area under the ROC curve of 92.67%, a classification accuracy of 87.8%, a sensitivity of 73.64% and a specificity of 97.5%. <b>Conclusions</b>: A machine learning based approach involving the combined use of interacting and non-interacting physiological MRI parameters shows promise to differentiate between GBMs and BMs with high accuracy. |
| format | Article |
| id | doaj-art-01823ad8442c4c7ab232c4a5ca03015a |
| institution | Kabale University |
| issn | 2075-4418 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-01823ad8442c4c7ab232c4a5ca03015a2025-01-10T13:16:32ZengMDPI AGDiagnostics2075-44182024-12-011513810.3390/diagnostics15010038Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain MetastasesSeyyed Ali Hosseini0Stijn Servaes1Brandon Hall2Sourav Bhaduri3Archith Rajan4Pedro Rosa-Neto5Steven Brem6Laurie A. Loevner7Suyash Mohan8Sanjeev Chawla9Translational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montreal, QC H4H 1R3, CanadaTranslational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montreal, QC H4H 1R3, CanadaTranslational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montreal, QC H4H 1R3, CanadaInstitute for Advancing Intelligence (IAI), The Chatterjee Group—Centre for Research and Education in Science and Technology (TCG CREST), Kolkata 700091, IndiaDepartment of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USATranslational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montreal, QC H4H 1R3, CanadaDepartment of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADepartment of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADepartment of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USADepartment of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA<b>Background</b>: The accurate and early distinction of glioblastomas (GBMs) from single brain metastases (BMs) provides a window of opportunity for reframing treatment strategies enabling optimal and timely therapeutic interventions. We sought to leverage physiologically sensitive parameters derived from diffusion tensor imaging (DTI) and dynamic susceptibility contrast (DSC)–perfusion-weighted imaging (PWI) along with machine learning-based methods to distinguish GBMs from single BMs. <b>Methods</b>: Patients with histopathology-confirmed GBMs (<i>n</i> = 62) and BMs (<i>n</i> = 26) and exhibiting contrast-enhancing regions (CERs) underwent 3T anatomical imaging, DTI and DSC-PWI prior to treatment. Median values of mean diffusivity (MD), fractional anisotropy, linear, planar and spheric anisotropic coefficients, and relative cerebral blood volume (rCBV) and maximum rCBV values were measured from CERs and immediate peritumor regions. Data normalization and scaling were performed. In the next step, most relevant features were extracted (non-interacting features), which were subsequently used to generate a set of new, innovative, high-order features (interacting features) using a feature engineering method. Finally, 10 machine learning classifiers were employed in distinguishing GBMs and BMs. Cross-validation and receiver operating characteristic (ROC) curve analyses were performed to determine the diagnostic performance. <b>Results</b>: A random forest classifier with ANOVA F-value feature selection algorithm using both interacting and non-interacting features provided the best diagnostic performance in distinguishing GBMs from BMs with an area under the ROC curve of 92.67%, a classification accuracy of 87.8%, a sensitivity of 73.64% and a specificity of 97.5%. <b>Conclusions</b>: A machine learning based approach involving the combined use of interacting and non-interacting physiological MRI parameters shows promise to differentiate between GBMs and BMs with high accuracy.https://www.mdpi.com/2075-4418/15/1/38glioblastomasbrain metastasesMRImachine learningfeature engineering |
| spellingShingle | Seyyed Ali Hosseini Stijn Servaes Brandon Hall Sourav Bhaduri Archith Rajan Pedro Rosa-Neto Steven Brem Laurie A. Loevner Suyash Mohan Sanjeev Chawla Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain Metastases Diagnostics glioblastomas brain metastases MRI machine learning feature engineering |
| title | Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain Metastases |
| title_full | Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain Metastases |
| title_fullStr | Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain Metastases |
| title_full_unstemmed | Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain Metastases |
| title_short | Quantitative Physiologic MRI Combined with Feature Engineering for Developing Machine Learning-Based Prediction Models to Distinguish Glioblastomas from Single Brain Metastases |
| title_sort | quantitative physiologic mri combined with feature engineering for developing machine learning based prediction models to distinguish glioblastomas from single brain metastases |
| topic | glioblastomas brain metastases MRI machine learning feature engineering |
| url | https://www.mdpi.com/2075-4418/15/1/38 |
| work_keys_str_mv | AT seyyedalihosseini quantitativephysiologicmricombinedwithfeatureengineeringfordevelopingmachinelearningbasedpredictionmodelstodistinguishglioblastomasfromsinglebrainmetastases AT stijnservaes quantitativephysiologicmricombinedwithfeatureengineeringfordevelopingmachinelearningbasedpredictionmodelstodistinguishglioblastomasfromsinglebrainmetastases AT brandonhall quantitativephysiologicmricombinedwithfeatureengineeringfordevelopingmachinelearningbasedpredictionmodelstodistinguishglioblastomasfromsinglebrainmetastases AT souravbhaduri quantitativephysiologicmricombinedwithfeatureengineeringfordevelopingmachinelearningbasedpredictionmodelstodistinguishglioblastomasfromsinglebrainmetastases AT archithrajan quantitativephysiologicmricombinedwithfeatureengineeringfordevelopingmachinelearningbasedpredictionmodelstodistinguishglioblastomasfromsinglebrainmetastases AT pedrorosaneto quantitativephysiologicmricombinedwithfeatureengineeringfordevelopingmachinelearningbasedpredictionmodelstodistinguishglioblastomasfromsinglebrainmetastases AT stevenbrem quantitativephysiologicmricombinedwithfeatureengineeringfordevelopingmachinelearningbasedpredictionmodelstodistinguishglioblastomasfromsinglebrainmetastases AT lauriealoevner quantitativephysiologicmricombinedwithfeatureengineeringfordevelopingmachinelearningbasedpredictionmodelstodistinguishglioblastomasfromsinglebrainmetastases AT suyashmohan quantitativephysiologicmricombinedwithfeatureengineeringfordevelopingmachinelearningbasedpredictionmodelstodistinguishglioblastomasfromsinglebrainmetastases AT sanjeevchawla quantitativephysiologicmricombinedwithfeatureengineeringfordevelopingmachinelearningbasedpredictionmodelstodistinguishglioblastomasfromsinglebrainmetastases |