Integrating Skin Cancer–Related Technologies into Clinical Practice

Analyzing the Impact of Image Denoising and Segmentation on Melanoma Classification Using Convolutional Neural Networks

Early skin cancer detection and its treatment are crucial for reducing death rates worldwide. Deep learning techniques have been used successfully to develop an automatic lesion detection system. This study explores the impact of pre-processing steps such as data augmentation, contrast enhancement, and segmentation on improving the convolutional neural network (CNN) performance for lesion classification. The classification network was designed from scratch by uniquely organizing its layers and using a different number of kernels, depth of the network, size, and hyperparameters. In addition, the network's performance was improved by pre-processing and segmentation steps. The proposed network was compared with the current state-of-the-art to demonstrate its best performance on the benchmark HAM10000 lesion dataset. The experimental study revealed that the classification network using denoised+segmented data achieved an accuracy (ACC), precision (PRE), recall (REC), specificity (SPE), and F-score of 93.40%, 93.45%, 94.51%, 92.08%, and 93.98%, respectively. To conclude, classification performance can be improved by incorporating pre-processing and segmentation steps.

Dermoscopic Photographs Impact Confidence and Management of Remotely Triaged Skin Lesions

Introduction

Improving remote triage is crucial given expansions in tele-dermatology and with limited in-person care during COVID-19. In addition to clinical pictures, dermoscopic images may provide utility for triage.

Objectives

To determine if dermoscopic images enhance confidence, triage accuracy, and triage prioritization for tele-dermatology.

Methods

In this preliminary parallel convergent mixed-methods study, a cohort of dermatologists and residents assessed skin lesions using clinical and dermoscopic images. For each case, participants viewed a clinical image and determined diagnostic category, management, urgency, and decision-making confidence. They subsequently viewed the associated dermoscopy and answered the same questions. A moderated focus group discussion followed to explore perceptions on the role of dermoscopy in tele-dermatology.

Results

Dermoscopy improved recognition of malignancies by 23% and significantly reduced triage urgency measures for non-malignant lesions. Participants endorsed specific utilities of tele-dermoscopy, such as for evaluating pigmented lesions, with limitations including poor image quality.

Conclusions

Dermoscopic images may be useful when remotely triaging skin lesions. Standardized imaging protocols are needed.

Integrating the melanoma 31-gene expression profile test with surgical oncology practice within national guideline and staging recommendations

Aim: Define changes in clinical management resulting from the use of the prognostic 31-gene expression profile (31-GEP) test for cutaneous melanoma in a surgical oncology practice. Patients & methods: Management plans for 112 consecutively tested patients with stage I-III melanoma were evaluated for duration and number of clinical visits, blood work and imaging. Results: 31-GEP high-risk (class 2; n = 46) patients received increased management compared with low-risk (class 1; n = 66) patients. Test results were most closely associated with follow-up and imaging. Of class 1 patients, 65% received surveillance intensity within guidelines for stage I-IIA patients; 98% of class 2 patients received surveillance intensity equal to stage IIB-IV patients. Conclusion: We suggest clinical follow-up and metastatic screening be adjusted according to 31-GEP test results.

Dermoscopy diagnosis of cancerous lesions utilizing dual deep learning algorithms via visual and audio (sonification) outputs: Laboratory and prospective observational studies

BACKGROUND

Early diagnosis of skin cancer lesions by dermoscopy, the gold standard in dermatological imaging, calls for a diagnostic upscale. The aim of the study was to improve the accuracy of dermoscopic skin cancer diagnosis through use of novel deep learning (DL) algorithms. An additional sonification-derived diagnostic layer was added to the visual classification to increase sensitivity.

METHODS

Two parallel studies were conducted: a laboratory retrospective study (LABS, n = 482 biopsies) and a non-interventional prospective observational study (OBS, n = 63 biopsies). A training data set of biopsy-verified reports, normal and cancerous skin lesions (n = 3954), were used to develop a DL classifier exploring visual features (System A). The outputs of the classifier were sonified, i.e. data conversion into sound (System B). Derived sound files were analyzed by a second machine learning classifier, either as raw audio (LABS, OBS) or following conversion into spectrograms (LABS) and by image analysis and human heuristics (OBS). The OBS criteria outcomes were System A specificity and System B sensitivity as raw sounds, spectrogram areas or heuristics.

FINDINGS

LABS employed dermoscopies, half benign half malignant, and compared the accuracy of Systems A and B. System A algorithm resulted in a ROC AUC of 0.976 (95% CI, 0.965-0.987). Secondary machine learning analysis of raw sound, FFT and Spectrogram ROC curves resulted in AUC's of 0.931 (95% CI 0.881-0.981), 0.90 (95% CI 0.838-0.963) and 0.988 (CI 95% 0.973-1.001), respectively. OBS analysis of raw sound dermoscopies by the secondary machine learning resulted in a ROC AUC of 0.819 (95% CI, 0.7956 to 0.8406). OBS image analysis of AUC for spectrograms displayed a ROC AUC of 0.808 (CI 95% 0.6945 To 0.9208). By applying a heuristic analysis of Systems A and B a sensitivity of 86% and specificity of 91% were derived in the clinical study.

INTERPRETATION

Adding a second stage of processing, which includes a deep learning algorithm of sonification and heuristic inspection with machine learning, significantly improves diagnostic accuracy. A combined two-stage system is expected to assist clinical decisions and de-escalate the current trend of over-diagnosis of skin cancer lesions as pathological. FUND: Bostel Technologies. Trial Registration clinicaltrials.gov Identifier: NCT03362138.