scholarly journals DIAROP: Automated Deep Learning-Based Diagnostic Tool for Retinopathy of Prematurity

Diagnostics ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 2034
Author(s):  
Omneya Attallah
Keyword(s):  
Deep Learning ◽  
Retinopathy Of Prematurity ◽  
Diagnostic Tool ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Diagnostic Tools ◽  
Preterm Neonates ◽  
Hadamard Transform ◽  
Spatial Features ◽  
Diagnostic Capability

Retinopathy of Prematurity (ROP) affects preterm neonates and could cause blindness. Deep learning (DL) can assist ophthalmologists in the diagnosis of ROP. This paper proposes an automated and reliable diagnostic tool based on DL techniques called DIAROP to support the ophthalmologic diagnosis of ROP. It extracts significant features by first obtaining spatial features from the four convolution neural networks (CNNs) DL techniques using transfer learning and then applying Fast Walsh Hadamard Transform (FWHT) to integrate these features. Moreover, DIAROP explores the best-integrated features extracted from the CNNs that influence its diagnostic capability. The results of DIAROP indicate that DIAROP achieved an accuracy of 93.2% and an area under receiving operating characteristic curve (AUC) of 0.98. Furthermore, DIAROP performance is compared with recent ROP diagnostic tools. Its promising performance shows that DIAROP may assist the ophthalmologic diagnosis of ROP.

scholarly journals Development and Verification of a Deep Learning Algorithm to Evaluate Small-Bowel Preparation Quality

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1127
Author(s):  
Ji Hyung Nam ◽  
Dong Jun Oh ◽  
Sumin Lee ◽  
Hyun Joo Song ◽  
Yun Jeong Lim
Keyword(s):  
Deep Learning ◽  
Small Bowel ◽  
Scoring System ◽  
Operating Characteristic ◽  
Clinical Evidence ◽  
Learning Algorithm ◽  
Characteristic Curve ◽  
External Validation ◽  
Test Results ◽  
Deep Learning Algorithm

Capsule endoscopy (CE) quality control requires an objective scoring system to evaluate the preparation of the small bowel (SB). We propose a deep learning algorithm to calculate SB cleansing scores and verify the algorithm’s performance. A 5-point scoring system based on clarity of mucosal visualization was used to develop the deep learning algorithm (400,000 frames; 280,000 for training and 120,000 for testing). External validation was performed using additional CE cases (n = 50), and average cleansing scores (1.0 to 5.0) calculated using the algorithm were compared to clinical grades (A to C) assigned by clinicians. Test results obtained using 120,000 frames exhibited 93% accuracy. The separate CE case exhibited substantial agreement between the deep learning algorithm scores and clinicians’ assessments (Cohen’s kappa: 0.672). In the external validation, the cleansing score decreased with worsening clinical grade (scores of 3.9, 3.2, and 2.5 for grades A, B, and C, respectively, p < 0.001). Receiver operating characteristic curve analysis revealed that a cleansing score cut-off of 2.95 indicated clinically adequate preparation. This algorithm provides an objective and automated cleansing score for evaluating SB preparation for CE. The results of this study will serve as clinical evidence supporting the practical use of deep learning algorithms for evaluating SB preparation quality.

scholarly journals Automated Breast Cancer Detection in Digital Mammograms of Various Densities via Deep Learning

2020 ◽  
Vol 10 (4) ◽  
pp. 211 ◽  
Author(s):  
Yong Joon Suh ◽  
Jaewon Jung ◽  
Bum-Joo Cho
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Operating Characteristic ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
Malignant Lesion ◽  
Model Performance ◽  
Mean Values ◽  
The Mean ◽  
Deep Learning Model

Mammography plays an important role in screening breast cancer among females, and artificial intelligence has enabled the automated detection of diseases on medical images. This study aimed to develop a deep learning model detecting breast cancer in digital mammograms of various densities and to evaluate the model performance compared to previous studies. From 1501 subjects who underwent digital mammography between February 2007 and May 2015, craniocaudal and mediolateral view mammograms were included and concatenated for each breast, ultimately producing 3002 merged images. Two convolutional neural networks were trained to detect any malignant lesion on the merged images. The performances were tested using 301 merged images from 284 subjects and compared to a meta-analysis including 12 previous deep learning studies. The mean area under the receiver-operating characteristic curve (AUC) for detecting breast cancer in each merged mammogram was 0.952 ± 0.005 by DenseNet-169 and 0.954 ± 0.020 by EfficientNet-B5, respectively. The performance for malignancy detection decreased as breast density increased (density A, mean AUC = 0.984 vs. density D, mean AUC = 0.902 by DenseNet-169). When patients’ age was used as a covariate for malignancy detection, the performance showed little change (mean AUC, 0.953 ± 0.005). The mean sensitivity and specificity of the DenseNet-169 (87 and 88%, respectively) surpassed the mean values (81 and 82%, respectively) obtained in a meta-analysis. Deep learning would work efficiently in screening breast cancer in digital mammograms of various densities, which could be maximized in breasts with lower parenchyma density.

scholarly journals Validating the validation: reanalyzing a large-scale comparison of deep learning and machine learning models for bioactivity prediction

2020 ◽  
Vol 34 (7) ◽  
pp. 717-730 ◽  
Author(s):  
Matthew C. Robinson ◽  
Robert C. Glen ◽  
Alpha A. Lee
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Numerical Experiments ◽  
Large Scale ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Learning Models ◽  
Bioactivity Prediction ◽  
Operating Characteristic Curve ◽  
Machine Learning Models

Abstract Machine learning methods may have the potential to significantly accelerate drug discovery. However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should be benchmarked and validated. We reanalyze the data generated by a recently published large-scale comparison of machine learning models for bioactivity prediction and arrive at a somewhat different conclusion. We show that the performance of support vector machines is competitive with that of deep learning methods. Additionally, using a series of numerical experiments, we question the relevance of area under the receiver operating characteristic curve as a metric in virtual screening. We further suggest that area under the precision–recall curve should be used in conjunction with the receiver operating characteristic curve. Our numerical experiments also highlight challenges in estimating the uncertainty in model performance via scaffold-split nested cross validation.

scholarly journals DeepSleep: Fast and Accurate Delineation of Sleep Arousals at Millisecond Resolution by Deep Learning

2019 ◽  
Author(s):  
Hongyang Li ◽  
Yuanfang Guan
Keyword(s):  
Deep Learning ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Learning Approach ◽  
Considerable Time ◽  
Negative Effects ◽  
High Quality ◽  
Data Points ◽  
Sleep Arousal ◽  
Operating Characteristic Curve

AbstractSleep arousals are transient periods of wakefulness punctuated into sleep. Excessive sleep arousals are associated with many negative effects including daytime sleepiness and sleep disorders. High-quality annotation of polysomnographic recordings is crucial for the diagnosis of sleep arousal disorders. Currently, sleep arousals are mainly annotated by human experts through looking at millions of data points manually, which requires considerable time and effort. Here we present a deep learning approach, DeepSleep, which ranked first in the 2018 PhysioNet Challenge for automatically segmenting sleep arousal regions based on polysomnographic recordings. DeepSleep features accurate (area under receiver operating characteristic curve of 0.93), high-resolution (5-millisecond resolution), and fast (10 seconds per sleep record) delineation of sleep arousals.

scholarly journals Same same but different: a web-based deep learning application for the histopathologic distinction of cortical malformations

2019 ◽  
Author(s):  
J. Kubach ◽  
A. Muehlebner-Farngruber ◽  
F. Soylemezoglu ◽  
H. Miyata ◽  
P. Niehusmann ◽  
...  
Keyword(s):  
Deep Learning ◽  
Web Application ◽  
Operating Characteristic ◽  
Focal Cortical Dysplasia ◽  
Characteristic Curve ◽  
Digital Processing ◽  
Web Based ◽  
Histopathologic Diagnosis ◽  
Dysmorphic Neurons ◽  
Whole Slide Images

AbstractWe trained a convolutional neural network (CNN) to classify H.E. stained microscopic images of focal cortical dysplasia type IIb (FCD IIb) and cortical tuber of tuberous sclerosis complex (TSC). Both entities are distinct subtypes of human malformations of cortical development that share histopathological features consisting of neuronal dyslamination with dysmorphic neurons and balloon cells. The microscopic review of routine stainings of such surgical specimens remains challenging. A digital processing pipeline was developed for a series of 56 FCD IIb and TSC cases to obtain 4000 regions of interest and 200.000 sub-samples with different zoom and rotation angles to train a CNN. Our best performing network achieved 91% accuracy and 0.88 AUCROC (area under the receiver operating characteristic curve) on a hold-out test-set. Guided gradient-weighted class activation maps visualized morphological features used by the CNN to distinguish both entities. We then developed a web application, which combined the visualization of whole slide images (WSI) with the possibility for classification between FCD IIb and TSC on demand by our pretrained and build-in CNN classifier. This approach might help to introduce deep learning applications for the histopathologic diagnosis of rare and difficult-to-classify brain lesions.

scholarly journals Quantitative Assessment of the Effects of Compression on Deep Learning in Digital Pathology Image Analysis

2020 ◽  
pp. 221-233
Author(s):  
Yijiang Chen ◽  
Andrew Janowczyk ◽  
Anant Madabhushi
Keyword(s):  
Deep Learning ◽  
Image Compression ◽  
Operating Characteristic ◽  
Performance Metrics ◽  
Signal To Noise Ratio ◽  
Characteristic Curve ◽  
Digital Pathology ◽  
Jpeg2000 Compression ◽  
Classifier Performance ◽  
Pathology Image

PURPOSE Deep learning (DL), a class of approaches involving self-learned discriminative features, is increasingly being applied to digital pathology (DP) images for tasks such as disease identification and segmentation of tissue primitives (eg, nuclei, glands, lymphocytes). One application of DP is in telepathology, which involves digitally transmitting DP slides over the Internet for secondary diagnosis by an expert at a remote location. Unfortunately, the places benefiting most from telepathology often have poor Internet quality, resulting in prohibitive transmission times of DP images. Image compression may help, but the degree to which image compression affects performance of DL algorithms has been largely unexplored. METHODS We investigated the effects of image compression on the performance of DL strategies in the context of 3 representative use cases involving segmentation of nuclei (n = 137), segmentation of lymph node metastasis (n = 380), and lymphocyte detection (n = 100). For each use case, test images at various levels of compression (JPEG compression quality score ranging from 1-100 and JPEG2000 compression peak signal-to-noise ratio ranging from 18-100 dB) were evaluated by a DL classifier. Performance metrics including F1 score and area under the receiver operating characteristic curve were computed at the various compression levels. RESULTS Our results suggest that DP images can be compressed by 85% while still maintaining the performance of the DL algorithms at 95% of what is achievable without any compression. Interestingly, the maximum compression level sustainable by DL algorithms is similar to where pathologists also reported difficulties in providing accurate interpretations. CONCLUSION Our findings seem to suggest that in low-resource settings, DP images can be significantly compressed before transmission for DL-based telepathology applications.

scholarly journals Peripapillary retinal artery in first diagnosed and untreated normal tension glaucoma

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Xin Rong ◽  
Yu Cai ◽  
Mei Li ◽  
Yuan Fang ◽  
Tian Tian ◽  
...  
Keyword(s):  
Operating Characteristic ◽  
Characteristic Curve ◽  
Normal Tension Glaucoma ◽  
Newly Diagnosed ◽  
Fiber Layer ◽  
Nerve Fiber Layer Thickness ◽  
Diagnostic Capability ◽  
Retinal Artery ◽  
Operating Characteristic Curve ◽  
Retinal Arteriolar

Abstract Background Glaucoma, an important cause of visual impairment in many countries, remains a common eye condition due to difficulties in its early diagnosis. We analyzed the characteristics of retinal arteries to add a valuable technology for helping the normal tension glaucoma (NTG) diagnosis. Methods This study included 51 patients with newly diagnosed NTG with hemifield defects and 60 age-matched controls. Peripapillary retinal arteriolar calibers (PRACs) photoed by non-mydriatic retinal camera were measured using ImageJ by two masked readers. We also performed spectral-domain optical coherence tomography to evaluate retinal nerve fiber layer thickness (RNFLT) and optic disc parameters. Their relations to retinal arteriolar calibers were investigated by univariate and multivariate linear regression. The area under the receiver operating characteristic curve (AUROC) was used to confirm the powers to detect NTG by PRACs. Results PRACs in four quadrants were significantly reduced in individuals with first diagnosed NTG (82 ± 15.1 μm, 80 ± 13.6 μm, 71 ± 11.6 μm, and 64 ± 10.0 μm) compared with those in age-matched controls (101 ± 9.8 μm, 105 ± 8.7 μm, 90 ± 7.5 μm, and 82 ± 9.8 μm). Superotemporal and inferotemporal PRACs in the visual field-affected hemifield were narrower than those in the unaffected hemifield in NTG group (P ≤ 0.004). Temporal PRACs in the RNFL unaffected hemifield were significantly narrower than in healthy eyes (P < 0.001). Superotemporal PRAC showed a significant correlation with superior RNFLT (β = 0.659, P < 0.001), and a similar relationship was found between inferotemporal PRAC and inferior RNFLT (β = 0.227, P = 0.015). The diagnostic capability of temporal PRACs was satisfactory (superotemporal PRAC; AUROC 0.983, cut-off value 84.7 μm, inferotemporal PRAC; AUROC 0.946, cut-off value 94.2 μm). Conclusions PRAC and inferotemporal PRAC are valid parameters for discriminating patients with NTG.

scholarly journals Functional MRI in awake dogs predicts suitability for assistance work

2016 ◽  
Author(s):  
Gregory S. Berns ◽  
Andrew M. Brooks ◽  
Mark Spivak ◽  
Kerinne Levy
Keyword(s):  
Operating Characteristic ◽  
Characteristic Curve ◽  
Differential Response ◽  
Successful Outcome ◽  
Service Dogs ◽  
Service Dog ◽  
Diagnostic Capability ◽  
Service Training ◽  
The Stranger ◽  
Fold Cross Validation

ABSTRACTThe overall goal of this work was to measure the efficacy of fMRI for predicting whether a dog would be a successful service dog. The training and imaging were performed in 50 dogs entering advanced training at 17-21 months of age. FMRI responses were measured while each dog observed hand signals indicating either reward or no reward and given by both a familiar handler and a stranger. 49 dogs successfully completed fMRI training and scanning. Of these, 33 eventually completed service training and were matched with a person, while 10 were released for behavioral reasons. Using anatomically defined regions-of-interest in the ventral caudate, amygdala, and visual cortex, we developed a classifier based on the dogs' outcomes. We found that responses in the stranger condition were sufficient to develop an accurate brain-based classifier. On all data, the classifier had a positive predictive value of 96% with 10% false positives. The area under the receiver operating characteristic curve was 0.90 (0.79 with 4-fold cross-validation, P=0.02), indicating a significant diagnostic capability. Within the stranger condition, the differential response to [reward – no reward] in ventral caudate was positively correlated with a successful outcome, while the differential response in the amygdala was negatively correlated to outcome. These results show that successful service dogs transfer knowledge to strangers as indexed by ventral caudate activity without excessive arousal as measured in the amygdala.

scholarly journals Peripapillary retinal artery in first diagnosed and untreated normal tension glaucoma

2019 ◽  
Author(s):  
XIN RONG ◽  
Yu Cai ◽  
Mei Li ◽  
Yuan Fang ◽  
Tian Tian ◽  
...  
Keyword(s):  
Operating Characteristic ◽  
Characteristic Curve ◽  
Normal Tension Glaucoma ◽  
Newly Diagnosed ◽  
Fiber Layer ◽  
Nerve Fiber Layer Thickness ◽  
Diagnostic Capability ◽  
Retinal Artery ◽  
Operating Characteristic Curve ◽  
Retinal Arteriolar

Abstract Background Glaucoma, an important cause of visual impairment in many countries, remains a common eye condition due to difficulties in its early diagnosis. We analyzed the characteristics of retinal arteries to add a valuable technology for helping the normal tension glaucoma (NTG) diagnosis. Methods This study included 51 patients with newly diagnosed NTG with hemifield defects and 60 age-matched controls. Peripapillary retinal arteriolar calibers (PRACs) photoed by non-mydriatic retinal camera were measured using ImageJ by two masked readers. We also performed spectral-domain optical coherence tomography to evaluate retinal nerve fiber layer thickness (RNFLT) and optic disc parameters. Their relations to retinal arteriolar calibers were investigated by univariate and multivariate linear regression. The area under the receiver operating characteristic curve (AUROC) was used to confirm the powers to detect NTG by PRACs. Results PRACs in four quadrants were significantly reduced in individuals with first diagnosed NTG (82 ± 15.1 μm, 80 ± 13.6 μm, 71 ± 11.6 μm, and 64 ±10.0 μm) compared with those in age-matched controls (101 ± 9.8 μm, 105 ± 8.7 μm, 90 ± 7.5 μm, and 82 ± 9.8 μm). Superotemporal and inferotemporal PRACs in the visual field-affected hemifield were narrower than those in the unaffected hemifield in NTG group ( P ≤0.004). Temporal PRACs in the RNFL unaffected hemifield were significantly narrower than in healthy eyes ( P <0.001). Superotemporal PRAC showed a significant correlation with superior RNFLT (β=0.659, P <0.001), and a similar relationship was found between inferotemporal PRAC and inferior RNFLT (β=0.227, P =0.015). The diagnostic capability of temporal PRACs was satisfactory (superotemporal PRAC; AUROC 0.983, cut-off value 84.7 μm, inferotemporal PRAC; AUROC 0.946, cut-off value 94.2 μm). Conclusions PRAC and infero temporal PRAC are valid parameters for discriminating patients with NTG.

scholarly journals Development of an Indirect ELISA Based on Spike Protein to Detect Antibodies against Feline Coronavirus

Viruses ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 2496
Author(s):  
Bo Dong ◽  
Gaoqiang Zhang ◽  
Xiaodong Zhang ◽  
Xufei Chen ◽  
Meiling Zhang ◽  
...  
Keyword(s):  
Operating Characteristic ◽  
Characteristic Curve ◽  
Systemic Disease ◽  
Analysis Data ◽  
Spike Protein ◽  
Diagnostic Tools ◽  
Enzyme Linked Immunosorbent Assay ◽  
Serum Samples ◽  
Pathogenic Virus ◽  
Feline Coronavirus

Feline coronavirus (FCoV) is a pathogenic virus commonly found in cats that causes a benign enteric illness and fatal systemic disease, feline infectious peritonitis. The development of serological diagnostic tools for FCoV is helpful for clinical diagnosis and epidemiological investigation. Therefore, this study aimed to develop an indirect enzyme-linked immunosorbent assay (iELISA) to detect antibodies against FCoV using histidine-tagged recombinant spike protein. FCoV S protein (1127–1400 aa) was expressed and used as an antigen to establish an ELISA. Mice and rabbits immunized with the protein produced antibodies that were recognized and bound to the protein. The intra-assay coefficient of variation (CV) was 1.15–5.04% and the inter-assay CV was 4.28–15.13%, suggesting an acceptable repeatability. iELISA did not cross-react with antisera against other feline viruses. The receiver operating characteristic curve analysis revealed an 86.7% sensitivity and 93.3% specificity for iELISA. Serum samples (n = 107) were tested for anti-FCoV antibodies, and 70.09% of samples were positive for antibodies against FCoV. The iELISA developed in our study can be used to measure serum FCoV antibodies due to its acceptable repeatability, sensitivity, and specificity. Additionally, field sample analysis data demonstrated that FCoV is highly prevalent in cat populations in Fujian province, China.

Sign in / Sign up

Export Citation Format

Share Document