LAMA: Lesion-Aware Mixup Augmentation for Skin Lesion Segmentation.

Deep learning can exceed dermatologists' diagnostic accuracy in experimental image environments. However, inaccurate segmentation of images with multiple skin lesions can be seen with current methods. Thus, information present in multiple-lesion images, available to specialists, is not retrievable by machine learning. While skin lesion images generally capture a single lesion, there may be cases in which a patient's skin variation may be identified as skin lesions, leading to multiple false positive segmentations in a single image. Conversely, image segmentation methods may find only one region and may not capture multiple lesions in an image. To remedy these problems, we propose a novel and effective data augmentation technique for skin lesion segmentation in dermoscopic images with multiple lesions. The lesion-aware mixup augmentation (LAMA) method generates a synthetic multi-lesion image by mixing two or more lesion images from the training set. We used the publicly available International Skin Imaging Collaboration (ISIC) 2017 Challenge skin lesion segmentation dataset to train the deep neural network with the proposed LAMA method. As none of the previous skin lesion datasets (including ISIC 2017) has considered multiple lesions per image, we created a new multi-lesion (MuLe) segmentation dataset utilizing publicly available ISIC 2020 skin lesion images with multiple lesions per image. MuLe was used as a test set to evaluate the effectiveness of the proposed method. Our test results show that the proposed method improved the Jaccard score 8.3% from 0.687 to 0.744 and the Dice score 5% from 0.7923 to 0.8321 over a baseline model on MuLe test images. On the single-lesion ISIC 2017 test images, LAMA improved the baseline model's segmentation performance by 0.08%, raising the Jaccard score from 0.7947 to 0.8013 and the Dice score 0.6% from 0.8714 to 0.8766. The experimental results showed that LAMA improved the segmentation accuracy on both single-lesion and multi-lesion dermoscopic images. The proposed LAMA technique warrants further study.

Basal Cell Carcinoma Diagnosis with Fusion of Deep Learning and Telangiectasia Features.

In recent years, deep learning (DL) has been used extensively and successfully to diagnose different cancers in dermoscopic images. However, most approaches lack clinical inputs supported by dermatologists that could aid in higher accuracy and explainability. To dermatologists, the presence of telangiectasia, or narrow blood vessels that typically appear serpiginous or arborizing, is a critical indicator of basal cell carcinoma (BCC). Exploiting the feature information present in telangiectasia through a combination of DL-based techniques could create a pathway for both, improving DL results as well as aiding dermatologists in BCC diagnosis. This study demonstrates a novel "fusion" technique for BCC vs non-BCC classification using ensemble learning on a combination of (a) handcrafted features from semantically segmented telangiectasia (U-Net-based) and (b) deep learning features generated from whole lesion images (EfficientNet-B5-based). This fusion method achieves a binary classification accuracy of 97.2%, with a 1.3% improvement over the corresponding DL-only model, on a holdout test set of 395 images. An increase of 3.7% in sensitivity, 1.5% in specificity, and 1.5% in precision along with an AUC of 0.99 was also achieved. Metric improvements were demonstrated in three stages: (1) the addition of handcrafted telangiectasia features to deep learning features, (2) including areas near telangiectasia (surround areas), (3) discarding the noisy lower-importance features through feature importance. Another novel approach to feature finding with weak annotations through the examination of the surrounding areas of telangiectasia is offered in this study. The experimental results show state-of-the-art accuracy and precision in the diagnosis of BCC, compared to three benchmark techniques. Further exploration of deep learning techniques for individual dermoscopy feature detection is warranted.

Hybrid Topological Data Analysis and Deep Learning for Basal Cell Carcinoma Diagnosis.

A critical clinical indicator for basal cell carcinoma (BCC) is the presence of telangiectasia (narrow, arborizing blood vessels) within the skin lesions. Many skin cancer imaging processes today exploit deep learning (DL) models for diagnosis, segmentation of features, and feature analysis. To extend automated diagnosis, recent computational intelligence research has also explored the field of Topological Data Analysis (TDA), a branch of mathematics that uses topology to extract meaningful information from highly complex data. This study combines TDA and DL with ensemble learning to create a hybrid TDA-DL BCC diagnostic model. Persistence homology (a TDA technique) is implemented to extract topological features from automatically segmented telangiectasia as well as skin lesions, and DL features are generated by fine-tuning a pre-trained EfficientNet-B5 model. The final hybrid TDA-DL model achieves state-of-the-art accuracy of 97.4% and an AUC of 0.995 on a holdout test of 395 skin lesions for BCC diagnosis. This study demonstrates that telangiectasia features improve BCC diagnosis, and TDA techniques hold the potential to improve DL performance.

SharpRazor: Automatic removal of hair and ruler marks from dermoscopy images.

BACKGROUND: The removal of hair and ruler marks is critical in handcrafted image analysis of dermoscopic skin lesions. No other dermoscopic artifacts cause more problems in segmentation and structure detection. PURPOSE: The aim of the work is to detect both white and black hair, artifacts and finally inpaint correctly the image. METHOD: We introduce a new algorithm: SharpRazor, to detect hair and ruler marks and remove them from the image. Our multiple-filter approach detects hairs of varying widths within varying backgrounds, while avoiding detection of vessels and bubbles. The proposed algorithm utilizes grayscale plane modification, hair enhancement, segmentation using tri-directional gradients, and multiple filters for hair of varying widths. We develop an alternate entropy-based processing adaptive thresholding method. White or light-colored hair, and ruler marks are detected separately and added to the final hair mask. A classifier removes noise objects. Finally, a new technique of inpainting is presented, and this is utilized to remove the detected object from the lesion image. RESULTS: The proposed algorithm is tested on two datasets, and compares with seven existing methods measuring accuracy, precision, recall, dice, and Jaccard scores. SharpRazor is shown to outperform existing methods. CONCLUSION: The Shaprazor techniques show the promise to reach the purpose of removing and inpaint both dark and white hair in a wide variety of lesions.

Skin Lesion Segmentation in Dermoscopic Images with Noisy Data.

We propose a deep learning approach to segment the skin lesion in dermoscopic images. The proposed network architecture uses a pretrained EfficientNet model in the encoder and squeeze-and-excitation residual structures in the decoder. We applied this approach on the publicly available International Skin Imaging Collaboration (ISIC) 2017 Challenge skin lesion segmentation dataset. This benchmark dataset has been widely used in previous studies. We observed many inaccurate or noisy ground truth labels. To reduce noisy data, we manually sorted all ground truth labels into three categories - good, mildly noisy, and noisy labels. Furthermore, we investigated the effect of such noisy labels in training and test sets. Our test results show that the proposed method achieved Jaccard scores of 0.807 on the official ISIC 2017 test set and 0.832 on the curated ISIC 2017 test set, exhibiting better performance than previously reported methods. Furthermore, the experimental results showed that the noisy labels in the training set did not lower the segmentation performance. However, the noisy labels in the test set adversely affected the evaluation scores. We recommend that the noisy labels should be avoided in the test set in future studies for accurate evaluation of the segmentation algorithms.

Part II: Missouri's Fentanyl Poisonings Rise to Record Levels.

Missouri's dramatic rise in fentanyl-related overdoses was reported in Part I of this two-part series. In Part II, we report that previous efforts to combat the surge in illicit fentanyl supply from China failed, as Chinese factories shifted production to basic fentanyl precursor chemicals, known as dual-use pre-precursors. Mexican drug cartels now synthesize fentanyl from these basic chemicals and have overpowered the Mexican government. All efforts to reduce the fentanyl supply appear to be failing. Missouri has implemented harm reduction methods: training first responders and educating people who use drugs in safer practices. Harm reduction agencies are distributing naloxone at unprecedented levels. The "One Pill Can Kill" campaign begun by the Drug Enforcement Agency (DEA) in 2021 and foundations created by bereaved parents aim to educate young people on the extraordinary danger of counterfeit pills. In 2022, Missouri is at a crossroads, with record numbers of fatalities from illicit fentanyl and new levels of effort by harm reduction agencies to combat the soaring rate of deaths from this powerful narcotic.

Improving Automatic Melanoma Diagnosis Using Deep Learning-Based Segmentation of Irregular Networks.

Deep learning has achieved significant success in malignant melanoma diagnosis. These diagnostic models are undergoing a transition into clinical use. However, with melanoma diagnostic accuracy in the range of ninety percent, a significant minority of melanomas are missed by deep learning. Many of the melanomas missed have irregular pigment networks visible using dermoscopy. This research presents an annotated irregular network database and develops a classification pipeline that fuses deep learning image-level results with conventional hand-crafted features from irregular pigment networks. We identified and annotated 487 unique dermoscopic melanoma lesions from images in the ISIC 2019 dermoscopic dataset to create a ground-truth irregular pigment network dataset. We trained multiple transfer learned segmentation models to detect irregular networks in this training set. A separate, mutually exclusive subset of the International Skin Imaging Collaboration (ISIC) 2019 dataset with 500 melanomas and 500 benign lesions was used for training and testing deep learning models for the binary classification of melanoma versus benign. The best segmentation model, U-Net++, generated irregular network masks on the 1000-image dataset. Other classical color, texture, and shape features were calculated for the irregular network areas. We achieved an increase in the recall of melanoma versus benign of 11% and in accuracy of 2% over DL-only models using conventional classifiers in a sequential pipeline based on the cascade generalization framework, with the highest increase in recall accompanying the use of the random forest algorithm. The proposed approach facilitates leveraging the strengths of both deep learning and conventional image processing techniques to improve the accuracy of melanoma diagnosis. Further research combining deep learning with conventional image processing on automatically detected dermoscopic features is warranted.

ChimeraNet: U-Net for Hair Detection in Dermoscopic Skin Lesion Images.

Hair and ruler mark structures in dermoscopic images are an obstacle preventing accurate image segmentation and detection of critical network features. Recognition and removal of hairs from images can be challenging, especially for hairs that are thin, overlapping, faded, or of similar color as skin or overlaid on a textured lesion. This paper proposes a novel deep learning (DL) technique to detect hair and ruler marks in skin lesion images. Our proposed ChimeraNet is an encoder-decoder architecture that employs pretrained EfficientNet in the encoder and squeeze-and-excitation residual (SERes) structures in the decoder. We applied this approach at multiple image sizes and evaluated it using the publicly available HAM10000 (ISIC2018 Task 3) skin lesion dataset. Our test results show that the largest image size (448 × 448) gave the highest accuracy of 98.23 and Jaccard index of 0.65 on the HAM10000 (ISIC 2018 Task 3) skin lesion dataset, exhibiting better performance than for two well-known deep learning approaches, U-Net and ResUNet-a. We found the Dice loss function to give the best results for all measures. Further evaluated on 25 additional test images, the technique yields state-of-the-art accuracy compared to 8 previously reported classical techniques. We conclude that the proposed ChimeraNet architecture may enable improved detection of fine image structures. Further application of DL techniques to detect dermoscopy structures is warranted.

Part I: Missouri's Fentanyl Poisonings Rise to Record Levels.

Missourians are dying of fentanyl poisoning at an unprecedented rate. We identified growth areas in Missouri for fatal fentanyl encounters in rural and western counties. Though the deaths occur for a multitude of reasons, a growing trend adds to the surge in fentanyl fatalities: poisonings from counterfeit pills. The tablets are often labeled with brand names for alprazolam or oxycodone, but may contain only fentanyl at a dangerous level. Teenagers find counterfeit pills all too easily via social media. Believing they have found an easy way to obtain a quick high or relief of minor pain and anxiety, they take the pill alone in their bedroom, with no possibility of reversing a fatal fentanyl dose. There is a wide range of respiratory depression from illicit drugs containing fentanyl. We reviewed the physiologic respiratory response to drugs containing fentanyl that varies with genetics and the unpredictable amount of fentanyl contained in illicit drugs.

Identification and quantification of 11 airborne biochemicals emitted by the brown recluse and another primitive hunting spider using headspace solid-phase microextraction-GC/MS.

Loxosceles reclusa, or brown recluse spider, is a harmful household spider whose habitat extends throughout the Midwest in the USA and other regions in the world. The pheromones and other biomolecules that facilitate signaling for brown recluses and other spider species are poorly understood. A rapid and sensitive method is needed to analyze airborne spider signaling biomolecules to better understand the structure and function of these biochemicals in order to control the population of the spiders. In this study, we developed a novel headspace solid-phase microextraction (HS-SPME)-GC/MS method to analyze potential pheromones and biomolecules emitted by the brown recluse spider. The method is highly selective and sensitive for biomolecule identification and quantification from a single live spider. Using this novel non-destructive HS-SPME-GC/MS technique, we identified 11 airborne biomolecules, including 4-methylquinazoline, dimethyl sulfone, 2-methylpropanoic acid, butanoic acid, hexanal, 3-methylbutanoic acid, 2-methylbutanoic acid, 2,4-dimethylbenzaldehyde, 2-phenoxyethanol, and citral (contains both isomers of neral and geranial). Some of these airborne biomolecules were also reported as semiochemicals associated with biological functions of other spiders and insects. The method was also applied to study the airborne biochemicals of Plectreurys tristis, another primitive hunting spider with a poor web, enabling quantitation of the same compounds and demonstrating a difference in signaling molecule concentrations between the two species. This method has potential application in the study of pheromones and biological signaling in other species, which allows for the possibility of utilizing attractant or deterrent functions to limit household populations of harmful species.

Viscerocutaneous Loxoscelism Manifesting with Myocarditis: A Case Report.

BACKGROUND Envenomation from the brown recluse spider (Loxosceles reclusa) is described to cause both local and systemic symptoms. We report a case of an adolescent boy who developed severe systemic loxoscelism, and his clinical course was complicated by myocarditis, which has not been previously reported in association with loxoscelism. CASE REPORT A 16-year-old boy presented with non-specific symptoms and forearm pain following a suspected spider bite, which subsequently evolved into a necrotic skin lesion. During his clinical course, he developed a characteristic syndrome of systemic loxoscelism with hemolysis, disseminated intravascular coagulopathy, and severe systemic inflammatory response syndrome, necessitating transfer to the Intensive Care Unit. The diagnosis was confirmed with an enzyme-linked immunosorbent assay that detected Loxosceles venom in the wound. Additionally, he developed pulmonary edema and cardiogenic shock secondary to myocarditis, which was confirmed with cardiac magnetic resonance imaging. Steroids and plasmapheresis were initiated to manage the severe inflammatory syndrome, and the myocarditis was treated with intravenous immunoglobulins, resulting in resolution of symptoms and improvement of cardiac function. CONCLUSIONS This is the first reported case of myocarditis associated with loxoscelism, providing evidence for Loxosceles toxin-associated cardiac injury, which has been previously described in animal models only. Furthermore, this case provides further support for the use of confirmatory testing in the clinical diagnosis of loxoscelism.

Automated Cervical Digitized Histology Whole-Slide Image Analysis Toolbox.

BACKGROUND: Cervical intraepithelial neoplasia (CIN) is regarded as a potential precancerous state of the uterine cervix. Timely and appropriate early treatment of CIN can help reduce cervical cancer mortality. Accurate estimation of CIN grade correlated with human papillomavirus type, which is the primary cause of the disease, helps determine the patient's risk for developing the disease. Colposcopy is used to select women for biopsy. Expert pathologists examine the biopsied cervical epithelial tissue under a microscope. The examination can take a long time and is prone to error and often results in high inter-and intra-observer variability in outcomes. METHODOLOGY: We propose a novel image analysis toolbox that can automate CIN diagnosis using whole slide image (digitized biopsies) of cervical tissue samples. The toolbox is built as a four-step deep learning model that detects the epithelium regions, segments the detected epithelial portions, analyzes local vertical segment regions, and finally classifies each epithelium block with localized attention. We propose an epithelium detection network in this study and make use of our earlier research on epithelium segmentation and CIN classification to complete the design of the end-to-end CIN diagnosis toolbox. RESULTS: The results show that automated epithelium detection and segmentation for CIN classification yields comparable results to manually segmented epithelium CIN classification. CONCLUSION: This highlights the potential as a tool for automated digitized histology slide image analysis to assist expert pathologists.

Optical Oxygen Sensor Patch Printed with Polystyrene Microparticles-based Ink on Flexible Substrate.

Optical oxygen sensors based on photoluminescence quenching have gained increasing attention as a superior method for continuous monitoring of oxygen in a growing number of applications. A simple and low-cost fabrication technique was developed to produce sensor arrays capable of two-dimensional oxygen tension measurement. Sensor patches were printed on polyvinylidene chloride film using an oxygen-sensitive ink cocktail, prepared by immobilizing Pt(II) mesotetra(pentafluorophenyl)porphine (PtTFPP) in monodispersed polystyrene microparticles. The dispersion media of the ink cocktail, high molecular weight polyvinyl pyrrolidone suspended in 50% ethanol (v/v in water), allowed adhesion promotion and compatibility with most common polymeric substrates. Ink phosphorescence intensity was found to vary primarily with fluorophore concentration and to a lesser extent with polystyrene particle size. The sensor performance was investigated as a function of oxygen concentrations employing two different techniques: a multi-frequency phase fluorometer and smart phone-based image acquisition. The printed sensor patch showed fast and repetitive response over 0-21% oxygen concentrations with high linearity (with R2 >0.99) in a Stern-Volmer plot, and sensitivity of I0/I21 >1.55. The optical sensor response on a surface was investigated further using two-dimensional images which were captured and analyzed under different oxygen environment. Printed sensor patch along with imaging read-out technique make an ideal platform for early detection of surface wounds associated with tissue oxygen.

Missouri's Fentanyl Problem: The China Connection.

Recently, Missouri has followed an overall upward trend in opioid overdose deaths. In 2018, Missouri was the state with the largest absolute and percentage increase in opioid-related overdose fatality rates per capita over the previous year (18.3% and 3.1/100,000). This increase occurred despite an overall decrease in U.S. opioid-related death rates in the same period. This report identifies illicitly manufactured fentanyl (IMF) (and analogues) as the drug most responsible for this rise in opioid deaths in Missouri, with stimulant overdoses (primarily from methamphetamine) in second place. Within Missouri, we find the areas where opioid deaths are highest: St. Louis and the city's fringe areas, following the national trend for high rates in fringe areas. Based on reports from CDC Wonder data, county medical examiners, law enforcement agencies, and drug addiction prevention agencies, we conclude that IMF and related synthetic opioids arriving from China are primarily responsible for fatal narcotic overdoses in Missouri. Despite the COVID-19 disruption of fentanyl manufacturing and distribution centers in and around Wuhan, China early in the pandemic, preliminary 2020 data from medical examiners' offices show an upswing in opioid deaths, an indicator that Chinese fentanyl producers have restored the supply chain.

EpithNet: Deep Regression for Epithelium Segmentation in Cervical Histology Images.

BACKGROUND: Automated pathology techniques for detecting cervical cancer at the premalignant stage have advantages for women in areas with limited medical resources. METHODS: This article presents EpithNet, a deep learning approach for the critical step of automated epithelium segmentation in digitized cervical histology images. EpithNet employs three regression networks of varying dimensions of image input blocks (patches) surrounding a given pixel, with all blocks at a fixed resolution, using varying network depth. RESULTS: The proposed model was evaluated on 311 digitized histology epithelial images and the results indicate that the technique maximizes region-based information to improve pixel-wise probability estimates. EpithNet-mc model, formed by intermediate concatenation of the convolutional layers of the three models, was observed to achieve 94% Jaccard index (intersection over union) which is 26.4% higher than the benchmark model. CONCLUSIONS: EpithNet yields better epithelial segmentation results than state-of-the-art benchmark methods.

First known person-to-person transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in the USA.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is a disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), first detected in China in December, 2019. In January, 2020, state, local, and federal public health agencies investigated the first case of COVID-19 in Illinois, USA. METHODS: Patients with confirmed COVID-19 were defined as those with a positive SARS-CoV-2 test. Contacts were people with exposure to a patient with COVID-19 on or after the patient's symptom onset date. Contacts underwent active symptom monitoring for 14 days following their last exposure. Contacts who developed fever, cough, or shortness of breath became persons under investigation and were tested for SARS-CoV-2. A convenience sample of 32 asymptomatic health-care personnel contacts were also tested. FINDINGS: Patient 1-a woman in her 60s-returned from China in mid-January, 2020. One week later, she was hospitalised with pneumonia and tested positive for SARS-CoV-2. Her husband (Patient 2) did not travel but had frequent close contact with his wife. He was admitted 8 days later and tested positive for SARS-CoV-2. Overall, 372 contacts of both cases were identified; 347 underwent active symptom monitoring, including 152 community contacts and 195 health-care personnel. Of monitored contacts, 43 became persons under investigation, in addition to Patient 2. These 43 persons under investigation and all 32 asymptomatic health-care personnel tested negative for SARS-CoV-2. INTERPRETATION: Person-to-person transmission of SARS-CoV-2 occurred between two people with prolonged, unprotected exposure while Patient 1 was symptomatic. Despite active symptom monitoring and testing of symptomatic and some asymptomatic contacts, no further transmission was detected. FUNDING: None.