Explainability agreement between dermatologists and five visual explanations techniques in deep neural networks for melanoma AI classification.

Introduction: The use of deep convolutional neural networks for analyzing skin lesion images has shown promising results. The identification of skin cancer by faster and less expensive means can lead to an early diagnosis, saving lives and avoiding treatment costs. However, to implement this technology in a clinical context, it is important for specialists to understand why a certain model makes a prediction; it must be explainable. Explainability techniques can be used to highlight the patterns of interest for a prediction. Methods: Our goal was to test five different techniques: Grad-CAM, Grad-CAM++, Score-CAM, Eigen-CAM, and LIME, to analyze the agreement rate between features highlighted by the visual explanation maps to 3 important clinical criteria for melanoma classification: asymmetry, border irregularity, and color heterogeneity (ABC rule) in 100 melanoma images. Two dermatologists scored the visual maps and the clinical images using a semi-quantitative scale, and the results were compared. They also ranked their preferable techniques. Results: We found that the techniques had different agreement rates and acceptance. In the overall analysis, Grad-CAM showed the best total+partial agreement rate (93.6%), followed by LIME (89.8%), Grad-CAM++ (88.0%), Eigen-CAM (86.4%), and Score-CAM (84.6%). Dermatologists ranked their favorite options: Grad-CAM and Grad-CAM++, followed by Score-CAM, LIME, and Eigen-CAM. Discussion: Saliency maps are one of the few methods that can be used for visual explanations. The evaluation of explainability with humans is ideal to assess the understanding and applicability of these methods. Our results demonstrated that there is a significant agreement between clinical features used by dermatologists to diagnose melanomas and visual explanation techniques, especially Grad-Cam.

Implementation of artificial intelligence algorithms for melanoma screening in a primary care setting.

Skin cancer is currently the most common type of cancer among Caucasians. The increase in life expectancy, along with new diagnostic tools and treatments for skin cancer, has resulted in unprecedented changes in patient care and has generated a great burden on healthcare systems. Early detection of skin tumors is expected to reduce this burden. Artificial intelligence (AI) algorithms that support skin cancer diagnoses have been shown to perform at least as well as dermatologists' diagnoses. Recognizing the need for clinically and economically efficient means of diagnosing skin cancers at early stages in the primary care attention, we developed an efficient computer-aided diagnosis (CAD) system to be used by primary care physicians (PCP). Additionally, we developed a smartphone application with a protocol for data acquisition (i.e., photographs, demographic data and short clinical histories) and AI algorithms for clinical and dermoscopic image classification. For each lesion analyzed, a report is generated, showing the image of the suspected lesion and its respective Heat Map; the predicted probability of the suspected lesion being melanoma or malignant; the probable diagnosis based on that probability; and a suggestion on how the lesion should be managed. The accuracy of the dermoscopy model for melanoma was 89.3%, and for the clinical model, 84.7% with 0.91 and 0.89 sensitivity and 0.89 and 0.83 specificity, respectively. Both models achieved an area under the curve (AUC) above 0.9. Our CAD system can screen skin cancers to guide lesion management by PCPs, especially in the contexts where the access to the dermatologist can be difficult or time consuming. Its use can enable risk stratification of lesions and/or patients and dramatically improve timely access to specialist care for those requiring urgent attention.

Treatment of Male-Pattern Alopecia with Platelet-Rich Plasma.

BACKGROUND: Androgenetic alopecia (AGA) affects up to 80% of men and 50% of women throughout their lifetime, causing significant discomfort. Minoxidil, finasteride, and low-level laser light therapy are the only Food and Drug Administration-approved treatments for AGA, and they have shown positive results in randomized controlled trials and meta-analyses. However, their efficacy is limited, and new therapies are needed. Injection of platelet-rich plasma (PRP), a minimally invasive technique, has been described by several authors as a promising treatment for AGA. Although many studies report beneficial effects of PRP on AGA, there is no standardized practice for PRP preparation and administration or a standard method to evaluate results. OBJECTIVE: The aim of this study was to evaluate the efficacy of manually prepared PRP in the treatment of male AGA. MATERIALS AND METHODS: We treated 20 male patients with AGA with 3 monthly injections of PRP and analyzed results by TrichoScan®. RESULTS: In this study, there was no statistically significant improvement in hair count or proportion of anagen hairs. CONCLUSIONS: This lack of response could be related to any of the variables during PRP preparation described above and also to the limited number of patients in the study.

Tratamento de psoríase vulgar pela microinfusão de medicamentos na pele (MMP®) usando ciclosporina e metotrexato / Treatment of psoriasis vulgaris with cyclosporine and methotrexate injections using the MMP® technique

Medicações sistêmicas orais como ciclosporina (CYA) ou metotrexato (MTX) para tratamento de psoríase tem biodisponibilidade limitada devido à absorção incompleta gastrointestinal e metabolização de primeira passagem hepática. Além disso, estão associados a efeitos adversos. A aplicação de CYA ou MTX através da Microinfusão de Medicamentos pela pele (MMP®) para tratamento de psoríase vulgar mostrou resposta terapêutica com redução significativa de lesões, sem indução de efeitos colaterais. Neste relato, descrevemos 4 casos de psoríase vulgar tratados com MMP® com CYA ou MTX.

Systemic oral medications ­ such as cyclosporine (CYA) or methotrexate (MTX) ­ for the treatment of psoriasis have limited bioavailability due to incomplete gastrointestinal absorption and first-pass hepatic metabolism. Moreover, they are associated with adverse effects. The application of CYA or MTX using the microinfusion of drugs into the skin method (MMP®) for the treatment of psoriasis vulgaris yielded a therapeutic response with significant reduction of lesions, and absence of side effects. In the present report, the authors describe 4 cases of psoriasis vulgaris treated using the MMP® method, with the application of CYA or MTX.

Use of Smartphones in Telemedicine: Comparative Study Between Standard and Teledermatological Evaluation of High-Complex Care Hospital Inpatients.

BACKGROUND: It is estimated that there are around 7 billion mobile phone subscriptions worldwide. Considering the availability and convenience, it appears to be a suitable device for store-and-forward (SF) consultations. INTRODUCTION: Although teledermatology has been suggested as an effective way of reducing costs and providing otherwise inaccessible expert evaluation, most studies have relied on high cost and high technological means. MATERIALS AND METHODS: We conducted a study with inpatients that required dermatological evaluation in a high-complexity university hospital, accessing the correlation between traditional face-to-face evaluation and SF teledermatology, with data and pictures collected by medical students using smartphone cameras and then sent to consultants by e-mail. RESULTS: For 2 months, we evaluated 100 patients and, as a result, the total agreement between both consultation modalities was 54%, the partial agreement was 27%, and the disagreement was 19%. DISCUSSION: This study points out that SF teledermatology with the use of mobile phone is comparable to traditional face-to-face evaluation. Furthermore, most of the disagreements were probably related to the inexperience of the medical residents. CONCLUSION: Our study suggests that a smartphone-based teledermatology inpatient consultation model could be a reasonable option for hospitals lacking dermatological services. Also, it may be as or more effective than face-to-face consultations, if performed by a more experienced dermatologist. When feasible, photographing training should be performed.