Pre-trained deep learning models for brain MRI image classification
Brain tumors are serious conditions caused by uncontrolled and abnormal cell division. Tumors can have devastating implications if not accurately and promptly detected. Magnetic resonance imaging (MRI) is one of the methods frequently used to detect brain tumors owing to its excellent resolution. In...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Human Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2023.1150120/full |
| _version_ | 1797843639777361920 |
|---|---|
| author | Srigiri Krishnapriya Yepuganti Karuna |
| author_facet | Srigiri Krishnapriya Yepuganti Karuna |
| author_sort | Srigiri Krishnapriya |
| collection | DOAJ |
| description | Brain tumors are serious conditions caused by uncontrolled and abnormal cell division. Tumors can have devastating implications if not accurately and promptly detected. Magnetic resonance imaging (MRI) is one of the methods frequently used to detect brain tumors owing to its excellent resolution. In the past few decades, substantial research has been conducted in the field of classifying brain images, ranging from traditional methods to deep-learning techniques such as convolutional neural networks (CNN). To accomplish classification, machine-learning methods require manually created features. In contrast, CNN achieves classification by extracting visual features from unprocessed images. The size of the training dataset had a significant impact on the features that CNN extracts. The CNN tends to overfit when its size is small. Deep CNNs (DCNN) with transfer learning have therefore been developed. The aim of this work was to investigate the brain MR image categorization potential of pre-trained DCNN VGG-19, VGG-16, ResNet50, and Inception V3 models using data augmentation and transfer learning techniques. Validation of the test set utilizing accuracy, recall, Precision, and F1 score showed that the pre-trained VGG-19 model with transfer learning exhibited the best performance. In addition, these methods offer an end-to-end classification of raw images without the need for manual attribute extraction. |
| first_indexed | 2024-04-09T17:08:34Z |
| format | Article |
| id | doaj.art-5e0a544d14ef4780a5df1552ca21001b |
| institution | Directory Open Access Journal |
| issn | 1662-5161 |
| language | English |
| last_indexed | 2024-04-09T17:08:34Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Human Neuroscience |
| spelling | doaj.art-5e0a544d14ef4780a5df1552ca21001b2023-04-20T08:45:18ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612023-04-011710.3389/fnhum.2023.11501201150120Pre-trained deep learning models for brain MRI image classificationSrigiri KrishnapriyaYepuganti KarunaBrain tumors are serious conditions caused by uncontrolled and abnormal cell division. Tumors can have devastating implications if not accurately and promptly detected. Magnetic resonance imaging (MRI) is one of the methods frequently used to detect brain tumors owing to its excellent resolution. In the past few decades, substantial research has been conducted in the field of classifying brain images, ranging from traditional methods to deep-learning techniques such as convolutional neural networks (CNN). To accomplish classification, machine-learning methods require manually created features. In contrast, CNN achieves classification by extracting visual features from unprocessed images. The size of the training dataset had a significant impact on the features that CNN extracts. The CNN tends to overfit when its size is small. Deep CNNs (DCNN) with transfer learning have therefore been developed. The aim of this work was to investigate the brain MR image categorization potential of pre-trained DCNN VGG-19, VGG-16, ResNet50, and Inception V3 models using data augmentation and transfer learning techniques. Validation of the test set utilizing accuracy, recall, Precision, and F1 score showed that the pre-trained VGG-19 model with transfer learning exhibited the best performance. In addition, these methods offer an end-to-end classification of raw images without the need for manual attribute extraction.https://www.frontiersin.org/articles/10.3389/fnhum.2023.1150120/fullconvolutional neural networkstransfer learningVGG-19VGG-16inception V3ResNet50 |
| spellingShingle | Srigiri Krishnapriya Yepuganti Karuna Pre-trained deep learning models for brain MRI image classification Frontiers in Human Neuroscience convolutional neural networks transfer learning VGG-19 VGG-16 inception V3 ResNet50 |
| title | Pre-trained deep learning models for brain MRI image classification |
| title_full | Pre-trained deep learning models for brain MRI image classification |
| title_fullStr | Pre-trained deep learning models for brain MRI image classification |
| title_full_unstemmed | Pre-trained deep learning models for brain MRI image classification |
| title_short | Pre-trained deep learning models for brain MRI image classification |
| title_sort | pre trained deep learning models for brain mri image classification |
| topic | convolutional neural networks transfer learning VGG-19 VGG-16 inception V3 ResNet50 |
| url | https://www.frontiersin.org/articles/10.3389/fnhum.2023.1150120/full |
| work_keys_str_mv | AT srigirikrishnapriya pretraineddeeplearningmodelsforbrainmriimageclassification AT yepugantikaruna pretraineddeeplearningmodelsforbrainmriimageclassification |