Glaucoma Expert-Level Detection of Angle Closure in Goniophotographs With Convolutional Neural Networks: The Chinese American Eye Study.

PURPOSE: To compare the performance of a novel convolutional neural network (CNN) classifier and human graders in detecting angle closure in EyeCam (Clarity Medical Systems, Pleasanton, California, USA) goniophotographs. DESIGN: Retrospective cross-sectional study. METHODS: Subjects from the Chinese American Eye Study underwent EyeCam goniophotography in 4 angle quadrants. A CNN classifier based on the ResNet-50 architecture was trained to detect angle closure, defined as inability to visualize the pigmented trabecular meshwork, using reference labels by a single experienced glaucoma specialist. The performance of the CNN classifier was assessed using an independent test dataset and reference labels by the single glaucoma specialist or a panel of 3 glaucoma specialists. This performance was compared to that of 9 human graders with a range of clinical experience. Outcome measures included area under the receiver operating characteristic curve (AUC) metrics and Cohen kappa coefficients in the binary classification of open or closed angle. RESULTS: The CNN classifier was developed using 29,706 open and 2,929 closed angle images. The independent test dataset was composed of 600 open and 400 closed angle images. The CNN classifier achieved excellent performance based on single-grader (AUC = 0.969) and consensus (AUC = 0.952) labels. The agreement between the CNN classifier and consensus labels (κ = 0.746) surpassed that of all non-reference human graders (κ = 0.578-0.702). Human grader agreement with consensus labels improved with clinical experience (P = 0.03). CONCLUSION: A CNN classifier can effectively detect angle closure in goniophotographs with performance comparable to that of an experienced glaucoma specialist. This provides an automated method to support remote detection of patients at risk for primary angle closure glaucoma.

DISEASE CLASSIFICATION OF MACULAR OPTICAL COHERENCE TOMOGRAPHY SCANS USING DEEP LEARNING SOFTWARE: Validation on Independent, Multicenter Data.

PURPOSE: To evaluate Pegasus optical coherence tomography (OCT), a clinical decision support software for the identification of features of retinal disease from macula OCT scans, across heterogenous populations involving varying patient demographics, device manufacturers, acquisition sites, and operators. METHODS: Five thousand five hundred and eighty-eight normal and anomalous macular OCT volumes (162,721 B-scans), acquired at independent centers in five countries, were processed using the software. Results were evaluated against ground truth provided by the data set owners. RESULTS: Pegasus-OCT performed with areas under the curve of the receiver operating characteristic of at least 98% for all data sets in the detection of general macular anomalies. For scans of sufficient quality, the areas under the curve of the receiver operating characteristic for general age-related macular degeneration and diabetic macular edema detection were found to be at least 99% and 98%, respectively. CONCLUSION: The ability of a clinical decision support system to cater for different populations is key to its adoption. Pegasus-OCT was shown to be able to detect age-related macular degeneration, diabetic macular edema, and general anomalies in OCT volumes acquired across multiple independent sites with high performance. Its use thus offers substantial promise, with the potential to alleviate the burden of growing demand in eye care services caused by retinal disease.

Computational pathology definitions, best practices, and recommendations for regulatory guidance: a white paper from the Digital Pathology Association.

In this white paper, experts from the Digital Pathology Association (DPA) define terminology and concepts in the emerging field of computational pathology, with a focus on its application to histology images analyzed together with their associated patient data to extract information. This review offers a historical perspective and describes the potential clinical benefits from research and applications in this field, as well as significant obstacles to adoption. Best practices for implementing computational pathology workflows are presented. These include infrastructure considerations, acquisition of training data, quality assessments, as well as regulatory, ethical, and cyber-security concerns. Recommendations are provided for regulators, vendors, and computational pathology practitioners in order to facilitate progress in the field. © 2019 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of Pathological Society of Great Britain and Ireland.

Medical Devices; Hematology and Pathology Devices; Classification of the Whole Slide Imaging System. Final order.

The Food and Drug Administration (FDA or we) is classifying the whole slide imaging system into class II (special controls). The special controls that apply to the device type are identified in this order and will be part of the codified language for the whole slide imaging system's classification. We are taking this action because we have determined that classifying the device into class II (special controls) will provide a reasonable assurance of safety and effectiveness of the device. We believe this action will also enhance patients' access to beneficial innovative devices, in part by reducing regulatory burdens.

What (not) to expect when classifying rare events.

When building classifiers, it is natural to require that the classifier correctly estimates the event probability (Constraint 1), that it has equal sensitivity and specificity (Constraint 2) or that it has equal positive and negative predictive values (Constraint 3). We prove that in the balanced case, where there is equal proportion of events and non-events, any classifier that satisfies one of these constraints will always satisfy all. Such unbiasedness of events and non-events is much more difficult to achieve in the case of rare events, i.e. the situation in which the proportion of events is (much) smaller than 0.5. Here, we prove that it is impossible to meet all three constraints unless the classifier achieves perfect predictions. Any non-perfect classifier can only satisfy at most one constraint, and satisfying one constraint implies violating the other two constraints in a specific direction. Our results have implications for classifiers optimized using g-means or F1-measure, which tend to satisfy Constraints 2 and 1, respectively. Our results are derived from basic probability theory and illustrated with simulations based on some frequently used classifiers.

Medical Devices; Neurological Devices; Classification of the Computerized Cognitive Assessment Aid for Concussion. Final order.

The Food and Drug Administration (FDA) is classifying the Computerized Cognitive Assessment Aid for Concussion into class II (special controls). The special controls that will apply to the device are identified in this order and will be part of the codified language for the computerized cognitive assessment aid for concussion's classification. The Agency is classifying the device into class II (special controls) in order to provide a reasonable assurance of safety and effectiveness of the device.

Medical Devices; Neurological Devices; Classification of the Computerized Cognitive Assessment Aid. Final order.

The Food and Drug Administration (FDA) is classifying the computerized cognitive assessment aid into class II (special controls). The special controls that will apply to the device are identified in this order, and will be part of the codified language for the computerized cognitive assessment aid's classification. The Agency is classifying the device into class II (special controls) in order to provide a reasonable assurance of safety and effectiveness of the device.

Clinical Documents Clustering Based on Medication/Symptom Names Using Multi-View Nonnegative Matrix Factorization.

Clinical documents are rich free-text data sources containing valuable medication and symptom information, which have a great potential to improve health care. In this paper, we build an integrating system for extracting medication names and symptom names from clinical notes. Then we apply nonnegative matrix factorization (NMF) and multi-view NMF to cluster clinical notes into meaningful clusters based on sample-feature matrices. Our experimental results show that multi-view NMF is a preferable method for clinical document clustering. Moreover, we find that using extracted medication/symptom names to cluster clinical documents outperforms just using words.

Automatic characterization of classic choroidal neovascularization by using AdaBoost for supervised learning.

PURPOSE: To provide a computer-aided visualization tool for accurate diagnosis and quantification of choroidal neovascularization (CNV) on the basis of fluorescence leakage characteristics. METHODS: All image frames of a fluorescein angiography (FA) sequence are first aligned and mapped to a global space. To automatically determine the severity of each pixel in the global space and hence the extent of CNV, the system matches the intensity variation of each set of spatially corresponding pixels across the sequence with the targeted leakage pattern, learned from a sampled population graded by a retina specialist. The learning strategy, known as the AdaBoost algorithm, has 12 classifiers for 12 features that summarize the variation in fluorescence intensity over time. Given a new sequence, the severity map image is generated using the contribution scores of the 12 classifiers. Initialized with points of low and high severity, regions of CNV are delineated using the random walk algorithm. RESULTS: A dataset of 33 FA sequences of classic CNV showed the average accuracy of CNV delineation to be 83.26%. In addition, the 30- to 60-second interval provided the most reliable information for differentiating CNV from the background. Using eight sequences of multiple visits of four patients for evaluation of the postphotodynamic therapy (PDT), the statistics derived from the segmented regions correlate closely with the clinical observed changes. CONCLUSIONS: The clinician can easily visualize the temporal characteristics of CNV fluorescence leakage using the severity map, which is a two-dimensional summary of a complete FA sequence. The computer-aided tool allows objective evaluation and computation of statistical data from the automatic delineation for surgical assessment.

Diagnosing scrapie in sheep: a classification experiment.

Scrapie is a neuro-degenerative disease in small ruminants. A data set of 3113 records of sheep reported to the Scrapie Notifications Database in Great Britain has been studied. Clinical signs were recorded as present/absent in each animal by veterinary officials (VO) and a post-mortem diagnosis was made. In an attempt to detect healthy animals within the set of suspects using only the clinical signs, 18 classification methods were applied ranging from simple linear classifiers to classifier ensembles such as Bagging, AdaBoost and Random Forests. The results suggest that the clinical classification by the VO was adequate as no further differentiation within the set of suspects was feasible.

Web-based triage in a college health setting.

The authors describe the initiation and use of a Web-based triage system in a college health setting. During the first 4 months of implementation, the system recorded 1,290 encounters. More women accessed the system (70%); the average age was 21.8 years. The Web-based triage system advised the majority of students to seek care within 24 hours; however, it recommended self-care management in 22.7% of encounters. Sore throat was the most frequent chief complaint (14.2%). A subset of 59 students received treatment at student health services after requesting an appointment via e-mail. The authors used kappa statistics to compare congruence between chief complaint and 24/7 WebMed classification (kappa = .94), between chief complaint and student health center diagnosis (kappa = .91), and between 24/7 WebMed classification and student health center diagnosis (kappa = .89). Initial evaluation showed high use and good accuracy of Web-based triage. This service provides education and advice to students about their health care concerns.

Comparison of machine learning and traditional classifiers in glaucoma diagnosis.

Glaucoma is a progressive optic neuropathy with characteristic structural changes in the optic nerve head reflected in the visual field. The visual-field sensitivity test is commonly used in a clinical setting to evaluate glaucoma. Standard automated perimetry (SAP) is a common computerized visual-field test whose output is amenable to machine learning. We compared the performance of a number of machine learning algorithms with STATPAC indexes mean deviation, pattern standard deviation, and corrected pattern standard deviation. The machine learning algorithms studied included multilayer perceptron (MLP), support vector machine (SVM), and linear (LDA) and quadratic discriminant analysis (QDA), Parzen window, mixture of Gaussian (MOG), and mixture of generalized Gaussian (MGG). MLP and SVM are classifiers that work directly on the decision boundary and fall under the discriminative paradigm. Generative classifiers, which first model the data probability density and then perform classification via Bayes' rule, usually give deeper insight into the structure of the data space. We have applied MOG, MGG, LDA, QDA, and Parzen window to the classification of glaucoma from SAP. Performance of the various classifiers was compared by the areas under their receiver operating characteristic curves and by sensitivities (true-positive rates) at chosen specificities (true-negative rates). The machine-learning-type classifiers showed improved performance over the best indexes from STATPAC. Forward-selection and backward-elimination methodology further improved the classification rate and also has the potential to reduce testing time by diminishing the number of visual-field location measurements.

Comparing machine learning classifiers for diagnosing glaucoma from standard automated perimetry.

PURPOSE: To determine which machine learning classifier learns best to interpret standard automated perimetry (SAP) and to compare the best of the machine classifiers with the global indices of STATPAC 2 and with experts in glaucoma. METHODS: Multilayer perceptrons (MLP), support vector machines (SVM), mixture of Gaussian (MoG), and mixture of generalized Gaussian (MGG) classifiers were trained and tested by cross validation on the numerical plot of absolute sensitivity plus age of 189 normal eyes and 156 glaucomatous eyes, designated as such by the appearance of the optic nerve. The authors compared performance of these classifiers with the global indices of STATPAC, using the area under the ROC curve. Two human experts were judged against the machine classifiers and the global indices by plotting their sensitivity-specificity pairs. RESULTS: MoG had the greatest area under the ROC curve of the machine classifiers. Pattern SD (PSD) and corrected PSD (CPSD) had the largest areas under the curve of the global indices. MoG had significantly greater ROC area than PSD and CPSD. Human experts were not better at classifying visual fields than the machine classifiers or the global indices. CONCLUSIONS: MoG, using the entire visual field and age for input, interpreted SAP better than the global indices of STATPAC. Machine classifiers may augment the global indices of STATPAC.

Computer-aided detection and diagnosis of breast cancer.

The limitations of radiologists when interpreting mammogram examinations provides a reasonable, if not compelling, basis for application of computer techniques that have the potential to improve diagnostic performance. Computer algorithms, at their present state of development, show great promise for clinical use. It can be expected that such use will only improve as computer technology and computer methods continue to become more formidable. The eventual role of computers in mammographic detection and diagnosis has not been fully defined, but their effect on practice may one day be very significant.

Spectroscopic diagnosis of esophageal cancer: new classification model, improved measurement system.

Laser-induced fluorescence spectroscopy was used to measure fluorescence emission of normal and malignant tissue during endoscopy in patients with esophageal cancer and volunteers with normal esophagus. The spectroscopy system consisted of a nitrogen-pumped dye-laser tuned at 410 nm for excitation source, an optical multichannel analyzer for spectrum analysis, and a fiberoptic probe designed for both the delivery of excitation light and the collection of fluorescence emission from tissue. The fluorescence lineshape of each spectrum was determined and sampled at 15-nm intervals from 430 to 716 nm. A calibration set of spectra from normal and malignant spectra was selected. Using stepwise discriminate analysis, significant wavelengths that separated normal from malignant spectra were selected. The intensities at these wavelengths were used to formulate a classification model using linear discriminate analysis. The model was then used to classify additional tissue spectra from 26 malignant and 108 normal sites into either normal or malignant spectra. A sensitivity of 100% and specificity of 98% were obtained.

Two-level classification schemes in medical diagnostics.

A two-level classifier for medical applications is considered. Such classifiers are expected to yield a more precise result than classical one-level classifiers. The underlying idea for two-level classification is supported by the routine practice of physicians to confirm the diagnosis by several data-driven inferences. An overview of the types of the two-level classifiers is presented. The competitive two-level classifier is emphasized. Three examples with real clinical data are presented from the fields of cardiology, aviation medicine, and neonatology.