scholarly journals Improving Brain Tumor Segmentation with Data Augmentation Strategies

2021 ◽  
Author(s):  
Radhika Malhotra ◽  
Jasleen Saini ◽  
Barjinder Singh Saini ◽  
Savita Gupta
Keyword(s):  
Brain Tumor ◽  
Data Augmentation ◽  
Large Data ◽  
Training Data ◽  
Tumor Segmentation ◽  
Biomedical Image Processing ◽  
Brain Tumor Segmentation ◽  
Biomedical Image ◽  
Augmentation Strategies ◽  
Unseen Data

In the past decade, there has been a remarkable evolution of convolutional neural networks (CNN) for biomedical image processing. These improvements are inculcated in the basic deep learning-based models for computer-aided detection and prognosis of various ailments. But implementation of these CNN based networks is highly dependent on large data in case of supervised learning processes. This is needed to tackle overfitting issues which is a major concern in supervised techniques. Overfitting refers to the phenomenon when a network starts learning specific patterns of the input such that it fits well on the training data but leads to poor generalization abilities on unseen data. The accessibility of enormous quantity of data limits the field of medical domain research. This paper focuses on utility of data augmentation (DA) techniques, which is a well-recognized solution to the problem of limited data. The experiments were performed on the Brain Tumor Segmentation (BraTS) dataset which is available online. The results signify that different DA approaches have upgraded the accuracies for segmenting brain tumor boundaries using CNN based model.

Brain Tumour Texture Analysis-A Method

2021 ◽  
Vol 4 (4) ◽  
Author(s):  
Samir Kumar Bandyopadhyay
Keyword(s):  
Image Processing ◽  
Brain Tumor ◽  
Texture Analysis ◽  
Brain Tumour ◽  
Tumor Segmentation ◽  
Biomedical Image Processing ◽  
Biomedical Analysis ◽  
Brain Tumor Segmentation ◽  
Human Brain Tumor ◽  
Biomedical Image

Computer aided technology is used in biomedical image processing. In biomedical analysis features are extracted and then the proposed method will detect any abnormalities present or not in the system to be considered. In recent days the detection of brain tumour through image processing is made in medical diagnosis. The separation of tumor is made by the process of segmentation. Brain in human is the most complicated and delicate anatomical structure. There are various brain ailments in human but the indication of cancer in brain tumour may be fatal for the human. Brain tumor can be malignant or benign. The neurologist or neurosurgeon wants to know the exact location, size, shape and texture of tumor from Magnetic Resonance Imaging (MRI) of brain before going to the operation of the brain tumour or decided whether operation of removing brain tumour is at all necessary or not. The disease is analyzed since operation may cause death to the patient. Initially they took a chance by prescribing medicines to see whether there is any improvement of the condition of the patient. If the result is not satisfactory then there is no option other than operation of the tumor. Doctors also take an attempt to find the texture of the tumor since it may help them to know the progress of the tumour. In addition to Brain tumor segmentation, the detection of surface of the texture of brain tumor is required for proper treatment. The chapter proposed methods for detection of the progressive nature of the texture in the tumor presence in brain. For this process segmentation of tumor from other parts of brain is essential. In the chapter segmentation techniques are presented before the texture analysis process is given. Finally, comparisons of the proposed method with other methods are analyzed.

scholarly journals Data Augmentation for Brain-Tumor Segmentation: A Review

2019 ◽  
Vol 13 ◽  
Author(s):  
Jakub Nalepa ◽  
Michal Marcinkiewicz ◽  
Michal Kawulok
Keyword(s):  
Brain Tumor ◽  
Data Augmentation ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation

Brain tumor segmentation using K‐means clustering and deep learning with synthetic data augmentation for classification

2021 ◽  
Author(s):  
Amjad Rehman Khan ◽  
Siraj Khan ◽  
Majid Harouni ◽  
Rashid Abbasi ◽  
Sajid Iqbal ◽  
...  
Keyword(s):  
Deep Learning ◽  
Brain Tumor ◽  
Data Augmentation ◽  
Synthetic Data ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation

scholarly journals TumorGAN: A Multi-Modal Data Augmentation Framework for Brain Tumor Segmentation

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4203 ◽  
Author(s):  
Qingyun Li ◽  
Zhibin Yu ◽  
Yubo Wang ◽  
Haiyong Zheng
Keyword(s):  
Brain Tumor ◽  
Data Augmentation ◽  
Labor Demand ◽  
Synthetic Data ◽  
Generative Adversarial Networks ◽  
Tumor Segmentation ◽  
Imaging Data ◽  
Brain Tumor Segmentation ◽  
Data Set ◽  
Image Pairs

The high human labor demand involved in collecting paired medical imaging data severely impedes the application of deep learning methods to medical image processing tasks such as tumor segmentation. The situation is further worsened when collecting multi-modal image pairs. However, this issue can be resolved through the help of generative adversarial networks, which can be used to generate realistic images. In this work, we propose a novel framework, named TumorGAN, to generate image segmentation pairs based on unpaired adversarial training. To improve the quality of the generated images, we introduce a regional perceptual loss to enhance the performance of the discriminator. We also develop a regional L1 loss to constrain the color of the imaged brain tissue. Finally, we verify the performance of TumorGAN on a public brain tumor data set, BraTS 2017. The experimental results demonstrate that the synthetic data pairs generated by our proposed method can practically improve tumor segmentation performance when applied to segmentation network training.

Data Augmentation for Improved Brain Tumor Segmentation

2021 ◽  
pp. 1-11
Author(s):  
Ankur Biswas ◽  
Paritosh Bhattacharya ◽  
Santi P. Maity ◽  
Rita Banik
Keyword(s):  
Brain Tumor ◽  
Data Augmentation ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation

scholarly journals What is The Best Data Augmentation For 3D Brain Tumor Segmentation?

2021 ◽  
Author(s):  
Marco Domenico Cirillo ◽  
David Abramian ◽  
Anders Eklund
Keyword(s):  
Brain Tumor ◽  
Data Augmentation ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation

scholarly journals Brain Tumor Segmentation From Multi-Modal MR Images via Ensembling UNets

2021 ◽  
Vol 1 ◽  
Author(s):  
Yue Zhang ◽  
Pinyuan Zhong ◽  
Dabin Jie ◽  
Jiewei Wu ◽  
Shanmei Zeng ◽  
...  
Keyword(s):  
Brain Tumor ◽  
Network Architecture ◽  
Biological Properties ◽  
Training Data ◽  
Validation Dataset ◽  
Tumor Segmentation ◽  
Post Processing ◽  
Mr Images ◽  
Brain Tumor Segmentation ◽  
The Third

Glioma is a type of severe brain tumor, and its accurate segmentation is useful in surgery planning and progression evaluation. Based on different biological properties, the glioma can be divided into three partially-overlapping regions of interest, including whole tumor (WT), tumor core (TC), and enhancing tumor (ET). Recently, UNet has identified its effectiveness in automatically segmenting brain tumor from multi-modal magnetic resonance (MR) images. In this work, instead of network architecture, we focus on making use of prior knowledge (brain parcellation), training and testing strategy (joint 3D+2D), ensemble and post-processing to improve the brain tumor segmentation performance. We explore the accuracy of three UNets with different inputs, and then ensemble the corresponding three outputs, followed by post-processing to achieve the final segmentation. Similar to most existing works, the first UNet uses 3D patches of multi-modal MR images as the input. The second UNet uses brain parcellation as an additional input. And the third UNet is inputted by 2D slices of multi-modal MR images, brain parcellation, and probability maps of WT, TC, and ET obtained from the second UNet. Then, we sequentially unify the WT segmentation from the third UNet and the fused TC and ET segmentation from the first and the second UNets as the complete tumor segmentation. Finally, we adopt a post-processing strategy by labeling small ET as non-enhancing tumor to correct some false-positive ET segmentation. On one publicly-available challenge validation dataset (BraTS2018), the proposed segmentation pipeline yielded average Dice scores of 91.03/86.44/80.58% and average 95% Hausdorff distances of 3.76/6.73/2.51 mm for WT/TC/ET, exhibiting superior segmentation performance over other state-of-the-art methods. We then evaluated the proposed method on the BraTS2020 training data through five-fold cross validation, with similar performance having also been observed. The proposed method was finally evaluated on 10 in-house data, the effectiveness of which has been established qualitatively by professional radiologists.

scholarly journals Divide and Conquer: Stratifying Training Data by Tumor Grade Improves Deep Learning-Based Brain Tumor Segmentation

2019 ◽  
Vol 13 ◽  
Author(s):  
Michael Rebsamen ◽  
Urspeter Knecht ◽  
Mauricio Reyes ◽  
Roland Wiest ◽  
Raphael Meier ◽  
...  
Keyword(s):  
Deep Learning ◽  
Brain Tumor ◽  
Tumor Grade ◽  
Training Data ◽  
Divide And Conquer ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation

scholarly journals A Fully Automatic Procedure for Brain Tumor Segmentation from Multi-Spectral MRI Records Using Ensemble Learning and Atlas-Based Data Enhancement

2021 ◽  
Vol 11 (2) ◽  
pp. 564
Author(s):  
Ágnes Győrfi ◽  
László Szilágyi ◽  
Levente Kovács
Keyword(s):  
Brain Tumor ◽  
Region Growing ◽  
Training Data ◽  
Gabor Wavelet ◽  
Intensity Inhomogeneity ◽  
Tumor Segmentation ◽  
Second Phase ◽  
High Quality ◽  
Brain Tumor Segmentation ◽  
Fully Automatic

The accurate and reliable segmentation of gliomas from magnetic resonance image (MRI) data has an important role in diagnosis, intervention planning, and monitoring the tumor’s evolution during and after therapy. Segmentation has serious anatomical obstacles like the great variety of the tumor’s location, size, shape, and appearance and the modified position of normal tissues. Other phenomena like intensity inhomogeneity and the lack of standard intensity scale in MRI data represent further difficulties. This paper proposes a fully automatic brain tumor segmentation procedure that attempts to handle all the above problems. Having its foundations on the MRI data provided by the MICCAI Brain Tumor Segmentation (BraTS) Challenges, the procedure consists of three main phases. The first pre-processing phase prepares the MRI data to be suitable for supervised classification, by attempting to fix missing data, suppressing the intensity inhomogeneity, normalizing the histogram of observed data channels, generating additional morphological, gradient-based, and Gabor-wavelet features, and optionally applying atlas-based data enhancement. The second phase accomplishes the main classification process using ensembles of binary decision trees and provides an initial, intermediary labeling for each pixel of test records. The last phase reevaluates these intermediary labels using a random forest classifier, then deploys a spatial region growing-based structural validation of suspected tumors, thus achieving a high-quality final segmentation result. The accuracy of the procedure is evaluated using the multi-spectral MRI records of the BraTS 2015 and BraTS 2019 training data sets. The procedure achieves high-quality segmentation results, characterized by average Dice similarity scores of up to 86%.

Sign in / Sign up

Export Citation Format

Share Document