Melanoma and other skin lesion detection using smart handheld devices

Towards the development of reliable and economical mHealth solutions: A methodology for accurate detection of Buruli ulcer for hard-to-reach communities

mHealth interventions have the potential to increase access to healthcare for the most hard-to-reach communities. For rural communities suffering disproportionately from skin-related NTDs, and Buruli ulcer, there is a need for low-cost, non-invasive and mobile tools for the early detection and management of disease. Dermoscopy is a noninvasive in-vivo technique that has been useful in improving the diagnostic accuracy of pigmented skin lesions based on anatomical features and morphological structures of lesions.

Objectives

Using dermoscopy, this study develops the automated tools necessary for developing an effective mHealth intervention towards identifying BU lesions in the early stages. Methods: This imaging methodology relies on an external attachment, a dermoscope, which uses polarized light to cancel out skin surface reflections. In our initial studies we used a dermoscope with only crosspolarized white-light (DL100, 3Gen) but later we adopted a more advanced multispectral dermoscope (DLIIm, 3Gen). The latter employed additional monochromatic light at different wavelengths of the visible spectral range, specifically blue (470 nm), yellow (580 nm), and red (660 nm) color, to visualize pigmented structures of skin layers at different depths.

Results

Results obtained using a subset of 58 white-light images with confirmed diagnosis (16 lesions BU and 42 lesions non-BU) resulting in sensitivity of 100 and specificity of 88.10, with an overall accuracy of 94.05 at 95% CI. Performance obtained using a second dataset of 197 dermoscopic multispectral images (16 lesions BU and 181 lesions non-BU) resulted in sensitivity of 90.00% and specificity of 93.39% with a balanced accuracy of 91.69% (86.95% to 95.12% at 95% CI).

Conclusions

This system will continue to perform even as the technology evolves and newer dermoscopes are available. Subsequent studies involve the DL4 which provides more uniform and brighter illumination, higher lesion magnification, and wider field of view which, combined with the superb resolution of modern smartphones, can result in faster and more accurate lesion assessment. This is an important step for the development of mHealth tools for use by non-specialists in community settings for the early detection of Buruli ulcer, skin-NTDs, and other dermatologic conditions associated with disease, including wound healing and management of disease progression.

Accurate diagnostic tissue segmentation and concurrent disease subtyping with small datasets

Purpose

To provide a flexible, end-to-end platform for visually distinguishing diseased from undiseased tissue in a medical image, in particular pathology slides, and classifying diseased regions by subtype. Highly accurate results are obtained using small training datasets and reduced-scale source images that can be easily shared.

Approach

An ensemble of lightweight convolutional neural networks (CNNs) is trained on different subsets of images derived from a relatively small number of annotated whole-slide histopathology images (WSIs). The WSIs are first reduced in scale in a manner that preserves anatomic features critical to analysis while also facilitating convenient handling and storage. The segmentation and subtyping tasks are performed sequentially on the reduced-scale images using the same basic workflow: generating and sifting tiles from the image, then classifying each tile with an ensemble of appropriately trained CNNs. For segmentation, the CNN predictions are combined using a function to favor a selected similarity metric, and a mask or map for a a candidate image is produced from tiles whose combined predictions exceed a decision boundary. For subtyping, the resulting mask is applied to the candidate image, and new tiles are derived from the unoccluded regions. These are classified by the subtyping CNNs to produce an overall subtype prediction.

Results and conclusion

This approach was applied successfully to two very different datasets of large WSIs, one (PAIP2020) involving multiple subtypes of colorectal cancer and the other (CAMELYON16) single-type breast cancer metastases. Scored using standard similarity metrics, the segmentations outperformed more complex models typifying the state of the art.

Smartphone applications for triaging adults with skin lesions that are suspicious for melanoma

BACKGROUND

Melanoma accounts for a small proportion of all skin cancer cases but is responsible for most skin cancer-related deaths. Early detection and treatment can improve survival. Smartphone applications are readily accessible and potentially offer an instant risk assessment of the likelihood of malignancy so that the right people seek further medical attention from a clinician for more detailed assessment of the lesion. There is, however, a risk that melanomas will be missed and treatment delayed if the application reassures the user that their lesion is low risk.

OBJECTIVES

To assess the diagnostic accuracy of smartphone applications to rule out cutaneous invasive melanoma and atypical intraepidermal melanocytic variants in adults with concerns about suspicious skin lesions.

SEARCH METHODS

We undertook a comprehensive search of the following databases from inception to August 2016: Cochrane Central Register of Controlled Trials; MEDLINE; Embase; CINAHL; CPCI; Zetoc; Science Citation Index; US National Institutes of Health Ongoing Trials Register; NIHR Clinical Research Network Portfolio Database; and the World Health Organization International Clinical Trials Registry Platform. We studied reference lists and published systematic review articles.

SELECTION CRITERIA

Studies of any design evaluating smartphone applications intended for use by individuals in a community setting who have lesions that might be suspicious for melanoma or atypical intraepidermal melanocytic variants versus a reference standard of histological confirmation or clinical follow-up and expert opinion.

DATA COLLECTION AND ANALYSIS

Two review authors independently extracted all data using a standardised data extraction and quality assessment form (based on QUADAS-2). Due to scarcity of data and poor quality of studies, we did not perform a meta-analysis for this review. For illustrative purposes, we plotted estimates of sensitivity and specificity on coupled forest plots for each application under consideration.

MAIN RESULTS

This review reports on two cohorts of lesions published in two studies. Both studies were at high risk of bias from selective participant recruitment and high rates of non-evaluable images. Concerns about applicability of findings were high due to inclusion only of lesions already selected for excision in a dermatology clinic setting, and image acquisition by clinicians rather than by smartphone app users.We report data for five mobile phone applications and 332 suspicious skin lesions with 86 melanomas across the two studies. Across the four artificial intelligence-based applications that classified lesion images (photographs) as melanomas (one application) or as high risk or 'problematic' lesions (three applications) using a pre-programmed algorithm, sensitivities ranged from 7% (95% CI 2% to 16%) to 73% (95% CI 52% to 88%) and specificities from 37% (95% CI 29% to 46%) to 94% (95% CI 87% to 97%). The single application using store-and-forward review of lesion images by a dermatologist had a sensitivity of 98% (95% CI 90% to 100%) and specificity of 30% (95% CI 22% to 40%).The number of test failures (lesion images analysed by the applications but classed as 'unevaluable' and excluded by the study authors) ranged from 3 to 31 (or 2% to 18% of lesions analysed). The store-and-forward application had one of the highest rates of test failure (15%). At least one melanoma was classed as unevaluable in three of the four application evaluations.

AUTHORS' CONCLUSIONS

Smartphone applications using artificial intelligence-based analysis have not yet demonstrated sufficient promise in terms of accuracy, and they are associated with a high likelihood of missing melanomas. Applications based on store-and-forward images could have a potential role in the timely presentation of people with potentially malignant lesions by facilitating active self-management health practices and early engagement of those with suspicious skin lesions; however, they may incur a significant increase in resource and workload. Given the paucity of evidence and low methodological quality of existing studies, it is not possible to draw any implications for practice. Nevertheless, this is a rapidly advancing field, and new and better applications with robust reporting of studies could change these conclusions substantially.

"The Smartphone's Guide to the Galaxy": In Situ Analysis in Space

A human mission to Mars can be viewed as the apex of human technological achievement. However, to make this dream a reality several obstacles need to be overcome. One is devising practical ways to safeguard the crew health during the mission through the development of easy operable and compact sensors. Lately, several smartphone-based sensing devices (SBDs) with the purpose to enable the immediate sensitive detection of chemicals, proteins or pathogens in remote settings have emerged. In this critical review, the potential to piggyback these systems for in situ analysis in space has been investigated on application of a systematic keyword search whereby the most relevant articles were examined comprehensively and existing SBDs were divided into 4 relevant groups for the monitoring of crew health during space missions. Recently developed recognition elements (REs), which could offer the enhanced ability to tolerate those harsh conditions in space, have been reviewed with recommendations offered. In addition, the potential use of cell free synthetic biology to obtain long-term shelf-stable reagents was reviewed. Finally, a synopsis of the possibilities of combining novel SBD, RE and nanomaterials to create a compact sensor-platform ensuring adequate crew health monitoring has been provided.

Improving outcomes in patients with melanoma: strategies to ensure an early diagnosis

Patients with thin, low-risk melanomas have an excellent long-term prognosis and higher quality of life than those who are diagnosed at later stages. From an economic standpoint, treatment of early stage melanoma consumes a fraction of the health care resources needed to treat advanced disease. Consequently, early diagnosis of melanoma is in the best interest of patients, payers, and health care systems. This review describes strategies to ensure that patients receive an early diagnosis through interventions ranging from better utilization of primary care clinics, to in vivo diagnostic technologies, to new "apps" available in the market. Strategies for screening those at high risk due to age, male sex, skin type, nevi, genetic mutations, or family history are discussed. Despite progress in identifying those at high risk for melanoma, there remains a lack of general consensus worldwide for best screening practices. Strategies to ensure early diagnosis of recurrent disease in those with a prior melanoma diagnosis are also reviewed. Variations in recurrence surveillance practices by type of provider and country are featured, with evidence demonstrating that various imaging studies, including ultrasound, computed tomography, positron emission tomography, and magnetic resonance imaging, provide only minimal gains in life expectancy, even for those with more advanced (stage III) disease. Because the majority of melanomas are attributable to ultraviolet radiation in the form of sunlight, primary prevention strategies, including sunscreen use and behavioral interventions, are reviewed. Recent international government regulation of tanning beds is described, as well as issues surrounding the continued use artificial ultraviolet sources among youth. Health care stakeholder strategies to minimize UV exposure are summarized. The recommendations encompass both specific behaviors and broad intervention targets (eg, individuals, social spheres, organizations, celebrities, governments).

A Review of the Quantification and Classification of Pigmented Skin Lesions: From Dedicated to Hand-Held Devices

In recent years, the incidence of skin cancer cases has risen, worldwide, mainly due to the prolonged exposure to harmful ultraviolet radiation. Concurrently, the computer-assisted medical diagnosis of skin cancer has undergone major advances, through an improvement in the instrument and detection technology, and the development of algorithms to process the information. Moreover, because there has been an increased need to store medical data, for monitoring, comparative and assisted-learning purposes, algorithms for data processing and storage have also become more efficient in handling the increase of data. In addition, the potential use of common mobile devices to register high-resolution images of skin lesions has also fueled the need to create real-time processing algorithms that may provide a likelihood for the development of malignancy. This last possibility allows even non-specialists to monitor and follow-up suspected skin cancer cases. In this review, we present the major steps in the pre-processing, processing and post-processing of skin lesion images, with a particular emphasis on the quantification and classification of pigmented skin lesions. We further review and outline the future challenges for the creation of minimum-feature, automated and real-time algorithms for the detection of skin cancer from images acquired via common mobile devices.