Background/Aims To develop a deep learning system (DLS) that can automatically detect malignant melanoma (MM) in the eyelid from histopathological sections with colossal information density. Methods Setting: Double institutional study. Study population: We retrospectively reviewed 225 230 pathological patches (small section cut from pathologist-labelled area from an H&E image), cut from 155 H&E-stained whole-slide images (WSI). Observation procedures: Labelled gigapixel pathological WSIs were used to train and test a model designed to assign patch-level classification. Using malignant probability from a convolutional neural network, the patches were embedded back into each WSI to generate a visualisation heatmap and leveraged a random forest model to establish a WSI-level diagnosis. Main outcome measure(s): For classification, the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity were used to evaluate the efficacy of the DLS in detecting MM. Results For patch diagnosis, the model achieved an AUC of 0.989 (95% CI 0.989 to 0.991), with an accuracy, sensitivity and specificity of 94.9%, 94.7% and 95.3%, respectively. We displayed the lesion area on the WSIs as graded by malignant potential. For WSI, the obtained sensitivity, specificity and accuracy were 100%, 96.5% and 98.2%, respectively, with an AUC of 0.998 (95% CI 0.994 to 1.000). Conclusion Our DLS, which uses artificial intelligence, can automatically detect MM in histopathological slides and highlight the lesion area on WSIs using a probabilistic heatmap. In addition, our approach has the potential to be applied to the histopathological sections of other tumour types.

Objectives To describe the clinicopathological characteristics of patients with eyelid tumours and tumour-like lesions in South China, investigate possible factors affecting tumour constitution. Design Retrospective cohort study. Setting All patients diagnosed with eyelid tumours were included from a high-volume tertiary eye care centre from South China which caring for over 2000 patients per day. All biopsied specimens were reviewed by two senior pathologists and were classified according to the fourth edition of the WHO Classification of Skin Tumours. Participant A total of 5146 cases of eyelid lesions were reviewed from 2000 to 2018, being classified by histogenesis and pathologic diagnosis, being compared with data from previous literature containing different races. Main outcome measures Age-specific and gender-specific incidence constitutions, time trends, tumour location, distribution in different age groups and relationship with Sociodmographic Index (SDI) were calculated. Results Benign tumours accounted for 85.08% (4378) of all cases, among which, nevus was most common (33.07%). Eight of top 10 benign lesions had higher occurrence in upper eyelids. The R² value of linear regression in patient annual number of benign lesions were 0.946 (p<0.01) for male and 0.914 (p<0.01) for female. More than 33.60% (1471/4378) were made up by patients younger than 40 years. The number of patients undergoing removal of benign lesions decreased with age. Among the malignant lesions, basal cell carcinoma (BCC) was most prevalent (48.70%), followed by sebaceous gland carcinoma (34.24%) and majority (81.8%) occurred in patients above 60 years. Conclusions Over the past 19 years, most eyelid tumours occurred at our centre were benign lesions. The number of patients presenting with benign lesions increased in both genders, especially among young females who were more likely to request surgeries. Among malignant lesions, BCC remains the most common type, appears a higher incidence in countries with higher SDI.

The COVID-19 pandemic has created substantial and dynamic disruptions in society, personal behavior, and potentially chronic sound exposures, which are associated with hearing loss, cardiovascular disease, and other health impacts. Leveraging preliminary data from our unique nationwide Apple Hearing Study, we explored changes in personal sound exposures resulting from COVID-19-related social distancing. Volunteer participants opted to share environmental sound data from their Apple Watch and headphone sound data from their iPhone. Participants for this analysis were chosen from four states which exhibited diverse responses to COVID-19. Equivalent continuous average sound exposures (in A-weighted decibels, dBA) were computed per person-day and normalized to 8 hour L_EX8h exposures. Daily mean L_EX8h exposures across two time periods, a baseline period (before the first known US COVID-19 death at the time of analysis) and an intervention period (starting with each state’s first COVID-related public health social distancing announcement and ending on April 22, 2020) were defined to assess changes in sound exposure. We modeled sound levels across 5,894 participants and 516,729 monitored days using a linear mixed-effects model with random effects for participant. The overall reduction in LEX8h between baseline and intervention was 2.6 ± 0.05 dBA (mean ± SE). There was a significant day-of-week effect during the baseline period, with the lowest exposures on Monday and the highest on Saturday. This effect was not noted during the intervention period. COVID-19 social distancing measures were associated with an approximately 3 dBA reduction in personal environmental sound exposures; this represents a substantial and meaningful reduction in this harmful exposure. Our analysis demonstrates the utility of everyday use devices in detecting behavior and exposure changes associated with the COVID-19 pandemic, and the usefulness of longitudinal, large-scale characterization of personal exposures and health impacts using wearable technology.

Retinal neovascularization (RNV), a typical pathological manifestation involved in most neovascular diseases, causes retinal detachment, vision loss, and ultimately irreversible blindness. Repeated intravitreal injections of anti-VEGF drugs were developed against RNV, with limitations of incomplete responses and adverse effects. Therefore, a new treatment with a better curative effect and more prolonged dosage is demanding. Here, we induced macrophage polarization to anti-inflammatory M2 phenotype by inhibiting cGAS-STING signaling with an antagonist C176, appreciating the role of cGAS-STING signaling in the retina in pro-inflammatory M1 polarization. C176-loaded and phosphatidylserine-modified dendritic mesoporous silica nanoparticles were constructed and examined by a single intravitreal injection. The biosafe nanoparticles were phagocytosed by retinal macrophages through a phosphatidylserine-mediated “eat me” signal, which persistently release C176 to suppress STING signaling and thereby promote macrophage M2 polarization specifically. A single dosage can effectively alleviate pathological angiogenesis phenotypes in murine oxygen-induced retinopathy models. In conclusion, these C176-loaded nanoparticles with enhanced cell uptake and long-lasting STING inhibition effects might serve as a promising way for treating RNV.

Deep learning methods are frequently used in segmenting histopathology images with high-quality annotations nowadays. Compared with well-annotated data, coarse, scribbling-like labelling is more cost-effective and easier to obtain in clinical practice. The coarse annotations provide limited supervision, so employing them directly for segmentation network training remains challenging. We present a sketch-supervised method, called DCTGN-CAM, based on a dual CNN-Transformer network and a modified global normalised class activation map. By modelling global and local tumour features simultaneously, the dual CNN-Transformer network produces accurate patch-based tumour classification probabilities by training only on lightly annotated data. With the global normalised class activation map, more descriptive gradient-based representations of the histopathology images can be obtained, and inference of tumour segmentation can be performed with high accuracy. Additionally, we collect a private skin cancer dataset named BSS, which contains fine and coarse annotations for three types of cancer. To facilitate reproducible performance comparison, experts are also invited to label coarse annotations on the public liver cancer dataset PAIP2019. On the BSS dataset, our DCTGN-CAM segmentation outperforms the state-of-the-art methods and achieves 76.68 % IOU and 86.69 % Dice scores on the sketch-based tumour segmentation task. On the PAIP2019 dataset, our method achieves a Dice gain of 8.37 % compared with U-Net as the baseline network. The annotation and code will be published at https://github.com/skdarkless/DCTGN–CAM .