Bounding box based automatic segmentation of brain tumors using random walker and active contours from brain MRI

Abstract The tumor detection is major challenging task in brain tumor quantitative evaluation. In recent years, owing to non-invasive and strong soft tissue comparison, Magnetic Resonance Imaging (MRI) has gained great interest. MRI is a commonly used image modality technique to locate brain tumors. An immense amount of data is produced by the MRI. Heterogeneity, isointense and hypointense tumor properties restrict manual segmentation in a fair period of time, thus restricting the use of reliable quantitative measures in clinical practice. In the clinical practice manual segmentation task is quite time consuming and their performance is highly depended on the operator’s experience. Accurate and automated tumor segmentation techniques are also needed; however, the severe spatial and structural heterogeneity of brain tumors makes automatic segmentation a difficult job. This paper proposes fully automatic segmentation of brain tumors using encoder-decoder based convolutional neural networks. The paper focuses on well-known semantic segmentation deep neural networks i.e., UNET and SEGNET for segmenting tumors from Brain MRI images. The networks are trained and tested using freely accessible standard dataset, with Dice Similarity Coefficient (DSC) as metric for whole predicted image i.e., including tumor and background. UNET’s average DSC on test dataset is 0.76 whereas for SEGNET we got average DSC 0.67. The evaluation of results proves that UNET is having better performance than SEGNET.

Download Full-text

Multiphase Region-based Active Contours for Semi-automatic Segmentation of Brain MRI Images

Proceedings of the 10th International Conference on Computer Vision Theory and Applications ◽

10.5220/0005294804470454 ◽

2015 ◽

Cited By ~ 1

Author(s):

Farhan Akram ◽

Domenec Puig ◽

Miguel Angel Garcia ◽

Adel Saleh

Keyword(s):

Active Contours ◽

Automatic Segmentation ◽

Brain Mri

Download Full-text

Recent advancements in Fuzzy C-means based techniques for brain MRI Segmentation

Current Medical Imaging Formerly Current Medical Imaging Reviews ◽

10.2174/1573405616666210104111218 ◽

2021 ◽

Vol 16 ◽

Author(s):

Ghazanfar Latif ◽

Jaafar Alghazo ◽

Fadi N. Sibai ◽

D.N.F. Awang Iskandar ◽

Adil H. Khan

Keyword(s):

Brain Tumor ◽

Brain Tumors ◽

Brain Mri ◽

Tumor Segmentation ◽

Brain Anatomy ◽

Mri Segmentation ◽

Brain Tumor Segmentation ◽

Brain Images ◽

Low Contrast ◽

Fuzzy C Means

Background: Variations of image segmentation techniques, particularly those used for Brain MRI segmentation, vary in complexity from basic standard Fuzzy C-means (FCM) to more complex and enhanced FCM techniques. Objective: In this paper, a comprehensive review is presented on all thirteen variations of FCM segmentation techniques. In the review process, the concentration is on the use of FCM segmentation techniques for brain tumors. Brain tumor segmentation is a vital step in the process of automatically diagnosing brain tumors. Unlike segmentation of other types of images, brain tumor segmentation is a very challenging task due to the variations in brain anatomy. The low contrast of brain images further complicates this process. Early diagnosis of brain tumors is indeed beneficial to patients, doctors, and medical providers. Results: FCM segmentation works on images obtained from magnetic resonance imaging (MRI) scanners, requiring minor modifications to hospital operations to early diagnose tumors as most, if not all, hospitals rely on MRI machines for brain imaging. In this paper, we critically review and summarize FCM based techniques for brain MRI segmentation.

Download Full-text