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.

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.

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.

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.

DeepCIN: Attention-Based Cervical histology Image Classification with Sequential Feature Modeling for Pathologist-Level Accuracy.

BACKGROUND: Cervical cancer is one of the deadliest cancers affecting women globally. Cervical intraepithelial neoplasia (CIN) assessment using histopathological examination of cervical biopsy slides is subject to interobserver variability. Automated processing of digitized histopathology slides has the potential for more accurate classification for CIN grades from normal to increasing grades of pre-malignancy: CIN1, CIN2, and CIN3. METHODOLOGY: Cervix disease is generally understood to progress from the bottom (basement membrane) to the top of the epithelium. To model this relationship of disease severity to spatial distribution of abnormalities, we propose a network pipeline, DeepCIN, to analyze high-resolution epithelium images (manually extracted from whole-slide images) hierarchically by focusing on localized vertical regions and fusing this local information for determining Normal/CIN classification. The pipeline contains two classifier networks: (1) a cross-sectional, vertical segment-level sequence generator is trained using weak supervision to generate feature sequences from the vertical segments to preserve the bottom-to-top feature relationships in the epithelium image data and (2) an attention-based fusion network image-level classifier predicting the final CIN grade by merging vertical segment sequences. RESULTS: The model produces the CIN classification results and also determines the vertical segment contributions to CIN grade prediction. CONCLUSION: Experiments show that DeepCIN achieves pathologist-level CIN classification accuracy.

The 5 P's of Pyoderma Gangrenosum

The diagnosis of pyoderma gangrenosum (PG) is often difficult to establish based on a clinical presentation, which can mimic other dermatologic conditions. The formation of a mnemonic that incorporates the most prevalent clinical features of PG could aid in accuracy and speed of diagnosis. The 5 P's of PG: Painful, Progressive, Purple, Pretibial, Pathergy, and systemic associations, incorporate parameters recognizable on the first encounter with a patient with PG without reliance on histopathology and laboratory findings or treatment response. We postulate that this simple mnemonic will have the most utility with non-dermatology clinicians encountering a lesion suspicious for PG. By assisting in differential diagnosis formation, this mnemonic may lead to timelier biopsies and treatment initiation. The limitations of this approach mirror those of other studies and include lower sensitivities in patients with an atypical PG presentation. In conclusion, the 5 P's of PG offer a useful mnemonic for the diagnosis of PG, particularly in the initial clinical diagnosis prior to skin biopsy and treatment. J Drugs Dermatol. 2019;18(12):1282-1283.

Automatic lesion border selection in dermoscopy images using morphology and color features.

PURPOSE: We present a classifier for automatically selecting a lesion border for dermoscopy skin lesion images, to aid in computer-aided diagnosis of melanoma. Variation in photographic technique of dermoscopy images makes segmentation of skin lesions a difficult problem. No single algorithm provides an acceptable lesion border to allow further processing of skin lesions. METHODS: We present a random forests border classifier model to select a lesion border from 12 segmentation algorithm borders, graded on a "good-enough" border basis. Morphology and color features inside and outside the automatic border are used to build the model. RESULTS: For a random forests classifier applied to an 802-lesion test set, the model predicts a satisfactory border in 96.38% of cases, in comparison to the best single border algorithm, which detects a satisfactory border in 85.91% of cases. CONCLUSION: The performance of the classifier-based automatic skin lesion finder is found to be better than any single algorithm used in this research.

CELLULITIS: A mnemonic to increase accuracy of cellulitis diagnosis.

Cellulitis, a bacterial infection of the skin and subcutaneous tissue, is often misdiagnosed. Cellulitis accounts for a large number of all infectious disease-related hospitalizations in the U.S. Cellulitis can be challenging to diagnose since it lacks pathognomonic findings. We reviewed all articles on cellulitis within the last 20 years that included a statistical analysis, with odds ratios (OR), of specific clinical features of cellulitis. We then constructed a mnemonic encompassing the features with the highest odds ratios. Our mnemonic is CELLULITIS for cellulitis history, edema, local warmth, lymphangitis, unilateral, leukocytosis, injury, tender, instant onset, and systemic signs. The first characteristic has the highest OR and may be the easiest to recall: past episode(s) of cellulitis.

Deep Learning and Handcrafted Method Fusion: Higher Diagnostic Accuracy for Melanoma Dermoscopy Images.

This paper presents an approach that combines conventional image processing with deep learning by fusing the features from the individual techniques. We hypothesize that the two techniques, with different error profiles, are synergistic. The conventional image processing arm uses three handcrafted biologically inspired image processing modules and one clinical information module. The image processing modules detect lesion features comparable to clinical dermoscopy information-atypical pigment network, color distribution, and blood vessels. The clinical module includes information submitted to the pathologist-patient age, gender, lesion location, size, and patient history. The deep learning arm utilizes knowledge transfer via a ResNet-50 network that is repurposed to predict the probability of melanoma classification. The classification scores of each individual module from both processing arms are then ensembled utilizing logistic regression to predict an overall melanoma probability. Using cross-validated results of melanoma classification measured by area under the receiver operator characteristic curve (AUC), classification accuracy of 0.94 was obtained for the fusion technique. In comparison, the ResNet-50 deep learning based classifier alone yields an AUC of 0.87 and conventional image processing based classifier yields an AUC of 0.90. Further study of fusion of conventional image processing techniques and deep learning is warranted.

Biologically Inspired QuadTree Color Detection in Dermoscopy Images of Melanoma.

This paper presents a QuadTree-based melanoma detection system inspired by dermatologists' color perception. Clinical color assessment in dermoscopy images is challenging because of subtle differences in shades, location-dependent color information, poor color contrast, and wide variation among images of the same class. To overcome these challenges, color enhancement and automatic color identification techniques, based on QuadTree segmentation and modeled after expert color assessments, are developed. The approach presented in this paper is shown to provide an accurate model of expert color assessment. Specifically, the proposed model is shown to: 1) identify significantly more colors in melanomas than in benign skin lesions; 2) identify a higher frequency in melanomas of three colors: blue-gray, black, and pink; and 3) delineate locations of melanoma colors by quintiles, specifically predilection for blue-gray and pink in the periphery and a trend for white and black in the lesion center. Performance of the proposed method is evaluated using four classifiers. The kernel support vector machine classifier is found to achieve the best results, with an area under the receiver operating characteristic (ROC) curve of 0.93, compared to average area under the ROC curve of 0.82 achieved by the dermatologists in this study. The results indicate that the biologically inspired method of automatic color detection proposed in this paper has the potential to play an important role in melanoma diagnosis in the clinic.

Marijuana Use in the Era of Changing Cannabis Laws: What Are the Risks? Who is Most at Risk?

We review recent findings on medical aspects of marijuana use in order to identify those who are at greatest risk of marijuana-related medical problems. We analyze the impact of medical marijuana laws on health, in particular the disproportionate effects on adolescents and children. Chronic marijuana use predominantly affects certain areas of the brain that overlap the default mode network, linked hubs in the brain that play a supervisory role in critical thought processes such as attention, memory, and social interactions. Disruption of the default mode network areas has been documented in schizophrenia and Alzheimer's disease, illnesses with symptoms and brain changes that parallel findings in marijuana abusers. These findings counter the claim that marijuana is a harmless drug and are a cause for alarm in persons with cannabis dependence.

Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels.

BACKGROUND: Advances in image analysis and computational techniques have facilitated automatic detection of critical features in histopathology images. Detection of nuclei is critical for squamous epithelium cervical intraepithelial neoplasia (CIN) classification into normal, CIN1, CIN2, and CIN3 grades. METHODS: In this study, a deep learning (DL)-based nuclei segmentation approach is investigated based on gathering localized information through the generation of superpixels using a simple linear iterative clustering algorithm and training with a convolutional neural network. RESULTS: The proposed approach was evaluated on a dataset of 133 digitized histology images and achieved an overall nuclei detection (object-based) accuracy of 95.97%, with demonstrated improvement over imaging-based and clustering-based benchmark techniques. CONCLUSIONS: The proposed DL-based nuclei segmentation Method with superpixel analysis has shown improved segmentation results in comparison to state-of-the-art methods.