scholarly journals Deep Learning for Non-Invasive Cortical Potential Imaging

2020 ◽  
Author(s):  
Alexandra Razorenova ◽  
Nikolay Yavich ◽  
Mikhail Malovichko ◽  
Maxim Fedorov ◽  
Nikolay Koshev ◽  
...  
Keyword(s):  
Inverse Problem ◽  
Deep Learning ◽  
Electric Fields ◽  
Spatial Resolution ◽  
Brain Activity ◽  
Invasive Technique ◽  
Problem Solver ◽  
Deep Convolutional Neural Networks ◽  
Non Invasive ◽  
Cortical Potential Imaging

AbstractElectroencephalography (EEG) is a well-established non-invasive technique to measure the brain activity, albeit with a limited spatial resolution. Variations in electric conductivity between different tissues distort the electric fields generated by cortical sources, resulting in smeared potential measurements on the scalp. One needs to solve an ill-posed inverse problem to recover the original neural activity. In this article, we present a generic method of recovering the cortical potentials from the EEG measurement by introducing a new inverse-problem solver based on deep Convolutional Neural Networks (CNN) in paired (U-Net) and unpaired (DualGAN) configurations. The solvers were trained on synthetic EEG-ECoG pairs that were generated using a head conductivity model computed using the Finite Element Method (FEM). These solvers are the first of their kind, that provide robust translation of EEG data to the cortex surface using deep learning. Providing a fast and accurate interpretation of the tracked EEG signal, our approach promises a boost to the spatial resolution of the future EEG devices.

scholarly journals Can Autism Be Diagnosed with Artificial Intelligence? A Narrative Review

Diagnostics ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 2032
Author(s):  
Ahmad Chaddad ◽  
Jiali Li ◽  
Qizong Lu ◽  
Yujie Li ◽  
Idowu Paul Okuwobi ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Texture Analysis ◽  
Molecular Data ◽  
Autism Spectrum ◽  
Invasive Technique ◽  
Non Invasive ◽  
Learning Techniques ◽  
Healthy Control ◽  
Aided Diagnosis

Radiomics with deep learning models have become popular in computer-aided diagnosis and have outperformed human experts on many clinical tasks. Specifically, radiomic models based on artificial intelligence (AI) are using medical data (i.e., images, molecular data, clinical variables, etc.) for predicting clinical tasks such as autism spectrum disorder (ASD). In this review, we summarized and discussed the radiomic techniques used for ASD analysis. Currently, the limited radiomic work of ASD is related to the variation of morphological features of brain thickness that is different from texture analysis. These techniques are based on imaging shape features that can be used with predictive models for predicting ASD. This review explores the progress of ASD-based radiomics with a brief description of ASD and the current non-invasive technique used to classify between ASD and healthy control (HC) subjects. With AI, new radiomic models using the deep learning techniques will be also described. To consider the texture analysis with deep CNNs, more investigations are suggested to be integrated with additional validation steps on various MRI sites.

scholarly journals Combined Color Semantics and Deep Learning for the Automatic Detection of Dolphin Dorsal Fins

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 758 ◽  
Author(s):  
Vito Renò ◽  
Gianvito Losapio ◽  
Flavio Forenza ◽  
Tiziano Politi ◽  
Ettore Stella ◽  
...  
Keyword(s):  
Deep Learning ◽  
Domain Knowledge ◽  
Large Scale ◽  
Binary Classification ◽  
Invasive Technique ◽  
Hybrid Technique ◽  
Domain Experts ◽  
Photo Identification ◽  
Non Invasive ◽  
Biological Studies

Photo-identification is a widely used non-invasive technique in biological studies for understanding if a specimen has been seen multiple times only relying on specific unique visual characteristics. This information is essential to infer knowledge about the spatial distribution, site fidelity, abundance or habitat use of a species. Today there is a large demand for algorithms that can help domain experts in the analysis of large image datasets. For this reason, it is straightforward that the problem of identify and crop the relevant portion of an image is not negligible in any photo-identification pipeline. This paper approaches the problem of automatically cropping cetaceans images with a hybrid technique based on domain analysis and deep learning. Domain knowledge is applied for proposing relevant regions with the aim of highlighting the dorsal fins, then a binary classification of fin vs. no-fin is performed by a convolutional neural network. Results obtained on real images demonstrate the feasibility of the proposed approach in the automated process of large datasets of Risso’s dolphins photos, enabling its use on more complex large scale studies. Moreover, the results of this study suggest to extend this methodology to biological investigations of different species.

scholarly journals Deep Learning for Non-invasive Cortical Potential Imaging

2020 ◽  
pp. 45-55
Author(s):  
Alexandra Razorenova ◽  
Nikolay Yavich ◽  
Mikhail Malovichko ◽  
Maxim Fedorov ◽  
Nikolay Koshev ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cortical Potential ◽  
Non Invasive ◽  
Cortical Potential Imaging

scholarly journals Deep Learning System for COVID-19 Diagnosis Aid Using X-ray Pulmonary Images

2020 ◽  
Vol 10 (13) ◽  
pp. 4640 ◽  
Author(s):  
Javier Civit-Masot ◽  
Francisco Luna-Perejón ◽  
Manuel Domínguez Morales ◽  
Anton Civit
Keyword(s):  
Deep Learning ◽  
High Sensitivity ◽  
Roc Curves ◽  
Learning System ◽  
Invasive Technique ◽  
X Ray ◽  
Non Invasive ◽  
Specialist Doctor ◽  
High Degree ◽  
Deep Learning Model

The spread of the SARS-CoV-2 virus has made the COVID-19 disease a worldwide epidemic. The most common tests to identify COVID-19 are invasive, time consuming and limited in resources. Imaging is a non-invasive technique to identify if individuals have symptoms of disease in their lungs. However, the diagnosis by this method needs to be made by a specialist doctor, which limits the mass diagnosis of the population. Image processing tools to support diagnosis reduce the load by ruling out negative cases. Advanced artificial intelligence techniques such as Deep Learning have shown high effectiveness in identifying patterns such as those that can be found in diseased tissue. This study analyzes the effectiveness of a VGG16-based Deep Learning model for the identification of pneumonia and COVID-19 using torso radiographs. Results show a high sensitivity in the identification of COVID-19, around 100%, and with a high degree of specificity, which indicates that it can be used as a screening test. AUCs on ROC curves are greater than 0.9 for all classes considered.

scholarly journals Deep Learning Analysis of in Vivo Hyperspectral Images for Automated Intraoperative Nerves Detection

2021 ◽  
Author(s):  
Manuel Barberio ◽  
Toby Collins ◽  
Valentin Bencteux ◽  
Richard Nkusi ◽  
Eric Felli ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cross Validation ◽  
State Of The Art ◽  
Invasive Technique ◽  
Midline Incision ◽  
Average Sensitivity ◽  
Non Invasive ◽  
First Time ◽  
Learning Analysis

Abstract Nerves are difficult to recognize during surgery and inadvertent injuries may occur, bringing catastrophic consequences for the patient. Hyperspectral imaging (HSI) is a non-invasive technique combining photography with spectroscopy, allowing biological tissue property quantification. We show for the first time that HSI combined with deep learning allows nerves and other tissue types to be automatically recognized in-vivo at the pixel level. An animal model is used comprising eight anesthetized pigs with a neck midline incision, exposing several structures (nerve, artery, vein, muscle, fat, skin). State-of-the-art machine learning models have been trained to recognize these tissue types in HSI data. The best model is a Convolutional Neural Network (CNN), achieving an overall average sensitivity of 0.91 and specificity of 0.99, validated with leave-one-patient-out cross-validation. For the nerve, the CNN achieves an average sensitivity of 0.76 and specificity of 1.0. In conclusion, HSI combined with a CNN model is suitable for in vivo nerve recognition.

scholarly journals Deep Learning Analysis of In Vivo Hyperspectral Images for Automated Intraoperative Nerve Detection

Diagnostics ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1508
Author(s):  
Manuel Barberio ◽  
Toby Collins ◽  
Valentin Bencteux ◽  
Richard Nkusi ◽  
Eric Felli ◽  
...  
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Hyperspectral Images ◽  
Invasive Technique ◽  
Average Sensitivity ◽  
Non Invasive ◽  
First Time ◽  
Learning Analysis

Nerves are critical structures that may be difficult to recognize during surgery. Inadvertent nerve injuries can have catastrophic consequences for the patient and lead to life-long pain and a reduced quality of life. Hyperspectral imaging (HSI) is a non-invasive technique combining photography with spectroscopy, allowing non-invasive intraoperative biological tissue property quantification. We show, for the first time, that HSI combined with deep learning allows nerves and other tissue types to be automatically recognized in in vivo hyperspectral images. An animal model was used, and eight anesthetized pigs underwent neck midline incisions, exposing several structures (nerve, artery, vein, muscle, fat, skin). State-of-the-art machine learning models were trained to recognize these tissue types in HSI data. The best model was a convolutional neural network (CNN), achieving an overall average sensitivity of 0.91 and a specificity of 1.0, validated with leave-one-patient-out cross-validation. For the nerve, the CNN achieved an average sensitivity of 0.76 and a specificity of 0.99. In conclusion, HSI combined with a CNN model is suitable for in vivo nerve recognition.

scholarly journals In Vivo Deformation and Strain Measurements in Human Bone Using Digital Volume Correlation (DVC) and 3T Clinical MRI

Materials ◽  
2020 ◽  
Vol 13 (23) ◽  
pp. 5354
Author(s):  
Saman Tavana ◽  
Jeffrey N. Clark ◽  
Nicolas Newell ◽  
James D. Calder ◽  
Ulrich Hansen
Keyword(s):  
Spatial Resolution ◽  
Injury Risk ◽  
Relevant Information ◽  
Invasive Technique ◽  
Digital Volume Correlation ◽  
Non Invasive ◽  
Bone Strains ◽  
Clinical Mri ◽  
Optimal Settings

Strains within bone play an important role in the remodelling process and the mechanisms of fracture. The ability to assess these strains in vivo can provide clinically relevant information regarding bone health, injury risk, and can also be used to optimise treatments. In vivo bone strains have been investigated using multiple experimental techniques, but none have quantified 3D strains using non-invasive techniques. Digital volume correlation based on clinical MRI (DVC-MRI) is a non-invasive technique that has the potential to achieve this. However, before it can be implemented, uncertainties associated with the measurements must be quantified. Here, DVC-MRI was evaluated to assess its potential to measure in vivo strains in the talus. A zero-strain test (two repeated unloaded scans) was conducted using three MRI sequences, and three DVC approaches to quantify errors and to establish optimal settings. With optimal settings, strains could be measured with a precision of 200 με and accuracy of 480 με for a spatial resolution of 7.5 mm, and a precision of 133 με and accuracy of 251 με for a spatial resolution of 10 mm. These results demonstrate that this technique has the potential to measure relevant levels of in vivo bone strain and to be used for a range of clinical applications.

scholarly journals Group-Level Analysis of Induced Electric Field in Deep Brain Regions by Different TMS Coils

2019 ◽  
Author(s):  
Jose Gomez-Tames ◽  
Atsushi Hamasaka ◽  
Akimasa Hirata ◽  
Ilkka Laakso ◽  
Mai Lu ◽  
...  
Keyword(s):  
Electric Fields ◽  
Brain Regions ◽  
Invasive Technique ◽  
Group Level ◽  
Registration Method ◽  
Non Invasive ◽  
Consistent Group ◽  
Coil Performance ◽  
Deep Brain Region ◽  
Deep Brain

AbstractDeep transcranial magnetic stimulation (dTMS) is a non-invasive technique used in treating depression. In this study, we computationally evaluate group-level dosage during dTMS with the aim of characterizing targeted deep brain regions to overcome the limitation of using individualized head models to characterize coil performance in a population.We use an inter-subject registration method adapted to deep brain regions that enable projection of computed electric fields (EFs) from individual realistic head models (n= 18) to the average space of deep brain regions. The computational results showed consistent group-level hotspots of the EF in deep brain region with intensities between 20%-50% of the maximum EF in the cortex. Large co-activation in other brain regions was confirmed while half-value penetration depth from the cortical surface was smaller than 2 cm. The halo figure-8 assembly and halo circular assembly coils induced the highest EFs for caudate, putamen, and hippocampus.Generalized induced EF maps of deep regions show target regions despite inter-individual difference. This is the first study that visualizes generalized target regions during dTMS and provides a method for making informed decisions during dTMS interventions in clinical practice.

Sign in / Sign up

Export Citation Format

Share Document