A new deep learning approach integrated with clinical data for the dermoscopic differentiation of early melanomas from atypical nevi

A Narrative Review: Opportunities and Challenges in Artificial Intelligence Skin Image Analyses Using Total Body Photography

Artificial intelligence (AI) algorithms for skin lesion classification have reported accuracy at par with and even outperformance of expert dermatologists in experimental settings. However, the majority of algorithms do not represent real-world clinical approach where skin phenotype and clinical background information are considered. We review the current state of AI for skin lesion classification and present opportunities and challenges when applied to total body photography (TBP). AI in TBP analysis presents opportunities for intrapatient assessment of skin phenotype and holistic risk assessment by incorporating patient-level metadata, although challenges exist for protecting patient privacy in algorithm development and improving explainable AI methods.

A systematic review and meta-analysis of artificial intelligence versus clinicians for skin cancer diagnosis

Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance.

The role of artificial intelligence and convolutional neural networks in the management of melanoma: a clinical, pathological, and radiological perspective

Clinical dermatoscopy and pathological slide assessment are essential in the diagnosis and management of patients with cutaneous melanoma. For those presenting with stage IIC disease and beyond, radiological investigations are often considered. The dermatoscopic, whole slide and radiological images used during clinical care are often stored digitally, enabling artificial intelligence (AI) and convolutional neural networks (CNN) to learn, analyse and contribute to the clinical decision-making. A keyword search of the Medline database was performed to assess the progression, capabilities and limitations of AI and CNN and its use in diagnosis and management of cutaneous melanoma. Full-text articles were reviewed if they related to dermatoscopy, pathological slide assessment or radiology. Through analysis of 95 studies, we demonstrate that diagnostic accuracy of AI/CNN can be superior (or at least equal) to clinicians. However, variability in image acquisition, pre-processing, segmentation, and feature extraction remains challenging. With current technological abilities, AI/CNN and clinicians synergistically working together are better than one another in all subspecialty domains relating to cutaneous melanoma. AI has the potential to enhance the diagnostic capabilities of junior dermatology trainees, primary care skin cancer clinicians and general practitioners. For experienced clinicians, AI provides a cost-efficient second opinion. From a pathological and radiological perspective, CNN has the potential to improve workflow efficiency, allowing clinicians to achieve more in a finite amount of time. Until the challenges of AI/CNN are reliably met, however, they can only remain an adjunct to clinical decision-making.

A European Multicentric Investigation of Atypical Melanocytic Skin Lesions of Palms and Soles: The iDScore-PalmoPlantar Database

Background: The differential diagnosis of atypical melanocytic palmoplantar skin lesions (aMPLs) represents a diagnostic challenge, including atypical nevi (AN) and early melanomas (MMs) that display overlapping clinical and dermoscopic features. We aimed to set up a multicentric dataset of aMPL dermoscopic cases paired with multiple anamnestic risk factors and demographic and morphologic data. Methods: Each aMPL case was paired with a dermoscopic and clinical picture and a series of lesion-related data (maximum diameter value; location on the palm/sole in 17 areas; histologic diagnosis; and patient-related data (age, sex, family history of melanoma/sunburns, phototype, pheomelanin, eye/hair color, multiple/dysplastic body nevi, and traumatism on palms/soles). Results: A total of 542 aMPL cases-113 MM and 429 AN-were collected from 195 males and 347 females. No sex prevalence was found for melanomas, while women were found to have relatively more nevi. Melanomas were prevalent on the heel, plantar arch, and fingers in patients aged 65.3 on average, with an average diameter of 17 mm. Atypical nevi were prevalent on the plantar arch and palmar area of patients aged 41.33 on average, with an average diameter of 7 mm. Conclusions: Keeping in mind the risk profile of an aMPL patient can help obtain a timely differentiation between malignant/benign cases, thus avoiding delayed and inappropriate excision, respectively, with the latter often causing discomfort/dysfunctional scarring, especially at acral sites.

A risk-scoring model for the differential diagnosis of lentigo maligna and other atypical pigmented facial lesions of the face: The facial iDScore

BACKGROUND

Due to progressive ageing of the population, the incidence of facial lentigo maligna (LM) of the face is increasing. Many benign simulators of LM and LMM, known as atypical pigmented facial lesions (aPFLs-pigmented actinic keratosis, solar lentigo, seborrheic keratosis, seborrheic-lichenoid keratosis, atypical nevus) may be found on photodamaged skin. This generates many diagnostic issues and increases the number of biopsies, with a subsequent impact on aesthetic outcome and health insurance costs.

OBJECTIVES

Our aim was to develop a risk-scoring classifier-based algorithm to estimate the probability of an aPFL being malignant. A second aim was to compare its diagnostic accuracy with that of dermoscopists so as to define the advantages of using the model in patient management.

MATERIALS AND METHODS

A total of 154 dermatologists analysed 1111 aPFLs and their management in a teledermatology setting: They performed pattern analysis, gave an intuitive clinical diagnosis and proposed lesion management options (follow-up/reflectance confocal microscopy/biopsy). Each case was composed of a dermoscopic and/or clinical picture plus metadata (histology, age, sex, location, diameter). The risk-scoring classifier was developed and tested on this dataset and then validated on 86 additional aPFLs.

RESULTS

The facial Integrated Dermoscopic Score (iDScore) model consisted of seven dermoscopic variables and three objective parameters (diameter ≥ 8 mm, age ≥ 70 years, male sex); the score ranged from 0 to 16. In the testing set, the facial iDScore-aided diagnosis was more accurate (AUC = 0.79 [IC 95% 0.757-0.843]) than the intuitive diagnosis proposed by dermatologists (average of 43.5%). In the management study, the score model reduced the number of benign lesions sent for biopsies by 41.5% and increased the number of LM/LMM cases sent for reflectance confocal microscopy or biopsy instead of follow-up by 66%.

CONCLUSIONS

The facial iDScore can be proposed as a feasible tool for managing patients with aPFLs.

Analysis of Artificial Intelligence-Based Approaches Applied to Non-Invasive Imaging for Early Detection of Melanoma: A Systematic Review

BACKGROUND

Melanoma, the deadliest form of skin cancer, poses a significant public health challenge worldwide. Early detection is crucial for improved patient outcomes. Non-invasive skin imaging techniques allow for improved diagnostic accuracy; however, their use is often limited due to the need for skilled practitioners trained to interpret images in a standardized fashion. Recent innovations in artificial intelligence (AI)-based techniques for skin lesion image interpretation show potential for the use of AI in the early detection of melanoma.

OBJECTIVE

The aim of this study was to evaluate the current state of AI-based techniques used in combination with non-invasive diagnostic imaging modalities including reflectance confocal microscopy (RCM), optical coherence tomography (OCT), and dermoscopy. We also aimed to determine whether the application of AI-based techniques can lead to improved diagnostic accuracy of melanoma.

METHODS

A systematic search was conducted via the Medline/PubMed, Cochrane, and Embase databases for eligible publications between 2018 and 2022. Screening methods adhered to the 2020 version of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Included studies utilized AI-based algorithms for melanoma detection and directly addressed the review objectives.

RESULTS

We retrieved 40 papers amongst the three databases. All studies directly comparing the performance of AI-based techniques with dermatologists reported the superior or equivalent performance of AI-based techniques in improving the detection of melanoma. In studies directly comparing algorithm performance on dermoscopy images to dermatologists, AI-based algorithms achieved a higher ROC (>80%) in the detection of melanoma. In these comparative studies using dermoscopic images, the mean algorithm sensitivity was 83.01% and the mean algorithm specificity was 85.58%. Studies evaluating machine learning in conjunction with OCT boasted accuracy of 95%, while studies evaluating RCM reported a mean accuracy rate of 82.72%.

CONCLUSIONS

Our results demonstrate the robust potential of AI-based techniques to improve diagnostic accuracy and patient outcomes through the early identification of melanoma. Further studies are needed to assess the generalizability of these AI-based techniques across different populations and skin types, improve standardization in image processing, and further compare the performance of AI-based techniques with board-certified dermatologists to evaluate clinical applicability.

Differentiating between early melanomas and melanocytic nevi: A state-of-the-art review

Clinicians and dermatologists are challenged by accurate diagnosis of melanocytic lesions, due to melanoma's resemblance to benign skin conditions. Several methodologies have been proposed to diagnose melanoma, and to differentiate between a cancerous and a benign skin condition. First, the ABCD rule and Menzies method use skin lesion characteristics to interpret the condition. The 7-point checklist, 3-point checklist, and CASH algorithm are score-based methods. Each of these methods attributes a score point to the features found on the skin lesion. Furthermore, reflectance confocal microscopy (RCM), an integrated clinical and dermoscopic risk scoring system (iDscore), and a deep convoluted neural network (DCNN) also aids in diagnosis. RCM optically sections live tissues to reveal morphological and cellular structures. The skin lesion's clinical parameters determine iDscore's score point system. The DCNN model is based on a detailed learning algorithm. Therefore, we discuss the conventional and new methodologies for the identification of skin diseases. Moreover, our review attempts to provide clinicians with a comprehensible summary of the wide range of techniques that can help differentiate between early melanomas and melanocytic nevi.

Development and Implementation of a Web-Based International Registry Dedicated to Atypical Pigmented Skin Lesions of the Face: Teledermatologic Investigation on Epidemiology and Risk Factors

Background: Atypical pigmented facial lesions (aPFLs) often display clinical and dermoscopic equivocal and/or overlapping features, thus causing a challenging and delayed diagnosis and/or inappropriate excisions. No specific registry dedicated to aPFL paired with clinical data is available to date. Methods: The dataset is hosted on a specifically designed web platform. Each complete case was composed of the following data: (1) one dermoscopic picture; (2) one clinical picture; (3) two lesion data, that is, maximum diameter and facial location (e.g., orbital area/forehead/nose/cheek/chin/mouth); (4) patient's demographics: family history of melanoma, history of sunburns in childhood, phototype, pheomelanine, eyes/hair color, multiple nevi/dysplastic nevi on the body; and (5) acquisition device (videodermatoscope/camera-based/smartphone-based system). Results: A total of 11 dermatologic centers contributed to a final teledermoscopy database of 1,197 aPFL with a distribution of 353 lentigo maligna (LM), 146 lentigo maligna melanoma (LMM), 231 pigmented actinic keratoses, 266 solar lentigo, 125 atypical nevi, 48 seborrheic keratosis, and 28 seborrheic-lichenoid keratoses. The cheek site was involved in half of aPFL cases (50%). Compared with those with the other aPFL cases, patients with LM/LMM were predominantly men, older (69.32 ± 12.9 years on average vs. 62.69 ± 14.51), exhibited larger lesions (11.88 ± 7.74 mm average maximum diameter vs. 9.33 ± 6.46 mm), and reported a positive history of sunburn in childhood. Conclusions: The iDScore facial dataset currently represents a precious source of data suitable for the design of diagnostic support tools based on risk scoring classifiers to help dermatologists in recognizing LM/LMM among challenging aPFL in clinical practice.

Assist-Dermo: A Lightweight Separable Vision Transformer Model for Multiclass Skin Lesion Classification

A dermatologist-like automatic classification system is developed in this paper to recognize nine different classes of pigmented skin lesions (PSLs), using a separable vision transformer (SVT) technique to assist clinical experts in early skin cancer detection. In the past, researchers have developed a few systems to recognize nine classes of PSLs. However, they often require enormous computations to achieve high performance, which is burdensome to deploy on resource-constrained devices. In this paper, a new approach to designing SVT architecture is developed based on SqueezeNet and depthwise separable CNN models. The primary goal is to find a deep learning architecture with few parameters that has comparable accuracy to state-of-the-art (SOTA) architectures. This paper modifies the SqueezeNet design for improved runtime performance by utilizing depthwise separable convolutions rather than simple conventional units. To develop this Assist-Dermo system, a data augmentation technique is applied to control the PSL imbalance problem. Next, a pre-processing step is integrated to select the most dominant region and then enhance the lesion patterns in a perceptual-oriented color space. Afterwards, the Assist-Dermo system is designed to improve efficacy and performance with several layers and multiple filter sizes but fewer filters and parameters. For the training and evaluation of Assist-Dermo models, a set of PSL images is collected from different online data sources such as Ph2, ISBI-2017, HAM10000, and ISIC to recognize nine classes of PSLs. On the chosen dataset, it achieves an accuracy (ACC) of 95.6%, a sensitivity (SE) of 96.7%, a specificity (SP) of 95%, and an area under the curve (AUC) of 0.95. The experimental results show that the suggested Assist-Dermo technique outperformed SOTA algorithms when recognizing nine classes of PSLs. The Assist-Dermo system performed better than other competitive systems and can support dermatologists in the diagnosis of a wide variety of PSLs through dermoscopy. The Assist-Dermo model code is freely available on GitHub for the scientific community.

Recent Advances in Melanoma Diagnosis and Prognosis Using Machine Learning Methods

PURPOSE OF REVIEW

The purpose was to summarize the current role and state of artificial intelligence and machine learning in the diagnosis and management of melanoma.

RECENT FINDINGS

Deep learning algorithms can identify melanoma from clinical, dermoscopic, and whole slide pathology images with increasing accuracy. Efforts to provide more granular annotation to datasets and to identify new predictors are ongoing. There have been many incremental advances in both melanoma diagnostics and prognostic tools using artificial intelligence and machine learning. Higher quality input data will further improve these models' capabilities.

Artificial intelligence applications in pediatric oncology diagnosis

Artificial intelligence (AI) algorithms have been applied in abundant medical tasks with high accuracy and efficiency. Physicians can improve their diagnostic efficiency with the assistance of AI techniques for improving the subsequent personalized treatment and surveillance. AI algorithms fundamentally capture data, identify underlying patterns, achieve preset endpoints, and provide decisions and predictions about real-world events with working principles of machine learning and deep learning. AI algorithms with sufficient graphic processing unit power have been demonstrated to provide timely diagnostic references based on preliminary training of large amounts of clinical and imaging data. The sample size issue is an inevitable challenge for pediatric oncology considering its low morbidity and individual heterogeneity. However, this problem may be solved in the near future considering the exponential advancements of AI algorithms technically to decrease the dependence of AI operation on the amount of data sets and the efficiency of computing power. For instance, it could be a feasible solution by shifting convolutional neural networks (CNNs) from adults and sharing CNN algorithms across multiple institutions besides original data. The present review provides important insights into emerging AI applications for the diagnosis of pediatric oncology by systematically overviewing of up-to-date literature.

A deep learning-based approach toward differentiating scalp psoriasis and seborrheic dermatitis from dermoscopic images

OBJECTIVES

This study aims to develop a new diagnostic method for discriminating scalp psoriasis and seborrheic dermatitis based on a deep learning (DL) model, which uses the dermatoscopic image as input and achieved higher accuracy than dermatologists trained with dermoscopy.

METHODS

A total of 1,358 pictures (obtained from 617 patients) with pathological and diagnostic confirmed skin diseases (508 psoriases, 850 seborrheic dermatitides) were randomly allocated into the training, validation, and testing datasets (1,088/134/136) in this study. A DL model concerning dermatoscopic images was established using the transfer learning technique and trained for diagnosing two diseases.

RESULTS

The developed DL model exhibits good sensitivity, specificity, and Area Under Curve (AUC) (96.1, 88.2, and 0.922%, respectively), it outperformed all dermatologists in the diagnosis of scalp psoriasis and seborrheic dermatitis when compared to five dermatologists with various levels of experience. Furthermore, non-proficient doctors with the assistance of the DL model can achieve comparable diagnostic performance to dermatologists proficient in dermoscopy. One dermatology graduate student and two general practitioners significantly improved their diagnostic performance, where their AUC values increased from 0.600, 0.537, and 0.575 to 0.849, 0.778, and 0.788, respectively, and their diagnosis consistency was also improved as the kappa values went from 0.191, 0.071, and 0.143 to 0.679, 0.550, and 0.568, respectively. DL enjoys favorable computational efficiency and requires few computational resources, making it easy to deploy in hospitals.

CONCLUSIONS

The developed DL model has favorable performance in discriminating two skin diseases and can improve the diagnosis, clinical decision-making, and treatment of dermatologists in primary hospitals.

The Impact of Artificial Intelligence on Health Equity in Oncology: Scoping Review

BACKGROUND

The field of oncology is at the forefront of advances in artificial intelligence (AI) in health care, providing an opportunity to examine the early integration of these technologies in clinical research and patient care. Hope that AI will revolutionize health care delivery and improve clinical outcomes has been accompanied by concerns about the impact of these technologies on health equity.

OBJECTIVE

We aimed to conduct a scoping review of the literature to address the question, "What are the current and potential impacts of AI technologies on health equity in oncology?"

METHODS

Following PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines for scoping reviews, we systematically searched MEDLINE and Embase electronic databases from January 2000 to August 2021 for records engaging with key concepts of AI, health equity, and oncology. We included all English-language articles that engaged with the 3 key concepts. Articles were analyzed qualitatively for themes pertaining to the influence of AI on health equity in oncology.

RESULTS

Of the 14,011 records, 133 (0.95%) identified from our review were included. We identified 3 general themes in the literature: the use of AI to reduce health care disparities (58/133, 43.6%), concerns surrounding AI technologies and bias (16/133, 12.1%), and the use of AI to examine biological and social determinants of health (55/133, 41.4%). A total of 3% (4/133) of articles focused on many of these themes.

CONCLUSIONS

Our scoping review revealed 3 main themes on the impact of AI on health equity in oncology, which relate to AI's ability to help address health disparities, its potential to mitigate or exacerbate bias, and its capability to help elucidate determinants of health. Gaps in the literature included a lack of discussion of ethical challenges with the application of AI technologies in low- and middle-income countries, lack of discussion of problems of bias in AI algorithms, and a lack of justification for the use of AI technologies over traditional statistical methods to address specific research questions in oncology. Our review highlights a need to address these gaps to ensure a more equitable integration of AI in cancer research and clinical practice. The limitations of our study include its exploratory nature, its focus on oncology as opposed to all health care sectors, and its analysis of solely English-language articles.

Lesion identification and malignancy prediction from clinical dermatological images

We consider machine-learning-based lesion identification and malignancy prediction from clinical dermatological images, which can be indistinctly acquired via smartphone or dermoscopy capture. Additionally, we do not assume that images contain single lesions, thus the framework supports both focal or wide-field images. Specifically, we propose a two-stage approach in which we first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy that can be used for high-level screening processes. Further, we consider augmenting the proposed approach with clinical covariates (from electronic health records) and publicly available data (the ISIC dataset). Comprehensive experiments validated on an independent test dataset demonstrate that (1) the proposed approach outperforms alternative model architectures; (2) the model based on images outperforms a pure clinical model by a large margin, and the combination of images and clinical data does not significantly improves over the image-only model; and (3) the proposed framework offers comparable performance in terms of malignancy classification relative to three board certified dermatologists with different levels of experience.

Automatic Classification of Melanoma Skin Cancer with Deep Convolutional Neural Networks

Melanoma skin cancer is one of the most dangerous types of skin cancer, which, if not diagnosed early, may lead to death. Therefore, an accurate diagnosis is needed to detect melanoma. Traditionally, a dermatologist utilizes a microscope to inspect and then provide a report on a biopsy for diagnosis; however, this diagnosis process is not easy and requires experience. Hence, there is a need to facilitate the diagnosis process while still yielding an accurate diagnosis. For this purpose, artificial intelligence techniques can assist the dermatologist in carrying out diagnosis. In this study, we considered the detection of melanoma through deep learning based on cutaneous image processing. For this purpose, we tested several convolutional neural network (CNN) architectures, including DenseNet201, MobileNetV2, ResNet50V2, ResNet152V2, Xception, VGG16, VGG19, and GoogleNet, and evaluated the associated deep learning models on graphical processing units (GPUs). A dataset consisting of 7146 images was processed using these models, and we compared the obtained results. The experimental results showed that GoogleNet can obtain the highest performance accuracy on both the training and test sets (74.91% and 76.08%, respectively).

Early Melanoma Diagnosis With Sequential Dermoscopic Images

Dermatologists often diagnose or rule out early melanoma by evaluating the follow-up dermoscopic images of skin lesions. However, existing algorithms for early melanoma diagnosis are developed using single time-point images of lesions. Ignoring the temporal, morphological changes of lesions can lead to misdiagnosis in borderline cases. In this study, we propose a framework for automated early melanoma diagnosis using sequential dermoscopic images. To this end, we construct our method in three steps. First, we align sequential dermoscopic images of skin lesions using estimated Euclidean transformations, extract the lesion growth region by computing image differences among the consecutive images, and then propose a spatio-temporal network to capture the dermoscopic changes from aligned lesion images and the corresponding difference images. Finally, we develop an early diagnosis module to compute probability scores of malignancy for lesion images over time. We collected 179 serial dermoscopic imaging data from 122 patients to verify our method. Extensive experiments show that the proposed model outperforms other commonly used sequence models. We also compared the diagnostic results of our model with those of seven experienced dermatologists and five registrars. Our model achieved higher diagnostic accuracy than clinicians (63.69% vs. 54.33%, respectively) and provided an earlier diagnosis of melanoma (60.7% vs. 32.7% of melanoma correctly diagnosed on the first follow-up images). These results demonstrate that our model can be used to identify melanocytic lesions that are at high-risk of malignant transformation earlier in the disease process and thereby redefine what is possible in the early detection of melanoma.

Segmentation of Aorta 3D CT Images Based on 2D Convolutional Neural Networks

The automatic segmentation of the aorta can be extremely useful in clinical practice, allowing the diagnosis of numerous pathologies to be sped up, such as aneurysms and dissections, and allowing rapid reconstructive surgery, essential in saving patients’ lives. In recent years, the success of Deep Learning (DL)-based decision support systems has increased their popularity in the medical field. However, their effective application is often limited by the scarcity of training data. In fact, collecting large annotated datasets is usually difficult and expensive, especially in the biomedical domain. In this paper, an automatic method for aortic segmentation, based on 2D convolutional neural networks (CNNs), using 3D CT (computed axial tomography) scans as input is presented. For this purpose, a set of 153 CT images was collected and a semi-automated approach was used to obtain their 3D annotations at the voxel level. Although less accurate, the use of a semi-supervised labeling technique instead of a full supervision proved necessary to obtain enough data in a reasonable amount of time. The 3D volume was analyzed using three 2D segmentation networks, one for each of the three CT views (axial, coronal and sagittal). Two different network architectures, U-Net and LinkNet, were used and compared. The main advantages of the proposed method lie in its ability to work with a reduced number of data even with noisy targets. In addition, analyzing 3D scans based on 2D slices allows for them to be processed even with limited computing power. The results obtained are promising and show that the neural networks employed can provide accurate segmentation of the aorta.

Design and Assessment of Convolutional Neural Network Based Methods for Vitiligo Diagnosis

Background: Today's machine-learning based dermatologic research has largely focused on pigmented/non-pigmented lesions concerning skin cancers. However, studies on machine-learning-aided diagnosis of depigmented non-melanocytic lesions, which are more difficult to diagnose by unaided eye, are very few. Objective: We aim to assess the performance of deep learning methods for diagnosing vitiligo by deploying Convolutional Neural Networks (CNNs) and comparing their diagnosis accuracy with that of human raters with different levels of experience. Methods: A Chinese in-house dataset (2,876 images) and a world-wide public dataset (1,341 images) containing vitiligo and other depigmented/hypopigmented lesions were constructed. Three CNN models were trained on close-up images in both datasets. The results by the CNNs were compared with those by 14 human raters from four groups: expert raters (>10 years of experience), intermediate raters (5-10 years), dermatology residents, and general practitioners. F1 score, the area under the receiver operating characteristic curve (AUC), specificity, and sensitivity metrics were used to compare the performance of the CNNs with that of the raters. Results: For the in-house dataset, CNNs achieved a comparable F1 score (mean [standard deviation]) with expert raters (0.8864 [0.005] vs. 0.8933 [0.044]) and outperformed intermediate raters (0.7603 [0.029]), dermatology residents (0.6161 [0.068]) and general practitioners (0.4964 [0.139]). For the public dataset, CNNs achieved a higher F1 score (0.9684 [0.005]) compared to the diagnosis of expert raters (0.9221 [0.031]). Conclusion: Properly designed and trained CNNs are able to diagnose vitiligo without the aid of Wood's lamp images and outperform human raters in an experimental setting.

Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis

Background and Objectives: A few deep learning studies have reported that combining image features with patient variables enhanced identification accuracy compared with image-only models. However, previous studies have not statistically reported the additional effect of patient variables on the image-only models. This study aimed to statistically evaluate the osteoporosis identification ability of deep learning by combining hip radiographs with patient variables. Materials andMethods: We collected a dataset containing 1699 images from patients who underwent skeletal-bone-mineral density measurements and hip radiography at a general hospital from 2014 to 2021. Osteoporosis was assessed from hip radiographs using convolutional neural network (CNN) models (ResNet18, 34, 50, 101, and 152). We also investigated ensemble models with patient clinical variables added to each CNN. Accuracy, precision, recall, specificity, F1 score, and area under the curve (AUC) were calculated as performance metrics. Furthermore, we statistically compared the accuracy of the image-only model with that of an ensemble model that included images plus patient factors, including effect size for each performance metric. Results: All metrics were improved in the ResNet34 ensemble model compared with the image-only model. The AUC score in the ensemble model was significantly improved compared with the image-only model (difference 0.004; 95% CI 0.002–0.0007; p = 0.0004, effect size: 0.871). Conclusions: This study revealed the additional effect of patient variables in identification of osteoporosis using deep CNNs with hip radiographs. Our results provided evidence that the patient variables had additive synergistic effects on the image in osteoporosis identification.