Machine and deep learning models for accurate detection of ischemia and scar with myocardial blood flow positron emission tomography imaging.

BACKGROUND: Quantification of myocardial blood flow (MBF) is used for the noninvasive diagnosis of patients with coronary artery disease (CAD). This study compared traditional statistics, machine learning, and deep learning techniques in their ability to diagnose disease using only the rest and stress MBF values. METHODS: This study included 3245 rest and stress rubidium-82 positron emission tomography (PET) studies and matching diagnostic labels from perfusion reports. Standard logistic regression, lasso logistic regression, support vector machine, random forest, multilayer perceptron, and dense U-Net were compared for per-patient detection and per-vessel localization of scars and ischemia. RESULTS: Receiver-operator characteristic area under the curve (AUC) of machine learning models was significantly higher than those of traditional statistics models for per-patient detection of disease (0.92-0.95 vs. 0.87) but not for per-vessel localization of ischemia or scar. Random forest showed the highest AUC = 0.95 among the different models compared. On the final hold-out set for generalizability, random forest showed an AUC of 0.92 for detection and 0.89 for localization of perfusion abnormalities. CONCLUSIONS: For per-vessel localization, simple models trained on segmental data performed similarly to a convolutional neural network trained on polar-map data, highlighting the need to justify the use of complex predictive algorithms through comparison with simpler methods.

An orally administered enzyme therapeutic for homocystinuria that suppresses homocysteine by metabolizing methionine in the gastrointestinal tract.

Classical homocystinuria (HCU) is a rare inborn error of amino acid metabolism characterized by accumulation of homocysteine, an intermediate product of methionine metabolism, leading to significant systemic toxicities, particularly within the vascular, skeletal, and ocular systems. Most patients require lifelong dietary therapy with severe restriction of natural protein to minimize methionine intake, and many patients still struggle to maintain healthy homocysteine levels. Since eliminating methionine from the diet reduces homocysteine levels, we hypothesized that an enzyme that can degrade methionine within the gastrointestinal (GI) tract could help HCU patients maintain healthy levels while easing natural protein restrictions. We describe the preclinical development of CDX-6512, a methionine gamma lyase (MGL) enzyme that was engineered for stability and activity within the GI tract for oral administration to locally degrade methionine. CDX-6512 is stable to low pH and intestinal proteases, enabling it to survive the harsh GI environment without enteric coating and to degrade methionine freed from dietary protein within the small intestine. Administering CDX-6512 to healthy non-human primates following a high protein meal led to a dose-dependent suppression of plasma methionine. In Tg-I278T Cbs-/- mice, an animal model that recapitulates aspects of HCU disease including highly elevated serum homocysteine levels, oral dosing of CDX-6512 after a high protein meal led to suppression in serum levels of both methionine and homocysteine. When animals received a daily dose of CDX-6512 with a high protein meal for two weeks, the Tg-I278T Cbs-/- mice maintained baseline homocysteine levels, whereas homocysteine levels in untreated animals increased by 39%. These preclinical data demonstrate the potential of CDX-6512 as an oral enzyme therapy for HCU.

Fast iterative reconstruction for photoacoustic tomography using learned physical model: Theoretical validation.

Iterative reconstruction has demonstrated superior performance in medical imaging under compressed, sparse, and limited-view sensing scenarios. However, iterative reconstruction algorithms are slow to converge and rely heavily on hand-crafted parameters to achieve good performance. Many iterations are usually required to reconstruct a high-quality image, which is computationally expensive due to repeated evaluations of the physical model. While learned iterative reconstruction approaches such as model-based learning (MBLr) can reduce the number of iterations through convolutional neural networks, it still requires repeated evaluations of the physical models at each iteration. Therefore, the goal of this study is to develop a Fast Iterative Reconstruction (FIRe) algorithm that incorporates a learned physical model into the learned iterative reconstruction scheme to further reduce the reconstruction time while maintaining robust reconstruction performance. We also propose an efficient training scheme for FIRe, which releases the enormous memory footprint required by learned iterative reconstruction methods through the concept of recursive training. The results of our proposed method demonstrate comparable reconstruction performance to learned iterative reconstruction methods with a 9x reduction in computation time and a 620x reduction in computation time compared to variational reconstruction.

Incidence of skin malignancies in patients with vitiligo or psoriasis who received narrowband ultraviolet B phototherapy (308 nm/311 nm): A retrospective review of 3730 patients.

BACKGROUND: Previous studies regarding the risk of skin malignancy with NBUVB have been performed in Caucasian patients, but few studies have been conducted in Asians. AIM: The aim of the study was to determine the risk of skin cancer in Asian patients with psoriasis and vitiligo receiving NBUVB phototherapy. METHODS: We performed a 9-year retrospective study including all patients with psoriasis and vitiligo receiving NBUVB (either 311 nm wavelength through cabin phototherapy or 308 nm through excimer lamp phototherapy) at the National Skin Centre. We matched the identification numbers of patients to the National Registry of Diseases Office database and collected data on all skin cancers diagnosed. RESULTS: A total of 3730 patients were included. During the course of the study, 12 cases of skin cancer were diagnosed, of which 10 were basal cell carcinomas, and 2 were squamous cell carcinomas. No cases of melanoma were detected in the study. The age-standardized incidence of skin cancer in psoriasis and vitiligo patients who received phototherapy was 47.5 and 26.5, respectively, which is higher than the incidence of skin cancers in the general population. Risk of skin malignancy was positively correlated with the cumulative (p = .008) and maximum dose of phototherapy (p = .011) as well as previous systemic treatments (p = .006). LIMITATIONS: Limitations include a relatively short follow-up period as well as the lack of quantification of solar exposure. CONCLUSIONS: NBUVB phototherapy in Asian skin increases the risk of skin malignancy. The risk of skin malignancy is higher with psoriasis patients, greater cumulative and maximal dose of phototherapy as well as the use of systemic therapy. Despite the increased risk, the absolute number of skin malignancies remains low, especially for vitiligo patients, with no cases of melanoma diagnosed-a reassuring finding that phototherapy remains a safe alternative in the treatment of psoriasis and vitiligo.

3D Single-Breath Chemical Shift Imaging Hyperpolarized Xe-129 MRI of Healthy, CF, IPF, and COPD Subjects.

3D Single-breath Chemical Shift Imaging (3D-SBCSI) is a hybrid MR-spectroscopic imaging modality that uses hyperpolarized xenon-129 gas (Xe-129) to differentiate lung diseases by probing functional characteristics. This study tests the efficacy of 3D-SBCSI in differentiating physiology among pulmonary diseases. A total of 45 subjects-16 healthy, 11 idiopathic pulmonary fibrosis (IPF), 13 cystic fibrosis (CF), and 5 chronic obstructive pulmonary disease (COPD)-were given 1/3 forced vital capacity (FVC) of hyperpolarized Xe-129, inhaled for a ~7 s MRI acquisition. Proton, Xe-129 ventilation, and 3D-SBCSI images were acquired with separate breath-holds using a radiofrequency chest coil tuned to Xe-129. The Xe-129 spectrum was analyzed in each lung voxel for ratios of spectroscopic peaks, chemical shifts, and T2* relaxation. CF and COPD subjects had significantly more ventilation defects than IPF and healthy subjects, which correlated with FEV1 predicted (R = -0.74). FEV1 predicted correlated well with RBC/Gas ratio (R = 0.67). COPD and IPF had significantly higher Tissue/RBC ratios than other subjects, longer RBC T2* relaxation times, and greater RBC chemical shifts. CF subjects had more ventilation defects than healthy subjects, elevated Tissue/RBC ratio, shorter Tissue T2* relaxation, and greater RBC chemical shift. 3D-SBCSI may be helpful in the detection and characterization of pulmonary disease, following treatment efficacy, and predicting disease outcomes.

Knowledge Graph and Deep Learning-based Text-to-GQL Model for Intelligent Medical Consultation Chatbot.

Text-to-GQL (Text2GQL) is a task that converts the user's questions into GQL (Graph Query Language) when a graph database is given. That is a task of semantic parsing that transforms natural language problems into logical expressions, which will bring more efficient direct communication between humans and machines. The existing related work mainly focuses on Text-to-SQL tasks, and there is no available semantic parsing method and data set for the graph database. In order to fill the gaps in this field to serve the medical Human-Robot Interactions (HRI) better, we propose this task and a pipeline solution for the Text2GQL task. This solution uses the Adapter pre-trained by "the linking of GQL schemas and the corresponding utterances" as an external knowledge introduction plug-in. By inserting the Adapter into the language model, the mapping between logical language and natural language can be introduced faster and more directly to better realize the end-to-end human-machine language translation task. In the study, the proposed Text2GQL task model is mainly constructed based on an improved pipeline composed of a Language Model, Pre-trained Adapter plug-in, and Pointer Network. This enables the model to copy objects' tokens from utterances, generate corresponding GQL statements for graph database retrieval, and builds an adjustment mechanism to improve the final output. And the experiments have proved that our proposed method has certain competitiveness on the counterpart datasets (Spider, ATIS, GeoQuery, and 39.net) converted from the Text2SQL task, and the proposed method is also practical in medical scenarios.

Machine Learning Assisted Handheld Confocal Raman Micro-Spectroscopy for Identification of Clinically Relevant Atopic Eczema Biomarkers.

Atopic dermatitis (AD) is a common chronic inflammatory skin dermatosis condition due to skin barrier dysfunction that causes itchy, red, swollen, and cracked skin. Currently, AD severity clinical scores are subjected to intra- and inter-observer differences. There is a need for an objective scoring method that is sensitive to skin barrier differences. The aim of this study was to evaluate the relevant skin chemical biomarkers in AD patients. We used confocal Raman micro-spectroscopy and advanced machine learning methods as means to classify eczema patients and healthy controls with sufficient sensitivity and specificity. Raman spectra at different skin depths were acquired from subjects' lower volar forearm location using an in-house developed handheld confocal Raman micro-spectroscopy system. The Raman spectra corresponding to the skin surface from all the subjects were further analyzed through partial least squares discriminant analysis, a binary classification model allowing the classification between eczema and healthy subjects with a sensitivity and specificity of 0.94 and 0.85, respectively, using stratified K-fold (K = 10) cross-validation. The variable importance in the projection score from the partial least squares discriminant analysis classification model further elucidated the role of important stratum corneum proteins and lipids in distinguishing two subject groups.

Colorimetric microneedle patches for multiplexed transdermal detection of metabolites.

Skin Interstitial Fluid (ISF) is an alternative source for biomarkers. Herein, a highly swellable microneedle patch (MNP) to rapidly extract ISF painlessly and bloodlessly is presented. The MNP is made of crosslinked methacrylated hyaluronic acid (MeHA) and dissolvable hyaluronic acid (HA) with the optimal balance of mechanical strength (0.6 N/MN) and absorption capability (16.22 µL in 20 min). Incorporated with wax-patterned and sensing-reagent-decorated test paper (TP) for multiplexed colorimetric detection of metabolites (glucose, lactate, cholesterol, and pH), this TP-MNP biosensor gives rapid color change in biomarker concentration-dependent manner based on specific enzymatic reactions, whereby allowing diagnosis by the naked eye or quantitative RGB analysis. Both the in vitro and in vivo experiments demonstrate the feasibility of TP-MNPs to detect multiple biomarkers in skin interstitial fluid within minutes. Such convenient and self-administrable profiling of metabolites shall be instrumental for home-based long-term monitoring and management of metabolic diseases.

Rheumatoid Arthritis Synovial Inflammation Quantification Using Computer Vision.

OBJECTIVE: We quantified inflammatory burden in rheumatoid arthritis (RA) synovial tissue by using computer vision to automate the process of counting individual nuclei in hematoxylin and eosin images. METHODS: We adapted and applied computer vision algorithms to quantify nuclei density (count of nuclei per unit area of tissue) on synovial tissue from arthroplasty samples. A pathologist validated algorithm results by labeling nuclei in synovial images that were mislabeled or missed by the algorithm. Nuclei density was compared with other measures of RA inflammation such as semiquantitative histology scores, gene-expression data, and clinical measures of disease activity. RESULTS: The algorithm detected a median of 112,657 (range 8,160-821,717) nuclei per synovial sample. Based on pathologist-validated results, the sensitivity and specificity of the algorithm was 97% and 100%, respectively. The mean nuclei density calculated by the algorithm was significantly higher (P < 0.05) in synovium with increased histology scores for lymphocytic inflammation, plasma cells, and lining hyperplasia. Analysis of RNA sequencing identified 915 significantly differentially expressed genes in correlation with nuclei density (false discovery rate is less than 0.05). Mean nuclei density was significantly higher (P < 0.05) in patients with elevated levels of C-reactive protein, erythrocyte sedimentation rate, rheumatoid factor, and cyclized citrullinated protein antibody. CONCLUSION: Nuclei density is a robust measurement of inflammatory burden in RA and correlates with multiple orthogonal measurements of inflammation.

COVID-19's impact on neglected pharmaceutical staff: wake-up call for needed research.

Discussion of the necessity of the compulsory vaccination of UK patient-facing care workers as an employment conditionality has deflected from the initial and ongoing impact of Coronavirus disease on relatively neglected occupational groups themselves, including community pharmacists. This commentary highlights the relative lack of research investigating the mental health and wellbeing impact of the pandemic on this occupational group in England and urges further study of their needs and experiences to inform evidence-based supportive psychological interventions.

Evaluation of Regional Lung Function in Pulmonary Fibrosis with Xenon-129 MRI.

Idiopathic pulmonary fibrosis, a pattern of interstitial lung disease, is often clinically unpredictable in its progression. This paper presents hyperpolarized Xenon-129 chemical shift imaging as a noninvasive, nonradioactive method of probing lung physiology as well as anatomy to monitor subtle changes in subjects with IPF. Twenty subjects, nine healthy and eleven IPF, underwent HP Xe-129 ventilation MRI and 3D-SBCSI. Spirometry was performed on all subjects before imaging, and DLCO and hematocrit were measured in IPF subjects after imaging. Images were post-processed in MATLAB and segmented using ANTs. IPF subjects exhibited, on average, higher Tissue/Gas ratios and lower RBC/Gas ratios compared with healthy subjects, and quantitative maps were more heterogeneous in IPF subjects. The higher ratios are likely due to fibrosis and thickening of the pulmonary interstitium. T2* relaxation was longer in IPF subjects and corresponded with hematocrit scores, although the mechanism is not well understood. A lower chemical shift in the red blood cell spectroscopic peak correlated well with a higher Tissue/RBC ratio and may be explained by reduced blood oxygenation. Tissue/RBC also correlated well, spatially, with areas of fibrosis in HRCT images. These results may help us understand the underlying mechanism behind gas exchange impairment and disease progression.

Comparing Deep Learning Frameworks for Photoacoustic Tomography Image Reconstruction.

Conventional reconstruction methods for photoacoustic images are not suitable for the scenario of sparse sensing and geometrical limitation. To overcome these challenges and enhance the quality of reconstruction, several learning-based methods have recently been introduced for photoacoustic tomography reconstruction. The goal of this study is to compare and systematically evaluate the recently proposed learning-based methods and modified networks for photoacoustic image reconstruction. Specifically, learning-based post-processing methods and model-based learned iterative reconstruction methods are investigated. In addition to comparing the differences inherently brought by the models, we also study the impact of different inputs on the reconstruction effect. Our results demonstrate that the reconstruction performance mainly stems from the effective amount of information carried by the input. The inherent difference of the models based on the learning-based post-processing method does not provide a significant difference in photoacoustic image reconstruction. Furthermore, the results indicate that the model-based learned iterative reconstruction method outperforms all other learning-based post-processing methods in terms of generalizability and robustness.

Limited-View and Sparse Photoacoustic Tomography for Neuroimaging with Deep Learning.

Photoacoustic tomography (PAT) is a non-ionizing imaging modality capable of acquiring high contrast and resolution images of optical absorption at depths greater than traditional optical imaging techniques. Practical considerations with instrumentation and geometry limit the number of available acoustic sensors and their "view" of the imaging target, which result in image reconstruction artifacts degrading image quality. Iterative reconstruction methods can be used to reduce artifacts but are computationally expensive. In this work, we propose a novel deep learning approach termed pixel-wise deep learning (Pixel-DL) that first employs pixel-wise interpolation governed by the physics of photoacoustic wave propagation and then uses a convolution neural network to reconstruct an image. Simulated photoacoustic data from synthetic, mouse-brain, lung, and fundus vasculature phantoms were used for training and testing. Results demonstrated that Pixel-DL achieved comparable or better performance to iterative methods and consistently outperformed other CNN-based approaches for correcting artifacts. Pixel-DL is a computationally efficient approach that enables for real-time PAT rendering and improved image reconstruction quality for limited-view and sparse PAT.

The Polyamine Putrescine Promotes Human Epidermal Melanogenesis.

Hyperpigmentary conditions can arise when melanogenesis in the epidermis is misregulated. Understanding the pathways underlying melanogenesis is essential for the development of effective treatments. Here, we report that a group of metabolites called polyamines are important in the control of melanogenesis in human skin. Polyamines are cationic molecules present in all cells and are essential for cellular function. We report that polyamine regulator ODC1 is upregulated in melanocytes from melasma lesional skin. We report that the polyamine putrescine can promote pigmentation in human skin explants and primary normal human epidermal melanocytes through induction of tyrosinase which is rate-limiting for the synthesis of melanin. Putrescine supplementation on normal human epidermal melanocytes results in the activation of polyamine catabolism, which results in increased intracellular H2O2. Polyamine catabolism is also increased in human skin explants that have been treated with putrescine. We further report that inhibition of polyamine catabolism prevents putrescine-induced promotion of tyrosinase levels and pigmentation in normal human epidermal melanocytes, showing that polyamine catabolism is responsible for the putrescine induction of melanogenesis. Our data showing that putrescine promotes pigmentation has important consequences for hyperpigmented and hypopigmented conditions. Further understanding of how polyamines control epidermal pigmentation could open the door for the development of new therapeutics.

Fully Dense UNet for 2-D Sparse Photoacoustic Tomography Artifact Removal.

Photoacoustic imaging is an emerging imaging modality that is based upon the photoacoustic effect. In photoacoustic tomography (PAT), the induced acoustic pressure waves are measured by an array of detectors and used to reconstruct an image of the initial pressure distribution. A common challenge faced in PAT is that the measured acoustic waves can only be sparsely sampled. Reconstructing sparsely sampled data using standard methods results in severe artifacts that obscure information within the image. We propose a modified convolutional neural network (CNN) architecture termed fully dense UNet (FD-UNet) for removing artifacts from two-dimensional PAT images reconstructed from sparse data and compare the proposed CNN with the standard UNet in terms of reconstructed image quality.

Standardizing serial photography for assessing and monitoring vitiligo: A core set of international recommendations for essential clinical and technical specifications.

BACKGROUND: Clinical photography is an important component of the initial assessment and follow-up of patients with vitiligo in clinical practice and research settings. Standardization of this photographic process is essential to achieve useful, high-quality, and comparable photographs over time. OBJECTIVE: The aim is to develop an international consensus for a core set of recommendations for standardized vitiligo clinical photography. METHODS: Based an international meeting of vitiligo experts, a standard operating procedure was developed for vitiligo photography in daily practice and research settings. This protocol was subsequently reviewed by 20 vitiligo experts until agreement was reached. RESULTS: The resulting protocol includes a set of 10 and 15 photographs for clinical practice and research purposes, respectively. The photographic series are based on anatomic units included in the Vitiligo Extent Score. Furthermore, graphic representations of standardized positioning and suggestions for guidelines to standardize the process (background color, lighting, position marking, scales, materials, instruments) for both color and ultraviolet photographs are described. CONCLUSIONS: This consensus-based protocol for vitiligo photography will harmonize imaging for both clinical practice, translational research, and clinical trials. It can improve outcome assessment, foster multicenter collaboration, and promote better communication with patients regarding outcomes of treatment.

Microneedle-Assisted Topical Delivery of Photodynamically Active Mesoporous Formulation for Combination Therapy of Deep-Seated Melanoma.

Topical treatment using photodynamic therapy (PDT) for many types of skin cancers has largely been limited by the inability of existing photosensitizers to penetrate into the deep skin tissue. To overcome these problems, we developed a mesoporous nanovehicle with dual loading of photosensitizers and clinically relevant drugs for combination therapy, while utilizing microneedle technology to facilitate their penetration into deep skin tissue. Sub-50 nm photodynamically active mesoporous organosilica nanoparticles were synthesized with photosensitizers covalently bonded to the silica matrix, which dramatically increased the quantum yield and photostability of these photosensitizers. The mesopores of the nanoparticles were further loaded with small-molecule inhibitors, i. e., dabrafenib and trametinib, that target the hyperactive mitogen-activated protein kinase (MAPK) pathway for melanoma treatment. As-prepared empty nanovehicle was cytocompatible with normal skin cells in the dark, while NIR-irradiated drug-loaded nanovehicle showed a synergistic killing effect on skin cancer cells mainly through reactive oxygen species and caspase-activated apoptosis. The nanovehicle could significantly inhibit the proliferation of tumor cells in a 3D spheroid model in vitro. Porcine skin fluorescence imaging demonstrated that microneedles could facilitate the penetration of nanovehicle across the epidermis layer of skin to reach deep-seated melanoma sites. Tumor regression studies in a xenografted melanoma mouse model confirmed superior therapeutic efficacy of the nanovehicle through combinational PDT and targeted therapy.

Treatment outcomes of vitiligo in Asian children.

This retrospective study aimed to identify factors that predict treatment response in a cohort of Asian children with vitiligo. Shorter duration of vitiligo was associated with better repigmentation. Patients with focal vitiligo of short duration have a good chance of achieving repigmentation with topical agents alone.

Interstitial Granulomatous Variant of Scleromyxedema-A Diagnostic Pitfall.

Scleromyxedema is a rare disorder where patients may develop systemic manifestations such as monoclonal gammopathy, inflammatory polyarthritis, and esophageal and neurological dysfunction. Histologically, there may be atypical variants of scleromyxedema showing features resembling interstitial granuloma annulare. We report an unusual case of scleromyxedema with interstitial granulomatous pattern and highlight potential diagnostic pitfalls when encountered with such a variant.