Pixel-level classification of pigmented skin cancer lesions using multispectral autofluorescence lifetime dermoscopy imaging.

There is no clinical tool available to primary care physicians or dermatologists that could provide objective identification of suspicious skin cancer lesions. Multispectral autofluorescence lifetime imaging (maFLIM) dermoscopy enables label-free biochemical and metabolic imaging of skin lesions. This study investigated the use of pixel-level maFLIM dermoscopy features for objective discrimination of malignant from visually similar benign pigmented skin lesions. Clinical maFLIM dermoscopy images were acquired from 60 pigmented skin lesions before undergoing a biopsy examination. Random forest and deep neural networks classification models were explored, as they do not require explicit feature selection. Feature pools with either spectral intensity or bi-exponential maFLIM features, and a combined feature pool, were independently evaluated with each classification model. A rigorous cross-validation strategy tailored for small-size datasets was adopted to estimate classification performance. Time-resolved bi-exponential autofluorescence features were found to be critical for accurate detection of malignant pigmented skin lesions. The deep neural network model produced the best lesion-level classification, with sensitivity and specificity of 76.84%±12.49% and 78.29%±5.50%, respectively, while the random forest classifier produced sensitivity and specificity of 74.73%±14.66% and 76.83%±9.58%, respectively. Results from this study indicate that machine-learning driven maFLIM dermoscopy has the potential to assist doctors with identifying patients in real need of biopsy examination, thus facilitating early detection while reducing the rate of unnecessary biopsies.

Discrimination of cancerous from benign pigmented skin lesions based on multispectral autofluorescence lifetime imaging dermoscopy and machine learning.

SIGNIFICANCE: Accurate early diagnosis of malignant skin lesions is critical in providing adequate and timely treatment; unfortunately, initial clinical evaluation of similar-looking benign and malignant skin lesions can result in missed diagnosis of malignant lesions and unnecessary biopsy of benign ones. AIM: To develop and validate a label-free and objective image-guided strategy for the clinical evaluation of suspicious pigmented skin lesions based on multispectral autofluorescence lifetime imaging (maFLIM) dermoscopy. APPROACH: We tested the hypothesis that maFLIM-derived autofluorescence global features can be used in machine-learning (ML) models to discriminate malignant from benign pigmented skin lesions. Clinical widefield maFLIM dermoscopy imaging of 41 benign and 19 malignant pigmented skin lesions from 30 patients were acquired prior to tissue biopsy sampling. Three different pools of global image-level maFLIM features were extracted: multispectral intensity, time-domain biexponential, and frequency-domain phasor features. The classification potential of each feature pool to discriminate benign versus malignant pigmented skin lesions was evaluated by training quadratic discriminant analysis (QDA) classification models and applying a leave-one-patient-out cross-validation strategy. RESULTS: Classification performance estimates obtained after unbiased feature selection were as follows: 68% sensitivity and 80% specificity with the phasor feature pool, 84% sensitivity, and 71% specificity with the biexponential feature pool, and 84% sensitivity and 32% specificity with the intensity feature pool. Ensemble combinations of QDA models trained with phasor and biexponential features yielded sensitivity of 84% and specificity of 90%, outperforming all other models considered. CONCLUSIONS: Simple classification ML models based on time-resolved (biexponential and phasor) autofluorescence global features extracted from maFLIM dermoscopy images have the potential to provide objective discrimination of malignant from benign pigmented lesions. ML-assisted maFLIM dermoscopy could potentially assist with the clinical evaluation of suspicious lesions and the identification of those patients benefiting the most from biopsy examination.

A Multicenter Clinical Study of Expected and Unexpected Side Reactions During and After Skin Cancer Treatment by Photodynamic Therapy.

Photodynamic therapy (PDT) has been widely used for oncologic indications, especially nonmelanoma skin cancer such as superficial and nodular basal cell carcinoma (BCC). We present a multicenter clinical study conducted between 2012 and 2014 analyzing the adverse reactions during and after PDT with a standardized protocol in 866 lesions. A total of 728 patients with positive clinical and histopathological diagnosis for BCC with up to 2 cm diameter were treated. The procedure consisted of curettage and topical application of cream containing 20% methyl 5-aminolevulinate. The illumination (630 nm and 150 J/cm2) was performed 3 hours after the cream application. The expected and unexpected effects observed were pain, healing, and inflammatory reactions. The pain intensity was correlated with the anatomical localization of the lesion. The patients reported a higher intensity of pain in lesions located on the head and neck rather than on the trunk and limbs. The number of sessions also influenced the pain response. A total of 83% of patients showed perfect healing and the other 17% presented abnormal healing. PDT plays an important role in BCC because of its low cost, ease of use, and low rate of side effects.

Experience and BCC subtypes as determinants of MAL-PDT response: preliminary results of a national Brazilian project.

Non-melanoma skin cancer is the most prevalent cancer type in Brazil and worldwide. Photodynamic therapy (PDT) is a noninvasive technique with excellent cosmetic outcome and good curative results, when used for the initial stages of skin cancer. A Brazilian program was established to determine the efficacy of methyl aminolevulinate (MAL)-PDT, using Brazilian device and drug. The equipment is a dual device that combines the photodiagnosis, based on widefield fluorescence, and the treatment at 630nm. A protocol was defined for the treatment of basal cell carcinoma with 20% MAL cream application. The program also involves the training of the medical teams at different Brazilian regions, and with distinct facilities and previous PDT education. In this report we present the partial results of 27 centers with 366 treated BCC lesions in 294 patients. A complete response (CR) was observed in 76.5% (280/366). The better response was observed for superficial BCC, with CR 160 lesions (80.4%), when compared with nodular or pigmented BCC. Experienced centers presented CR of 85.8% and 90.6% for superficial and nodular BCC respectively. A high influence of the previous doctor experience on the CR values was observed, especially due to a better tumor selection.