scholarly journals The Impact of Resampling and Denoising Deep Learning Algorithms on Radiomics in Brain Metastases MRI

Cancers ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 36
Author(s):  
Ilyass Moummad ◽  
Cyril Jaudet ◽  
Alexis Lechervy ◽  
Samuel Valable ◽  
Charlotte Raboutet ◽  
...  
Keyword(s):  
Deep Learning ◽  
Brain Metastases ◽  
Pearson Correlation ◽  
Texture Features ◽  
Acquisition Time ◽  
Brain Images ◽  
Fast Mri ◽  
Long Time ◽  
Magnetic Resonance Imaging Mri ◽  
The Impact

Background: Magnetic resonance imaging (MRI) is predominant in the therapeutic management of cancer patients, unfortunately, patients have to wait a long time to get an appointment for examination. Therefore, new MRI devices include deep-learning (DL) solutions to save acquisition time. However, the impact of these algorithms on intensity and texture parameters has been poorly studied. The aim of this study was to evaluate the impact of resampling and denoising DL models on radiomics. Methods: Resampling and denoising DL model was developed on 14,243 T1 brain images from 1.5T-MRI. Radiomics were extracted from 40 brain metastases from 11 patients (2049 images). A total of 104 texture features of DL images were compared to original images with paired t-test, Pearson correlation and concordance-correlation-coefficient (CCC). Results: When two times shorter image acquisition shows strong disparities with the originals concerning the radiomics, with significant differences and loss of correlation of 79.81% and 48.08%, respectively. Interestingly, DL models restore textures with 46.15% of unstable parameters and 25.96% of low CCC and without difference for the first-order intensity parameters. Conclusions: Resampling and denoising DL models reconstruct low resolution and noised MRI images acquired quickly into high quality images. While fast MRI acquisition loses most of the radiomic features, DL models restore these parameters.

scholarly journals Spatial evaluation of volcanic ash forecasts using satellite observations

2015 ◽  
Vol 15 (17) ◽  
pp. 24727-24749 ◽  
Author(s):  
N. J. Harvey ◽  
H. F. Dacre
Keyword(s):  
Volcanic Ash ◽  
Pearson Correlation ◽  
Skill Score ◽  
Near Miss ◽  
Model Parameters ◽  
Time Period ◽  
Long Time ◽  
The Impact ◽  
Success Index ◽  
Ash Transport

Abstract. The decision to close airspace in the event of a volcanic eruption is based on hazard maps of predicted ash extent. These are produced using output from volcanic ash transport and dispersion (VATD) models. In this paper an objective metric to evaluate the spatial accuracy of VATD simulations relative to satellite retrievals of volcanic ash is presented. The metric is based on the fractions skill score (FSS). This measure of skill provides more information than traditional point-by-point metrics, such as success index and Pearson correlation coefficient, as it takes into the account spatial scale over which skill is being assessed. The FSS determines the scale over which a simulation has skill and can differentiate between a "near miss" and a forecast that is badly misplaced. The idealised scenarios presented show that even simulations with considerable displacement errors have useful skill when evaluated over neighbourhood scales of 200–700 km2. This method could be used to compare forecasts produced by different VATDs or using different model parameters, assess the impact of assimilating satellite retrieved ash data and evaluate VATD forecasts over a long time period.

scholarly journals Development of brain tumor segmentation of magnetic resonance imaging (MRI) using U-Net deep learning

2021 ◽  
Vol 4 (9(112)) ◽  
pp. 23-31
Author(s):  
Wasan M. Jwaid ◽  
Zainab Shaker Matar Al-Husseini ◽  
Ahmad H. Sabry
Keyword(s):  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Brain Tumor ◽  
Magnetic Resonance ◽  
Tumor Segmentation ◽  
Resonance Imaging ◽  
Brain Tumor Segmentation ◽  
Brain Images ◽  
Magnetic Resonance Imaging Mri ◽  
The Brain

Brain tumors are the growth of abnormal cells or a mass in a brain. Numerous kinds of brain tumors were discovered, which need accurate and early detection techniques. Currently, most diagnosis and detection methods rely on the decision of neuro-specialists and radiologists to evaluate brain images, which may be time-consuming and cause human errors. This paper proposes a robust U-Net deep learning Convolutional Neural Network (CNN) model that can classify if the subject has a tumor or not based on Brain Magnetic resonance imaging (MRI) with acceptable accuracy for medical-grade application. The study built and trained the 3D U-Net CNN including encoding/decoding relationship architecture to perform the brain tumor segmentation because it requires fewer training images and provides more precise segmentation. The algorithm consists of three parts; the first part, the downsampling part, the bottleneck part, and the optimum part. The resultant semantic maps are inserted into the decoder fraction to obtain the full-resolution probability maps. The developed U-Net architecture has been applied on the MRI scan brain tumor segmentation dataset in MICCAI BraTS 2017. The results using Matlab-based toolbox indicate that the proposed architecture has been successfully evaluated and experienced for MRI datasets of brain tumor segmentation including 336 images as training data and 125 images for validation. This work demonstrated comparative performance and successful feasibility of implementing U-Net CNN architecture in an automated framework of brain tumor segmentations in Fluid-attenuated inversion recovery (FLAIR) MR Slices. The developed U-Net CNN model succeeded in performing the brain tumor segmentation task to classify the input brain images into a tumor or not based on the MRI dataset.

scholarly journals Deep Learning Applications in Magnetic Resonance Imaging: Has the Future Become Present?

Diagnostics ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 2181
Author(s):  
Sebastian Gassenmaier ◽  
Thomas Küstner ◽  
Dominik Nickel ◽  
Judith Herrmann ◽  
Rüdiger Hoffmann ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Clinical Practice ◽  
Magnetic Resonance ◽  
Image Reconstruction ◽  
Learning Technologies ◽  
Acquisition Time ◽  
Resonance Imaging ◽  
Major Player ◽  
The Impact

Deep learning technologies and applications demonstrate one of the most important upcoming developments in radiology. The impact and influence of these technologies on image acquisition and reporting might change daily clinical practice. The aim of this review was to present current deep learning technologies, with a focus on magnetic resonance image reconstruction. The first part of this manuscript concentrates on the basic technical principles that are necessary for deep learning image reconstruction. The second part highlights the translation of these techniques into clinical practice. The third part outlines the different aspects of image reconstruction techniques, and presents a review of the current literature regarding image reconstruction and image post-processing in MRI. The promising results of the most recent studies indicate that deep learning will be a major player in radiology in the upcoming years. Apart from decision and diagnosis support, the major advantages of deep learning magnetic resonance imaging reconstruction techniques are related to acquisition time reduction and the improvement of image quality. The implementation of these techniques may be the solution for the alleviation of limited scanner availability via workflow acceleration. It can be assumed that this disruptive technology will change daily routines and workflows permanently.

scholarly journals Deep Learning For Denoising Hi-C Chromosomal Contact Data

2019 ◽  
Author(s):  
Max Highsmith ◽  
Oluwatosin Oluwadare ◽  
Jianlin Cheng
Keyword(s):  
Deep Learning ◽  
Signal To Noise Ratio ◽  
Pearson Correlation ◽  
3D Structure ◽  
Three Dimensional ◽  
Yeast Genome ◽  
Chromosome Conformation ◽  
Contact Matrix ◽  
The Impact

AbstractMotivationThe three-dimensional (3D) organization of an organism’s genome and chromosomes plays a significant role in many biological processes. Currently, methods exist for modeling chromosomal 3D structure using contact matrices generated via chromosome conformation capture (3C) techniques such as Hi-C. However, the effectiveness of these methods is inherently bottlenecked by the quality of the Hi-C data, which may be corrupted by experimental noise. Consequently, it is valuable to develop methods for eliminating the impact of noise on the quality of reconstructed structures.ResultsWe develop unsupervised and semi-supervised deep learning algorithms (i.e. deep convolutional autoencoders) to denoise Hi-C contact matrix data and improve the quality of chromosome structure predictions. When applied to noisy synthetic contact matrices of the yeast genome, our network demonstrates consistent improvement across metrics for contact matrix similarity including: Pearson Correlation, Spearman Correlation and Signal-to-Noise Ratio. Positive improvement across these metrics is seen consistently across a wide space of parameters to both gaussian and poisson noise [email protected] and [email protected]

scholarly journals Chaotic Compressed Sensing and Its Application to Magnetic Resonance Imaging

2014 ◽  
Vol 3 (3-4) ◽  
Author(s):  
Nguyen Linh-Trung ◽  
Truong Minh-Chinh ◽  
Tan Tran-Duc ◽  
Ha Vu Le ◽  
Minh Ngoc Do
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Compressed Sensing ◽  
Acquisition Time ◽  
Parallel Mri ◽  
Resonance Imaging ◽  
Measurement Matrix ◽  
Fast Mri ◽  
Mri Scans ◽  
Magnetic Resonance Imaging Mri

Fast image acquisition in magnetic resonance imaging (MRI) is important, due to the need to find ways that help relieve patient’s stress during MRI scans. Methods for fast MRI have been proposed, most notably among them are pMRI (parallel MRI), SWIFT (SWeep Imaging with Fourier Transformation), and compressed sensing (CS) based MRI. Although it promises to significantly reduce acquisition time, applying CS to MRI leads to difficulties with hardware design because of the randomness nature of the measurement matrix used by the conventional CS methods. In this paper, we propose a novel method that combines the above-mentioned three approaches for fast MRI by designing a compound measurement matrix from a series of single measurement matrices corresponding to pMRI, SWIFT, and CS. In our method, the CS measurement matrix is designed to be deterministic via chaotic systems. This chaotic compressed sensing (CCS) measurement matrix, while retaining most features of the random CS matrix, is simpler to realize in hardware. Several compound measurement matrices have been constructed and examined in this work, including CCS-MRI, CCS-pMRI, CCS-SWIFT, and CCS-pSWIFT. Simulation results showed that the proposed method allows an increase in the speed of the MRI acquisition process while not compromising the quality of the acquired MR images.

The Impact of Patient’s Body Habitus on PET Image Quality in Digital and Analogic PET/CT

2020 ◽  
Author(s):  
Kathleen Weyts ◽  
Elske Quak ◽  
Idlir Licaj ◽  
Charline Lasnon ◽  
Renaud Ciappuccini ◽  
...  
Keyword(s):  
Image Quality ◽  
Fdg Pet ◽  
Pearson Correlation ◽  
Linear Regression Analysis ◽  
Acquisition Time ◽  
Body Habitus ◽  
Pet Ct ◽  
Digital Pet ◽  
Bed Position ◽  
The Impact

Abstract Background: New digital versus analogic PET has higher temporal resolution and more stable count rate, potentially limiting the degradation of PET image quality in larger patients. We wanted to describe the influence of patient’s body habitus on [18F]FDG PET image quality primary in digital PET/CT and analogic PET/CT.Results:We studied retrospectively the relation between patient’s weight, BMI, fatty massand PET image quality, described by the coefficient of variance in the liver (CVliv) and visually.177 unique patient exams on digital PET/CT (weight 35-127 kg; BMI 15-44 kg/m2) were performed with 2 protocols (protocol 1: N=52: 3MBq (0,08mCi)/kg [18F]FDG; 2minutes/bed position; 2iterations10subsets; 2mm diameter voxels and protocol 2: N=125: 4MBq (0,11mCi) /kg [18F]FDG; 1min/bed position; 4iterations4subsets; 2mm voxels).74 unique patient exams were analyzed on analogic PET/CT (weight 38-130 kg; BMI 14-52 kg/m2; with one protocol: 4MBq (0,11mCi)/kg [18F]FDG; 2min40sec/bedposition for BMI<25 and 3min40sec for BMI ≥25; 3iterations21subsets; 4mm voxels).Uni-and multivariable linear regression analysis showed positive association of CVliv with weight, BMI, fatty mass (p£0.009) and male sex (p£0,03) for both camera’s, with good fit in CVliv versus weight model on digital PET/CT (R2 up to 0.62). 4MBq (0,11mCi) protocol on digital PET/CT versus analogic PET/CT obtained lower CVliv on digital PET/CT in patients <70kg, without a difference if 70-<90kg and in Pearson correlation coefficients (p=0,26) despite substantially longer acquisition time for analogic PET/CT. For digital PET/CT CVliv increased similarly with weight for both protocols, up to 26% [95% Confidence Interval 2-56%] for ³90 kg versus <70kg, but overall CVliv values were lower in 4MBq (0,11mCi) protocol 2.Also visually PET image quality decreased with habitus on each camera (p£0.001) and was lower in females on digital PET/CT only (p=0,04).Conclusions:[18F]FDG PET image quality decreases with weight and enlarging body habitus on digital and analogic PET/CT imposing further optimization and harmonization also in digital PET/CT. This is important for clinical routine, but also (multicentric) research and development of artificial intelligence software.

A Novel deep learning approach for the automated diagnosis of normal pressure hydrocephalus

2021 ◽  
pp. 1-9
Author(s):  
B Rudhra ◽  
G Malu ◽  
Elizabeth Sherly ◽  
Robert Mathew
Keyword(s):  
Deep Learning ◽  
Normal Pressure Hydrocephalus ◽  
Normal Pressure ◽  
Test Accuracy ◽  
Brain Images ◽  
Bladder Control ◽  
Unsharp Mask ◽  
Atypical Parkinsonian Syndrome ◽  
Skull Stripping ◽  
Magnetic Resonance Imaging Mri

 Normal Pressure Hydrocephalus (NPH), an Atypical Parkinsonian syndrome, is a neurological syndrome that mainly affects elderly people. This syndrome shows the symptoms of Parkinson’s disease (PD), such as walking impairment, dementia, impaired bladder control, and mental impairment. The Magnetic Resonance Imaging (MRI) is the aptest modality for the detection of the abnormal build-up of cerebrospinal fluid in the brain’s cavities or ventricles, which is the major cause of NPH. This work aims to develop an automated biomarker for NPH segmentation and classification (NPH-SC) that efficiently detect hydrocephalus using a deep learning-based approach. Removal of non-cerebral tissues (skull, scalp, and dura) and noise from brain images by skull stripping, unsharp-mask based edge sharpening, segmentation by marker-based watershed algorithm, and labelling are performed to improve the accuracy of the CNN based classification system. The brain ventricles are extracted using the external and internal markers and then fed into the convolutional neural networks (CNN) for classification. This automated NPH-SC model achieved a sensitivity of 96%, a specificity of 100%, and a validation accuracy of 97%. The prediction system, with the help of a CNN classifier, is used for the calculation of test accuracy of the system and obtained promising 98% accuracy.

scholarly journals Spatial evaluation of volcanic ash forecasts using satellite observations

2016 ◽  
Vol 16 (2) ◽  
pp. 861-872 ◽  
Author(s):  
N. J. Harvey ◽  
H. F. Dacre
Keyword(s):  
Volcanic Ash ◽  
Pearson Correlation ◽  
Objective Measure ◽  
Skill Score ◽  
Near Miss ◽  
Model Parameters ◽  
Time Period ◽  
Long Time ◽  
The Impact ◽  
First Time

Abstract. The decision to close airspace in the event of a volcanic eruption is based on hazard maps of predicted ash extent. These are produced using output from volcanic ash transport and dispersion (VATD) models. In this paper the fractions skill score has been used for the first time to evaluate the spatial accuracy of VATD simulations relative to satellite retrievals of volcanic ash. This objective measure of skill provides more information than traditional point-by-point metrics, such as success index and Pearson correlation coefficient, as it takes into the account spatial scale over which skill is being assessed. The FSS determines the scale over which a simulation has skill and can differentiate between a "near miss" and a forecast that is badly misplaced. The idealized scenarios presented show that even simulations with considerable displacement errors have useful skill when evaluated over neighbourhood scales of 200–700 (km)2. This method could be used to compare forecasts produced by different VATDs or using different model parameters, assess the impact of assimilating satellite-retrieved ash data and evaluate VATD forecasts over a long time period.

scholarly journals Detection and classification of brain tumours from MRI images using faster R-CNN

2019 ◽  
Vol 13 (4) ◽  
pp. 337-342 ◽  
Author(s):  
Ercan Avşar ◽  
Kerem Salçin
Keyword(s):  
Deep Learning ◽  
Brain Tumours ◽  
Powerful Method ◽  
Resonance Imaging ◽  
Brain Images ◽  
Mri Brain ◽  
Classification Tasks ◽  
Magnetic Resonance Imaging Mri ◽  
Mri Brain Images

Magnetic resonance imaging (MRI) is a useful method for diagnosis of tumours in human brain. In this work, MRI images have been analysed to detect the regions containing tumour and classify these regions into three different tumour categories: meningioma, glioma, and pituitary. Deep learning is a relatively recent and powerful method for image classification tasks. Therefore, faster Region-based Convolutional Neural Networks (faster R-CNN), a deep learning method, has been utilized and implemented via TensorFlow library in this study. A publicly available dataset containing 3,064 MRI brain images (708 meningioma, 1426 glioma, 930 pituitary) of 233 patients has been used for training and testing of the classifier. It has been shown that faster R-CNN method can yield an accuracy of 91.66% which is higher than the related work using the same dataset.

Sign in / Sign up

Export Citation Format

Share Document