Digital skin imaging applications, part II: a comprehensive survey of post-acquisition image utilization features and technology standards.

BACKGROUND: Despite the increasing ubiquity and accessibility of teledermatology applications, few studies have comprehensively surveyed their features and technical standards. Importantly, features implemented after the point of capture are often intended to augment image utilization, while technical standards affect interoperability with existing healthcare systems. We aim to comprehensively survey image utilization features and technical characteristics found within publicly discoverable digital skin imaging applications. MATERIALS AND METHODS: Applications were identified and categorized as described in Part I. Included applications were then further assessed by three independent reviewers for post-imaging content, tools, and functionality. Publicly available information was used to determine the presence or absence of relevant technology standards and/or data characteristics. RESULTS: A total of 20 post-image acquisition features were identified across three general categories: (1) metadata attachment, (2) functional tools (i.e., those that utilized images or in-app content to perform a user-directed function), and (3) image processing. Over 80% of all applications implemented metadata features, with nearly half having metadata features only. Individual feature occurred and feature richness varied significantly by primary audience (p < 0.0001) and function (p < 0.0001). On average, each application included under three features. Less than half of all applications requested consent for user-uploaded photos and fewer than 10% provided clear data use and privacy policies. CONCLUSION: Post-imaging functionality in skin imaging applications varies significantly by primary audience and intended function, though nearly all applications implemented metadata labeling. Technical standards are often not implemented or reported consistently. Gaps in the provision of clear consent, data privacy, and data use policies should be urgently addressed.

Prospective validation of dermoscopy-based open-source artificial intelligence for melanoma diagnosis (PROVE-AI study).

The use of artificial intelligence (AI) has the potential to improve the assessment of lesions suspicious of melanoma, but few clinical studies have been conducted. We validated the accuracy of an open-source, non-commercial AI algorithm for melanoma diagnosis and assessed its potential impact on dermatologist decision-making. We conducted a prospective, observational clinical study to assess the diagnostic accuracy of the AI algorithm (ADAE) in predicting melanoma from dermoscopy skin lesion images. The primary aim was to assess the reliability of ADAE's sensitivity at a predefined threshold of 95%. Patients who had consented for a skin biopsy to exclude melanoma were eligible. Dermatologists also estimated the probability of melanoma and indicated management choices before and after real-time exposure to ADAE scores. All lesions underwent biopsy. Four hundred thirty-five participants were enrolled and contributed 603 lesions (95 melanomas). Participants had a mean age of 59 years, 54% were female, and 96% were White individuals. At the predetermined 95% sensitivity threshold, ADAE had a sensitivity of 96.8% (95% CI: 91.1-98.9%) and specificity of 37.4% (95% CI: 33.3-41.7%). The dermatologists' ability to assess melanoma risk significantly improved after ADAE exposure (AUC 0.7798 vs. 0.8161, p = 0.042). Post-ADAE dermatologist decisions also had equivalent or higher net benefit compared to biopsying all lesions. We validated the accuracy of an open-source melanoma AI algorithm and showed its theoretical potential for improving dermatology experts' ability to evaluate lesions suspicious of melanoma. Larger randomized trials are needed to fully evaluate the potential of adopting this AI algorithm into clinical workflows.

Prevalence and Age-Related Patterns in Health Information-Seeking Behaviors and Technology Use Among Skin Cancer Survivors: Survey Study.

Background: Information is an unmet need among cancer survivors. There is a paucity of population-based data examining the health information-seeking behaviors and attitudes of skin cancer survivors. Objective: We aimed to identify the prevalence and patterns of health information-seeking behaviors and attitudes among skin cancer survivors across age groups. Methods: We analyzed population-based data from the 2019 Health Information National Trends Survey 5 (Cycle 3). Results: The 5438 respondents included 346 (6.4%) skin cancer survivors (mean age 65.8 years); of the 346 skin cancer survivors, the majority were White (96.4% [weighted percentages]), and 171 (47.8%) were men. Most reported having ever looked for health- (86.1%) or cancer-related (76.5%) information; 28.2% stated their last search took a lot of effort, and 21.6% were frustrated. The internet was most often cited as being the first source that was recently used for health or medical information (45.6%). Compared to skin cancer survivors younger than 65 years old, those 65 years of age or older were more likely to see a doctor first for important health information (≥65 years: 68.3%;<65 years: 36.2%; P<.001) and less likely to have health and wellness apps (≥65 years: 26.4%; <65 years: 54.0%, P=.10), to have watched a health-related YouTube video (≥65 years: 13.3%; <65 years: 27.4%; P=.02), and to have used electronic means to look for information (≥65 years: 61.4%;<65 years: 82.3%, P<.001). Conclusions: Searches for health information are common among skin cancer survivors, but behaviors and attitudes are associated with age, which highlights the importance of access to doctors and personalized information sources.

An Epidemiologic Analysis of Melanoma Overdiagnosis in the United States, 1975-2017.

The primary cause of the increase in melanoma incidence in the United States has been suggested to be overdiagnosis. We used Surveillance, Epidemiology, and End Result Program data from 1975 to 2017 to examine epidemiologic trends of melanoma incidence and mortality and better characterize overdiagnosis in white Americans. Over the 43-year period, incidence and mortality showed discordant temporal changes across population subgroups; trends most suggestive of overdiagnosis alone were present in females aged 55-74. Other groups showed mixed changes suggestive of overdiagnosis plus changes in underlying disease risk (decreasing risk in younger individuals and increasing risk in older males). Cohort effects were identified for male and female mortality and male incidence but were not as apparent for female incidence, suggesting that period effects have had a greater influence on changes in incidence over time in females. Encouraging trends included long-term declines in mortality in younger individuals and recent stabilization of invasive incidence in individuals aged 15-44 years and males aged 45-54 years. Melanoma in situ incidence, however, has continued to increase throughout the population. Overdiagnosis appears to be relatively greater in American females and for melanoma in situ.

Immune checkpoint inhibitors in patients with pre-existing psoriasis: safety and efficacy.

BACKGROUND: Immune checkpoint inhibitors (ICIs) are approved to treat multiple cancers. Retrospective analyses demonstrate acceptable safety of ICIs in most patients with autoimmune disease, although disease exacerbation may occur. Psoriasis vulgaris is a common, immune-mediated disease, and outcomes of ICI treatment in patients with psoriasis are not well described. Thus we sought to define the safety profile and effectiveness of ICIs in patients with pre-existing psoriasis. METHODS: In this retrospective cohort study, patients from eight academic centers with pre-existing psoriasis who received ICI treatment for cancer were evaluated. Main safety outcomes were psoriasis exacerbation and immune-related adverse events (irAEs). We also assessed progression-free survival (PFS) and overall survival. RESULTS: Of 76 patients studied (50 (66%) male; median age 67 years; 62 (82%) with melanoma, 5 (7%) with lung cancer, 2 (3%) with head and neck cancer, and 7 (9%) with other cancers; median follow-up 25.1 months (range=0.2-99 months)), 51 (67%) received anti-PD-1 antibodies, 8 (11%) anti-CTLA-4, and 17 (22%) combination of anti-PD-1/CTLA-4. All patients had pre-existing psoriasis, most frequently plaque psoriasis (46 patients (61%)) and 15 (20%) with psoriatic arthritis. Forty-one patients (54%) had received any prior therapy for psoriasis although only two (3%) were on systemic immunosuppression at ICI initiation. With ICI treatment, 43 patients (57%) experienced a psoriasis flare of cutaneous and/or extracutaneous disease after a median of 44 days of receiving ICI. Of those who experienced a flare, 23 patients (53%) were managed with topical therapy only; 16 (21%) needed systemic therapy. Only five patients (7%) required immunotherapy discontinuation for psoriasis flare. Forty-five patients (59%) experienced other irAEs, 17 (22%) of which were grade 3/4. PFS with landmark analysis was significantly longer in patients with a psoriasis flare versus those without (39 vs 8.7 months, p=0.049). CONCLUSIONS: In this multicenter study, ICI therapy was associated with frequent psoriasis exacerbation, although flares were manageable with standard psoriasis treatments and few required ICI discontinuation. Patients who experienced disease exacerbation performed at least as well as those who did not. Thus, pre-existing psoriasis should not prevent patients from receiving ICIs for treatment of malignancy.

Skin cancer classification via convolutional neural networks: systematic review of studies involving human experts.

BACKGROUND: Multiple studies have compared the performance of artificial intelligence (AI)-based models for automated skin cancer classification to human experts, thus setting the cornerstone for a successful translation of AI-based tools into clinicopathological practice. OBJECTIVE: The objective of the study was to systematically analyse the current state of research on reader studies involving melanoma and to assess their potential clinical relevance by evaluating three main aspects: test set characteristics (holdout/out-of-distribution data set, composition), test setting (experimental/clinical, inclusion of metadata) and representativeness of participating clinicians. METHODS: PubMed, Medline and ScienceDirect were screened for peer-reviewed studies published between 2017 and 2021 and dealing with AI-based skin cancer classification involving melanoma. The search terms skin cancer classification, deep learning, convolutional neural network (CNN), melanoma (detection), digital biomarkers, histopathology and whole slide imaging were combined. Based on the search results, only studies that considered direct comparison of AI results with clinicians and had a diagnostic classification as their main objective were included. RESULTS: A total of 19 reader studies fulfilled the inclusion criteria. Of these, 11 CNN-based approaches addressed the classification of dermoscopic images; 6 concentrated on the classification of clinical images, whereas 2 dermatopathological studies utilised digitised histopathological whole slide images. CONCLUSIONS: All 19 included studies demonstrated superior or at least equivalent performance of CNN-based classifiers compared with clinicians. However, almost all studies were conducted in highly artificial settings based exclusively on single images of the suspicious lesions. Moreover, test sets mainly consisted of holdout images and did not represent the full range of patient populations and melanoma subtypes encountered in clinical practice.

Combined ultrasonic thermal ablation with interleaved ARFI image monitoring using a single diagnostic curvilinear array: a feasibility study.

The goal of this work is to demonstrate the feasibility of using a diagnostic ultrasound system (Siemens Antares and CH6-2 curvilinear array) to ablate ex vivo liver with a custom M-mode sequence and monitor the resulting tissue stiffening with 2-D Acoustic Radiation Force Impulse (ARFI) imaging. Images were taken before and after ablation, as well as in 5- s intervals during the ablation sequence in order to monitor the ablation lesion formation temporally. Ablation lesions were generated at depths up to 1.5 cm from the surface of the liver and were not visible in B-mode. ARFI images showed liver stiffening with heating that corresponded to discolored regions in gross pathology. As expected, the contrast of ablation lesions in ARFI images is observed to increase with ablation lesion size. This study demonstrated the ability of a diagnostic system using custom beam sequences to localize an ablation site, heat the site to the point of irreversible damage and monitor the formation of the ablation lesion with ARFI imaging.

Improving the robustness of time-of-flight based shear wave speed reconstruction methods using RANSAC in human liver in vivo.

The stiffness of tissue can be quantified by measuring the shear wave speed (SWS) within the medium. Ultrasound is a real-time imaging modality capable of tracking the propagation of shear waves in soft tissue. Time-of-flight (TOF) methods have previously been shown to be effective for quantifying SWS from ultrasonically tracked displacements. However, the application of these methods to in vivo data is challenging due to the presence of additional sources of error, such as physiologic motion or spatial inhomogeneities in tissue. This article introduces the use of random sample consensus (RANSAC), a model fitting paradigm robust to the presence of gross outlier data, for estimating the SWS from ultrasonically tracked tissue displacements in vivo. SWS reconstruction is posed as a parameter estimation problem and the RANSAC solution to this problem is described. Simulations using synthetic TOF data show that RANSAC is capable of good stiffness reconstruction accuracy (mean error 0.5 kPa) and precision (standard deviation 0.6 kPa) over a range of shear stiffness (0.6-10 kPa) and proportion of inlier data (50%-95%). As with all TOF SWS estimation methods, the accuracy and precision of the RANSAC reconstructed shear modulus decreases with increasing tissue stiffness. The RANSAC SWS estimator was applied to radiation force induced shear wave data from 123 human patient livers acquired with a modified SONOLINE Antares ultrasound system (Siemens Healthcare, Ultrasound Business Unit, Mountain View, CA, USA) in a clinical setting before liver biopsy was performed. Stiffness measurements were not possible in 19 patients due to the absence of shear wave propagation inside the liver. The mean liver stiffness for the remaining 104 patients ranged from 1.3 to 24.2 kPa and the proportion of inliers for the successful reconstructions ranged between 42% to 99%. Using RANSAC for SWS estimation improved the diagnostic accuracy of liver stiffness for delineating fibrosis stage compared with ordinary least squares (OLS) without outlier removal (AUROC = 0.94 for F >or= 3 and AUROC = 0.98 for F = 4). These results show that RANSAC is a suitable method for estimating the SWS from noisy in vivo shear wave displacements tracked by ultrasound.

CoC: a database of universally conserved residues in protein folds.

UNLABELLED: The conservatism of conservatism (CoC) database presents statistically analyzed information about the conservation of residue positions in folds across protein families. AVAILABILITY: On the web at http://kulibin.mit.edu/coc/