Accuracy of Deep-learning Algorithm for Detection and Risk Stratification of Lung Nodules

2019 ◽  
Author(s):  
Keyword(s):  
Deep Learning ◽  
Risk Stratification ◽  
Learning Algorithm ◽  
Lung Nodules ◽  
Deep Learning Algorithm

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 Highly Robust Prediction of Lung Nodule Malignancy by Deep Learning Model: A Multiracial, Multinational Study

2020 ◽  
Author(s):  
Hao Wu ◽  
Wen Tang ◽  
Chu Wu ◽  
Yufeng Deng ◽  
Rongguo Zhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Clinical Features ◽  
Learning Algorithm ◽  
Lung Nodule ◽  
Ct Scans ◽  
Multivariate Logistic Regression Model ◽  
Lung Nodules ◽  
Deep Learning Algorithm

AbstractPurposeAlthough statistical models have been employed to detect and classify lung nodules using deep learning-extracted and clinical features, there is a lack of model validation in independent, multinational datasets from computed tomography (CT) scans and patient clinical information. To this end, we developed a deep learning-based algorithm to predict the malignancy of pulmonary nodules and validated its performance in three independent datasets containing multiracial and multinational populations.MethodsIn this study, a convolutional neural network-based algorithm to predict lung nodule malignancy was built based on CT scans and patient-wise clinical features (i.e. sex, spiculation, and nodule location). The model consists of three steps: (1) a deep learning algorithm to automatically extract features from CT scans, (2) clinical features were concatenated with the nodule features after dimension reduction by the principal component analysis (PCA), and (3) a multivariate logistic regression model was employed to classify the malignancy of the lung nodules. The model was trained by a dataset containing 1,556 nodules from 813 patients from the National Lung Screening Trial (NLST). The performance of the model was evaluated on three independent, multi-institutional datasets LIDC and Infervision Multi-Center (IMC) dataset, which contains 562 nodules from 293 patients, and 2044 nodules from 589 patients, respectively. The model accuracy was measured by the area under curve (AUC) of receiver operating characteristic (ROC) analysis.ResultsThe study shows that the AUCs of ROCs on the NLST dataset, LIDC dataset, and IMC dataset are 0.91, 0.86, and 0.95, respectively. The inclusion of clinical features does not significantly improve the model performance. Quantitatively, the summed-up weight on the prediction accuracy of the 10 nodule features extracted by the deep learning algorithm equals to 0.091, while the weight of patient sex, nodule spiculation, and location is 0.031, 0.052, and 0.008, respectively.ConclusionThe convolutional neural network-based model for lung nodule classification could be generalized to multiple datasets containing diverse populations. The addition of three patient clinical features to the nodule features extracted by deep learning does not boost the performance of the model.

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 Deep learning diagnostic and risk-stratification pattern detection for COVID-19 in digital lung auscultations: clinical protocol for a case–control and prospective cohort study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Alban Glangetas ◽  
Mary-Anne Hartley ◽  
Aymeric Cantais ◽  
Delphine S. Courvoisier ◽  
David Rivollet ◽  
...  
Keyword(s):  
Deep Learning ◽  
Risk Stratification ◽  
Learning Algorithm ◽  
Signs And Symptoms ◽  
Support Vector ◽  
Nasopharyngeal Swab ◽  
University Hospitals ◽  
Deep Learning Algorithm ◽  
Audio Recordings ◽  
Lung Auscultation

Abstract Background Lung auscultation is fundamental to the clinical diagnosis of respiratory disease. However, auscultation is a subjective practice and interpretations vary widely between users. The digitization of auscultation acquisition and interpretation is a particularly promising strategy for diagnosing and monitoring infectious diseases such as Coronavirus-19 disease (COVID-19) where automated analyses could help decentralise care and better inform decision-making in telemedicine. This protocol describes the standardised collection of lung auscultations in COVID-19 triage sites and a deep learning approach to diagnostic and prognostic modelling for future incorporation into an intelligent autonomous stethoscope benchmarked against human expert interpretation. Methods A total of 1000 consecutive, patients aged ≥ 16 years and meeting COVID-19 testing criteria will be recruited at screening sites and amongst inpatients of the internal medicine department at the Geneva University Hospitals, starting from October 2020. COVID-19 is diagnosed by RT-PCR on a nasopharyngeal swab and COVID-positive patients are followed up until outcome (i.e., discharge, hospitalisation, intubation and/or death). At inclusion, demographic and clinical data are collected, such as age, sex, medical history, and signs and symptoms of the current episode. Additionally, lung auscultation will be recorded with a digital stethoscope at 6 thoracic sites in each patient. A deep learning algorithm (DeepBreath) using a Convolutional Neural Network (CNN) and Support Vector Machine classifier will be trained on these audio recordings to derive an automated prediction of diagnostic (COVID positive vs negative) and risk stratification categories (mild to severe). The performance of this model will be compared to a human prediction baseline on a random subset of lung sounds, where blinded physicians are asked to classify the audios into the same categories. Discussion This approach has broad potential to standardise the evaluation of lung auscultation in COVID-19 at various levels of healthcare, especially in the context of decentralised triage and monitoring. Trial registration: PB_2016-00500, SwissEthics. Registered on 6 April 2020.

Sign in / Sign up

Export Citation Format

Share Document