Multimodal Segmentation of Brain Tumours in Volumetric MRI Scans of the Brain Using Time-Distributed U-Net

Dutta, Jeet; Chakraborty, Debajyoti; Mondal, Debanjan

doi:10.1007/978-981-13-9042-5_62

Cited by 6 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As briefly introduced in Section 2.2, one of the most recent and promising approaches developed in the computer vision field is U-Net [43]. The model, inspired from a Convolutional Neural Network presented to the Computer Vision for Pattern Recognition conference [44], was originally employed in the medical field for the segmentation of biological cells and for the analysis of MRI scans for the detection of a number of pathologies [45][46][47].…”

Section: Methodsmentioning

confidence: 99%

Double-Step U-Net: A Deep Learning-Based Approach for the Estimation of Wildfire Damage Severity through Sentinel-2 Satellite Data

2020

View full text Add to dashboard Cite

Wildfire damage severity census is a crucial activity for estimating monetary losses and for planning a prompt restoration of the affected areas. It consists in assigning, after a wildfire, a numerical damage/severity level, between 0 and 4, to each sub-area of the hit area. While burned area identification has been automatized by means of machine learning algorithms, the wildfire damage severity census operation is usually still performed manually and requires a significant effort of domain experts through the analysis of imagery and, sometimes, on-site missions. In this paper, we propose a novel supervised learning approach for the automatic estimation of the damage/severity level of the hit areas after the wildfire extinction. Specifically, the proposed approach, leveraging on the combination of a classification algorithm and a regression one, predicts the damage/severity level of the sub-areas of the area under analysis by processing a single post-fire satellite acquisition. Our approach has been validated in five different European countries and on 21 wildfires. It has proved to be robust for the application in several geographical contexts presenting similar geological aspects.

show abstract

Section: Methodsmentioning

confidence: 99%

Double-Step U-Net: A Deep Learning-Based Approach for the Estimation of Wildfire Damage Severity through Sentinel-2 Satellite Data

2020

View full text Add to dashboard Cite

show abstract

“…Intensive review has suggested that the most common architectures include U-Net [7,12,14,21,22,23,30,36,37,55]. U-Net architectures of both 2D and 3D types have successfully produced significant results for different performance measures of PAEE in different research studies.…”

Section: Recently Developed Dlnn Methodsmentioning

confidence: 99%

“…Different hyperparameters have been used for the experiment including Learning Rate = 0.001, Exponential Decay = 0.995 after each epoch, and Fixed Kernel Size = 3×3 [37]. Time Distributed U-Net based CNN method has been tested with Model Accuracy = 0.583 in intra-method comparison with T1 weighted images taken from the database of MICCAI Brain Tumor Segmentation (BraTS) [12]. Researchers experimented with the method of Cascade 3D U-Net based CNN while using hyperparameters of Learning Rate = 10 -5, Weight Decay = 0.0005, Momentum = 0.9 (in Adam optimizer), and Epochs = 300 [23].…”

Section: Recently Developed Dlnn Methodsmentioning

confidence: 99%

“…Leading databases provided different types of brain MR images like T1 weighted, T2 weighted, FLAIR etc. and such databases include OASIS [10,13,24,36,37,38,52], IBSR [24,57], LPBA [13,22,24], MALC [7,30], ADNI [30], PASCAL [19,32], COCO [18,19,31,32], Hammers [7], NAMIC [49], MPRAGE [49], UKBB [7], BraTS [12,14], Visual Genome [19], NFBS [21,22,55], and Calgary-Campinas, [22,36].…”

Section: Data and Systems Used For Dlnn Methodsmentioning

confidence: 99%

“…In addition to databases, different GPU based computer systems have been utilized by researchers for image processing; out of which, NVIDIA Tesla M40 [18,19], NVIDIA GTX 1050 TI [12,23] NVIDIA GTX 970 [55], and NVIDIA GTX Titan [13,22,30,37,38,47] are common.…”

Section: Data and Systems Used For Dlnn Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Skull stripping using traditional and soft-computing approaches for magnetic resonance images: a semi-systematic meta-analysis

Azam

Tariq

2020

MG&V

View full text Add to dashboard Cite

MRI scanner captures the skull along with the brain and the skull needs to be removed for enhanced reliability and validity of medical diagnostic practices. Skull Stripping from Brain MR Images is significantly a core area in medical applications. It is a complicated task to segment an image for skull stripping manually. It is not only time consuming but expensive as well. An automated skull stripping method with good efficiency and effectiveness is required. Currently, a number of skull stripping methods are used in practice. In this review paper, many soft-computing segmentation techniques have been discussed. The purpose of this research study is to review the existing literature to compare the existing traditional and modern methods used for skull stripping from Brain MR images along with their merits and demerits. The semi-systematic review of existing literature has been carried out using the meta-synthesis approach. Broadly, analyses are bifurcated into traditional and modern, i.e. soft-computing methods proposed, experimented with, or applied in practice for effective skull stripping. Popular databases with desired data of Brain MR Images have also been identified, categorized and discussed. Moreover, CPU and GPU based computer systems and their specifications used by different researchers for skull stripping have also been discussed. In the end, the research gap has been identified along with the proposed lead for future research work.

show abstract

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

et al. 2021

View full text Add to dashboard Cite

U-net is an image segmentation technique developed primarily for image segmentation tasks. These traits provide U-net with a high utility within the medical imaging community and have resulted in extensive adoption of U-net as the primary tool for segmentation tasks in medical imaging. The success of U-net is evident in its widespread use in nearly all major image modalities, from CT scans and MRI to Xrays and microscopy. Furthermore, while U-net is largely a segmentation tool, there have been instances of the use of U-net in other applications. Given that U-net's potential is still increasing, this narrative literature review examines the numerous developments and breakthroughs in the U-net architecture and provides observations on recent trends. We also discuss the many innovations that have advanced in deep learning and discuss how these tools facilitate U-net. In addition, we review the different image modalities and application areas that have been enhanced by U-net.

show abstract

Multimodal Segmentation of Brain Tumours in Volumetric MRI Scans of the Brain Using Time-Distributed U-Net

Cited by 6 publications

References 14 publications

Double-Step U-Net: A Deep Learning-Based Approach for the Estimation of Wildfire Damage Severity through Sentinel-2 Satellite Data

Double-Step U-Net: A Deep Learning-Based Approach for the Estimation of Wildfire Damage Severity through Sentinel-2 Satellite Data

Skull stripping using traditional and soft-computing approaches for magnetic resonance images: a semi-systematic meta-analysis

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

Contact Info

Product

Resources

About