Which symptoms are linked to a delayed presentation among melanoma patients? A retrospective study.

BACKGROUND: The incidence of melanoma is rising. Early detection is associated with a more favourable outcome. The factors that influence the timing of a patient's presentation for medical assessment are not fully understood. The aims of the study were to measure the nature and duration of melanoma symptoms in a group of patients diagnosed with melanoma within the preceding 18 months and to identify the symptoms and barriers associated with a delay in presentation. METHODS: A questionnaire was distributed to a random sample of 200 of the 963 melanoma patients who had participated in the Cancer Patient Experience Survey 2010 and were known to be alive 1 year later. Data were collected on symptoms, duration of symptoms prior to presentation and the reasons for not attending a doctor sooner. RESULTS: A total of 159 patients responded to the questionnaire; 74 (47%) were men; mean age was 62 (range 24-90) years. Of the 149 patients who reported a symptom, 40 (27%) had a delayed presentation (i.e. >3 months). A mole growing bigger was the most common symptom and reporting this symptom was significantly associated with a delayed presentation (odds ratio (OR) 2.04, 95% confidence interval (95% CI) 1.14-5.08). Patients aged ≥65 years were less likely to report a barrier to presentation and were less likely to delay than those under 40, although this was of borderline statistical significance (OR 0.28, 95% CI 0.08-1.00). CONCLUSIONS: This study highlights that an enlarging mole is a significant symptom influencing the timing of presentation. Increasing public awareness of the signs of melanoma and of the importance of early presentation is desirable. Health professionals should take advantage of the opportunity to educate patients on such symptoms and signs where feasible. Further exploration of the barriers to presentation in younger people should be considered.

Towards the automatic detection of skin lesion shape asymmetry, color variegation and diameter in dermoscopic images.

Asymmetry, color variegation and diameter are considered strong indicators of malignant melanoma. The subjectivity inherent in the first two features and the fact that 10% of melanomas tend to be missed in the early diagnosis due to having a diameter less than 6mm, deem it necessary to develop an objective computer vision system to evaluate these criteria and aid in the early detection of melanoma which could eventually lead to a higher 5-year survival rate. This paper proposes an approach for evaluating the three criteria objectively, whereby we develop a measure to find asymmetry with the aid of a decision tree which we train on the extracted asymmetry measures and then use to predict the asymmetry of new skin lesion images. A range of colors that demonstrate the suspicious colors for the color variegation feature have been derived, and Feret's diameter has been utilized to find the diameter of the skin lesion. The decision tree is 80% accurate in determining the asymmetry of skin lesions, and the number of suspicious colors and diameter values are objectively identified.

A machine learning approach to automatic detection of irregularity in skin lesion border using dermoscopic images.

Skin lesion border irregularity is considered an important clinical feature for the early diagnosis of melanoma, representing the B feature in the ABCD rule. In this article we propose an automated approach for skin lesion border irregularity detection. The approach involves extracting the skin lesion from the image, detecting the skin lesion border, measuring the border irregularity, training a Convolutional Neural Network and Gaussian naive Bayes ensemble, to the automatic detection of border irregularity, which results in an objective decision on whether the skin lesion border is considered regular or irregular. The approach achieves outstanding results, obtaining an accuracy, sensitivity, specificity, and F-score of 93.6%, 100%, 92.5% and 96.1%, respectively.

Transcriptomic Analysis Reveals Prognostic Molecular Signatures of Stage I Melanoma.

PURPOSE: Previously identified transcriptomic signatures have been based on primary and metastatic melanomas with relatively few American Joint Committee on Cancer (AJCC) stage I tumors, given difficulties in sampling small tumors. The advent of adjuvant therapies has highlighted the need for better prognostic and predictive biomarkers, especially for AJCC stage I and stage II disease. EXPERIMENTAL DESIGN: A total of 687 primary melanoma transcriptomes were generated from the Leeds Melanoma Cohort (LMC). The prognostic value of existing signatures across all the AJCC stages was tested. Unsupervised clustering was performed, and the prognostic value of the resultant signature was compared with that of sentinel node biopsy (SNB) and tested as a biomarker in three published immunotherapy datasets. RESULTS: Previous Lund and The Cancer Genome Atlas signatures predicted outcome in the LMC dataset (P = 10-8 to 10-4) but showed a significant interaction with AJCC stage (P = 0.04) and did not predict outcome in stage I tumors (P = 0.3-0.7). Consensus-based classification of the LMC dataset identified six classes that predicted outcome, notably in stage I disease. LMC class was a similar indicator of prognosis when compared with SNB, and it added prognostic value to the genes reported by Gerami and colleagues. One particular LMC class consistently predicted poor outcome in patients receiving immunotherapy in two of three tested datasets. Biological characterization of this class revealed high JUN and AXL expression and evidence of epithelial-to-mesenchymal transition. CONCLUSIONS: A transcriptomic signature of primary melanoma was identified with prognostic value, including in stage I melanoma and in patients undergoing immunotherapy.