scholarly journals Multi-decoder Networks with Multi-denoising Inputs for Tumor Segmentation

2021 ◽  
pp. 412-423
Author(s):  
Minh H. Vu ◽  
Tufve Nyholm ◽  
Tommy Löfstedt
Keyword(s):  
Tumor Segmentation

Integrating Improved U-Net and Continuous Maximum Flow Algorithm for 3D Brain Tumor Image Segmentation

2020 ◽  
Vol 64 (4) ◽  
pp. 40412-1-40412-11
Author(s):  
Kexin Bai ◽  
Qiang Li ◽  
Ching-Hsin Wang
Keyword(s):  
Brain Tumor ◽  
Data Augmentation ◽  
A Priori ◽  
Class Imbalance ◽  
Maximum Flow ◽  
Magnetic Resonance Images ◽  
Tumor Segmentation ◽  
Similarity Coefficients ◽  
Segmentation Algorithms ◽  
Flow Algorithm

Abstract To address the issues of the relatively small size of brain tumor image datasets, severe class imbalance, and low precision in existing segmentation algorithms for brain tumor images, this study proposes a two-stage segmentation algorithm integrating convolutional neural networks (CNNs) and conventional methods. Four modalities of the original magnetic resonance images were first preprocessed separately. Next, preliminary segmentation was performed using an improved U-Net CNN containing deep monitoring, residual structures, dense connection structures, and dense skip connections. The authors adopted a multiclass Dice loss function to deal with class imbalance and successfully prevented overfitting using data augmentation. The preliminary segmentation results subsequently served as the a priori knowledge for a continuous maximum flow algorithm for fine segmentation of target edges. Experiments revealed that the mean Dice similarity coefficients of the proposed algorithm in whole tumor, tumor core, and enhancing tumor segmentation were 0.9072, 0.8578, and 0.7837, respectively. The proposed algorithm presents higher accuracy and better stability in comparison with some of the more advanced segmentation algorithms for brain tumor images.

2019 Kidney Tumor Segmentation Challenge Method Manuscript

2019 ◽  
Author(s):  
MengLei Jiao ◽  
Hong Liu
Keyword(s):  
Tumor Segmentation ◽  
Kidney Tumor

Submission to the Kidney Tumor Segmentation Challenge 2019

2019 ◽  
Author(s):  
Pengxin Yu ◽  
Xing Cui ◽  
Xi Tian ◽  
Jiechao Ma ◽  
Rongguo Zhang
Keyword(s):  
Tumor Segmentation ◽  
Kidney Tumor

Multi-stage Threshold Method for Liver Tumor Segmentation in CT Scan Images and Its Implementation for FPGA

2020 ◽  
Author(s):  
Y. Rakesh Kumar ◽  
Dr. Chandra Sekhar V ◽  
Sravanthi A ◽  
B. Sreekanth Reddy
Keyword(s):  
Ct Scan ◽  
Liver Tumor ◽  
Tumor Segmentation ◽  
Threshold Method ◽  
Multi Stage ◽  
Liver Tumor Segmentation

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

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.

Brain Tumor Segmentation Using Deep Belief Networks and Pathological Knowledge

2017 ◽  
Vol 16 (2) ◽  
pp. 129-136 ◽  
Author(s):  
Tianming Zhan ◽  
Yi Chen ◽  
Xunning Hong ◽  
Zhenyu Lu ◽  
Yunjie Chen
Keyword(s):  
Brain Tumor ◽  
Tumor Segmentation ◽  
Belief Networks ◽  
Deep Belief Networks ◽  
Brain Tumor Segmentation

scholarly journals Domain Mapping and Deep Learning from Multiple MRI Clinical Datasets for Prediction of Molecular Subtypes in Low Grade Gliomas

2020 ◽  
Vol 10 (7) ◽  
pp. 463 ◽  
Author(s):  
Muhaddisa Barat Ali ◽  
Irene Yu-Hua Gu ◽  
Mitchel S. Berger ◽  
Johan Pallud ◽  
Derek Southwell ◽  
...  
Keyword(s):  
Molecular Subtypes ◽  
Negative Impact ◽  
Molecular Classification ◽  
Tumor Segmentation ◽  
Test Accuracy ◽  
Low Grade ◽  
Idh Mutation ◽  
Molecular Type ◽  
Low Grade Gliomas ◽  
Domain Mapping

Brain tumors, such as low grade gliomas (LGG), are molecularly classified which require the surgical collection of tissue samples. The pre-surgical or non-operative identification of LGG molecular type could improve patient counseling and treatment decisions. However, radiographic approaches to LGG molecular classification are currently lacking, as clinicians are unable to reliably predict LGG molecular type using magnetic resonance imaging (MRI) studies. Machine learning approaches may improve the prediction of LGG molecular classification through MRI, however, the development of these techniques requires large annotated data sets. Merging clinical data from different hospitals to increase case numbers is needed, but the use of different scanners and settings can affect the results and simply combining them into a large dataset often have a significant negative impact on performance. This calls for efficient domain adaption methods. Despite some previous studies on domain adaptations, mapping MR images from different datasets to a common domain without affecting subtitle molecular-biomarker information has not been reported yet. In this paper, we propose an effective domain adaptation method based on Cycle Generative Adversarial Network (CycleGAN). The dataset is further enlarged by augmenting more MRIs using another GAN approach. Further, to tackle the issue of brain tumor segmentation that requires time and anatomical expertise to put exact boundary around the tumor, we have used a tight bounding box as a strategy. Finally, an efficient deep feature learning method, multi-stream convolutional autoencoder (CAE) and feature fusion, is proposed for the prediction of molecular subtypes (1p/19q-codeletion and IDH mutation). The experiments were conducted on a total of 161 patients consisting of FLAIR and T1 weighted with contrast enhanced (T1ce) MRIs from two different institutions in the USA and France. The proposed scheme is shown to achieve the test accuracy of 74 . 81 % on 1p/19q codeletion and 81 . 19 % on IDH mutation, with marked improvement over the results obtained without domain mapping. This approach is also shown to have comparable performance to several state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document