Domain-adaptation method between acoustic-response data using different insert earphones.

Classifying acoustic responses captured through earphones offers valuable insights into nearby environments, such as whether the earphones are in or out of the ear. However, the performances of classification algorithms often suffer when applied to other devices due to domain mismatches. This study proposes a domain-adaptation method tailored for acoustic-response data from two distinct insert earphone models. The method trains a domain-adaptation function using a pair of datasets obtained from a set of acoustic loads, yielding a domain-adapted dataset suitable for training classification algorithms in a target domain. The effectiveness of this approach is validated through assessments of domain adaptation quality and resulting performance enhancements in the classification algorithm tasked with discerning whether an earphone is positioned inside or outside the ear. Importantly, our method requires significantly fewer measurements than the original dataset, reducing data collection time while providing a suitable training dataset for the target domain. Additionally, the method's reusability across future devices streamlines data collection time and efforts for the future devices.

Comparison of Patterns of Structural Progression in Primary Open Angle Glaucoma and Pseudoexfoliation Glaucoma.

PRCIS: Primary open angle glaucoma and pseudoexfoliation glaucoma showed different progression patterns of the retinal nerve fiber layer and ganglion cell-inner plexiform layer thinning in OCT-guided progression analysis. PURPOSE: To compare the patterns of progression of retinal nerve fiber layer (RNFL) and macular ganglion cell-inner plexiform layer (GCIPL) thinning by guided progression analysis (GPA) of optical coherence tomography (OCT) in primary open angle glaucoma (POAG) and pseudoexfoliation glaucoma (PXG). MATERIALS AND METHODS: The progression of RNFL and GCIPL thinning was assessed by the GPA of Cirrus HD-OCT (Carl Zeiss Meditec, Dublin, CA). By overlaying the acquired images of the RNFL and GCIPL thickness-change maps, the topographic patterns of progressive RNFL and GCIPL thinning were evaluated. The rates of progression of RNFL and GCIPL thinning were analyzed and compared between patients with POAG and those with PXG. RESULTS: Of the 248 eyes of 248 patients with POAG (175 eyes of 175 patients) or PXG (73 eyes of 73 patients) enrolled, 156 POAG eyes and 48 PXG eyes were included. Progressive RNFL thinning was significantly more common in PXG than in POAG ( P =0.005). According to the RNFL progression-frequency maps, progression appeared mainly in the superotemporal and inferotemporal areas in POAG, whereas it had invaded more into the temporal area in PXG. According to the GCIPL maps, progression was most common in the inferotemporal area in both POAG and PXG. The average progression rate of GCIPL thinning was faster in PXG than in POAG ( P =0.013), and when analyzed in 2 halves (superior/inferior), the progression rate of the inferior half was faster in PXG than in POAG ( P =0.011). CONCLUSIONS: OCT GPA showed progression patterns of RNFL and GCIPL thinning in POAG and PXG. Understanding the specific patterns of progressive RNFL and GCIPL thinning according to glaucoma type may prove helpful to glaucoma-patient treatment and monitoring.

Deep-learning-based prediction of glaucoma conversion in normotensive glaucoma suspects.

BACKGROUND/AIMS: To assess the performance of deep-learning (DL) models for prediction of conversion to normal-tension glaucoma (NTG) in normotensive glaucoma suspect (GS) patients. METHODS: Datasets of 12 458 GS eyes were reviewed. Two hundred and ten eyes (105 eyes showing NTG conversion and 105 without conversion), followed up for a minimum of 7 years during which intraocular pressure (IOP) was lower than 21 mm Hg, were included. The features of two fundus images (optic disc photography and red-free retinal nerve fibre layer (RNFL) photography) were extracted by convolutional auto encoder. The extracted features as well as 15 clinical features including age, sex, IOP, spherical equivalent, central corneal thickness, axial length, average circumpapillary RNFL thickness, systolic/diastolic blood pressure and body mass index were used to predict NTG conversion. Prediction was performed using three machine-learning classifiers (ie, XGBoost, Random Forest, Gradient Boosting) with different feature combinations. RESULTS: All three algorithms achieved high diagnostic accuracy for NTG conversion prediction. The AUCs ranged from 0.987 (95% CI 0.978 to 1.000; Random Forest trained with both fundus images and clinical features) and 0.994 (95% CI 0.984 to 1.000; XGBoost trained with both fundus images and clinical features). XGBoost showed the best prediction performance for time to NTG conversion (mean squared error, 2.24). The top three important clinical features for time-to-conversion prediction were baseline IOP, diastolic blood pressure and average circumpapillary RNFL thickness. CONCLUSION: DL models, trained with both fundus images and clinical data, showed the potential to predict whether and when normotensive GS patients will show conversion to NTG.

Automated Facial Acne Lesion Detecting and Counting Algorithm for Acne Severity Evaluation and Its Utility in Assisting Dermatologists.

BACKGROUND: Although lesion counting is an evaluation method that effectively analyzes facial acne severity, its usage is limited because of difficult implementation. OBJECTIVES: We aimed to develop and validate an automated algorithm that detects and counts acne lesions by type, and to evaluate its clinical applicability as an assistance tool through a reader test. METHODS: A total of 20,699 lesions (closed and open comedones, papules, nodules/cysts, and pustules) were manually labeled on 1213 facial images of 398 facial acne photography sets (frontal and both lateral views) acquired from 258 patients and used for training and validating algorithms based on a convolutional neural network for classifying five classes of acne lesions or for binary classification into noninflammatory and inflammatory lesions. RESULTS: In the validation dataset, the highest mean average precision was 28.48 for the binary classification algorithm. Pearson's correlation of lesion counts between algorithm and ground-truth was 0.72 (noninflammatory) and 0.90 (inflammatory), respectively. In the reader test, eight readers (100.0%) detected and counted lesions more accurately using the algorithm compared with the reader-alone evaluation. CONCLUSIONS: Overall, our algorithm demonstrated clinically applicable performance in detecting and counting facial acne lesions by type and its utility as an assistance tool for evaluating acne severity.

Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning.

Macular OCT angiography (OCTA) measurements have been reported to be useful for glaucoma diagnostics. However, research on highly myopic glaucoma is lacking, and the diagnostic value of macular OCTA measurements versus OCT parameters remains inconclusive. We aimed to evaluate the diagnostic ability of the macular microvasculature assessed with OCTA for highly myopic glaucoma and to compare it with that of macular thickness parameters, using deep learning (DL). A DL model was trained, validated and tested using 260 pairs of macular OCTA and OCT images from 260 eyes (203 eyes with highly myopic glaucoma, 57 eyes with healthy high myopia). The DL model achieved an AUC of 0.946 with the OCTA superficial capillary plexus (SCP) images, which was comparable to that with the OCT GCL+ (ganglion cell layer + inner plexiform layer; AUC, 0.982; P = 0.268) or OCT GCL++ (retinal nerve fiber layer + ganglion cell layer + inner plexiform layer) images (AUC, 0.997; P = 0.101), and significantly superior to that with the OCTA deep capillary plexus images (AUC, 0.779; P = 0.028). The DL model with macular OCTA SCP images demonstrated excellent and comparable diagnostic ability to that with macular OCT images in highly myopic glaucoma, which suggests macular OCTA microvasculature could serve as a potential biomarker for glaucoma diagnosis in high myopia.

Demographics Prediction and Heatmap Generation From OCT Images of Anterior Segment of the Eye: A Vision Transformer Model Study.

Purpose: To predict demographic characteristics from anterior segment optical coherence tomography (AS-OCT) images of eyes using a Vision Transformer (ViT) model. Methods: A total of 2970 AS-OCT images were used to train, validate, and test a ViT to predict age and sex, and 2616 images were used for height, weight, and body mass index (BMI). The main outcome measure was the area under the receiver operating characteristic curve (AUC) of the ViT. Results: The ViT achieved the largest AUC (0.910) for differentiating age ≤75 versus >75 years, followed by age ≤60 versus 60-75 versus >75 years (AUC, 0.844), and for discriminating sex (AUC, 0.665). The prediction abilities for the other demographic characteristics were lower: an AUC of 0.521 for classifying height ≤170 versus >170 cm in males and ≤155 versus >155 cm in females; 0.522 for weight <70 versus ≥70 kg in males and 0.503 for <55 versus ≥55 kg in females, and 0.517 for BMI <23 versus 23-25 versus ≥25 kg/m2. Heatmaps highlighted the area of the iridocorneal angle for its contribution to the prediction of age ≤75 versus >75 years. Conclusions: Although the ViT demonstrated a good ability to classify age from AS-OCT images, it performed poorly for sex, height, weight, and BMI. The heatmap obtained of the prediction will provide clues to understanding the age-related anterior segment changes in eyes. Translational Relevance: The ViT can determine age-related anterior segment structural changes using AS-OCT images, which will aid clinicians in the management of ocular diseases.

Patterns of Optical Coherence Tomography Imaging in Preperimetric Open Angle Glaucoma: A Comparative Study With Young-Age-Onset and Old-Age-Onset Eyes.

PRCIS: Optic coherence tomography imaging in preperimetric open angle glaucoma (OAG) differed between young-age-onset and old-age-onset eyes. Inferior and superior quadrants were thinner in young and old-age-onset eyes, respectively. Understanding the specific patterns of early glaucomatous damage based on age-at-onset may improve glaucoma diagnosis and monitoring. PURPOSE: To investigate the patterns of retinal nerve fiber layer (RNFL) and macular ganglion cell-inner plexiform layer (GCIPL) thinning in preperimetric OAG by optical coherence tomography based on age at onset ("young-age onset (<40 y)" vs. "old-age onset (≥40 y)". MATERIALS AND METHODS: The RNFL and GCIPL deviation images were acquired by Cirrus HD-optical coherence tomography, and overlaid, thus converted to a "deviation frequency map", respectively. The topographic thinning patterns and parameters of RNFL and GCIPL thickness measurements were compared. RESULTS: A total of 194 eyes of 194 patients with preperimetric OAG and 97 eyes of 97 age-matched normal subjects were analyzed. Young-age-onset eyes of preperimetric OAG mainly had RNFL defects inferotemporally (264-296 degrees) with GCIPL defects in the inferior region (213-357 degrees). Old-age-onset preperimetric OAG eyes had RNFL defects inferotemporally (266-294°) and superotemporally (33-67 degrees), with GCIPL defects in the inferior and superior regions (206-360 degrees, 0-22 degrees). The inferior quadrant of RNFL and GCIPL thicknesses were significantly thinner in young-age-onset eyes compared with old-age-onset eyes ( P =0.012, 0.016), while the superior quadrant of those were significantly thinner in the old-age-onset eyes ( P =0.003, 0.005). CONCLUSION: Young-age-onset and old-age-onset eyes of preperimetric OAG present different specific patterns of RNFL and GCIPL thinning.

Predicting demographic characteristics from anterior segment OCT images with deep learning: A study protocol.

INTRODUCTION: Anterior segment optical coherence tomography (AS-OCT) is a non-contact, rapid, and high-resolution in vivo modality for imaging of the eyeball's anterior segment structures. Because progressive anterior segment deformation is a hallmark of certain eye diseases such as angle-closure glaucoma, identification of AS-OCT structural changes over time is fundamental to their diagnosis and monitoring. Detection of pathologic damage, however, relies on the ability to differentiate it from normal, age-related structural changes. METHODS AND ANALYSIS: This proposed large-scale, retrospective cross-sectional study will determine whether demographic characteristics including age can be predicted from deep learning analysis of AS-OCT images; it will also assess the importance of specific anterior segment areas of the eyeball to the prediction. We plan to extract, from SUPREME®, a clinical data warehouse (CDW) of Seoul National University Hospital (SNUH; Seoul, South Korea), a list of patients (at least 2,000) who underwent AS-OCT imaging between 2008 and 2020. AS-OCT images as well as demographic characteristics including age, gender, height, weight and body mass index (BMI) will be collected from electronic medical records (EMRs). The dataset of horizontal AS-OCT images will be split into training (80%), validation (10%), and test (10%) datasets, and a Vision Transformer (ViT) model will be built to predict demographics. Gradient-weighted Class Activation Mapping (Grad-CAM) will be used to visualize the regions of AS-OCT images that contributed to the model's decisions. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) will be applied to evaluate the model performance. CONCLUSION: This paper presents a study protocol for prediction of demographic characteristics from AS-OCT images of the eyeball using a deep learning model. The results of this study will aid clinicians in understanding and identifying age-related structural changes and other demographics-based structural differences. TRIAL REGISTRATION: Registration ID with open science framework: 10.17605/OSF.IO/FQ46X.

Clinical outcome prediction from analysis of microelectrode recordings using deep learning in subthalamic deep brain stimulation for Parkinson`s disease.

BACKGROUND: Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is an effective treatment for improving the motor symptoms of advanced Parkinson's disease (PD). Accurate positioning of the stimulation electrodes is necessary for better clinical outcomes. OBJECTIVE: We applied deep learning techniques to microelectrode recording (MER) signals to better predict motor function improvement, represented by the UPDRS part III scores, after bilateral STN DBS in patients with advanced PD. If we find the optimal stimulation point with MER by deep learning, we can improve the clinical outcome of STN DBS even under restrictions such as general anesthesia or non-cooperation of the patients. METHODS: In total, 696 4-second left-side MER segments from 34 patients with advanced PD who underwent bilateral STN DBS surgery under general anesthesia were included. We transformed the original signal into three wavelets of 1-50 Hz, 50-500 Hz, and 500-5,000 Hz. The wavelet-transformed MER was used for input data of the deep learning. The patients were divided into two groups, good response and moderate response groups, according to DBS on to off ratio of UPDRS part III score for the off-medication state, 6 months postoperatively. The ratio were used for output data in deep learning. The Visual Geometry Group (VGG)-16 model with a multitask learning algorithm was used to estimate the bilateral effect of DBS. Different ratios of the loss function in the task-specific layer were applied considering that DBS affects both sides differently. RESULTS: When we divided the MER signals according to the frequency, the maximal accuracy was higher in the 50-500 Hz group than in the 1-50 Hz and 500-5,000 Hz groups. In addition, when the multitask learning method was applied, the stability of the model was improved in comparison with single task learning. The maximal accuracy (80.21%) occurred when the right-to-left loss ratio was 5:1 or 6:1. The area under the curve (AUC) was 0.88 in the receiver operating characteristic (ROC) curve. CONCLUSION: Clinical improvements in PD patients who underwent bilateral STN DBS could be predicted based on a multitask deep learning-based MER analysis.

Dual-input convolutional neural network for glaucoma diagnosis using spectral-domain optical coherence tomography.

BACKGROUND/AIMS: To evaluate, with spectral-domain optical coherence tomography (SD-OCT), the glaucoma-diagnostic ability of a deep-learning classifier. METHODS: A total of 777 Cirrus high-definition SD-OCT image sets of the retinal nerve fibre layer (RNFL) and ganglion cell-inner plexiform layer (GCIPL) of 315 normal subjects, 219 patients with early-stage primary open-angle glaucoma (POAG) and 243 patients with moderate-to-severe-stage POAG were aggregated. The image sets were divided into a training data set (252 normal, 174 early POAG and 195 moderate-to-severe POAG) and a test data set (63 normal, 45 early POAG and 48 moderate-to-severe POAG). The visual geometry group (VGG16)-based dual-input convolutional neural network (DICNN) was adopted for the glaucoma diagnoses. Unlike other networks, the DICNN structure takes two images (both RNFL and GCIPL) as inputs. The glaucoma-diagnostic ability was computed according to both accuracy and area under the receiver operating characteristic curve (AUC). RESULTS: For the test data set, DICNN could distinguish between patients with glaucoma and normal subjects accurately (accuracy=92.793%, AUC=0.957 (95% CI 0.943 to 0.966), sensitivity=0.896 (95% CI 0.896 to 0.917), specificity=0.952 (95% CI 0.921 to 0.952)). For distinguishing between patients with early-stage glaucoma and normal subjects, DICNN's diagnostic ability (accuracy=85.185%, AUC=0.869 (95% CI 0.825 to 0.879), sensitivity=0.921 (95% CI 0.813 to 0.905), specificity=0.756 (95% CI 0.610 to 0.790)]) was higher than convolutional neural network algorithms that trained with RNFL or GCIPL separately. CONCLUSION: The deep-learning algorithm using SD-OCT can distinguish normal subjects not only from established patients with glaucoma but also from patients with early-stage glaucoma. The deep-learning model with DICNN, as trained by both RNFL and GCIPL thickness map data, showed a high diagnostic ability for discriminatingpatients with early-stage glaucoma from normal subjects.

Deep-learning-based enhanced optic-disc photography.

Optic-disc photography (ODP) has proven to be very useful for optic nerve evaluation in glaucoma. In real clinical practice, however, limited patient cooperation, small pupils, or media opacities can limit the performance of ODP. The purpose of this study was to propose a deep-learning approach for increased resolution and improved legibility of ODP by contrast, color, and brightness compensation. Each high-resolution original ODP was transformed into two counterparts: (1) down-scaled 'low-resolution ODPs', and (2) 'compensated high-resolution ODPs' produced via enhancement of the visibility of the optic disc margin and surrounding retinal vessels using a customized image post-processing algorithm. Then, the differences between these two counterparts were directly learned through a super-resolution generative adversarial network (SR-GAN). Finally, by inputting the high-resolution ODPs into SR-GAN, 4-times-up-scaled and overall-color-and-brightness-transformed 'enhanced ODPs' could be obtained. General ophthalmologists were instructed (1) to assess each ODP's image quality, and (2) to note any abnormal findings, at 1-month intervals. The image quality score for the enhanced ODPs was significantly higher than that for the original ODP, and the overall optic disc hemorrhage (DH)-detection accuracy was significantly higher with the enhanced ODPs. We expect that this novel deep-learning approach will be applied to various types of ophthalmic images.

Macular Ganglion Cell-Inner Plexiform Layer Thickness Prediction from Red-free Fundus Photography using Hybrid Deep Learning Model.

We developed a hybrid deep learning model (HDLM) algorithm that quantitatively predicts macular ganglion cell-inner plexiform layer (mGCIPL) thickness from red-free retinal nerve fiber layer photographs (RNFLPs). A total of 789 pairs of RNFLPs and spectral domain-optical coherence tomography (SD-OCT) scans for 431 eyes of 259 participants (183 eyes of 114 healthy controls, 68 eyes of 46 glaucoma suspects, and 180 eyes of 99 glaucoma patients) were enrolled. An HDLM was built by combining a pre-trained deep learning network and support vector machine. The correlation coefficient and mean absolute error (MAE) between the predicted and measured mGCIPL thicknesses were calculated. The measured (OCT-based) and predicted (HDLM-based) average mGCIPL thicknesses were 73.96 ± 8.81 µm and 73.92 ± 7.36 µm, respectively (P = 0.844). The predicted mGCIPL thickness showed a strong correlation and good agreement with the measured mGCIPL thickness (Correlation coefficient r = 0.739; P < 0.001; MAE = 4.76 µm). Even when the peripapillary area (diameter: 1.5 disc diameters) was masked, the correlation (r = 0.713; P < 0.001) and agreement (MAE = 4.87 µm) were not changed significantly (P = 0.378 and 0.724, respectively). The trained HDLM algorithm showed a great capability for mGCIPL thickness prediction from RNFLPs.

Automated Quantification of Macular Ellipsoid Zone Intensity in Glaucoma Patients: the Method and its Comparison with Manual Quantification.

The macular ellipsoid zone intensity (mEZi) is a known marker of disease severity in a number of diverse ocular diseases. The purpose of this study was to establish an automated method (AM) for mEZi quantification and to compare the method's performance with that of a manual method (MM) for glaucoma patients and healthy controls. Seventy-one (71) mild-to-moderate glaucoma patients, 71 severe-glaucoma patients, and 51 controls were enrolled. Both calibration (n = 160) and validation (n = 33) image sets were compiled. The correlation of AM to MM quantification was assessed by Deming regression for the calibration set, and a compensation formula was generated. Then, for each image in the validation set, the compensated AM quantification was compared with the mean of five repetitive MM quantifications. The AM quantification of the calibration set was found to be linearly correlated with MM in the normal-to-severe-stage glaucoma patients (R2 = 0.914). The validation set's compensated AM quantification produced R2 = 0.991, and the relationship between the 2 quantifications was AM = 1.004(MM) + 0.139. In the validation set, the compensated AM quantification fell within MM quantification's 95% confidence interval in 96.9% of the images. An AM for mEZi quantification was calibrated and validated relative to MM quantification for both glaucoma patients and healthy controls.

Bidirectional Recurrent Auto-Encoder for Photoplethysmogram Denoising.

Photoplethysmography (PPG) has become ubiquitous with the development of smart watches and the mobile healthcare market. However, PPG is vulnerable to various types of noises that are ever present in uncontrolled environments, and the key to obtaining meaningful signals depends on successful denoising of PPG. In this context, algorithms have been developed to denoise PPG, but many were validated in controlled settings or are reliant on multiple steps that must all work correctly. This paper proposes a novel PPG denoising algorithm based on bidirectional recurrent denoising auto-encoder (BRDAE) that requires minimal pre-processing steps and have the benefit of waveform feature accentuation beyond simple denoising. The BRDAE was trained and validated on a dataset with artificially augmented noise, and was tested on a large open database of PPG signals collected from patients enrolled in intensive care units as well as from PPG data collected intermittently during the daily routine of nine subjects over 24 h. Denoising with the trained BRDAE improved signal-to-noise ratio of the noise-augmented data by 7.9 dB during validation. In the test datasets, the denoised PPG showed statistically significant improvement in heart rate detection as compared with the original PPG in terms of correlation to reference and root-mean-squared error. These results indicate that the proposed method is an effective solution for denoising the PPG signal, and promises values beyond traditional denoising by providing PPG feature accentuation for pulse waveform analysis.

Brain stimulation patterns emulating endogenous thalamocortical input to parvalbumin-expressing interneurons reduce nociception in mice.

BACKGROUND: The bursting pattern of thalamocortical (TC) pathway dampens nociception. Whether brain stimulation mimicking endogenous patterns can engage similar sensory gating processes in the cortex and reduce nociceptive behaviors remains uninvestigated. OBJECTIVE: We investigated the role of cortical parvalbumin expressing (PV) interneurons within the TC circuit in gating nociception and their selective response to TC burst patterns. We then tested if transcranial magnetic stimulation (TMS) patterned on endogenous nociceptive TC bursting modulate nociceptive behaviors. METHODS: The switching of TC neurons between tonic (single spike) and burst (high frequency spikes) firing modes may be a critical component in modulating nociceptive signals. Deep brain electrical stimulation of TC neurons and immunohistochemistry were used to examine the differential influence of each firing mode on cortical PV interneuron activity. Optogenetic stimulation of cortical PV interneurons assessed a direct role in nociceptive modulation. A new TMS protocol mimicking thalamic burst firing patterns, contrasted with conventional continuous and intermittent theta burst protocols, tested if TMS patterned on endogenous TC activity reduces nociceptive behaviors in mice. RESULTS: Immunohistochemical evidence confirmed that burst, but not tonic, deep brain stimulation of TC neurons increased the activity of PV interneurons in the cortex. Both optogenetic activation of PV interneurons and TMS protocol mimicking thalamic burst reduced nociceptive behaviors. CONCLUSIONS: Our findings suggest that burst firing of TC neurons recruits PV interneurons in the cortex to reduce nociceptive behaviors and that neuromodulation mimicking thalamic burst firing may be useful for modulating nociception.