Addressing healthcare disparities in homeless neurosurgical patients: A comprehensive literature review on strategies for equitable care and improved outcomes.

Background: Homelessness is a growing concern in the US, with 3.5 million people experiencing it annually and 600,000 on any given night. Homeless individuals face increased vulnerability to 30-day hospital readmissions and higher mortality rates, straining the healthcare system and exacerbating existing disparities. This study aims to inform neurosurgeons on evidence-based strategies to reduce readmission and mortality rates among homeless patients by reviewing the literature on the impact of medical respite on 30-day readmission rates. The study aims to gauge the efficacy of medical respite in reducing hospital readmissions and improving health outcomes for homeless individuals. Methods: A comprehensive literature search was conducted across PubMed, Embase/Medline, and Cochrane databases, as well as consulting the National Institute for Medical Respite Care and the Department of Health Care Access and Information. Ten articles were chosen from an initial 296 to investigate the impact of respite programs on readmission rates among homeless patients. Results: Homeless patients experience high readmission rates due to various factors. Interventions such as respite programs and a comprehensive approach to healthcare can lower these rates. Collaboration between hospitals and medical respites has proven particularly effective. Conclusion: Inadequate healthcare for homeless individuals leads to increased readmissions, longer hospital stays, and higher costs. Medical respites are a viable solution, but limited resources hamper their effectiveness. Therefore, it is crucial to facilitate cooperation between hospitals, respites, and other entities. Future research should focus on disparity in neurosurgical procedures and explore alternative services. An interdisciplinary approach is key to addressing healthcare inequalities.

Leukocyte differential gene expression prognostic value for high versus low seizure frequency in temporal lobe epilepsy.

BACKGROUND: This study was performed to test the hypothesis that systemic leukocyte gene expression has prognostic value differentiating low from high seizure frequency refractory temporal lobe epilepsy (TLE). METHODS: A consecutive series of patients with refractory temporal lobe epilepsy was studied. Based on a median baseline seizure frequency of 2.0 seizures per month, low versus high seizure frequency was defined as ≤ 2 seizures/month and > 2 seizures/month, respectively. Systemic leukocyte gene expression was analyzed for prognostic value for TLE seizure frequency. All differentially expressed genes were analyzed, with Ingenuity® Pathway Analysis (IPA®) and Reactome, to identify leukocyte gene expression and biological pathways with prognostic value for seizure frequency. RESULTS: There were ten males and six females with a mean age of 39.4 years (range: 16 to 62 years, standard error of mean: 3.6 years). There were five patients in the high and eleven patients in the low seizure frequency cohorts, respectively. Based on a threshold of twofold change (p < 0.001, FC > 2.0, FDR < 0.05) and expression within at least two pathways from both Reactome and Ingenuity® Pathway Analysis (IPA®), 13 differentially expressed leukocyte genes were identified which were all over-expressed in the low when compared to the high seizure frequency groups, including NCF2, HMOX1, RHOB, FCGR2A, PRKCD, RAC2, TLR1, CHP1, TNFRSF1A, IFNGR1, LYN, MYD88, and CASP1. Similar analysis identified four differentially expressed genes which were all over-expressed in the high when compared to the low seizure frequency groups, including AK1, F2R, GNB5, and TYMS. CONCLUSIONS: Low and high seizure frequency TLE are predicted by the respective upregulation and downregulation of specific leukocyte genes involved in canonical pathways of neuroinflammation, oxidative stress and lipid peroxidation, GABA (γ-aminobutyric acid) inhibition, and AMPA and NMDA receptor signaling. Furthermore, high seizure frequency-TLE is distinguished prognostically from low seizure frequency-TLE by differentially increased specific leukocyte gene expression involved in GABA inhibition and NMDA receptor signaling. High and low seizure frequency patients appear to represent two mechanistically different forms of temporal lobe epilepsy based on leukocyte gene expression.

Emotional intelligence in neurosurgery: Mitigating burnout and enhancing performance.

Background: This study underscores the high burnout rates among physicians, particularly surgical residents, attributing it to the demanding health-care ecosystem. It highlights the negative impacts of burnout, such as medical errors and increased health-care costs, while exploring the potential mitigating role of emotional intelligence (EI) and mindfulness. The research aimed to analyze the existing literature on EI in neurosurgery, focusing on its relationship with physician burnout and its potential role in healthcare leadership and residency training programs. Methods: A comprehensive literature review was conducted using multiple databases, including PubMed, OVID Embase, and OVID Medline, using the keywords "Emotional Intelligence" and "neurosurgery." The search duration spanned from each database's inception to June 2023. Results: The review highlighted various studies emphasizing the importance of integrating EI and mindfulness training into medical education and leadership, suggesting that a balance between technical competencies and interpersonal skills are critical. It identified personal integrity, effective communication, professional ethics, pursuit of excellence, relationship building, and critical thinking as key competencies for health-care leadership. Conclusion: EI and a growth mindset play a critical role in managing burnout, enhancing job satisfaction and performance, and promoting effective healthcare leadership. The review, however, acknowledges certain limitations such as small sample sizes, single-institution experiences, potential biases, and inconsistencies in burnout parameters and EI measurement tools. Despite these, it points toward potential areas for future investigation and highlights the importance of standardized EI measurement tools and robust quantitative assessment methods.

Accuracy of Artificial Intelligence in Estimating Best-Corrected Visual Acuity From Fundus Photographs in Eyes With Diabetic Macular Edema.

Importance: Best-corrected visual acuity (BCVA) is a measure used to manage diabetic macular edema (DME), sometimes suggesting development of DME or consideration of initiating, repeating, withholding, or resuming treatment with anti-vascular endothelial growth factor. Using artificial intelligence (AI) to estimate BCVA from fundus images could help clinicians manage DME by reducing the personnel needed for refraction, the time presently required for assessing BCVA, or even the number of office visits if imaged remotely. Objective: To evaluate the potential application of AI techniques for estimating BCVA from fundus photographs with and without ancillary information. Design, Setting, and Participants: Deidentified color fundus images taken after dilation were used post hoc to train AI systems to perform regression from image to BCVA and to evaluate resultant estimation errors. Participants were patients enrolled in the VISTA randomized clinical trial through 148 weeks wherein the study eye was treated with aflibercept or laser. The data from study participants included macular images, clinical information, and BCVA scores by trained examiners following protocol refraction and VA measurement on Early Treatment Diabetic Retinopathy Study (ETDRS) charts. Main Outcomes: Primary outcome was regression evaluated by mean absolute error (MAE); the secondary outcome included percentage of predictions within 10 letters, computed over the entire cohort as well as over subsets categorized by baseline BCVA, determined from baseline through the 148-week visit. Results: Analysis included 7185 macular color fundus images of the study and fellow eyes from 459 participants. Overall, the mean (SD) age was 62.2 (9.8) years, and 250 (54.5%) were male. The baseline BCVA score for the study eyes ranged from 73 to 24 letters (approximate Snellen equivalent 20/40 to 20/320). Using ResNet50 architecture, the MAE for the testing set (n = 641 images) was 9.66 (95% CI, 9.05-10.28); 33% of the values (95% CI, 30%-37%) were within 0 to 5 letters and 28% (95% CI, 25%-32%) within 6 to 10 letters. For BCVA of 100 letters or less but more than 80 letters (20/10 to 20/25, n = 161) and 80 letters or less but more than 55 letters (20/32 to 20/80, n = 309), the MAE was 8.84 letters (95% CI, 7.88-9.81) and 7.91 letters (95% CI, 7.28-8.53), respectively. Conclusions and Relevance: This investigation suggests AI can estimate BCVA directly from fundus photographs in patients with DME, without refraction or subjective visual acuity measurements, often within 1 to 2 lines on an ETDRS chart, supporting this AI concept if additional improvements in estimates can be achieved.

Spinal cord stimulation for genitofemoral neuropathy: A case report and review of the literature.

Background: Chronic testicular pain due to genitofemoral neuropathy often becomes refractory to conservative medical therapy. Neurostimulation is a potentially useful treatment option, should the neuropathic pain remain refractory to more invasive procedures such as orchiectomy. We provide a case report of spinal cord stimulation (SCS) for successful treatment of genitofemoral neuropathy and have also reviewed the literature to find similar cases which required a similar treatment paradigm. Case Description: A 42-year-old male underwent SCS for refractory testicular and groin pain. SCS through a four-column, 2 × 8 contact neurostimulator paddle lead, was implanted in the mid-thoracic-9 (T9) vertebral level, providing > 50% testicular pain relief with a decrease in visual analog scale scores from 8-10/10 to 3-4/10. The patient required one adjustment to the stimulation parameters at the time of the 6 weeks follow-up visit due to over-stimulation. He then continued to experience >50% resolution in pain 9 months later. A review of the literature yielded only two similar cases that successfully utilized SCS for treatment of chronic testicular pain. Conclusion: SCS should be considered as a possible treatment option for patients with chronic testicular pain localized to the genitofemoral nerve distribution.

Assessment of germinal matrix hemorrhage on head ultrasound with deep learning algorithms.

BACKGROUND: Germinal matrix hemorrhage-intraventricular hemorrhage is among the most common intracranial complications in premature infants. Early detection is important to guide clinical management for improved patient prognosis. OBJECTIVE: The purpose of this study was to assess whether a convolutional neural network (CNN) can be trained via transfer learning to accurately diagnose germinal matrix hemorrhage on head ultrasound. MATERIALS AND METHODS: Over a 10-year period, 400 head ultrasounds performed in patients ages 6 months or younger were reviewed. Key sagittal images at the level of the caudothalamic groove were obtained from 200 patients with germinal matrix hemorrhage and 200 patients without hemorrhage; all images were reviewed by a board-certified pediatric radiologist. One hundred cases were randomly allocated from the total for validation and an additional 100 for testing of a CNN binary classifier. Transfer learning and data augmentation were used to train the model. RESULTS: The median age of patients was 0 weeks old with a median gestational age of 30 weeks. The final trained CNN model had a receiver operating characteristic area under the curve of 0.92 on the validation set and accuracy of 0.875 on the test set, with 95% confidence intervals of [0.86, 0.98] and [0.81, 0.94], respectively. CONCLUSION: A CNN trained on a small set of images with data augmentation can detect germinal matrix hemorrhage on head ultrasounds with strong accuracy.

TARA: Training and Representation Alteration for AI Fairness and Domain Generalization.

We propose a novel method for enforcing AI fairness with respect to protected or sensitive factors. This method uses a dual strategy performing training and representation alteration (TARA) for the mitigation of prominent causes of AI bias. It includes the use of representation learning alteration via adversarial independence to suppress the bias-inducing dependence of the data representation from protected factors and training set alteration via intelligent augmentation to address bias-causing data imbalance by using generative models that allow the fine control of sensitive factors related to underrepresented populations via domain adaptation and latent space manipulation. When testing our methods on image analytics, experiments demonstrate that TARA significantly or fully debiases baseline models while outperforming competing debiasing methods that have the same amount of information-for example, with (% overall accuracy, % accuracy gap) = (78.8, 0.5) versus the baseline method's score of (71.8, 10.5) for Eye-PACS, and (73.7, 11.8) versus (69.1, 21.7) for CelebA. Furthermore, recognizing certain limitations in current metrics used for assessing debiasing performance, we propose novel conjunctive debiasing metrics. Our experiments also demonstrate the ability of these novel metrics in assessing the Pareto efficiency of the proposed methods.

Transrectal ultrasound-guided prostate needle biopsy remains a safe method in confirming a prostate cancer diagnosis: a multicentre Australian analysis of infection rates.

PURPOSE: Worldwide, transrectal ultrasound-guided prostate needle remains the most common method of diagnosing prostate cancer. Due to high infective complications reported, some have suggested it is now time to abandon this technique in preference of a trans-perineal approach. The aim of this study was to report on the infection rates following transrectal ultrasound-guided prostate needle biopsy in multiple Australian centres. MATERIALS AND METHODS: Data were collected from seven Australian centres across four states and territories that undertake transrectal ultrasound-guided prostate needle biopsies for the diagnosis of prostate cancer, including major metropolitan and regional centres. In four centres, the data were collected prospectively. Rates of readmissions due to infection, urosepsis resulting in intensive care admission and mortality were recorded. RESULTS: 12,240 prostate biopsies were performed in seven Australian centres between July 1998 and December 2020. There were 105 readmissions for infective complications with rates between centres ranging from 0.19 to 2.60% and an overall rate of 0.86%. Admission to intensive care with sepsis ranged from 0 to 0.23% and overall 0.03%. There was no mortality in the 12,240 cases. CONCLUSION: Infective complications following transrectal ultrasound-guided prostate needle biopsies are very low, occurring in less than 1% of 12,240 biopsies. Though this study included a combination of both prospective and retrospective data and did not offer a comparison with a trans-perineal approach, TRUS prostate biopsy is a safe means of obtaining a prostate cancer diagnosis. Further prospective studies directly comparing the techniques are required prior to abandoning TRUS based upon infectious complications.

Addressing Artificial Intelligence Bias in Retinal Diagnostics.

Purpose: This study evaluated generative methods to potentially mitigate artificial intelligence (AI) bias when diagnosing diabetic retinopathy (DR) resulting from training data imbalance or domain generalization, which occurs when deep learning systems (DLSs) face concepts at test/inference time they were not initially trained on. Methods: The public domain Kaggle EyePACS dataset (88,692 fundi and 44,346 individuals, originally diverse for ethnicity) was modified by adding clinician-annotated labels and constructing an artificial scenario of data imbalance and domain generalization by disallowing training (but not testing) exemplars for images of retinas with DR warranting referral (DR-referable) from darker-skin individuals, who presumably have greater concentration of melanin within uveal melanocytes, on average, contributing to retinal image pigmentation. A traditional/baseline diagnostic DLS was compared against new DLSs that would use training data augmented via generative models for debiasing. Results: Accuracy (95% confidence intervals [CIs]) of the baseline diagnostics DLS for fundus images of lighter-skin individuals was 73.0% (66.9% to 79.2%) versus darker-skin of 60.5% (53.5% to 67.3%), demonstrating bias/disparity (delta = 12.5%; Welch t-test t = 2.670, P = 0.008) in AI performance across protected subpopulations. Using novel generative methods for addressing missing subpopulation training data (DR-referable darker-skin) achieved instead accuracy, for lighter-skin, of 72.0% (65.8% to 78.2%), and for darker-skin, of 71.5% (65.2% to 77.8%), demonstrating closer parity (delta = 0.5%) in accuracy across subpopulations (Welch t-test t = 0.111, P = 0.912). Conclusions: Findings illustrate how data imbalance and domain generalization can lead to disparity of accuracy across subpopulations, and show that novel generative methods of synthetic fundus images may play a role for debiasing AI. Translational Relevance: New AI methods have possible applications to address potential AI bias in DR diagnostics from fundus pigmentation, and potentially other ophthalmic DLSs too.

Low-Shot Deep Learning of Diabetic Retinopathy With Potential Applications to Address Artificial Intelligence Bias in Retinal Diagnostics and Rare Ophthalmic Diseases.

Importance: Recent studies have demonstrated the successful application of artificial intelligence (AI) for automated retinal disease diagnostics but have not addressed a fundamental challenge for deep learning systems: the current need for large, criterion standard-annotated retinal data sets for training. Low-shot learning algorithms, aiming to learn from a relatively low number of training data, may be beneficial for clinical situations involving rare retinal diseases or when addressing potential bias resulting from data that may not adequately represent certain groups for training, such as individuals older than 85 years. Objective: To evaluate whether low-shot deep learning methods are beneficial when using small training data sets for automated retinal diagnostics. Design, Setting, and Participants: This cross-sectional study, conducted from July 1, 2019, to June 21, 2020, compared different diabetic retinopathy classification algorithms, traditional and low-shot, for 2-class designations (diabetic retinopathy warranting referral vs not warranting referral). The public domain EyePACS data set was used, which originally included 88 692 fundi from 44 346 individuals. Statistical analysis was performed from February 1 to June 21, 2020. Main Outcomes and Measures: The performance (95% CIs) of the various AI algorithms was measured via receiver operating curves and their area under the curve (AUC), precision recall curves, accuracy, and F1 score, evaluated for different training data sizes, ranging from 5120 to 10 samples per class. Results: Deep learning algorithms, when trained with sufficiently large data sets (5120 samples per class), yielded comparable performance, with an AUC of 0.8330 (95% CI, 0.8140-0.8520) for a traditional approach (eg, fined-tuned ResNet), compared with low-shot methods (AUC, 0.8348 [95% CI, 0.8159-0.8537]) (using self-supervised Deep InfoMax [our method denoted as DIM]). However, when far fewer training images were available (n = 160), the traditional deep learning approach had an AUC decreasing to 0.6585 (95% CI, 0.6332-0.6838) and was outperformed by a low-shot method using self-supervision with an AUC of 0.7467 (95% CI, 0.7239-0.7695). At very low shots (n = 10), the traditional approach had performance close to chance, with an AUC of 0.5178 (95% CI, 0.4909-0.5447) compared with the best low-shot method (AUC, 0.5778 [95% CI, 0.5512-0.6044]). Conclusions and Relevance: These findings suggest the potential benefits of using low-shot methods for AI retinal diagnostics when a limited number of annotated training retinal images are available (eg, with rare ophthalmic diseases or when addressing potential AI bias).

AI-based detection of erythema migrans and disambiguation against other skin lesions.

This study examines the use of AI methods and deep learning (DL) for prescreening skin lesions and detecting the characteristic erythema migrans rash of acute Lyme disease. Accurate identification of erythema migrans allows for early diagnosis and treatment, which avoids the potential for later neurologic, rheumatologic, and cardiac complications of Lyme disease. We develop and test several deep learning models for detecting erythema migrans versus several other clinically relevant skin conditions, including cellulitis, tinea corporis, herpes zoster, erythema multiforme, lesions due to tick bites and insect bites, as well as non-pathogenic normal skin. We consider a set of clinically-relevant binary and multiclass classification problems of increasing complexity. We train the DL models on a combination of publicly available images and test on public images as well as images obtained in the clinical setting. We report performance metrics that measure agreement with a gold standard, as well as a receiver operating characteristic curve and associated area under the curve. On public images, we find that the DL system has an accuracy ranging from 71.58% (and 95% error margin equal to 3.77%) for an 8-class problem of EM versus 7 other classes including other skin pathologies, insect bites and normal skin, to 94.23% (3.66%) for a binary problem of EM vs. non-pathological skin. On clinical images of affected individuals, the DL system has a sensitivity of 88.55% (2.39%). These results suggest that a DL system can help in prescreening and referring individuals to physicians for earlier diagnosis and treatment, in the presence of clinically relevant confusers, thereby reducing further complications and morbidity.

The Neural Sulcus of the Cervical Vertebrae: A Review of Its Anatomy and Surgical Perspectives.

The neural sulcus is a bony channel that spans the transverse process in the subaxial cervical spine. It is located between the anterior and posterior tubercles on either side of the transverse foramen, housing the spinal nerve as it passes through the intervertebral foramina. Although numerous studies have evaluated the anatomy of the cervical spine, very little data on detailed anatomy of the neural sulcus and its implication in cervical spine surgery exist. Here, we review the anatomy of the neural sulcus and surgical considerations. The neural sulcus has important surgical implications, and knowledge of its anatomy is important in considering and planning posterior cervical segmented instrumentation. This increases the ability of the neurosurgeon to choose the best suitable surgical approach to the subaxial cervical spine, allowing good outcomes for the patient.

Social Media in Neurosurgery: Using ResearchGate.

BACKGROUND: Neurosurgery is a unique field, which would benefit greatly from increased global collaboration, furthering research efforts. ResearchGate is a social media platform geared toward scientists and researchers. OBJECTIVE: This study evaluated the use of ResearchGate for neurosurgical research collaboration and compared the ResearchGate score with more classic bibliometrics. ResearchGate is a unifying social platform that can strengthen global research collaboration (e.g., data sharing) in the neurosurgery community. METHODS: Publicly available metrics on 3718 neurosurgery clinical faculty and residents in Canada and the United States were obtained from the American Association of Neurological Surgeons Web site. The following metrics were collected: program name, clinician name, sex, attending (yes or no), resident (yes or no), postgraduate year (if resident), and ResearchGate profile (yes or no). ResearchGate score and its components and h index excluding self-citations were collected. Fellows were not included. RESULTS: Of the 3718 total individuals included, 1338 (36.0%) were present on ResearchGate, comprising 181 women (13.5%) and 1157 men (86.5%). Women and men were present in similar proportions (33.8% of women and 36.3% of men) (χ2 [1, N = 3718] = 1.26; P = 0.26). More faculty were present on ResearchGate than residents (62.4%) (χ2 [1, N = 3718] = 11.42; P = 0.001). A strong positive monotonic correlation between h index and ResearchGate score was shown (rs [1292] = 0.93; P < 0.0005). More than 400 international departments were determined. CONCLUSIONS: ResearchGate may be a useful platform to increase neurosurgical networking and research collaboration. Its novel bibliometrics are strongly correlated with more classic platforms.

Automated detection of erythema migrans and other confounding skin lesions via deep learning.

Lyme disease can lead to neurological, cardiac, and rheumatologic complications when untreated. Timely recognition of the erythema migrans rash of acute Lyme disease by patients and clinicians is crucial to early diagnosis and treatment. Our objective in this study was to develop deep learning approaches using deep convolutional neural networks for detecting acute Lyme disease from erythema migrans images of varying quality and acquisition conditions. This study used a cross-sectional dataset of images to train a model employing a deep convolutional neural network to perform classification of erythema migrans versus other skin conditions including tinea corporis and herpes zoster, and normal, non-pathogenic skin. Evaluation of the machine's ability to classify skin types was also performed on a validation set of images. Machine performance for detecting erythema migrans was further tested against a panel of non-medical humans. Online, publicly available images of both erythema migrans and non-Lyme confounding skin lesions were mined, and combined with erythema migrans images from an ongoing, longitudinal study of participants with acute Lyme disease enrolled in 2016 and 2017 who were recruited from primary and urgent care centers. The final dataset had 1834 images, including 1718 expert clinician-curated online images from unknown individuals with erythema migrans, tinea corporis, herpes zoster, and normal skin. It also included 116 images taken of 63 research participants from the Mid-Atlantic region. Two clinicians carefully annotated all lesion images. A convenience sample of 7 non-medically-trained humans were used as a panel to compare against machine performance. We calculated several performance metrics, including accuracy and Kappa (characterizing agreement with gold standard), as well as a receiver operating characteristic curve and associated area under the curve. For detecting erythema migrans, the machine had an accuracy (95% confidence interval error margin) of 86.53% (2.70), ROCAUC of 0.9510 (0.0171) and Kappa of 0.7143. Our results suggested substantial agreement between machine and clinician criterion standard. Comparison of machine with non-medical expert human performance indicated that the machine almost always exceeded acceptable specificity, and could operate with higher sensitivity. This could have benefits for prescreening prior to physician referral, earlier treatment, and reductions in morbidity.

Assessment of Deep Generative Models for High-Resolution Synthetic Retinal Image Generation of Age-Related Macular Degeneration.

Importance: Deep learning (DL) used for discriminative tasks in ophthalmology, such as diagnosing diabetic retinopathy or age-related macular degeneration (AMD), requires large image data sets graded by human experts to train deep convolutional neural networks (DCNNs). In contrast, generative DL techniques could synthesize large new data sets of artificial retina images with different stages of AMD. Such images could enhance existing data sets of common and rare ophthalmic diseases without concern for personally identifying information to assist medical education of students, residents, and retinal specialists, as well as for training new DL diagnostic models for which extensive data sets from large clinical trials of expertly graded images may not exist. Objective: To develop DL techniques for synthesizing high-resolution realistic fundus images serving as proxy data sets for use by retinal specialists and DL machines. Design, Setting, and Participants: Generative adversarial networks were trained on 133 821 color fundus images from 4613 study participants from the Age-Related Eye Disease Study (AREDS), generating synthetic fundus images with and without AMD. We compared retinal specialists' ability to diagnose AMD on both real and synthetic images, asking them to assess image gradability and testing their ability to discern real from synthetic images. The performance of AMD diagnostic DCNNs (referable vs not referable AMD) trained on either all-real vs all-synthetic data sets was compared. Main Outcomes and Measures: Accuracy of 2 retinal specialists (T.Y.A.L. and K.D.P.) for diagnosing and distinguishing AMD on real vs synthetic images and diagnostic performance (area under the curve) of DL algorithms trained on synthetic vs real images. Results: The diagnostic accuracy of 2 retinal specialists on real vs synthetic images was similar. The accuracy of diagnosis as referable vs nonreferable AMD compared with certified human graders for retinal specialist 1 was 84.54% (error margin, 4.06%) on real images vs 84.12% (error margin, 4.16%) on synthetic images and for retinal specialist 2 was 89.47% (error margin, 3.45%) on real images vs 89.19% (error margin, 3.54%) on synthetic images. Retinal specialists could not distinguish real from synthetic images, with an accuracy of 59.50% (error margin, 3.93%) for retinal specialist 1 and 53.67% (error margin, 3.99%) for retinal specialist 2. The DCNNs trained on real data showed an area under the curve of 0.9706 (error margin, 0.0029), and those trained on synthetic data showed an area under the curve of 0.9235 (error margin, 0.0045). Conclusions and Relevance: Deep learning-synthesized images appeared to be realistic to retinal specialists, and DCNNs achieved diagnostic performance on synthetic data close to that for real images, suggesting that DL generative techniques hold promise for training humans and machines.

Deep embeddings for novelty detection in myopathy.

We address the challenge of finding anomalies in ultrasound images via deep learning, specifically applying this to screening for myopathies and finding rare presentations of myopathic disease. Among myopathic diseases, this study focuses on the use case of myositis given the spectrum of muscle involvement seen in these inflammatory muscle diseases, as well as the potential for treatment. For this study, we have developed a fully annotated dataset (called "Myositis3K") which includes 3586 images of eighty-nine individuals (35 control and 54 with myositis) acquired with informed consent. We approach this challenge as one of performing unsupervised novelty detection (ND), and use tools leveraging deep embeddings combined with several novelty scoring methods. We evaluated these various ND algorithms and compared their performance against human clinician performance, against other methods including supervised binary classification approaches, and against unsupervised novelty detection approaches using generative methods. Our best performing approach resulted in a (ROC) AUC (and 95% CI error margin) of 0.7192 (0.0164), which is a promising baseline for developing future clinical tools for unsupervised prescreening of myopathies.

Use of Deep Learning for Detailed Severity Characterization and Estimation of 5-Year Risk Among Patients With Age-Related Macular Degeneration.

Importance: Although deep learning (DL) can identify the intermediate or advanced stages of age-related macular degeneration (AMD) as a binary yes or no, stratified gradings using the more granular Age-Related Eye Disease Study (AREDS) 9-step detailed severity scale for AMD provide more precise estimation of 5-year progression to advanced stages. The AREDS 9-step detailed scale's complexity and implementation solely with highly trained fundus photograph graders potentially hampered its clinical use, warranting development and use of an alternate AREDS simple scale, which although valuable, has less predictive ability. Objective: To describe DL techniques for the AREDS 9-step detailed severity scale for AMD to estimate 5-year risk probability with reasonable accuracy. Design, Setting, and Participants: This study used data collected from November 13, 1992, to November 30, 2005, from 4613 study participants of the AREDS data set to develop deep convolutional neural networks that were trained to provide detailed automated AMD grading on several AMD severity classification scales, using a multiclass classification setting. Two AMD severity classification problems using criteria based on 4-step (AMD-1, AMD-2, AMD-3, and AMD-4 from classifications developed for AREDS eligibility criteria) and 9-step (from AREDS detailed severity scale) AMD severity scales were investigated. The performance of these algorithms was compared with a contemporary human grader and against a criterion standard (fundus photograph reading center graders) used at the time of AREDS enrollment and follow-up. Three methods for estimating 5-year risk were developed, including one based on DL regression. Data were analyzed from December 1, 2017, through April 15, 2018. Main Outcomes and Measures: Weighted κ scores and mean unsigned errors for estimating 5-year risk probability of progression to advanced AMD. Results: This study used 67 401 color fundus images from the 4613 study participants. The weighted κ scores were 0.77 for the 4-step and 0.74 for the 9-step AMD severity scales. The overall mean estimation error for the 5-year risk ranged from 3.5% to 5.3%. Conclusions and Relevance: These findings suggest that DL AMD grading has, for the 4-step classification evaluation, performance comparable with that of humans and achieves promising results for providing AMD detailed severity grading (9-step classification), which normally requires highly trained graders, and for estimating 5-year risk of progression to advanced AMD. Use of DL has the potential to assist physicians in longitudinal care for individualized, detailed risk assessment as well as clinical studies of disease progression during treatment or as public screening or monitoring worldwide.