scholarly journals Multicenter Validation of a Deep Learning Detection Algorithm for Focal Cortical Dysplasia

Neurology ◽  
2021 ◽  
pp. 10.1212/WNL.0000000000012698
Author(s):  
Ravnoor Singh Gill ◽  
Hyo-Min Lee ◽  
Benoit Caldairou ◽  
Seok-Jun Hong ◽  
Carmen Barba ◽  
...  
Keyword(s):  
Deep Learning ◽  
Risk Stratification ◽  
Learning Algorithm ◽  
Focal Cortical Dysplasia ◽  
Detection Algorithm ◽  
Cortical Dysplasia ◽  
False Positives ◽  
Class Iii ◽  
Deep Learning Algorithm ◽  
Independent Cohort

Objective.To test the hypothesis that a multicenter-validated computer deep learning algorithm detects MRI-negative focal cortical dysplasia (FCD).Methods.We used clinically-acquired 3D T1-weighted and 3D FLAIR MRI of 148 patients (median age, 23 years [range, 2-55]; 47% female) with histologically-verified FCD at nine centers to train a deep convolutional neural network (CNN) classifier. Images were initially deemed as MRI-negative in 51% of cases, in whom intracranial EEG determined the focus. For risk stratification, the CNN incorporated Bayesian uncertainty estimation as a measure of confidence. To evaluate performance, detection maps were compared to expert FCD manual labels. Sensitivity was tested in an independent cohort of 23 FCD cases (13±10 years). Applying the algorithm to 42 healthy and 89 temporal lobe epilepsy disease controls tested specificity.Results.Overall sensitivity was 93% (137/148 FCD detected) using a leave-one-site-out cross-validation, with an average of six false positives per patient. Sensitivity in MRI-negative FCD was 85%. In 73% of patients, the FCD was among the clusters with the highest confidence; in half it ranked the highest. Sensitivity in the independent cohort was 83% (19/23; average of five false positives per patient). Specificity was 89% in healthy and disease controls.Conclusions.This first multicenter-validated deep learning detection algorithm yields the highest sensitivity to date in MRI-negative FCD. By pairing predictions with risk stratification this classifier may assist clinicians to adjust hypotheses relative to other tests, increasing diagnostic confidence. Moreover, generalizability across age and MRI hardware makes this approach ideal for pre-surgical evaluation of MRI-negative epilepsy.Classification of evidence.This study provides Class III evidence that deep learning on multimodal MRI accurately identifies FCD in epilepsy patients initially diagnosed as MRI-negative.

scholarly journals Classification of Shellfish Recognition Based on Improved Faster R-CNN Framework of Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Yiran Feng ◽  
Xueheng Tao ◽  
Eung-Joo Lee
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Experimental Tests ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Multiple Objects ◽  
Detection Model ◽  
Deep Learning Algorithm ◽  
Quality Sorting

In view of the current absence of any deep learning algorithm for shellfish identification in real contexts, an improved Faster R-CNN-based detection algorithm is proposed in this paper. It achieves multiobject recognition and localization through a second-order detection network and replaces the original feature extraction module with DenseNet, which can fuse multilevel feature information, increase network depth, and avoid the disappearance of network gradients. Meanwhile, the proposal merging strategy is improved with Soft-NMS, where an attenuation function is designed to replace the conventional NMS algorithm, thereby avoiding missed detection of adjacent or overlapping objects and enhancing the network detection accuracy under multiple objects. By constructing a real contexts shellfish dataset and conducting experimental tests on a vision recognition seafood sorting robot production line, we were able to detect the features of shellfish in different scenarios, and the detection accuracy was improved by nearly 4% compared to the original detection model, achieving a better detection accuracy. This provides favorable technical support for future quality sorting of seafood using the improved Faster R-CNN-based approach.

scholarly journals Geographic Generalization in Airborne RGB Deep Learning Tree Detection

2019 ◽  
Author(s):  
Ben. G. Weinstein ◽  
Sergio Marconi ◽  
Stephanie A. Bohlman ◽  
Alina Zare ◽  
Ethan P. White
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Forest Type ◽  
Detection Algorithm ◽  
Forest Types ◽  
Individual Tree ◽  
Tree Detection ◽  
Deep Learning Algorithm ◽  
Local Site ◽  
Using Data

AbstractTree detection is a fundamental task in remote sensing for forestry and ecosystem ecology applications. While many individual tree segmentation algorithms have been proposed, the development and testing of these algorithms is typically site specific, with few methods evaluated against data from multiple forest types simultaneously. This makes it difficult to determine the generalization of proposed approaches, and limits tree detection at broad scales. Using data from the National Ecological Observatory Network we extend a recently developed semi-supervised deep learning algorithm to include data from a range of forest types, determine whether information from one forest can be used for tree detection in other forests, and explore the potential for building a universal tree detection algorithm. We find that the deep learning approach works well for overstory tree detection across forest conditions, outperforming conventional LIDAR-only methods in all forest types. Performance was best in open oak woodlands and worst in alpine forests. When models were fit to one forest type and used to predict another, performance generally decreased, with better performance when forests were more similar in structure. However, when models were pretrained on data from other sites and then fine-tuned using a small amount of hand-labeled data from the evaluation site, they performed similarly to local site models. Most importantly, a universal model fit to data from all sites simultaneously performed as well or better than individual models trained for each local site. This result suggests that RGB tree detection models that can be applied to a wide array of forest types at broad scales should be possible.

scholarly journals Development and Validation of Suspicious Liver Lesion Deep Learning Algorithm for Computed Tomography

2021 ◽  
Author(s):  
Jacob Johnson ◽  
Kaneel Senevirathne ◽  
Lawrence Ngo
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Small Sample Size ◽  
Liver Lesion ◽  
The United States ◽  
Detection Algorithm ◽  
Small Sample ◽  
Lesion Detection ◽  
Liver Lesions ◽  
Deep Learning Algorithm

In this work, we report the results of a deep-learning based liver lesion detection algorithm. While several liver lesion segmentation and classification algorithms have been developed, none of the previous work has focused on detecting suspicious liver lesions. Furthermore, their generalizability remains a pitfall due to their small sample size and sample homogeneity. Here, we developed and validated a highly generalizable deep-learning algorithm for detection of suspicious liver lesions. The algorithm was trained and tested on a diverse dataset containing CT exams from over 2,000 hospital sites in the United States. Our final model achieved an AUROC of 0.84 with a specificity of 0.99 while maintaining a sensitivity of 0.33.

scholarly journals Soft Transducer for Patient’s Vitals Telemonitoring with Deep Learning-Based Personalized Anomaly Detection

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 536
Author(s):  
Pasquale Arpaia ◽  
Federica Crauso ◽  
Egidio De Benedetto ◽  
Luigi Duraccio ◽  
Giovanni Improta ◽  
...  
Keyword(s):  
Deep Learning ◽  
Anomaly Detection ◽  
Short Term Memory ◽  
Learning Algorithm ◽  
Diastolic Pressure ◽  
True Positive Rate ◽  
Detection Algorithm ◽  
Design Development ◽  
Specific Patient ◽  
Deep Learning Algorithm

This work addresses the design, development and implementation of a 4.0-based wearable soft transducer for patient-centered vitals telemonitoring. In particular, first, the soft transducer measures hypertension-related vitals (heart rate, oxygen saturation and systolic/diastolic pressure) and sends the data to a remote database (which can be easily consulted both by the patient and the physician). In addition to this, a dedicated deep learning algorithm, based on a Long-Short-Term-Memory Autoencoder, was designed, implemented and tested for providing an alert when the patient’s vitals exceed certain thresholds, which are automatically personalized for the specific patient. Furthermore, a mobile application (EcO2u) was developed to manage the entire data flow and facilitate the data fruition; this application also implements an innovative face-detection algorithm that ensures the identity of the patient. The robustness of the proposed soft transducer was validated experimentally on five individuals, who used the system for 30 days. The experimental results demonstrated an accuracy in anomaly detection greater than 93%, with a true positive rate of more than 94%.

scholarly journals Risk Score Stratification of Alzheimer’s Disease and Mild Cognitive Impairment using Deep Learning

2020 ◽  
Author(s):  
Sanjay Nagaraj ◽  
Tim Q Duong
Keyword(s):  
Alzheimer’S Disease ◽  
Deep Learning ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Risk Stratification ◽  
Risk Score ◽  
Learning Algorithm ◽  
Clinical Variables ◽  
Deep Learning Algorithm ◽  
Neurocognitive Tests

ABSTRACTAlzheimer Disease (AD) is a progressive neurodegenerative disease that can significantly impair cognition and memory. AD is the leading cause of dementia and affects one in ten people age 65 and older. Current diagnoses methods of AD heavily rely on the use of Magnetic Resonance Imaging (MRI) since non-imaging methods can vary widely leading to inaccurate diagnoses. Furthermore, recent research has revealed a substage of AD, Mild Cognitive Impairment (MCI), that is characterized by symptoms between normal cognition and dementia which makes it more prone to misdiagnosis.A large battery of clinical variables are currently used to detect cognitive impairment and classify early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), and AD from cognitive normal (CN) patients. The goal of this study was to derive a simplified risk-stratification algorithm for diagnosis and identify a few significant clinical variables that can accurately classify these four groups using an empirical deep learning approach. Over 100 variables that included neuropsychological/neurocognitive tests, demographics, genetic factors, and blood biomarkers were collected from EMCI, LMCI, AD, and CN patients from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Feature engineering was performed with 5 different methods and a neural network was trained on 90% of the data and tested on 10% using 10-fold cross validation. Prediction performance used area under the curve (AUC) of the receiver operating characteristic analysis.The five different feature selection methods consistently yielded the top classifiers to be the Clinical Dementia Rating Scale - Sum of Boxes (CDRSB), Delayed total recall (LDELTOTAL), Modified Preclinical Alzheimer Cognitive Composite with Trails test (mPACCtrailsB), the Modified Preclinical Alzheimer Cognitive Composite with Digit test (mPACCdigit), and Mini-Mental State Examination (MMSE). The best classification model yielded an AUC of 0.984, and the simplified risk-stratification score yielded an AUC of 0.963 on the test dataset.Our results show that this deep-learning algorithm and simplified risk score derived from our deep-learning algorithm accurately diagnose EMCI, LMCI, AD and CN patients using a few commonly available neurocognitive tests. The project was successful in creating an accurate, clinically translatable risk-stratified scoring aid for primary care providers to diagnose AD in a fast and inexpensive manner.

scholarly journals Development of an Underground Tunnels Detection Algorithm for Electrical Resistivity Tomography Based on Deep Learning

2022 ◽  
Vol 12 (2) ◽  
pp. 639
Author(s):  
Yin-Chun Hung ◽  
Yu-Xiang Zhao ◽  
Wei-Chen Hung
Keyword(s):  
Artificial Intelligence ◽  
Electrical Resistivity ◽  
Deep Learning ◽  
Electrical Resistivity Tomography ◽  
Learning Algorithm ◽  
Detection Algorithm ◽  
Image Resolution ◽  
Resistivity Tomography ◽  
Military Installations ◽  
Deep Learning Algorithm

Kinmen Island was in a state of combat readiness during the 1950s–1980s. It opened for tourism in 1992, when all troops withdrew from the island. Most military installations, such as bunkers, anti airborne piles, and underground tunnels, became deserted and disordered. The entries to numerous underground bunkers are closed or covered with weeds, creating dangerous spaces on the island. This study evaluates the feasibility of using Electrical Resistivity Tomography (ERT) to detect and discuss the location, size, and depth of underground tunnels. In order to discuss the reliability of the 2D-ERT result, this study built a numerical model to validate the correctness of in situ measured data. In addition, this study employed the artificial intelligence deep learning technique for reprocessing and predicting the ERT image and discussed using an artificial intelligence deep learning algorithm to enhance the image resolution and interpretation. A total of three 2D-ERT survey lines were implemented in this study. The results indicate that the three survey lines clearly show the tunnel location and shape. The numerical simulation results also indicate that using 2D-ERT to survey underground tunnels is highly feasible. Moreover, according to a series of studies in Multilayer Perceptron of deep learning, using deep learning can clearly show the tunnel location and path and effectively enhance the interpretation ability and resolution for 2D-ERT measurement results.

scholarly journals Development and Validation of a Highly Generalizable Deep Learning Pulmonary Embolism Detection Algorithm

2020 ◽  
Author(s):  
Ryan Schmid ◽  
Jacob Johnson ◽  
Jennifer Ngo ◽  
Christine Lamoureux ◽  
Brian Baker ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Pulmonary Embolism ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Small Sample Size ◽  
Detection Algorithm ◽  
Small Sample ◽  
Deep Learning Algorithm ◽  
Development And Validation ◽  
Sample Homogeneity

AbstractSeveral algorithms have been developed for the detection of pulmonary embolism, though generalizability and bias remain potential weaknesses due to small sample size and sample homogeneity. We developed and validated a highly generalizable deep-learning algorithm, Emboleye, for the detection of PE by using a large and diverse dataset, which included 30,574 computed tomography (CT) exams sourced from over 2,000 hospital sites. On angiography exams, Emboleye demonstrates an AUROC of 0.79 with a specificity of 0.99 while maintaining a sensitivity of 0.37 and PPV of 0.77. On non-angiography CT exams, Emboleye demonstrates an AUROC of 0.77 with a specificity of 0.99 while maintaining a sensitivity of 0.18 and PPV of 0.35.

scholarly journals Object Detection Method by using Yolov3 with Machine Learning

2020 ◽  
Vol 8 (6) ◽  
pp. 5247-5250
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Object Detection ◽  
Moving Objects ◽  
Learning Algorithm ◽  
Detection Algorithm ◽  
Video Object ◽  
Long Distance ◽  
Deep Learning Algorithm ◽  
Tracking Movement

Detecting the object is a vision technique of a computer for detectng or locating long distance or short distance objects and images. Object detection algorithm mainly works on the machine learning and the artificial intelligence algorithms. Present trending algorithm in detecting the object is deep learning algorithm, By using the deep learning algorithm we can get the accurate results of the object which is detected. it is mainly or widely used in the system vision tasks like video object co-segmentations, tracking movement of the ball in the ground, image annotating etc. Each and every object has its own features ,for example if you select the ball , Actually all the ball are in the round shape but in every game different type of balls are used ,object detection camera will detect the ball it will check the ball specifications with its data if any data was matched with its data base the system will display all the specifications of ball. By using the deep learning algorithm we introduced one new technique to detect detect object accurately the algorithm is named as the YOLO V3 we can detect the very small objects and the fastly moving objects easily. This yolo v3 will convert the image into N number of layers and it will work on the each and every minute spot on the image.

Sign in / Sign up

Export Citation Format

Share Document