Age-related prevalence and morphological appearance of facial skin tumours: a prospective, cross-sectional, observational, multicentre study with special emphasis on melanocytic tumours

Computer-aided diagnosis of eyelid skin tumors using machine learning

OBJECTIVE

To develop an automated, new framework based on machine learning to diagnose malignant eyelid skin tumors.

METHODS

This study used eyelid lesion images from Sheba Medical Center, a large tertiary center in Israel. Before model training, we pretrained our models on the International Skin Imaging Collaboration (ISIC) 2019 dataset consisting of 25,332 images. The proprietary eyelid data set was then used for fine-tuning. The data set contained multiple images per patient, aiming to classify malignant lesions in comparison to benign counterparts.

RESULTS

The analyzed data set consisted of images representing both benign and malignant eyelid lesions. For the benign category, a total of 373 images were sourced. By comparison, for the malignant category, 186 images were sourced. For the final model, at sensitivity of 93.8% (95% CI 80.0-100.0%), the model has a corresponding specificity of 73.7% (95% CI 60.0-87.1%). To further understand the decision-making process of our model, we employed heatmap visualization techniques, specifically gradient-weighted Class Activation Mapping.

DISCUSSION

This study introduces a dependable model-aided diagnostic technology for assessing eyelid skin lesions. The model demonstrated accuracy comparable to human evaluation, effectively determining whether a lesion raises a high suspicion of malignancy or is benign. Such a model has the potential to alleviate the burden on the health care system, particularly benefiting rural areas, and enhancing the efficiency of clinicians and overall health care.

Clinical and Dermoscopic Features of Melanocytic Lesions on the Face Versus the External Ear

Introduction

Melanoma of the external ear is a rare condition accounting for 7-20% of all melanomas of the head and neck region. They present classical features of extra-facial melanomas clinically and dermoscopically. In contrast, facial melanomas show peculiar patterns in dermoscopy.

Objectives

To evaluate whether there are clinical and/or dermoscopic differences in melanocytic lesions located either at the external ear or on the face.

Methods

In this retrospective study we reviewed an image database for clinical and dermoscopic images of melanomas and nevi located either on the face or at the level of the external ear.

Results

65 patients (37 men; 63.8%) with 65 lesions were included. We found no significant differences in comparing face melanomas with melanomas at the level of the external ear, neither clinically nor dermoscopically. However, we provided evidence for differences in some clinical and dermoscopic features of melanomas and nevi of the external ear.

Conclusions

In this study, we reported no significant differences in comparing melanomas on the face with melanomas of the external ear, both clinically and dermoscopically. Furthermore, we provided data on clinical and dermoscopic differences comparing nevi and melanoma of the external ear.

Morphological features of benign pigmented ear lesions: a cross-sectional study

BACKGROUND

The morphology of benign pigmented lesions on the ears has been scarcely studied.

METHODS

We prospectively screened all patients presenting to a pigmented lesion clinic at a tertiary academic hospital, between November 2015 and August 2016, for the presence of benign pigmented ear lesions. Clinical and dermoscopic images were obtained for all lesions. Additionally, we performed a retrospective analysis of reflectance confocal microscopy (RCM) of benign pigmented ear lesions and a retrospective analysis of clinical and dermoscopic findings of biopsy-confirmed ear melanomas.

RESULTS

In total, 165 patients (median age 48, 53% female) contributed 708 benign pigmented ear lesions to the study. Participants with multiple body nevi and those with an atypical nevus phenotype (multiple body nevi and ≥ one atypical nevus) had a higher mean number of ear lesions than those without multiple body nevi (4.5 and 5.4 vs. 3.9, P < 0.05). The most common diagnoses were nevus (35%) and solar lentigo (34%), followed by pigmented lentiginous macules (PLM) (27%). Dermoscopically scattered pigmented small globules/dots were observed in 30% of nevi and 17% of PLMs. RCM analysis of 24 ear lesions showed a comparable frequency of RCM-clods between nevi and PLMs. Analysis of 29 ear melanomas revealed larger lesions with more complex dermoscopic patterns.

CONCLUSION

Multiple body nevi, and particularly an atypical nevus phenotype, were associated with having more pigmented ear lesions. Based on RCM analysis, PLMs of the ear likely represent small nevi. Ear melanomas tend to be larger and dermoscopically complex compared to ear nevi.

Neck Melanoma: Clinical, Dermoscopic and Confocal Features

BACKGROUND

The head and neck are considered one single anatomical unit. No data on clinical, dermoscopic and confocal aspects of neck melanoma are currently available.

OBJECTIVES

To identify clinical, dermoscopic and confocal diagnostic features of neck melanomas.

METHODS

Consecutive malignant (cases) and benign (controls) melanocytic skin lesions located on the neck, excised as suspected of being melanoma from March 2011 to February 2018, were retrospectively retrieved. Dermoscopic criteria of the 7-point checklist, integrated by other melanoma features (such as grey colour and irregular hyperpigmented areas) were assessed. Reflectance confocal microscopy (RCM) images were examined when available.

RESULTS

282 lesions located to the head and neck area were biopsied to rule out melanoma. Thirty-one out of 282 (11%) lesions were located on the neck: 21 melanomas and 10 naevi. Melanoma patients were older than patients with naevi (mean age: 60.4 vs. 37.9 years, p < 0.001). Neck melanomas were more frequently located on sun-damaged skin compared to naevi (76.2 vs. 30%, p = 0.02). Dermoscopically, neck melanomas were characterized by irregular dots/globules, grey colour and regression (76.2, 81 and 46.7% of cases) and showed criteria of lentigo maligna melanoma (LMM) in 52.4% of cases. Regression, grey colour, irregular hyperpigmented areas and criteria of LMM typified melanomas on sun-damaged skin, whereas tumours located on non-sun-damaged areas were often characterized by irregular pigmentation (blotches). RCM, implemented to dermoscopy, correctly diagnosed 10/12 melanomas and 3/5 naevi.

CONCLUSION

Neck melanoma has peculiar clinical and dermoscopic aspects that could help clinicians to distinguish it from naevi and to diagnose melanoma earlier.