Automatic discrimination of actinic keratoses from clinical photographs

Where Artificial Intelligence Can Take Us in the Management and Understanding of Cancerization Fields

Squamous cell carcinoma and its precursor lesion actinic keratosis are often found together in areas of skin chronically exposed to sun, otherwise called cancerisation fields. The clinical assessment of cancerisation fields and the correct diagnosis of lesions within these fields is usually challenging for dermatologists. The recent adoption of skin cancer diagnostic imaging techniques, particularly LC-OCT, helps clinicians in guiding treatment decisions of cancerization fields in a non-invasive way. The combination of artificial intelligence and non-invasive skin imaging opens up many possibilities as AI can perform tasks impossible for humans in a reasonable amount of time. In this text we review past examples of the application of AI to dermatological images for actinic keratosis/squamous cell carcinoma diagnosis, and we discuss about the prospects of the application of AI for the characterization and management of cancerization fields.

The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild

AK is a common precancerous skin condition that requires effective detection and treatment monitoring. To improve the monitoring of the AK burden in clinical settings with enhanced automation and precision, the present study evaluates the application of semantic segmentation based on the U-Net architecture (i.e., AKU-Net). AKU-Net employs transfer learning to compensate for the relatively small dataset of annotated images and integrates a recurrent process based on convLSTM to exploit contextual information and address the challenges related to the low contrast and ambiguous boundaries of AK-affected skin regions. We used an annotated dataset of 569 clinical photographs from 115 patients with actinic keratosis to train and evaluate the model. From each photograph, patches of 512 × 512 pixels were extracted using translation lesion boxes that encompassed lesions in different positions and captured different contexts of perilesional skin. In total, 16,488 translation-augmented crops were used for training the model, and 403 lesion center crops were used for testing. To demonstrate the improvements in AK detection, AKU-Net was compared with plain U-Net and U-Net++ architectures. The experimental results highlighted the effectiveness of AKU-Net, improving upon both automation and precision over existing approaches, paving the way for more effective and reliable evaluation of actinic keratosis in clinical settings.

The accuracy of artificial intelligence used for non-melanoma skin cancer diagnoses: a meta-analysis

BACKGROUND

With rising incidence of skin cancer and relatively increased mortality rates, an improved diagnosis of such a potentially fatal disease is of vital importance. Although frequently curable, it nevertheless places a considerable burden upon healthcare systems. Among the various types of skin cancers, non-melanoma skin cancer is most prevalent. Despite such prevalence and its associated cost, scant proof concerning the diagnostic accuracy via Artificial Intelligence (AI) for non-melanoma skin cancer exists. This study meta-analyzes the diagnostic test accuracy of AI used to diagnose non-melanoma forms of skin cancer, and it identifies potential covariates that account for heterogeneity between extant studies.

METHODS

Various electronic databases (Scopus, PubMed, ScienceDirect, SpringerLink, and Dimensions) were examined to discern eligible studies beginning from March 2022. Those AI studies predictive of non-melanoma skin cancer were included. Summary estimates of sensitivity, specificity, and area under receiver operating characteristic curves were used to evaluate diagnostic accuracy. The revised Quality Assessment of Diagnostic Studies served to assess any risk of bias.

RESULTS

A literature search produced 39 eligible articles for meta-analysis. The summary sensitivity, specificity, and area under receiver operating characteristic curve of AI for diagnosing non-melanoma skin cancer was 0.78, 0.98, & 0.97, respectively. Skin cancer typology, data sources, cross validation, ensemble models, types of techniques, pre-trained models, and image augmentation became significant covariates accounting for heterogeneity in terms of both sensitivity and/or specificity.

CONCLUSIONS

Meta-analysis results revealed that AI is predictive of non-melanoma with an acceptable performance, but sensitivity may become improved. Further, ensemble models and pre-trained models are employable to improve true positive rating.

Image Perceptual Similarity Metrics for the Assessment of Basal Cell Carcinoma

Efficient management of basal cell carcinomas (BCC) requires reliable assessments of both tumors and post-treatment scars. We aimed to estimate image similarity metrics that account for BCC's perceptual color and texture deviation from perilesional skin. In total, 176 clinical photographs of BCC were assessed by six physicians using a visual deviation scale. Internal consistency and inter-rater agreement were estimated using Cronbach's α, weighted Gwet's AC2, and quadratic Cohen's kappa. The mean visual scores were used to validate a range of similarity metrics employing different color spaces, distances, and image embeddings from a pre-trained VGG16 neural network. The calculated similarities were transformed into discrete values using ordinal logistic regression models. The Bray-Curtis distance in the YIQ color model and rectified embeddings from the 'fc6' layer minimized the mean squared error and demonstrated strong performance in representing perceptual similarities. Box plot analysis and the Wilcoxon rank-sum test were used to visualize and compare the levels of agreement, conducted on a random validation round between the two groups: 'Human-System' and 'Human-Human.' The proposed metrics were comparable in terms of internal consistency and agreement with human raters. The findings suggest that the proposed metrics offer a robust and cost-effective approach to monitoring BCC treatment outcomes in clinical settings.

A Deep Learning Based Framework for Diagnosing Multiple Skin Diseases in a Clinical Environment

Background: Numerous studies have attempted to apply artificial intelligence (AI) in the dermatological field, mainly on the classification and segmentation of various dermatoses. However, researches under real clinical settings are scarce. Objectives: This study was aimed to construct a novel framework based on deep learning trained by a dataset that represented the real clinical environment in a tertiary class hospital in China, for better adaptation of the AI application in clinical practice among Asian patients. Methods: Our dataset was composed of 13,603 dermatologist-labeled dermoscopic images, containing 14 categories of diseases, namely lichen planus (LP), rosacea (Rosa), viral warts (VW), acne vulgaris (AV), keloid and hypertrophic scar (KAHS), eczema and dermatitis (EAD), dermatofibroma (DF), seborrheic dermatitis (SD), seborrheic keratosis (SK), melanocytic nevus (MN), hemangioma (Hem), psoriasis (Pso), port wine stain (PWS), and basal cell carcinoma (BCC). In this study, we applied Google's EfficientNet-b4 with pre-trained weights on ImageNet as the backbone of our CNN architecture. The final fully-connected classification layer was replaced with 14 output neurons. We added seven auxiliary classifiers to each of the intermediate layer groups. The modified model was retrained with our dataset and implemented using Pytorch. We constructed saliency maps to visualize our network's attention area of input images for its prediction. To explore the visual characteristics of different clinical classes, we also examined the internal image features learned by the proposed framework using t-SNE (t-distributed Stochastic Neighbor Embedding). Results: Test results showed that the proposed framework achieved a high level of classification performance with an overall accuracy of 0.948, a sensitivity of 0.934 and a specificity of 0.950. We also compared the performance of our algorithm with three most widely used CNN models which showed our model outperformed existing models with the highest area under curve (AUC) of 0.985. We further compared this model with 280 board-certificated dermatologists, and results showed a comparable performance level in an 8-class diagnostic task. Conclusions: The proposed framework retrained by the dataset that represented the real clinical environment in our department could accurately classify most common dermatoses that we encountered during outpatient practice including infectious and inflammatory dermatoses, benign and malignant cutaneous tumors.

Classification of Dermoscopy Skin Lesion Color-Images Using Fractal-Deep Learning Features

The detection of skin diseases is becoming one of the priority tasks worldwide due to the increasing amount of skin cancer. Computer-aided diagnosis is a helpful tool to help dermatologists in the detection of these kinds of illnesses. This work proposes a computer-aided diagnosis based on 1D fractal signatures of texture-based features combining with deep-learning features using transferred learning based in Densenet-201. This proposal works with three 1D fractal signatures built per color-image. The energy, variance, and entropy of the fractal signatures are used combined with 100 features extracted from Densenet-201 to construct the features vector. Because commonly, the classes in the dataset of skin lesion images are imbalanced, we use the technique of ensemble of classifiers: K-nearest neighbors and two types of support vector machines. The computer-aided diagnosis output was determined based on the linear plurality vote. In this work, we obtained an average accuracy of 97.35%, an average precision of 91.61%, an average sensitivity of 66.45%, and an average specificity of 97.85% in the eight classes’ classification in the International Skin Imaging Collaboration (ISIC) archive-2019.

Artificial Intelligence Applications in Dermatology: Where Do We Stand?

Artificial intelligence (AI) has become a progressively prevalent Research Topic in medicine and is increasingly being applied to dermatology. There is a need to understand this technology's progress to help guide and shape the future for medical care providers and recipients. We reviewed the literature to evaluate the types of publications on the subject, the specific dermatological topics addressed by AI, and the most challenging barriers to its implementation. A substantial number of original articles and commentaries have been published to date and only few detailed reviews exist. Most AI applications focus on differentiating between benign and malignant skin lesions, however; others exist pertaining to ulcers, inflammatory skin diseases, allergen exposure, dermatopathology, and gene expression profiling. Applications commonly analyze and classify images, however, other tools such as risk assessment calculators are becoming increasingly available. Although many applications are technologically feasible, important implementation barriers have been identified including systematic biases, difficulty of standardization, interpretability, and acceptance by physicians and patients alike. This review provides insight into future research needs and possibilities. There is a strong need for clinical investigation in dermatology providing evidence of success overcoming the identified barriers. With these research goals in mind, an appropriate role for AI in dermatology may be achieved in not so distant future.

The impact of patient clinical information on automated skin cancer detection

Skin cancer is one of the most common types of cancer worldwide. Over the past few years, different approaches have been proposed to deal with automated skin cancer detection. Nonetheless, most of them are based only on dermoscopic images and do not take into account the patient clinical information, an important clue towards clinical diagnosis. In this work, we present an approach to fill this gap. First, we introduce a new dataset composed of clinical images, collected using smartphones, and clinical data related to the patient. Next, we propose a straightforward method that includes an aggregation mechanism in well-known deep learning models to combine features from images and clinical data. Last, we carry out experiments to compare the models' performance with and without using this mechanism. The results present an improvement of approximately 7% in balanced accuracy when the aggregation method is applied. Overall, the impact of clinical data on models' performance is significant and shows the importance of including these features on automated skin cancer detection.

Cryosurgery, Intralesional Methotrexate and Imiquimod for Keratoacanthoma: Tuning the Combination

Keratoacanthomas (KA) are self-regressing, destructively expanding keratinocyte skin neoplasms typically characterized by sudden onset of explosive growth followed by complete involution. Cryosurgery, intralesional methotrexate and imiquimod have been used alone or in combination of two for the treatment of KA. Presently 3 patients (49, 60, and 65 years old; two females, one suspected with Ferguson-Smith syndrome), with 5 KA (6–24 mm maximal diameter) were treated with the combination of cryosurgery (liquid N₂, open spray, 2 cycles of 15 sec each) and intralesional methotrexate (2.5–30 mg cumulative dose) and subsequent daily application of imiquimod (14–35 days). Starting with 4 cryosurgery/intralesional methotrexate sessions and 5 weeks daily imiquimod, to document feasibility and efficacy we progressively reduced the intensity of the treatment to one cryosurgery/intralesional methotrexate (total dose: 5 mg) session and 14 days of daily imiquimod without compromising efficacy. KA stopped growing promptly with sustained clearance after 6–24 months follow up, implicating a huge potential of therapeutic synergy of the employed modalities in the management of KA. We suggest that, optimized, the present three modalities combination (one session mild cryosurgery/low dose, 5 mg intralesional methotrexate and 2 weeks once daily imiquimod) is a promising treatment for KA that merits evaluation in further studies.

Systematic review of machine learning for diagnosis and prognosis in dermatology

Background: Software systems using artificial intelligence for medical purposes have been developed in recent years. The success of deep neural networks (DNN) in 2012 in the image recognition challenge ImageNet LSVRC 2010 fueled expectations of the potential for using such systems in dermatology.Objective: To evaluate the ways in which machine learning has been utilized in dermatology to date and provide an overview of the findings in current literature on the subject.Methods: We conducted a systematic review of existing literature, identifying the literature through a systematic search of the PubMed database. Two doctors assessed screening and eligibility with respect to pre-determined inclusion and exclusion criteria.Results: A total of 2175 publications were identified, and 64 publications were included. We identified eight major categories where machine learning tools were tested in dermatology. Most systems involved image recognition tools that were primarily aimed at binary classification of malignant melanoma (MM). Short system descriptions and results of all included systems are presented in tables.Conclusions: We present a complete overview of artificial intelligence implemented in dermatology. Impressive outcomes were reported in all of the identified eight categories, but head-to-head comparison proved difficult. The many areas of dermatology where we identified machine learning tools indicate the diversity of machine learning.

Late fusion of deep and shallow features to improve discrimination of actinic keratosis from normal skin using clinical photography

BACKGROUND

Actinic keratosis (AK) is a common premalignant skin lesion that can potentially progress to squamous cell carcinoma. Appropriate long-term management of AK requires close patient monitoring in addition to therapeutic interventions. Computer-aided diagnostic systems based on clinical photography might evolve in the future into valuable adjuncts to AK patient management. The present study proposes a late fusion approach of color-texture features (shallow features) and deep features extracted from pre-trained convolutional neural networks (CNN) to boost AK detection accuracy on clinical photographs.

MATERIALS AND METHODS

System uses a sliding rectangular window of 50 × 50 pixels and a classifier that assigns the window region to either the AK or the healthy skin class. 6010 and 13 915 cropped regions of interest (ROI) of 50 × 50 pixels of AK and healthy skin, respectively, from 22 patients were used for system implementation. Different support vector machine (SVM) classifiers employing shallow or deep features and their late fusion using the max rule at decision level were compared with the McNemar test and Yule's Q-statistic.

RESULTS

Support vector machine classifiers based on deep and shallow features exhibited overall competitive performances with complementary improvements in detection accuracy. Late fusion yielded significant improvement (6%) in both sensitivity (87%) and specificity (86%) compared to single classifier performance.

CONCLUSION

The parallel improvement of sensitivity and specificity is encouraging, demonstrating the potential use of our system in evaluating AK burden. The latter might be of value in future clinical studies for the comparison of field-directed treatment interventions.