Hybrid Deep Learning Framework for Melanoma Diagnosis Using Dermoscopic Medical Images

Background: Melanoma, or skin cancer, is a dangerous form of cancer that is the major cause of the demise of thousands of people around the world. Methods: In recent years, deep learning has become more popular for analyzing and detecting these medical issues. In this paper, a hybrid deep learning approach has been proposed based on U-Net for image segmentation, Inception-ResNet-v2 for feature extraction, and the Vision Transformer model with a self-attention mechanism for refining the features for early and accurate diagnosis and classification of skin cancer. Furthermore, in the proposed approach, hyperparameter tuning helps to obtain more accurate and optimized results for image classification. Results: Dermoscopic shots gathered by the worldwide skin imaging collaboration (ISIC2020) challenge dataset are used in the proposed research work and achieved 98.65% accuracy, 99.20% sensitivity, and 98.03% specificity, which outperforms the other existing approaches for skin cancer classification. Furthermore, the HAM10000 dataset is used for ablation studies to compare and validate the performance of the proposed approach. Conclusions: The achieved outcome suggests that the proposed approach would be able to serve as a valuable tool for assisting dermatologists in the early detection of melanoma.

NICE 2022 guidelines on the management of melanoma: Update and implications

AIMS

In July 2022, NICE updated the guidelines on the management of melanoma by lowering the number of follow-up appointments and sentinel lymph node biopsy (SLNB) but increasing the number of scans. This study aims to evaluate the implications of executing the new guidelines in terms of cost-effectiveness and personnel.

METHODS

All patients newly diagnosed with melanoma in 2019 at a regional skin cancer specialist center were reviewed. Data were analyzed for their journey on an idealized pathway modeled over a 5-year follow-up period when adhering to both the previous and new guidelines. Differences in the management of melanoma were elucidated by comparing these changes. The cost was quantified on a perpatient basis and the financial implication on each department was considered.

RESULTS

One hundred and ten patients were diagnosed with melanoma in 2019, stages I-III. The changes ease the burden on plastic surgery and dermatology; however, increased pressure is faced by radiologists and histopathologists. An overall cost benefit of £141.85 perpatient was calculated, resulting in a decrease of 1.22 hospital visits on average and an increase in the time spent there (19.55 min). The additional expenses of implementing the new guidelines due to the added BRAF tests, CT, and ultrasound scans are outweighed by savings from the reduction in follow-up appointments and SLNB.

CONCLUSION

The focus has shifted to less invasive procedures for lower melanoma stages and fewer follow-up appointments, at the expense of more genetic testing and imaging. This paper serves as a useful baseline for other centers to plan their service provision and resource allocation to adhere to the updated guidelines.

Surveillance After a Previous Cutaneous Melanoma Diagnosis: A Scoping Review of Melanoma Follow-Up Guidelines

INTRODUCTION

Cutaneous melanoma accounts for more than 70% of all skin cancer deaths. Follow-up surveillance is an integral part of melanoma patient care, to facilitate early detection of recurrences and subsequent primary melanomas. The purpose of this scoping review is to provide an overview of recently published melanoma surveillance guidelines from regional and national melanoma working groups.

METHODS

A systematic search for relevant studies in MEDLINE and Embase was conducted in September 2022 and was limited to publications from 2010 or later.

RESULTS

A total of 1047 articles were retrieved, and after abstract and full text review, 26 articles from 19 different organizations met inclusion criteria. Life-long annual skin surveillance with a physician was recommended by 53% (9/17) of guidelines. Routine laboratory investigations were recommended by 7/19 guidelines. Regional lymph node ultrasound was recommended by 9/16 guidelines, most often in stage IB or higher, and was optional in 7/16 for patients who met specific criteria. Surveillance with PET-CT or CT and MRI was recommended by 15 and 11 guidelines, respectively, most commonly in stage IIC or higher, with a variable frequency and total duration. Five out of 9 guidelines indicated a preference for skin surveillance to be completed with a dermatologist.

CONCLUSION

Guidelines were highly variable for many aspects of melanoma surveillance, which may be partly attributed to regional differences in healthcare workforce distribution and availability of imaging technologies. Further high-level studies are recommended to provide more evidence on the most effective clinical and imaging follow-up surveillance protocols.

Key Points to Select a Device for Dermatologic Ultrasound

What points to consider when selecting a device for practicing dermatologic ultrasound is an excellent question. After we met the requisites published in the guidelines for practicing dermatologic ultrasound, it is necessary to consider the main objective of the use because it is not the same to be focused mostly on the avoidance of the puncture of important facial vessels such as the case of injectors of cosmetic fillers in comparison to the use of operators that need to deal with the diagnosis and monitoring of a wide range of dermatologic pathologies. Currently, a broad variety of ultrasound devices meets the minimum requirements for practicing these examinations in the market. Thus, small, portable, and high-end devices may present advantages and limitations that must be balanced according to the primary purposes and the budget. Moreover, the shape and footprint of the probes can make difficult or facilitate a dermatologic procedure. Other points to consider are the type of storage and the need for technical service. In summary, there are key points that we need to consider when we select a dermatologic ultrasound device in dermatology or aesthetics.

[Conventional ultrasound diagnostics in dermatology]

The imaging of changes to the skin, the subcutis and especially the regional lymph nodes by high-resolution ultrasound is an integral part of routine dermatological diagnostics. This is mainly done with electronic scanners operating at frequencies between 7.5 and 20 MHz (conventional ultrasound diagnostics). In addition, there are very high-frequency ultrasound systems (frequencies up to 100 MHz) that are used for special scientific questions. Ultrasound diagnostics has a number of advantages over other cross-sectional imaging techniques but is more dependent than these on the individual experience of the examiner. Structured training and continuing education are therefore essential for ultrasound diagnostics, also in dermatology. The following overview describes the most important indications for conventional sonography in dermatology in addition to the physical, technical and administrative principles.

Optimal surveillance strategies for patients with stage 1 cutaneous melanoma post primary tumour excision: three systematic reviews and an economic model

BACKGROUND

Malignant melanoma is the fifth most common cancer in the UK, with rates continuing to rise, resulting in considerable burden to patients and the NHS.

OBJECTIVES

The objectives were to evaluate the effectiveness and cost-effectiveness of current and alternative follow-up strategies for stage IA and IB melanoma.

REVIEW METHODS

Three systematic reviews were conducted. (1) The effectiveness of surveillance strategies. Outcomes were detection of new primaries, recurrences, metastases and survival. Risk of bias was assessed using the Cochrane Collaboration's Risk-of-Bias 2.0 tool. (2) Prediction models to stratify by risk of recurrence, metastases and survival. Model performance was assessed by study-reported measures of discrimination (e.g. D-statistic, Harrel's c-statistic), calibration (e.g. the Hosmer-Lemeshow 'goodness-of-fit' test) or overall performance (e.g. Brier score, R ²). Risk of bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). (3) Diagnostic test accuracy of fine-needle biopsy and ultrasonography. Outcomes were detection of new primaries, recurrences, metastases and overall survival. Risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Review data and data from elsewhere were used to model the cost-effectiveness of alternative surveillance strategies and the value of further research.

RESULTS

(1) The surveillance review included one randomised controlled trial. There was no evidence of a difference in new primary or recurrence detected (risk ratio 0.75, 95% confidence interval 0.43 to 1.31). Risk of bias was considered to be of some concern. Certainty of the evidence was low. (2) Eleven risk prediction models were identified. Discrimination measures were reported for six models, with the area under the operating curve ranging from 0.59 to 0.88. Three models reported calibration measures, with coefficients of ≥ 0.88. Overall performance was reported by two models. In one, the Brier score was slightly better than the American Joint Committee on Cancer scheme score. The other reported an R ² of 0.47 (95% confidence interval 0.45 to 0.49). All studies were judged to have a high risk of bias. (3) The diagnostic test accuracy review identified two studies. One study considered fine-needle biopsy and the other considered ultrasonography. The sensitivity and specificity for fine-needle biopsy were 0.94 (95% confidence interval 0.90 to 0.97) and 0.95 (95% confidence interval 0.90 to 0.97), respectively. For ultrasonography, sensitivity and specificity were 1.00 (95% confidence interval 0.03 to 1.00) and 0.99 (95% confidence interval 0.96 to 0.99), respectively. For the reference standards and flow and timing domains, the risk of bias was rated as being high for both studies. The cost-effectiveness results suggest that, over a lifetime, less intensive surveillance than recommended by the National Institute for Health and Care Excellence might be worthwhile. There was considerable uncertainty. Improving the diagnostic performance of cancer nurse specialists and introducing a risk prediction tool could be promising. Further research on transition probabilities between different stages of melanoma and on improving diagnostic accuracy would be of most value.

LIMITATIONS

Overall, few data of limited quality were available, and these related to earlier versions of the American Joint Committee on Cancer staging. Consequently, there was considerable uncertainty in the economic evaluation.

CONCLUSIONS

Despite adoption of rigorous methods, too few data are available to justify changes to the National Institute for Health and Care Excellence recommendations on surveillance. However, alternative strategies warrant further research, specifically on improving estimates of incidence, progression of recurrent disease; diagnostic accuracy and health-related quality of life; developing and evaluating risk stratification tools; and understanding patient preferences.

STUDY REGISTRATION

This study is registered as PROSPERO CRD42018086784.

FUNDING

This project was funded by the National Institute for Health Research Health Technology Assessment programme and will be published in full in Health Technology Assessment; Vol 25, No. 64. See the NIHR Journals Library website for further project information.

Usefulness of real-time elastography for diagnosing lymph node metastasis of skin cancer: does elastography potentially eliminate the need for sentinel lymph node biopsy in squamous cell carcinoma?

BACKGROUND

The metastatic involvement of regional lymph nodes is the most important prognostic factor for overall survival of skin cancer patients. The sonographic technique of freehand real-time tissue elastography (RTE), which displays tissue rigidity as a colour overlay of the tissue image, was developed.

OBJECTIVE

Our purpose was to evaluate the benefit of RTE for detecting lymph node metastases of skin cancer non-invasively before operation.

METHODS

We first selected lymph nodes of skin cancer patients which had already been diagnosed by biopsy as being reactive or metastatic, and then retrospectively collected images of RTE and B-mode and colour Doppler ultrasound on those lymph nodes performed preoperatively. Twenty-one lymph nodes from 12 patients with squamous cell carcinoma (SCC), 23 lymph nodes from 14 patients with malignant melanoma (MM) and 14 lymph nodes from six patients with extramammary Paget disease (Paget) were investigated. Elastographic images were assessed on a scale of one to four according to the percentage of high elasticity (hard) area (HEA) in the lymph node.

RESULTS

In all three skin cancers, lymph nodes evaluated as grade 3 or 4 by RTE were metastatic. All lymph nodes evaluated as grade 1 or 2 by RTE were reactive in SCC, whereas some lymph nodes evaluated as grade 1 or 2 were metastatic in MM and Paget.

CONCLUSION

Real-time tissue elastography may aid in distinguishing reactive lymph nodes from metastatic ones especially in SCC.

Cost-effectiveness analysis of imaging strategy for an intensive follow-up of patients with American Joint Committee on Cancer stage IIB, IIC and III malignant melanoma

BACKGROUND

Many follow-up guidelines for patients with high-risk melanoma include expensive imaging studies, serum biomarkers and regular visits to the dermatologist, with little attention to cost-effectiveness.

OBJECTIVES

To establish the cost-effectiveness of chest-abdomen-pelvis computed tomography (CT) and brain magnetic resonance imaging (MRI) in a follow-up protocol for patients at high risk of relapse.

METHODS

This was a prospective single-centre cohort study of 290 patients with clinicopathological American Joint Committee on Cancer (AJCC) stage IIB, IIC and III melanoma. Patients had a body CT scan and brain MRI every 6 months and were withdrawn from the study after completing a 5-year follow-up or when metastases were detected. A cost-effectiveness analysis for each follow-up radiological procedure was performed.

RESULTS

Patients underwent 1805 body CT scans and 1683 brain MRIs. Seventy-six metastases (26·2%) were identified by CT or MRI. CT scan was cost-effective in the first 4 years (cost-effectiveness ratio €4710·70-€14 437·10/patient with metastasis); brain MRI was cost-effective during the first year (cost-effectiveness ratio €14 090·60/patient with metastasis). Limitations included lack of survival analysis and comparisons with willingness-to-pay thresholds.

CONCLUSIONS

Six-monthly CT scan of the chest, abdomen and pelvis is a cost-effective technique for the early detection of metastases in the first 4 years of follow-up in patients with AJCC stage IIC and III melanoma, and in the first 3 years in patients with AJCC stage IIB melanoma. In addition, brain MRI has been shown to be cost-effective only in the first year of follow-up in patients with AJCC stage IIC and III melanoma.

Use of Lymph Node Ultrasound Prior to Sentinel Lymph Node Biopsy in 384 Patients with Melanoma: A Cost-Effectiveness Analysis

BACKGROUND AND OBJECTIVES

Locoregional lymph node ultrasound is not typically included in guidelines as part of the staging process prior to sentinel lymph node biopsy (SLNB). The objective of the present study was to make a clinical and economic analysis of lymph node ultrasound prior to SLNB.

MATERIALS AND METHODS

We performed a retrospective study of 384 patients with clinical stage I-II primary melanoma who underwent locorregional lymph node ultrasound (with or without ultrasound-guided biopsy) prior to SLNB between 2004 and 2015. We evaluated the reliability and cost-effectiveness of the strategy.

RESULTS

Use of locorregional lymph node ultrasound avoided SLNB in 23 patients (6%). Ultrasound had a sensitivity of 46% and specificity of 76% for the detection of metastatic lymph nodes that were not clinically palpable. False negatives were significantly more common in patients aged over 60 years and in tumors with a thickness of less than 2mm. The staging process using SLNB and ultrasound with ultrasound-guided biopsy produced an increase of €16.30 in the unit price. Our cost-effectiveness analysis identified the staging protocol with ultrasound and SLNB as the dominant strategy, with a lower cost-effectiveness ratio than the alternative, consisting of SLNB alone (8,095.24 vs. €28,605.00).

CONCLUSIONS

Ultrasound with ultrasound-guided biopsy for the diagnostic staging of melanoma prior to SLNB is a useful and cost-effective tool. This procedure does not substitute SLNB, though it does allow to avoid SLNB in a not insignificant proportion of patients.

High-Frequency Ultrasound Examination in the Diagnosis of Skin Cancer

Ultrasound above 14 MHz images epidermis, dermis, and subcutaneous tissues in real time. Tumor depth is ascertained with B-mode. Three-dimensional imaging depicts nonpalpable, in-transit, and satellite lesions. Doppler blood flow technologies measure tumor neovascularity and map vascular structures. Three-dimensional Doppler histogram reconstruction measures tumor aggression and metastatic potential proportional to the percentage of malignant vessels. Subcutaneous investigation reveals nonpalpable metastatic disease and nodal basin lymphadenopathy. Adjacent nerves may be studied. Preservation of the fat-fascia border refines surgical staging of deeper malignancies. Image-guided biopsy is facilitated. Treatment under image guidance is optimized with radiation and various photo and thermal technologies.

Performance of diagnostic tests in an intensive follow-up protocol for patients with American Joint Committee on Cancer (AJCC) stage IIB, IIC, and III localized primary melanoma: A prospective cohort study

BACKGROUND

There is no international consensus on optimal follow-up schedules and which supplementary tests should be used after resection of a primary melanoma.

OBJECTIVE

We sought to analyze the performance of the follow-up components and identify procedures that detect melanoma metastasis earlier.

METHODS

This was a prospective cohort from 290 consecutive patients given a diagnosis of stage IIB, IIC, and III melanoma. Patients were followed up with an intensive protocol based on imaging studies (computed tomography of the chest, abdomen, and pelvis, and brain magnetic resonance imaging), periodic laboratory tests, regular physical examinations, and patient self-examinations.

RESULTS

A total of 2382 clinical examinations and 3069 imaging tests were performed. The patients completed 899.8 person-years of follow-up, with a median of 2.5 years. In all, 115 recurrences in 290 patients were recorded, of which computed tomography detected 48.3%; brain magnetic resonance imaging, 7.6%; laboratory test, 2.5%; physician, 23.7%; and patient, 17.8%.

LIMITATIONS

Patients with stage III melanoma were not systematically classified into subgroups and overall survival was not evaluated.

CONCLUSION

We observed that this intensive monitoring is appropriate for early detection of recurrence in stage IIB, IIC, and III melanoma. Prompt diagnosis of metastasis and the recent development of new therapeutic targets may improve overall survival.

Sonographic diagnostics in dermatology

Ultrasonography non-invasively visualizes changes within the skin, skin appendages, subcutaneous tissue, subcutaneous (regional) lymph nodes and peripheral vessels. Thus it is an established diagnostic tool in dermatology. Compared to X-ray, MRI and PET, ultrasonography has some advantages; however, it is more dependent on the individual experience of the investigator. Therefore a structured education and continuous training are necessary. This review describes the physical and technical basics, the administrative requirements and the main indications in dermatology.

Positron emission tomography/ultrasound fusion technique in patients with malignant melanoma

(18)F-fluorodeoxyglucose positron emission tomography (FDG-PET)/CT is commonly used to assess tumour recurrence in high-risk patients with malignant melanoma (MM). However, results can be ambiguous either because of the CT's insufficient soft-tissue contrast or non-specific FDG accumulation caused by inflammation. Ultrasound (US) can provide additional morphologic information that is superior to CT. For precisely combining PET and US findings, we used a real-time fusion technique based on navigated US (PET/US fusion). Here, we describe our results from patients where PET/US fusion proved helpful in differentiating unclear PET/CT findings. This fusion technique is likely to be helpful for decision making in MM patients and biopsy guidance.

Long-term follow-up for melanoma patients: is there any evidence of a benefit?

As the incidence of melanoma and the number of melanoma survivors continues to rise, optimal surveillance strategies are needed that balance the risks and benefits of screening in the context of contemporary resource use. Detection of recurrences has important implications for clinical management. Most current surveillance recommendations for melanoma survivors are based on low-level evidence with wide variations in practice patterns and an unknown clinical impact for the melanoma survivor.

Accuracy of real-time ultrasound elastography in the differential diagnosis of lymph nodes in cutaneous malignant melanoma (CMM): a pilot study

BACKGROUND

We investigated the diagnostic ability of real-time elastography to differentiate between reactive and metastatic lymph nodes in cutaneous malignant melanoma (CMM) patients and to determine the optimum cutoff value for elastography scores for diagnosis CMM.

METHODS

Twenty lymph nodes (metastatic, n = 13; reactive, n = 7) from 12 patients with CMM were examined by both elastography and B-mode ultrasound in this prospective study. Elastographic patterns were given scores of 1-5 according to the percentage of high elasticity (hard) areas in the lymph node. Elastographic patterns 1, 2, 3, 4, and 5 were assigned elastography scores (ES) of 1, 2, 3, 4, and 5, respectively. B-mode ultrasound diagnosis was performed on the basis of the morphological patterns (balloon-shaped lymph node and loss of central echoes). The sensitivity, specificity, and accuracy were calculated, and receiver operating characteristic analysis was performed, comparing with elastograms and B-mode images, with histological findings as the reference standard.

RESULTS

Sensitivity, specificity, and accuracy of elastography were 100, 71, and 90 %, respectively, with an ES cutoff value of 3; 92, 100, and 95 % for elastography with an ES cutoff value of 4; and 77, 57, and 70 % for B-mode ultrasound.

CONCLUSION

Elastography can enhance the diagnostic accuracy of ultrasound for differentiating between reactive and malignant lymph nodes in CMM and might eliminate the need for sentinel lymph node biopsy. The optimum ES cutoff value for reactive versus metastatic lymph nodes is 4.

The role of ultrasound and ultrasound-guided fine needle aspiration biopsy of lymph nodes in patients with skin tumours

Background

The primary aim of this study was to evaluate the diagnostic accuracy of ultrasound (US) in the study of superficial lymph nodes during the follow-up of patients surgically treated for skin tumours. The secondary objective was to compare positive cytological results with histological reports.

Patients and methods

From 2004 to 2011, 480 patients (male/female: 285/195; median age 57 years; prevalent skin tumour: melanoma) underwent US-guided fine-needle aspiration biopsy (FNAB) of suspicious recurrent lymph nodes. An expert radiologist first performed US testing of the lymph nodes, expressing either a negative or positive outcome of the test. Subsequently, US-guided FNAB was performed. FNAB positive patients were subjected to lymphadenectomy; the patients who tested negative underwent the follow-up.

Results

The size of lymph nodes was ≤ 2 cm in 90% of cases. Out of the 336 (70%) US “positive” patients, 231 (68.8%) were FNAB positives. Out of the 144 (30%) US “negatives”, 132 (91.7%) were FNAB negatives. The sensitivity and specificity of the US were 95% and 55.7%, respectively; the negative predictive value was 91.7% and the positive predictive value was 68.8%. Definitive histological results confirmed FNAB positivity in 97.5% of lymphadenectomies.

Conclusions

US is a sensitive method in the evaluation of superficial lymph nodes during the follow-up of patients with skin tumours. High positive predictive value of cytology was confirmed.

Ultrasound and fine-needle aspiration in dermatology, underuse of minimally invasive, efficient diagnostic tools

BACKGROUND

Ultrasound imaging and ultrasound-guided fine-needle aspiration (FNA) are common procedures used to evaluate and sample cutaneous and subcutaneous tissue. Although ultrasound and FNA have been explored for individual neoplasms, lymph node involvement, and metastases, their use in day-to-day dermatology is not well defined.

OBJECTIVE

To investigate the use and utility of ultrasound and FNA in the dermatologic surgery division of a large academic institution.

METHODS

Retrospective case review of all ultrasound and FNA procedures ordered by a dermatologic surgeon over a 3-year period.

RESULTS

Metastatic disease was suspected in 11 of 21 (52.4%) cases. Cytology confirmed the presence of metastatic disease in two of the 11 cases, and metastatic disease was identified in one additional case in which the diagnosis was not suspected at clinical presentation. Cytology revealed leukemia or lymphoma in three (14.3%) cases, two of which were new diagnoses. Sonographic imaging and cytology revealed a benign diagnosis in 16 (76.2%) cases, five of which were reactive lymph nodes.

CONCLUSIONS

The results suggest that ultrasound and FNA are underused techniques that may play an important role in dermatology diagnostics and have the potential for expansion in day-to-day clinical practice.

Ultrasound examination and fine needle aspiration cytology-useful for followup of the regional nodes in penile cancer?

PURPOSE

Routine followup of the groins of patients with penile squamous cell carcinoma after primary treatment consists of physical examination together with ultrasound of the groins, followed by fine needle aspiration cytology if suspicious. We assessed the value of this routine followup.

MATERIALS AND METHODS

Using ultrasound and fine needle aspiration cytology we assessed 247 patients during followup who were treated from 2004 to 2010 and underwent dynamic sentinel node biopsy only or observation of the inguinal regions. A negative result was defined as no evidence of metastatic disease after at least 2 years of followup. We calculated the sensitivity, specificity, and positive and negative predictive values of ultrasound and ultrasound guided fine needle aspiration cytology using standard statistical methods.

RESULTS

Recurrence was diagnosed in 47 of 247 patients (55 groins). In 40 of 55 groins (73%) recurrence was detectable by physical examination. In 12 of 15 cases of nonpalpable recurrence (80%) ultrasound guided fine needle aspiration cytology revealed the recurrence. We considered 217 groins to be suspicious on ultrasound followed by fine needle aspiration cytology. Fine needle aspiration cytology revealed tumor in 49 groins and showed false-positive findings in 1 patient after negative completion lymphadenectomy. Sensitivity and specificity were 87.3% (48 of 55 cases) and 99.9% (1,304 of 1,305), respectively.

CONCLUSIONS

Although inguinal recurrence manifests clinically in most patients, ultrasound guided fine needle aspiration cytology detected 80% of metastatic disease in patients with nonpalpable disease. Therefore, it has great value for detecting lymph node metastases during followup.

Melanoma m (zero): diagnosis and therapy

This paper reviews the epidemiology, diagnosis, and treatment of M zero cutaneous melanoma including the most recent developments. This review also examined the main risk factors for melanoma. Tumor thickness measured according to Breslow, mitotic rate, ulceration, and growth phase has the greatest predictive value for survival and metastasis. Wide excision of the primary tumor is the only potentially curative treatment for primary melanoma. The sentinel node biopsy must be performed on all patients who have a primary melanoma with a Breslow thickness > 1 mm, or if the melanoma is from 0,75 mm to 1 mm thick but it is ulcerated and/or the mitotic index is ≥1. Total lymph node dissection consists in removing the residual lymph nodes in patients with positive sentinel node biopsy, or found positive on needle aspiration biopsy, without radiological evidence of spread. Isolated limb perfusion and isolated limb infusion are employed in patients within transit metastases with a rate of complete remission in around 50% and 38% of cases. Electrochemotherapy is mainly indicated for palliation in cases of metastatic disease, though it may sometimes be useful to complete isolated limb perfusion. The only agent found to affect survival as an adjuvant treatment is interferon alpha-2. Adjuvant radiotherapy improves local control of melanoma in patients at a high risk of recurrence after lymph node dissection.