A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classification
Glioma grading is critical in treatment planning and prognosis. This study aims to address this issue through MRI-based classification to develop an accurate model for glioma diagnosis. Here, we employed a deep learning pipeline with three essential steps: (1) MRI images were segmented using preproc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | IBRO Neuroscience Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667242122000884 |
| _version_ | 1811293309678649344 |
|---|---|
| author | Khiet Dang Toi Vo Lua Ngo Huong Ha |
| author_facet | Khiet Dang Toi Vo Lua Ngo Huong Ha |
| author_sort | Khiet Dang |
| collection | DOAJ |
| description | Glioma grading is critical in treatment planning and prognosis. This study aims to address this issue through MRI-based classification to develop an accurate model for glioma diagnosis. Here, we employed a deep learning pipeline with three essential steps: (1) MRI images were segmented using preprocessing approaches and UNet architecture, (2) brain tumor regions were extracted using segmentation, then (3) high-grade gliomas and low-grade gliomas were classified using the VGG and GoogleNet implementations. Among the additional preprocessing techniques used in conjunction with the segmentation task, the combination of data augmentation and Window Setting Optimization was found to be the most effective tool, resulting in the Dice coefficient of 0.82, 0.91, and 0.72 for enhancing tumor, whole tumor, and tumor core, respectively. While most of the proposed models achieve comparable accuracies of about 93 % on the testing dataset, the pipeline of VGG combined with UNet segmentation obtains the highest accuracy of 97.44 %. In conclusion, the presented architecture illustrates a realistic model for detecting gliomas; moreover, it emphasizes the significance of data augmentation and segmentation in improving model performance. |
| first_indexed | 2024-04-13T04:59:27Z |
| format | Article |
| id | doaj.art-047a29006964455c985e108bcdbd5838 |
| institution | Directory Open Access Journal |
| issn | 2667-2421 |
| language | English |
| last_indexed | 2024-04-13T04:59:27Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | IBRO Neuroscience Reports |
| spelling | doaj.art-047a29006964455c985e108bcdbd58382022-12-22T03:01:23ZengElsevierIBRO Neuroscience Reports2667-24212022-12-0113523532A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classificationKhiet Dang0Toi Vo1Lua Ngo2Huong Ha3School of Biomedical Engineering, International University, Vietnam National University – Ho Chi Minh City, Ho Chi Minh City, Viet Nam; Vietnam National University – Ho Chi Minh City, Ho Chi Minh City, Viet NamSchool of Biomedical Engineering, International University, Vietnam National University – Ho Chi Minh City, Ho Chi Minh City, Viet Nam; Vietnam National University – Ho Chi Minh City, Ho Chi Minh City, Viet NamSchool of Biomedical Engineering, International University, Vietnam National University – Ho Chi Minh City, Ho Chi Minh City, Viet Nam; Vietnam National University – Ho Chi Minh City, Ho Chi Minh City, Viet Nam; Corresponding authors at: School of Biomedical Engineering, International University, Vietnam National University – Ho Chi Minh City, Ho Chi Minh City, Viet Nam.School of Biomedical Engineering, International University, Vietnam National University – Ho Chi Minh City, Ho Chi Minh City, Viet Nam; Vietnam National University – Ho Chi Minh City, Ho Chi Minh City, Viet Nam; Corresponding authors at: School of Biomedical Engineering, International University, Vietnam National University – Ho Chi Minh City, Ho Chi Minh City, Viet Nam.Glioma grading is critical in treatment planning and prognosis. This study aims to address this issue through MRI-based classification to develop an accurate model for glioma diagnosis. Here, we employed a deep learning pipeline with three essential steps: (1) MRI images were segmented using preprocessing approaches and UNet architecture, (2) brain tumor regions were extracted using segmentation, then (3) high-grade gliomas and low-grade gliomas were classified using the VGG and GoogleNet implementations. Among the additional preprocessing techniques used in conjunction with the segmentation task, the combination of data augmentation and Window Setting Optimization was found to be the most effective tool, resulting in the Dice coefficient of 0.82, 0.91, and 0.72 for enhancing tumor, whole tumor, and tumor core, respectively. While most of the proposed models achieve comparable accuracies of about 93 % on the testing dataset, the pipeline of VGG combined with UNet segmentation obtains the highest accuracy of 97.44 %. In conclusion, the presented architecture illustrates a realistic model for detecting gliomas; moreover, it emphasizes the significance of data augmentation and segmentation in improving model performance.http://www.sciencedirect.com/science/article/pii/S2667242122000884Glioma gradingDeep learningThree-dimensionalData augmentationSegmentation |
| spellingShingle | Khiet Dang Toi Vo Lua Ngo Huong Ha A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classification IBRO Neuroscience Reports Glioma grading Deep learning Three-dimensional Data augmentation Segmentation |
| title | A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classification |
| title_full | A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classification |
| title_fullStr | A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classification |
| title_full_unstemmed | A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classification |
| title_short | A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classification |
| title_sort | deep learning framework integrating mri image preprocessing methods for brain tumor segmentation and classification |
| topic | Glioma grading Deep learning Three-dimensional Data augmentation Segmentation |
| url | http://www.sciencedirect.com/science/article/pii/S2667242122000884 |
| work_keys_str_mv | AT khietdang adeeplearningframeworkintegratingmriimagepreprocessingmethodsforbraintumorsegmentationandclassification AT toivo adeeplearningframeworkintegratingmriimagepreprocessingmethodsforbraintumorsegmentationandclassification AT luango adeeplearningframeworkintegratingmriimagepreprocessingmethodsforbraintumorsegmentationandclassification AT huongha adeeplearningframeworkintegratingmriimagepreprocessingmethodsforbraintumorsegmentationandclassification AT khietdang deeplearningframeworkintegratingmriimagepreprocessingmethodsforbraintumorsegmentationandclassification AT toivo deeplearningframeworkintegratingmriimagepreprocessingmethodsforbraintumorsegmentationandclassification AT luango deeplearningframeworkintegratingmriimagepreprocessingmethodsforbraintumorsegmentationandclassification AT huongha deeplearningframeworkintegratingmriimagepreprocessingmethodsforbraintumorsegmentationandclassification |