Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation
Background: Detection and segmentation of brain tumors using MR images are challenging and valuable tasks in the medical field. Early diagnosing and localizing of brain tumors can save lives and provide timely options for physicians to select efficient treatment plans. Deep learning approaches have...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Translational Engineering in Health and Medicine |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9779760/ |
| _version_ | 1811336437300199424 |
|---|---|
| author | Mohammad Ashraf Ottom Hanif Abdul Rahman Ivo D. Dinov |
| author_facet | Mohammad Ashraf Ottom Hanif Abdul Rahman Ivo D. Dinov |
| author_sort | Mohammad Ashraf Ottom |
| collection | DOAJ |
| description | Background: Detection and segmentation of brain tumors using MR images are challenging and valuable tasks in the medical field. Early diagnosing and localizing of brain tumors can save lives and provide timely options for physicians to select efficient treatment plans. Deep learning approaches have attracted researchers in medical imaging due to their capacity, performance, and potential to assist in accurate diagnosis, prognosis, and medical treatment technologies. Methods and procedures: This paper presents a novel framework for segmenting 2D brain tumors in MR images using deep neural networks (DNN) and utilizing data augmentation strategies. The proposed approach (Znet) is based on the idea of skip-connection, encoder-decoder architectures, and data amplification to propagate the intrinsic affinities of a relatively smaller number of expert delineated tumors, e.g., hundreds of patients of the low-grade glioma (LGG), to many thousands of synthetic cases. Results: Our experimental results showed high values of the mean dice similarity coefficient (dice = 0.96 during model training and dice = 0.92 for the independent testing dataset). Other evaluation measures were also relatively high, e.g., pixel accuracy = 0.996, F1 score = 0.81, and Matthews Correlation Coefficient, MCC = 0.81. The results and visualization of the DNN-derived tumor masks in the testing dataset showcase the ZNet model’s capability to localize and auto-segment brain tumors in MR images. This approach can further be generalized to 3D brain volumes, other pathologies, and a wide range of image modalities. Conclusion: We can confirm the ability of deep learning methods and the proposed Znet framework to detect and segment tumors in MR images. Furthermore, pixel accuracy evaluation may not be a suitable evaluation measure for semantic segmentation in case of class imbalance in MR images segmentation. This is because the dominant class in ground truth images is the background. Therefore, a high value of pixel accuracy can be misleading in some computer vision applications. On the other hand, alternative evaluation metrics, such as dice and IoU (Intersection over Union), are more factual for semantic segmentation. Clinical impact: Artificial intelligence (AI) applications in medicine are advancing swiftly, however, there is a lack of deployed techniques in clinical practice. This research demonstrates a practical example of AI applications in medical imaging, which can be deployed as a tool for auto-segmentation of tumors in MR images. |
| first_indexed | 2024-04-13T17:39:27Z |
| format | Article |
| id | doaj.art-2aafc19a836946a1bd8e892407bed835 |
| institution | Directory Open Access Journal |
| issn | 2168-2372 |
| language | English |
| last_indexed | 2024-04-13T17:39:27Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Translational Engineering in Health and Medicine |
| spelling | doaj.art-2aafc19a836946a1bd8e892407bed8352022-12-22T02:37:14ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722022-01-01101810.1109/JTEHM.2022.31767379779760Znet: Deep Learning Approach for 2D MRI Brain Tumor SegmentationMohammad Ashraf Ottom0https://orcid.org/0000-0002-6751-8811Hanif Abdul Rahman1https://orcid.org/0000-0003-3022-8690Ivo D. Dinov2https://orcid.org/0000-0003-3825-4375Department of Information Systems, Yarmouk University, Irbid, JordanDepartments of Health Behavior and Biological Sciences and Computational Medicine and Bioinformatics, Statistics Online Computational Resource, University of Michigan, Ann Arbor, MI, USADepartments of Health Behavior and Biological Sciences and Computational Medicine and Bioinformatics, Statistics Online Computational Resource, University of Michigan, Ann Arbor, MI, USABackground: Detection and segmentation of brain tumors using MR images are challenging and valuable tasks in the medical field. Early diagnosing and localizing of brain tumors can save lives and provide timely options for physicians to select efficient treatment plans. Deep learning approaches have attracted researchers in medical imaging due to their capacity, performance, and potential to assist in accurate diagnosis, prognosis, and medical treatment technologies. Methods and procedures: This paper presents a novel framework for segmenting 2D brain tumors in MR images using deep neural networks (DNN) and utilizing data augmentation strategies. The proposed approach (Znet) is based on the idea of skip-connection, encoder-decoder architectures, and data amplification to propagate the intrinsic affinities of a relatively smaller number of expert delineated tumors, e.g., hundreds of patients of the low-grade glioma (LGG), to many thousands of synthetic cases. Results: Our experimental results showed high values of the mean dice similarity coefficient (dice = 0.96 during model training and dice = 0.92 for the independent testing dataset). Other evaluation measures were also relatively high, e.g., pixel accuracy = 0.996, F1 score = 0.81, and Matthews Correlation Coefficient, MCC = 0.81. The results and visualization of the DNN-derived tumor masks in the testing dataset showcase the ZNet model’s capability to localize and auto-segment brain tumors in MR images. This approach can further be generalized to 3D brain volumes, other pathologies, and a wide range of image modalities. Conclusion: We can confirm the ability of deep learning methods and the proposed Znet framework to detect and segment tumors in MR images. Furthermore, pixel accuracy evaluation may not be a suitable evaluation measure for semantic segmentation in case of class imbalance in MR images segmentation. This is because the dominant class in ground truth images is the background. Therefore, a high value of pixel accuracy can be misleading in some computer vision applications. On the other hand, alternative evaluation metrics, such as dice and IoU (Intersection over Union), are more factual for semantic segmentation. Clinical impact: Artificial intelligence (AI) applications in medicine are advancing swiftly, however, there is a lack of deployed techniques in clinical practice. This research demonstrates a practical example of AI applications in medical imaging, which can be deployed as a tool for auto-segmentation of tumors in MR images.https://ieeexplore.ieee.org/document/9779760/Brain tumorregion segmentationdeep learningaugmentationneural networks |
| spellingShingle | Mohammad Ashraf Ottom Hanif Abdul Rahman Ivo D. Dinov Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation IEEE Journal of Translational Engineering in Health and Medicine Brain tumor region segmentation deep learning augmentation neural networks |
| title | Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation |
| title_full | Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation |
| title_fullStr | Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation |
| title_full_unstemmed | Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation |
| title_short | Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation |
| title_sort | znet deep learning approach for 2d mri brain tumor segmentation |
| topic | Brain tumor region segmentation deep learning augmentation neural networks |
| url | https://ieeexplore.ieee.org/document/9779760/ |
| work_keys_str_mv | AT mohammadashrafottom znetdeeplearningapproachfor2dmribraintumorsegmentation AT hanifabdulrahman znetdeeplearningapproachfor2dmribraintumorsegmentation AT ivoddinov znetdeeplearningapproachfor2dmribraintumorsegmentation |