No abstract

This use of teledermoscopy as a triage tool offers the potential to shorten waiting lists and thus improve healthcare access and delivery.

Early detection of skin cancer, particularly melanoma, is crucial to enable advanced treatment. Due to the rapid growth in the number of skin cancers, there is a growing need of computerised analysis for skin lesions. The state-of-the-art public available datasets for skin lesions are often accompanied with a very limited amount of segmentation ground truth labeling. Also, the available segmentation datasets consist of noisy expert annotations reflecting the fact that precise annotations to represent the boundary of skin lesions are laborious and expensive. The lesion boundary segmentation is vital to locate the lesion accurately in dermoscopic images and lesion diagnosis of different skin lesion types. In this work, we propose the fully automated deep learning ensemble methods to achieve high sensitivity and high specificity in lesion boundary segmentation. We trained the ensemble methods based on Mask R-CNN and DeeplabV3+ methods on ISIC-2017 segmentation training set and evaluate the performance of the ensemble networks on ISIC-2017 testing set and PH2 dataset. Our results showed that the proposed ensemble methods segmented the skin lesions with Sensitivity of 89.93% and Specificity of 97.94% for the ISIC-2017 testing set. The proposed ensemble method Ensemble-A outperformed FrCN, FCNs, U-Net, and SegNet in Sensitivity by 4.4%, 8.8%, 22.7%, and 9.8% respectively. Furthermore, the proposed ensemble method EnsembleS achieved a specificity score of 97.98% for clinically benign cases, 97.30% for the melanoma cases, and 98.58% for the seborrhoeic keratosis cases on ISIC-2017 testing set, exhibiting better performance than FrCN, FCNs, U-Net, and SegNet.

A community-based teledermoscopy service may allow improved management of outpatient referrals while providing a better, quicker and more convenient service. It may also provide cost savings, as teledermoscopy assessment can be cheaper than traditional assessment.

A randomized controlled trial was carried out to measure the societal costs of realtime teledermatology compared with those of conventional hospital care in New Zealand. Two rural health centres were linked to a specialist hospital via ISDN at 128 kbit/s. Over 10 months, 203 patients were referred for a specialist dermatological consultation and 26 were followed up, giving a total of 229 consultations. Fifty-four per cent were randomized to the teledermatology consultation and 46% to the conventional hospital consultation. A cost-minimization analysis was used to calculate the total costs of both types of dermatological consultation. The total cost of the 123 teledermatology consultations was NZ$34,346 and the total cost of the 106 conventional hospital consultations was NZ$30,081. The average societal cost of the teledermatology consultation was therefore NZ$279.23 compared with NZ$283.79 for the conventional hospital consultation. The marginal cost of seeing an additional patient was NZ$135 via teledermatology and NZ$284 via conventional hospital appointment. From a societal viewpoint, and assuming an equal outcome, teledermatology was a more cost-efficient use of resources than conventional hospital care.

As part of a randomized controlled trial of the costs and benefits of realtime teledermatology in comparison with conventional face-to-face appointments, patients were asked to complete a questionnaire at the end of their consultation. One hundred and nine patients took part in an initial teledermatology consultation and 94 in a face-to-face consultation. The proportion of patients followed up by the dermatologist was almost the same after teledermatology (24%) as after a hospital appointment (26%) and for similar reasons. Two hundred and three questionnaires were completed after the first visit and a further 20 after subsequent visits. Patients seen by teledermatology at their own health centre travelled an average of 12 km, whereas those who attended a conventional clinic travelled an average of 271 km. The telemedicine group spent an average of 51 min attending the appointment compared with 4.3 h for those seen at the hospital. The results of the present study, as in a similar study conducted in Northern Ireland, show that the economic benefits of teledermatology favour the patient rather than the health-care system.

A 19-year-old woman with a 6 month history of systemic lupus erythematosus (SLE) developed a widespread urticated, erythematous eruption associated with tense, fluid-filled blisters, erosions and crusting. Biopsy showed subepidermal blistering with a prominent neutrophilic infiltrate. Direct immunofluorescence showed markedly positive granular IgG deposition with weak IgM, IgA and C3 at the dermoepidermal junction. No circulating antibodies were detected on indirect immunofluorescence. A diagnosis of bullous systemic erythematosus was made. Treatment with prednisone was ineffective. Subsequent treatment with dapsone led to rapid sustained remission of skin symptoms. Bullous SLE is a rare manifestation of SLE. We review the recent literature and discuss the distinctive features of this condition and contrast them with cutaneous SLE with blisters and the subepidermal blistering disorders.

The VLC offered an efficient, accurate and cost effective way of processing suspected melanoma referrals to the public health system.