Understanding the anatomy of dermoscopy of melanocytic skin tumours: Correlation in vivo with line-field optical coherence tomography

BACKGROUND

Early melanoma detection is the main factor affecting prognosis and survival. For that reason, non-invasive technologies have been developed to provide a more accurate diagnosis. Recently, line-field confocal optical coherence tomography (LC-OCT) was developed to provide an in vivo, imaging device, with deep penetration and cellular resolution in three dimensions. Combining the advantages of conventional OCT and reflectance confocal microscopy, this tool seems to be particularly suitable for melanocytic lesions.

OBJECTIVES

The objective of this study was to identify and describe the correlation between specific dermoscopic criteria and LC-OCT features in three dimensions associated with melanocytic lesions.

METHODS

Dermoscopic and LC-OCT images of 126 melanocytic lesions were acquired in three different centres. The following dermoscopic criteria have been considered: reticular pattern, dots and globules, structureless areas, blue-whitish veil, regression structures, negative network, homogeneous pattern, streaks and blotches.

RESULTS

69 (55%) benign and 57 (45%) malignant lesions were analysed. A regular reticular pattern was found associated in the 75% of the cases with the presence of elongated rete ridges with pigmented cells along the basal layer, while atypical reticular pattern showed an irregular organization of rete ridges with melanocytic hyperplasia, broadened and fused ridges and elongated nests. Both typical and atypical dots and globules were found associated with melanocytic nests in the dermis or at the dermoepidermal junction (DEJ), as well as with keratin cysts/pseudocysts. Grey globules corresponded to the presence of melanin-containing dermal inflammatory cells (melanophages) within the papillae. Structureless brown/black areas correlated with alterations of the DEJ. We observed the same DEJ alterations, but with the presence of dermal melanophages, in 36% of the cases of blue/white/grey structureless areas. A description of each LC-OCT/dermoscopy correlation was made.

CONCLUSIONS

LC-OCT permitted for the first time to perform an in vivo, 3D correlation between dermoscopic criteria and pathological-like features of melanocytic lesions.

Mohs micrographic surgery challenges and new technologies to optimize care of cutaneous malignancies of the ear

Cutaneous malignancies affecting the ear, exacerbated by extensive ultraviolet (UV) exposure, pose intricate challenges owing to the organ's complex anatomy. This article investigates how the anatomy contributes to late-stage diagnoses and ensuing complexities in surgical interventions. Mohs Micrographic Surgery (MMS), acknowledged as the gold standard for treating most cutaneous malignancies of the ear, ensures superior margin control and cure rates. However, the ear's intricacy necessitates careful consideration of tissue availability and aesthetic outcomes. The manuscript explores new technologies like Reflectance Confocal Microscopy (RCM), Optical Coherence Tomography (OCT), High-Frequency, High-Resolution Ultrasound (HFHRUS), and Raman spectroscopy (RS). These technologies hold the promise of enhancing diagnostic accuracy and providing real-time visualization of excised tissue, thereby improving tumor margin assessments. Dermoscopy continues to be a valuable non-invasive tool for identifying malignant lesions. Staining methods in Mohs surgery are discussed, emphasizing hematoxylin and eosin (H&E) as the gold standard for evaluating tumor margins. Toluidine blue is explored for potential applications in assessing basal cell carcinomas (BCC), and immunohistochemical staining is considered for detecting proteins associated with specific malignancies. As MMS and imaging technologies advance, a thorough evaluation of their practicality, cost-effectiveness, and benefits becomes essential for enhancing surgical outcomes and patient care. The potential synergy of artificial intelligence with these innovations holds promise in revolutionizing tumor detection and improving the efficacy of cutaneous malignancy treatments.

Multi-scale feature fusion and class weight loss for skin lesion classification

Skin cancer is one of the common types of cancer. It spreads quickly and is not easy to detect in the early stages, posing a major threat to human health. In recent years, deep learning methods have attracted widespread attention for skin cancer detection in dermoscopic images. However, training a practical classifier becomes highly challenging due to inter-class similarity and intra-class variation in skin lesion images. To address these problems, we propose a multi-scale fusion structure that combines shallow and deep features for more accurate classification. Simultaneously, we implement three approaches to the problem of class imbalance: class weighting, label smoothing, and resampling. In addition, the HAM10000_RE dataset strips out hair features to demonstrate the role of hair features in the classification process. We demonstrate that the region of interest is the most critical classification feature for the HAM10000_SE dataset, which segments lesion regions. We evaluated the effectiveness of our model using the HAM10000 and ISIC2019 dataset. The results showed that this method performed well in dermoscopic classification tasks, with ACC and AUC of 94.0% and 99.3%, on the HAM10000 dataset and ACC of 89.8% for the ISIC2019 dataset. The overall performance of our model is excellent in comparison to state-of-the-art models.

A novel approach for melanoma detection utilizing GAN synthesis and vision transformer

BACKGROUND AND OBJECTIVE

Melanoma, a malignant form of skin cancer, is a critical health concern worldwide. Early and accurate detection plays a pivotal role in improving patient's conditions. Current diagnosis of skin cancer largely relies on visual inspections such as dermoscopy examinations, clinical screening and histopathological examinations. However, these approaches are characterized by low efficiency, high costs, and a lack of guaranteed accuracy. Consequently, deep learning based techniques have emerged in the field of melanoma detection, successfully aiding in improving the accuracy of diagnosis. However, the high similarity between benign and malignant melanomas, combined with the class imbalance issue in skin lesion datasets, present a significant challenge in further improving the diagnosis accuracy. We propose a two-stage framework for melanoma detection to address these issues.

METHODS

In the first stage, we use Style Generative Adversarial Networks with Adaptive discriminator augmentation synthesis to generate realistic and diverse melanoma images, which are then combined with the original dataset to create an augmented dataset. In the second stage, we utilize a vision Transformer of BatchFormer to extract features and detect melanoma or non-melanoma skin lesions on the augmented dataset obtained in the previous step, specifically, we employed a dual-branch training strategy in this process.

RESULTS

Our experimental results on the ISIC2020 dataset demonstrate the effectiveness of the proposed approach, showing a significant improvement in melanoma detection. The method achieved an accuracy of 98.43%, an AUC value of 98.63%, and an F1 value of 99.01%, surpassing some existing methods.

CONCLUSION

The method is feasible, efficient, and achieves early melanoma screening. It significantly enhances detection accuracy and can assist physicians in diagnosis to a great extent.

Dermoscopic structures and patterns used in melanoma detection

Melanoma is the leading cause of skin cancer-related deaths. Yet, early detection remains the most cost-effective means of preventing death from melanoma. Early detection can be achieved by a physician and/or the patient (also known as a self-skin exam). Skin exams performed by physicians are further enhanced using dermoscopy. Dermoscopy is a non-invasive technique that allows for the visualization of subsurface structures that are otherwise not visible to the naked eye. Evidence demonstrates that dermoscopy improves the diagnostic accuracy for skin cancer, including melanoma; it decreases the number of unnecessary skin biopsies of benign lesions and improves the benign-to-malignant biopsy ratio. Yet, these improvements are contingent on acquiring dermoscopy training. Dermoscopy is used by clinicians who evaluate skin lesions and perform skin cancer screenings. In general, under dermoscopy nevi tend to appear as organized lesions, with one or two structures and colors, and no melanoma-specific structures. In contrast, melanomas tend to manifest a disorganized pattern, with more than two colors and, usually, at least one melanoma-specific structure. This review is intended to familiarize the reader with the dermoscopic structures and patterns used in melanoma detection.

Automated Prediction of Malignant Melanoma using Two-Stage Convolutional Neural Network

PURPOSE

A skin lesion refers to an area of the skin that exhibits anomalous growth or distinctive visual characteristics compared to the surrounding skin. Benign skin lesions are noncancerous and generally pose no threat. These irregular skin growths can vary in appearance. On the other hand, malignant skin lesions correspond to skin cancer, which happens to be the most prevalent form of cancer in the United States. Skin cancer involves the unusual proliferation of skin cells anywhere on the body. The conventional method for detecting skin cancer is relatively more painful.

METHODS

This work involves the automated prediction of skin cancer and its types using two stage Convolutional Neural Network (CNN). The first stage of CNN extracts low level features and second stage extracts high level features. Feature selection is done using these two CNN and ABCD (Asymmetry, Border irregularity, Colour variation, and Diameter) technique. The features extracted from the two CNNs are fused with ABCD features and fed into classifiers for the final prediction. The classifiers employed in this work include ensemble learning methods such as gradient boosting and XG boost, as well as machine learning classifiers like decision trees and logistic regression. This methodology is evaluated using the International Skin Imaging Collaboration (ISIC) 2018 and 2019 dataset.

RESULTS

As a result, the first stage CNN which is used for creation of new dataset achieved an accuracy of 97.92%. Second stage CNN which is used for feature selection achieved an accuracy of 98.86%. Classification results are obtained for both with and without fusion of features.

CONCLUSION

Therefore, two stage prediction model achieved better results with feature fusion.

The effect of a dermoscopy training programme on diagnostic accuracy and management decisions regarding pigmented skin lesions: a comparison between dermal therapists and general practitioners

BACKGROUND

Dermoscopy is known to increase the diagnostic accuracy of pigmented skin lesions (PSLs) when used by trained professionals. The effect of dermoscopy training on the diagnostic ability of dermal therapists (DTs) has not been studied so far.

OBJECTIVES

This study aimed to investigate whether DTs, in comparison with general practitioners (GPs), benefited from a training programme including dermoscopy, in both their ability to differentiate between different forms of PSL and to assign the correct therapeutic strategy.

METHODS

In total, 24 DTs and 96 GPs attended a training programme on PSLs. Diagnostic skills as well as therapeutic strategy were assessed, prior to the training (pretest) and after the training (post-test) using clinical images alone, as well as after the addition of dermatoscopic images (integrated post-test). Bayesian hypothesis testing was used to determine statistical significance of differences between pretest, post-test and integrated post-test scores.

RESULTS

Both the DTs and the GPs demonstrated benefit from the training: at the integrated post-test, the median proportion of correctly diagnosed PSLs was 73% (range 30-90) for GPs and 63% (range 27-80) for DTs. A statistically significant difference between pretest results and integrated test results was seen, with a Bayes factor > 100. At 12 percentage points higher, the GPs outperformed DTs in the accuracy of detecting PSLs.

CONCLUSIONS

The study shows that a training programme focusing on PSLs while including dermoscopy positively impacts detection of PSLs by DTs and GPs. This training programme could form an integral part of the training of DTs in screening procedures, although additional research is needed.

Patient-led teledermatology for skin lesion triage: a service evaluation of the DyplensTM dermoscope

Despite the huge improvement in smartphone cameras, there has not been any real interest in the UK in pursuing patient-facing teledermatology within the sphere of skin lesion triage. High-specification dermoscopic images can be generated with smartphone attachments, but, to date, no formal clinical trial has been performed to establish the efficacy and feasibility of these consumer-level dermoscopes in skin lesion triage. The objectives of this study were to assess the ability of patients to capture dermoscopic images using a smartphone attachment, and to identify the safety and diagnostic accuracy of consumer-level dermoscopy in triaging out benign skin lesions from the 2-week-wait (2WW) cancer pathway. We recruited 78 patients already attending a face-to-face clinic at two locations. They were provided with instruction leaflets and asked to obtain dermoscopic and macroscopic images of their lesion(s) using their own smartphones. The images (and a brief history) were distributed to five experienced blinded assessors (consultants), who were asked to state their working diagnosis and outcome (reassurance, routine review or 2WW pathway), as they would in teledermatology. We compared their outcomes to the gold-standard in-person diagnosis and/or histological diagnosis, where available. The device achieved 100% sensitivity in diagnosing melanoma and squamous cell carcinoma (SCC). The specificity for the diagnoses of melanoma (89%) and SCC (83%) was high. The overall diagnostic accuracy was 77% for both benign and malignant lesions, The diagnostic accuracy was high for seborrhoeic keratosis (91%) and simple naevi (81%). Patient-captured dermoscopic images using bespoke smartphone attachments could be the future in safely triaging out benign lesions.

From diagnosis to intervention: a review of telemedicine's role in skin cancer care

Skin cancer treatment is a core aspect of dermatology that relies on accurate diagnosis and timely interventions. Teledermatology has emerged as a valuable asset across various stages of skin cancer care including triage, diagnosis, management, and surgical consultation. With the integration of traditional dermoscopy and store-and-forward technology, teledermatology facilitates the swift sharing of high-resolution images of suspicious skin lesions with consulting dermatologists all-over. Both live video conference and store-and-forward formats have played a pivotal role in bridging the care access gap between geographically isolated patients and dermatology providers. Notably, teledermatology demonstrates diagnostic accuracy rates that are often comparable to those achieved through traditional face-to-face consultations, underscoring its robust clinical utility. Technological advancements like artificial intelligence and reflectance confocal microscopy continue to enhance image quality and hold potential for increasing the diagnostic accuracy of virtual dermatologic care. While teledermatology serves as a valuable clinical tool for all patient populations including pediatric patients, it is not intended to fully replace in-person procedures like Mohs surgery and other necessary interventions. Nevertheless, its role in facilitating the evaluation of skin malignancies is gaining recognition within the dermatologic community and fostering high approval rates from patients due to its practicality and ability to provide timely access to specialized care.

Comprehensive analysis of clinical images contributions for melanoma classification using convolutional neural networks

BACKGROUND

Timely diagnosis plays a critical role in determining melanoma prognosis, prompting the development of deep learning models to aid clinicians. Questions persist regarding the efficacy of clinical images alone or in conjunction with dermoscopy images for model training. This study aims to compare the classification performance for melanoma of three types of CNN models: those trained on clinical images, dermoscopy images, and a combination of paired clinical and dermoscopy images from the same lesion.

MATERIALS AND METHODS

We divided 914 image pairs into training, validation, and test sets. Models were built using pre-trained Inception-ResNetV2 convolutional layers for feature extraction, followed by binary classification. Training comprised 20 models per CNN type using sets of random hyperparameters. Best models were chosen based on validation AUC-ROC.

RESULTS

Significant AUC-ROC differences were found between clinical versus dermoscopy models (0.661 vs. 0.869, p < 0.001) and clinical versus clinical + dermoscopy models (0.661 vs. 0.822, p = 0.001). Significant sensitivity differences were found between clinical and dermoscopy models (0.513 vs. 0.799, p = 0.01), dermoscopy versus clinical + dermoscopy models (0.799 vs. 1.000, p = 0.02), and clinical versus clinical + dermoscopy models (0.513 vs. 1.000, p < 0.001). Significant specificity differences were found between dermoscopy versus clinical + dermoscopy models (0.800 vs. 0.288, p < 0.001) and clinical versus clinical + dermoscopy models (0.650 vs. 0.288, p < 0.001).

CONCLUSION

CNN models trained on dermoscopy images outperformed those relying solely on clinical images under our study conditions. The potential advantages of incorporating paired clinical and dermoscopy images for CNN-based melanoma classification appear less clear based on our findings.

Consistency of convolutional neural networks in dermoscopic melanoma recognition: A prospective real-world study about the pitfalls of augmented intelligence

BACKGROUND

Deep-learning convolutional neural networks (CNNs) have outperformed even experienced dermatologists in dermoscopic melanoma detection under controlled conditions. It remains unexplored how real-world dermoscopic image transformations affect CNN robustness.

OBJECTIVES

To investigate the consistency of melanoma risk assessment by two commercially available CNNs to help formulate recommendations for current clinical use.

METHODS

A comparative cohort study was conducted from January to July 2022 at the Department of Dermatology, University Hospital Basel. Five dermoscopic images of 116 different lesions on the torso of 66 patients were captured consecutively by the same operator without deliberate rotation. Classification was performed by two CNNs (CNN-1/CNN-2). Lesions were divided into four subgroups based on their initial risk scoring and clinical dignity assessment. Reliability was assessed by variation and intraclass correlation coefficients. Excisions were performed for melanoma suspicion or two consecutively elevated CNN risk scores, and benign lesions were confirmed by expert consensus (n = 3).

RESULTS

117 repeated image series of 116 melanocytic lesions (2 melanomas, 16 dysplastic naevi, 29 naevi, 1 solar lentigo, 1 suspicious and 67 benign) were classified. CNN-1 demonstrated superior measurement repeatability for clinically benign lesions with an initial malignant risk score (mean variation coefficient (mvc): CNN-1: 49.5(±34.3)%; CNN-2: 71.4(±22.5)%; p = 0.03), while CNN-2 outperformed for clinically benign lesions with benign scoring (mvc: CNN-1: 49.7(±22.7)%; CNN-2: 23.8(±29.3)%; p = 0.002). Both systems exhibited lowest score consistency for lesions with an initial malignant risk score and benign assessment. In this context, averaging three initial risk scores achieved highest sensitivity of dignity assessment (CNN-1: 94%; CNN-2: 89%). Intraclass correlation coefficients indicated 'moderate'-to-'good' reliability for both systems (CNN-1: 0.80, 95% CI:0.71-0.87, p < 0.001; CNN-2: 0.67, 95% CI:0.55-0.77, p < 0.001).

CONCLUSIONS

Potential user-induced image changes can significantly influence CNN classification. For clinical application, we recommend using the average of three initial risk scores. Furthermore, we advocate for CNN robustness optimization by cross-validation with repeated image sets.

TRIAL REGISTRATION

ClinicalTrials.gov (NCT04605822).

Dermatoscopy and reflectance confocal microscopy for basal cell carcinoma diagnosis and diagnosis prediction score: A prospective and multicenter study on 1005 lesions

BACKGROUND

Basal cell carcinoma (BCC) is usually diagnosed by clinical and dermatoscopy examination, but diagnostic accuracy may be suboptimal. Reflectance confocal microscopy (RCM) imaging increases skin cancer diagnostic accuracy.

OBJECTIVE

To evaluate additional benefit in diagnostic accuracy of handheld RCM in a prospective controlled clinical setting.

METHODS

A prospective, multicenter study in 3 skin cancer reference centers in Italy enrolling consecutive lesions with clinical-dermatoscopic suspicion of BCC (ClinicalTrials.gov: NCT04789421).

RESULTS

A total of 1005 lesions were included, of which 474 histopathologically confirmed versus 531 diagnosed by clinical-dermatoscopic-RCM correlation, confirmed with 2 years of follow-up. Specifically, 740 were confirmed BCCs. Sensitivity and specificity for dermatoscopy alone was 93.2% (95% CI, 91.2-94.9) and 51.7% (95% CI, 45.5-57.9); positive predictive value was 84.4 (95% CI, 81.7-86.8) and negative predictive value 73.3 (95% CI, 66.3-79.5). Adjunctive RCM reported higher rates: 97.8 (95% CI, 96.5-98.8) sensitivity and 86.8 (95% CI, 82.1-90.6) specificity, with positive predictive value of 95.4 (95% CI, 93.6-96.8) and negative predictive value 93.5 (95% CI, 89.7-96.2).

LIMITATIONS

Study conducted in a single country.

CONCLUSIONS

Adjunctive handheld RCM assessment of lesions clinically suspicious for BCC permits higher diagnostic accuracy with minimal false negative lesions.

Early automated detection system for skin cancer diagnosis using artificial intelligent techniques

Recently, skin cancer is one of the spread and dangerous cancers around the world. Early detection of skin cancer can reduce mortality. Traditional methods for skin cancer detection are painful, time-consuming, expensive, and may cause the disease to spread out. Dermoscopy is used for noninvasive diagnosis of skin cancer. Artificial Intelligence (AI) plays a vital role in diseases' diagnosis especially in biomedical engineering field. The automated detection systems based on AI reduce the complications in the traditional methods and can improve skin cancer's diagnosis rate. In this paper, automated early detection system for skin cancer dermoscopic images using artificial intelligent is presented. Adaptive snake (AS) and region growing (RG) algorithms are used for automated segmentation and compared with each other. The results show that AS is accurate and efficient (accuracy = 96%) more than RG algorithm (accuracy = 90%). Artificial Neural networks (ANN) and support vector machine (SVM) algorithms are used for automated classification compared with each other. The proposed system with ANN algorithm shows high accuracy (94%), precision (96%), specificity (95.83%), sensitivity (recall) (92.30%), and F1-score (0.94). The proposed system is easy to use, time consuming, enables patients to make early detection for skin cancer and has high efficiency.

A novel SpaSA based hyper-parameter optimized FCEDN with adaptive CNN classification for skin cancer detection

Skin cancer is the most prevalent kind of cancer in people. It is estimated that more than 1 million people get skin cancer every year in the world. The effectiveness of the disease's therapy is significantly impacted by early identification of this illness. Preprocessing is the initial detecting stage in enhancing the quality of skin images by removing undesired background noise and objects. This study aims is to compile preprocessing techniques for skin cancer imaging that are currently accessible. Researchers looking into automated skin cancer diagnosis might use this article as an excellent place to start. The fully convolutional encoder-decoder network and Sparrow search algorithm (FCEDN-SpaSA) are proposed in this study for the segmentation of dermoscopic images. The individual wolf method and the ensemble ghosting technique are integrated to generate a neighbour-based search strategy in SpaSA for stressing the correct balance between navigation and exploitation. The classification procedure is accomplished by using an adaptive CNN technique to discriminate between normal skin and malignant skin lesions suggestive of disease. Our method provides classification accuracies comparable to commonly used incremental learning techniques while using less energy, storage space, memory access, and training time (only network updates with new training samples, no network sharing). In a simulation, the segmentation performance of the proposed technique on the ISBI 2017, ISIC 2018, and PH2 datasets reached accuracies of 95.28%, 95.89%, 92.70%, and 98.78%, respectively, on the same dataset and assessed the classification performance. It is accurate 91.67% of the time. The efficiency of the suggested strategy is demonstrated through comparisons with cutting-edge methodologies.

Dermoscopy to differentiate clinically similar inflammatory and neoplastic skin lesions

INTRODUCTION

Over the few last decades, dermoscopy has become an invaluable and popular imaging technique that complements the diagnostic armamentarium of dermatologists, being employed for both tumors and inflammatory diseases. Whereas distinction between neoplastic and inflammatory lesions is often straightforward based on clinical data, there are some scenarios that may be troublesome, e.g., solitary inflammatory lesions or tumors superimposed to a widespread inflammatory condition that may share macroscopic morphological findings.

EVIDENCE ACQUISITION

We reviewed the literature to identify dermoscopic clues to support the differential diagnosis of clinically similar inflammatory and neoplastic skin lesions, also providing the histological background of such dermoscopic points of differentiation.

EVIDENCE SYNTHESIS

Dermoscopic differentiating features were identified for 12 relatively common challenging scenarios, including Bowen's disease and basal cell carcinoma vs. psoriasis and dermatitis, erythroplasia of Queyrat vs. inflammatory balanitis, mammary and extramammary Paget's disease vs. inflammatory mimickers, actinic keratoses vs. discoid lupus erythematosus, squamous cell carcinoma vs. hypertrophic lichen planus and lichen simplex chronicus, actinic cheilitis vs. inflammatory cheilitis, keratoacanthomas vs. prurigo nodularis, nodular lymphomas vs. pseudolymphomas and inflammatory mimickers, mycosis fungoides vs. parapsoriasis and inflammatory mimickers, angiosarcoma vs granuloma faciale, and Kaposi sarcoma vs pseudo-Kaposi.

CONCLUSIONS

Dermoscopy may be of aid in differentiating clinically similar inflammatory and neoplastic skin lesions.

Assessing field cancerization and actinic keratosis using ultraviolet-induced fluorescence dermatoscopy after the application of 5-aminolevulinic acid - An observational study

BACKGROUND

Actinic keratoses (AK) are one of the most frequent reasons for consultations in dermatology. Ultraviolet-induced fluorescence dermatoscopy (UVFD) is a new method that allows the assessment of lesions in a spectrum of light that originates from the fluorochromes emitting UV-excited luminescence. The aim of this study was to assess the UVFD features of AKs before PDT and their intensity in field cancerization and single lesions.

METHODS

This retrospective study was conducted from June to November 2023. Lesions were assessed with the Olsen scale clinically and dermatoscopically (DermLite DL5, 10x magnification) and photographed. UVFD fluorescence was categorized as 'none', 'weak', 'moderate', and 'intense'. A 1-mm thick layer of 10 % 5-ALA gel was applied to single lesions or cancerization field (depending on the patient) and covered with an occlusive dressing for 3 h. Prior the application of 10 % 5-ALA gel, the lesions were degreased with an alcoholic solution. The occlusion was removed, and the field was cleaned with a 0,9 % saline solution. Afterward, each lesion was photographed in polarized light and UVFD mode.

RESULTS

A total of 194 dermatoscopic images were analyzed, 111 corresponded to field cancerization and 81 to single AKs. Overall, weak fluorescence was noticed in 22 of them (11,3 %), moderate in 107 (55,15 %), and intense in 65 (33,5 %). Amongst field cancerization (111 images), weak fluorescence was seen in 11 (9.9 %), moderate in 68 (61,26 %), and intense in 32 (28,82 %). In single lesions (81 images), weak fluorescence was detected in 11 (13,2 %), moderate in 39 (46,99 %), and intense in 33 (28.83 %) of the lesions. Slightly more intense fluorescence was noticed in higher Olsen grade (p = 0.04).

CONCLUSIONS

UVFD can enhance our efficacy of pre-procedural examination and might arise as a useful device to predict the therapeutic effect of PDT.

Enhancing assisted diagnostic accuracy in scalp psoriasis: A Multi-Network Fusion Object Detection Framework for dermoscopic pattern diagnosis

BACKGROUND

Dermoscopy is a common method of scalp psoriasis diagnosis, and several artificial intelligence techniques have been used to assist dermoscopy in the diagnosis of nail fungus disease, the most commonly used being the convolutional neural network algorithm; however, convolutional neural networks are only the most basic algorithm, and the use of object detection algorithms to assist dermoscopy in the diagnosis of scalp psoriasis has not been reported.

OBJECTIVES

Establishment of a dermoscopic modality diagnostic framework for scalp psoriasis based on object detection technology and image enhancement to improve diagnostic efficiency and accuracy.

METHODS

We analyzed the dermoscopic patterns of scalp psoriasis diagnosed at 72nd Group army hospital of PLA from January 1, 2020 to December 31, 2021, and selected scalp seborrheic dermatitis as a control group. Based on dermoscopic images and major dermoscopic patterns of scalp psoriasis and scalp seborrheic dermatitis, we investigated a multi-network fusion object detection framework based on the object detection technique Faster R-CNN and the image enhancement technique contrast limited adaptive histogram equalization (CLAHE), for assisting in the diagnosis of scalp psoriasis and scalp seborrheic dermatitis, as well as to differentiate the major dermoscopic patterns of the two diseases. The diagnostic performance of the multi-network fusion object detection framework was compared with that between dermatologists.

RESULTS

A total of 1876 dermoscopic images were collected, including 1218 for scalp psoriasis versus 658 for scalp seborrheic dermatitis. Based on these images, training and testing are performed using a multi-network fusion object detection framework. The results showed that the test accuracy, specificity, sensitivity, and Youden index for the diagnosis of scalp psoriasis was: 91.0%, 89.5%, 91.0%, and 0.805, and for the main dermoscopic patterns of scalp psoriasis and scalp seborrheic dermatitis, the diagnostic results were: 89.9%, 97.7%, 89.9%, and 0.876. Comparing the diagnostic results with those of five dermatologists, the fusion framework performs better than the dermatologists' diagnoses.

CONCLUSIONS

Studies have shown some differences in dermoscopic patterns between scalp psoriasis and scalp seborrheic dermatitis. The proposed multi-network fusion object detection framework has higher diagnostic performance for scalp psoriasis than for dermatologists.

DMpDP: a Diagnostic Multiple-patient DermoFeature Profile store-and-forward teledermoscopy system

Telehealth demand is rapidly growing along with the necessity of providing wide-scale services covering multiple patients at the same time. In this work, the development of a store-and-forward (SAF) teledermoscopy system was considered. The dermoFeatures profile (DP) was proposed to decrease the size of the original dermoscopy image using its most significant features in the form of a newly generated diagonal alignment to generate a small-sized image DP, which is based on the extraction of a weighted intensity-difference frequency (WIDF) features along with morphological features (MOFs). These DPs were assembled to establish a Diagnostic Multiple-patient DermoFeature Profile (DMpDP). Different arrangements are proposed, namely the horizontally aligned, the diagonal-based, and the sequential-based DMpDPs to support the SAF systems. The DMpDPs are then embedded in a recorded patient-information signal (RPS) using a weight factor β to boost the transmitted patient-information signal. The effect of the different transform domains, β values, and number of DPs within the DMpDP were investigated in terms of the diagnostic classification accuracy at the receiver based on the extracted DPs, along with the recorded signal quality evaluation metrics of the recovered RPS. The sequential-based DMpDP achieved the highest classification accuracy, under - 5 dB additive white Gaussian noise, with a realized signal-to-noise ratio of 98.79% during the transmission of 248 DPs using β = 100, and spectral subtraction filtering.

Analysis of dermoscopy images of multi-class for early detection of skin lesions by hybrid systems based on integrating features of CNN models

Skin cancer is one of the most fatal skin lesions, capable of leading to fatality if not detected in its early stages. The characteristics of skin lesions are similar in many of the early stages of skin lesions. The AI in categorizing diverse types of skin lesions significantly contributes to and helps dermatologists to preserve patients' lives. This study introduces a novel approach that capitalizes on the strengths of hybrid systems of Convolutional Neural Network (CNN) models to extract intricate features from dermoscopy images with Random Forest (Rf) and Feed Forward Neural Networks (FFNN) networks, leading to the development of hybrid systems that have superior capabilities early detection of all types of skin lesions. By integrating multiple CNN features, the proposed methods aim to improve the robustness and discriminatory capabilities of the AI system. The dermoscopy images were optimized for the ISIC2019 dataset. Then, the area of the lesions was segmented and isolated from the rest of the image by a Gradient Vector Flow (GVF) algorithm. The first strategy for dermoscopy image analysis for early diagnosis of skin lesions is by the CNN-RF and CNN-FFNN hybrid models. CNN models (DenseNet121, MobileNet, and VGG19) receive a region of interest (skin lesions) and produce highly representative feature maps for each lesion. The second strategy to analyze the area of skin lesions and diagnose their type by means of CNN-RF and CNN-FFNN hybrid models based on the features of the combined CNN models. Hybrid models based on combined CNN features have achieved promising results for diagnosing dermoscopy images of the ISIC 2019 dataset and distinguishing skin cancers from other skin lesions. The Dense-Net121-MobileNet-RF hybrid model achieved an AUC of 95.7%, an accuracy of 97.7%, a precision of 93.65%, a sensitivity of 91.93%, and a specificity of 99.49%.

DVFNet: A deep feature fusion-based model for the multiclassification of skin cancer utilizing dermoscopy images

Skin cancer is a common cancer affecting millions of people annually. Skin cells inside the body that grow in unusual patterns are a sign of this invasive disease. The cells then spread to other organs and tissues through the lymph nodes and destroy them. Lifestyle changes and increased solar exposure contribute to the rise in the incidence of skin cancer. Early identification and staging are essential due to the high mortality rate associated with skin cancer. In this study, we presented a deep learning-based method named DVFNet for the detection of skin cancer from dermoscopy images. To detect skin cancer images are pre-processed using anisotropic diffusion methods to remove artifacts and noise which enhances the quality of images. A combination of the VGG19 architecture and the Histogram of Oriented Gradients (HOG) is used in this research for discriminative feature extraction. SMOTE Tomek is used to resolve the problem of imbalanced images in the multiple classes of the publicly available ISIC 2019 dataset. This study utilizes segmentation to pinpoint areas of significantly damaged skin cells. A feature vector map is created by combining the features of HOG and VGG19. Multiclassification is accomplished by CNN using feature vector maps. DVFNet achieves an accuracy of 98.32% on the ISIC 2019 dataset. Analysis of variance (ANOVA) statistical test is used to validate the model's accuracy. Healthcare experts utilize the DVFNet model to detect skin cancer at an early clinical stage.

Utility of Dermoscopy Training in Improving Diagnostic Accuracy of Skin Lesions Among Physician Assistant Students

INTRODUCTION

Patients often first present to their primary care provider for skin lesion concerns, and dermoscopy is a tool that enhances diagnostic acumen of both malignant and benign skin lesions. Physician assistants (PAs) frequently serve as primary care and dermatology providers, but to our knowledge, no current research on dermoscopy expertise with PAs exists. We hypothesize that PA students could be taught dermoscopy based on the triage amalgamated dermoscopic algorithm (TADA) to increase their diagnostic skill, as previously shown with medical students.

METHODS

Dermoscopy was taught to first-year PA students at all 5 PA programs in the state of Minnesota. The training was 50 minutes in length and focused on the fundamentals of the TADA method. Physician assistant students participated in a pretraining and post-training test, consisting of 30 dermoscopic images.

RESULTS

A total of 139/151 (92%) PA students completed both the pretraining and post-training tests. Overall, mean scores for all students increased significantly ( P < .0001) after dermoscopy training was given (18.5 ± 7.1 vs. 23.8 ± 6.7).

CONCLUSION

Our study demonstrates that after TADA training, PA students improved their ability to assess dermoscopy images of both skin cancer and benign lesions accurately, suggesting that PAs can be trained as novice dermoscopists and provide better dermatologic care to patients. We strongly encourage integration of dermoscopy into didactic education across PA programs. Implementing a dermoscopy curriculum in established PA programs will enable future PAs to provide better clinical care when evaluating skin lesions.

Understanding skin color bias in deep learning-based skin lesion segmentation

BACKGROUND

The field of dermatological image analysis using deep neural networks includes the semantic segmentation of skin lesions, pivotal for lesion analysis, pathology inference, and diagnoses. While biases in neural network-based dermatoscopic image classification against darker skin tones due to dataset imbalance and contrast disparities are acknowledged, a comprehensive exploration of skin color bias in lesion segmentation models is lacking. It is imperative to address and understand the biases in these models.

METHODS

Our study comprehensively evaluates skin tone bias within prevalent neural networks for skin lesion segmentation. Since no information about skin color exists in widely used datasets, to quantify the bias we use three distinct skin color estimation methods: Fitzpatrick skin type estimation, Individual Typology Angle estimation as well as manual grouping of images by skin color. We assess bias across common models by training a variety of U-Net-based models on three widely-used datasets with 1758 different dermoscopic and clinical images. We also evaluate commonly suggested methods to mitigate bias.

RESULTS

Our findings expose a significant and large correlation between segmentation performance and skin color, revealing consistent challenges in segmenting lesions for darker skin tones across diverse datasets. Using various methods of skin color quantification, we have found significant bias in skin lesion segmentation against darker-skinned individuals when evaluated both in and out-of-sample. We also find that commonly used methods for bias mitigation do not result in any significant reduction in bias.

CONCLUSIONS

Our findings suggest a pervasive bias in most published lesion segmentation methods, given our use of commonly employed neural network architectures and publicly available datasets. In light of our findings, we propose recommendations for unbiased dataset collection, labeling, and model development. This presents the first comprehensive evaluation of fairness in skin lesion segmentation.

Demonstration of Convolutional Neural Networks to Determine Patch Test Reactivity

Background: Convolutional neural networks (CNNs) have the potential to assist allergists and dermatologists in the analysis of patch tests. Such models can help reduce interprovider variability and improve consistency of patch test interpretations. Objective: Our aim is to evaluate the performance of a CNN model as a proof of concept in discriminating between patch tests with reactions and patch tests without reactions. Methods: We performed a retrospective analysis of patch test images from March 2020 to March 2021. The CNN model was trained as a binary classifier to discriminate between reaction and nonreaction patches. Performance of the model was determined using summary statistics and receiver operator characteristics (ROC) curves. Results: In total, 13,622 images from 125 patients were recorded for analysis. The majority of patients in the cohort were female (81.6%) with Fitzpatrick skin types I-II (88.0%). The area under curve was 0.940, indicating a high discriminative performance of the model for this data set. This resulted in a total accuracy of 90.1%, sensitivity of 86.0%, and specificity of 90.2%. Conclusions: CNNs have the capacity to determine the presence of delayed-type reactions in patch tests. Future prospective studies are required to assess the generalizability of such models.