Investigating the Behaviour of Machine Learning Techniques to Segment Brain Metastases in Radiation Therapy Planning
This work aimed to investigate whether automated classifiers belonging to feature-based and deep learning may approach brain metastases segmentation successfully. Support Vector Machine and V-Net Convolutional Neural Network are selected as representatives of the two approaches. In the experiments,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/16/3335 |
| _version_ | 1818489877821390848 |
|---|---|
| author | Gloria Gonella Elisabetta Binaghi Paola Nocera Cinzia Mordacchini |
| author_facet | Gloria Gonella Elisabetta Binaghi Paola Nocera Cinzia Mordacchini |
| author_sort | Gloria Gonella |
| collection | DOAJ |
| description | This work aimed to investigate whether automated classifiers belonging to feature-based and deep learning may approach brain metastases segmentation successfully. Support Vector Machine and V-Net Convolutional Neural Network are selected as representatives of the two approaches. In the experiments, we consider several configurations of the two methods to segment brain metastases on contrast-enhanced T1-weighted magnetic resonance images. Performances were evaluated and compared under critical conditions imposed by the clinical radiotherapy domain, using in-house dataset and public dataset created for the Multimodal Brain Tumour Image Segmentation (BraTS) challenge. Our results showed that the feature-based and the deep network approaches are promising for the segmentation of Magnetic Resonance Imaging (MRI) brain metastases achieving both an acceptable level of performance. Experimental results also highlight different behaviour between the two methods. Support vector machine (SVM) improves performance with a smaller training set, but it is unable to manage a high level of heterogeneity in the data and requires post-processing refinement stages. The V-Net model shows good performances when trained on multiple heterogeneous cases but requires data augmentations and transfer learning procedures to optimise its behaviour. The paper illustrates a software package implementing an integrated set of procedures for active support in segmenting brain metastases within the radiotherapy workflow. |
| first_indexed | 2024-12-10T17:09:43Z |
| format | Article |
| id | doaj.art-4f3980bc79544df0b606163aeaca9bd8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-10T17:09:43Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4f3980bc79544df0b606163aeaca9bd82022-12-22T01:40:22ZengMDPI AGApplied Sciences2076-34172019-08-01916333510.3390/app9163335app9163335Investigating the Behaviour of Machine Learning Techniques to Segment Brain Metastases in Radiation Therapy PlanningGloria Gonella0Elisabetta Binaghi1Paola Nocera2Cinzia Mordacchini3Department of Theoretical and Applied Science, University of Insubria, 21100 Varese, ItalyDepartment of Physics, University of Milan, 20122 Milan, ItalyDepartment of Physics, University of Milan, 20122 Milan, ItalyC.S. Health Physics, ASST dei Sette Laghi, 21100 Varese, ItalyThis work aimed to investigate whether automated classifiers belonging to feature-based and deep learning may approach brain metastases segmentation successfully. Support Vector Machine and V-Net Convolutional Neural Network are selected as representatives of the two approaches. In the experiments, we consider several configurations of the two methods to segment brain metastases on contrast-enhanced T1-weighted magnetic resonance images. Performances were evaluated and compared under critical conditions imposed by the clinical radiotherapy domain, using in-house dataset and public dataset created for the Multimodal Brain Tumour Image Segmentation (BraTS) challenge. Our results showed that the feature-based and the deep network approaches are promising for the segmentation of Magnetic Resonance Imaging (MRI) brain metastases achieving both an acceptable level of performance. Experimental results also highlight different behaviour between the two methods. Support vector machine (SVM) improves performance with a smaller training set, but it is unable to manage a high level of heterogeneity in the data and requires post-processing refinement stages. The V-Net model shows good performances when trained on multiple heterogeneous cases but requires data augmentations and transfer learning procedures to optimise its behaviour. The paper illustrates a software package implementing an integrated set of procedures for active support in segmenting brain metastases within the radiotherapy workflow.https://www.mdpi.com/2076-3417/9/16/3335MRI brain segmentationbrain metastasesmachine learningfeatures extractionconvolutional neural networkmedical software |
| spellingShingle | Gloria Gonella Elisabetta Binaghi Paola Nocera Cinzia Mordacchini Investigating the Behaviour of Machine Learning Techniques to Segment Brain Metastases in Radiation Therapy Planning Applied Sciences MRI brain segmentation brain metastases machine learning features extraction convolutional neural network medical software |
| title | Investigating the Behaviour of Machine Learning Techniques to Segment Brain Metastases in Radiation Therapy Planning |
| title_full | Investigating the Behaviour of Machine Learning Techniques to Segment Brain Metastases in Radiation Therapy Planning |
| title_fullStr | Investigating the Behaviour of Machine Learning Techniques to Segment Brain Metastases in Radiation Therapy Planning |
| title_full_unstemmed | Investigating the Behaviour of Machine Learning Techniques to Segment Brain Metastases in Radiation Therapy Planning |
| title_short | Investigating the Behaviour of Machine Learning Techniques to Segment Brain Metastases in Radiation Therapy Planning |
| title_sort | investigating the behaviour of machine learning techniques to segment brain metastases in radiation therapy planning |
| topic | MRI brain segmentation brain metastases machine learning features extraction convolutional neural network medical software |
| url | https://www.mdpi.com/2076-3417/9/16/3335 |
| work_keys_str_mv | AT gloriagonella investigatingthebehaviourofmachinelearningtechniquestosegmentbrainmetastasesinradiationtherapyplanning AT elisabettabinaghi investigatingthebehaviourofmachinelearningtechniquestosegmentbrainmetastasesinradiationtherapyplanning AT paolanocera investigatingthebehaviourofmachinelearningtechniquestosegmentbrainmetastasesinradiationtherapyplanning AT cinziamordacchini investigatingthebehaviourofmachinelearningtechniquestosegmentbrainmetastasesinradiationtherapyplanning |