New-generation diagnostics in inflammatory skin diseases: Immunofluorescence and histopathological assessment using ex vivo confocal laser scanning microscopy in cutaneous lupus erythematosus

Ex Vivo Confocal Laser Scanning Microscopy in Rare Skin Diseases

While ex vivo confocal laser scanning microscopy has previously demonstrated its utility in most common skin diseases, its use in the assessment of dermatological entities with lower incidence remains unexplored in most cases. We therefore aimed to evaluate the diagnostic efficacy of some rare skin tumors as well as a few inflammatory skin diseases, that have not yet been studied in ex vivo confocal laser scanning microscopy. A total of 50 tissue samples comprising 10 healthy controls, 10 basal cell carcinoma, 10 squamous cell carcinoma, and 20 rare skin conditions were imaged using the newest generation ex vivo confocal microscopy (Vivascope 2500 M-G4, Vivascope GmbH, Munich, Germany). Three blinded investigators were asked to identify characteristic features of rare skin disorders and distinguish them from more common skin diseases in the ex vivo confocal microscopy images. Our findings present the capability of ex vivo confocal microscopy to display distinctive morphologic patterns in common and rare skin diseases. As might be expected, we found a strong correlation between imaging experience and diagnostic accuracy. While the imaging inexperienced dermatohistopathologist reached 60% concordance, the imaging-trained dermatologist obtained 88% agreement with dermatohistopathology. The imaging-trained dermatohistopathologist achieved concordance up to 92% with gold-standard dermatohistopathology. This study highlights the potential of ex vivo confocal laser scanning microscopy as a promising adjunct to conventional dermatohistopathology for the early and precise identification of rare dermatological disorders.

Visually Hidden, Self-Assembled Porous Polymers for Optical Physically Unclonable Functions

Owing to the advancement of security technologies, several encryption methods have been proposed. Despite such efforts, forging artifices is financially and somatically becoming a constraint for individuals and society (e.g., imprinting replicas of luxury goods or directly life-connected medicines). Physically unclonable functions (PUFs) are one of the promising solutions to address these personal and social issues. The unreplicability of PUFs is a crucial factor for high security levels. Here, this study proposes a visually hidden and self-assembled porous polymer (VSPP) as a tag for optical PUF systems. The VSPP has virtues in terms of wavelength dependency, lens-free compact PUF system, and simple/affordable fabrication processes (i.e., spin coating and annealing). The VSPP consists of an external saturated surface, which covers the inner structures, and an internally abundant porous layer, which triggers stochastic multiple Mie scattering with wavelength dependency. We theoretically and experimentally validate the unobservability of the VSPP and the uniqueness of optical responses by image sensors. Finally, we establish a wavelength-dependent PUF system by using the following three components: solid-state light sources, a VSPP tag, and an image sensor. The captured raw images by the sensor serve as "seed" for unique bit sequences. The robustness of our system is successfully confirmed in terms of bit uniformity (∼0.5), intra/interdevice Hamming distances (∼0.04/∼0.5), and randomness (using NIST test).

Ex vivo confocal laser scanning microscopy: A diagnostic technique for easy real-time evaluation of benign and malignant skin tumours

Ex vivo confocal laser scanning microscopy (ex vivo CLSM) is a novel diagnostic tool for a quick bedside evaluation of freshly excised tissue, comparable to histology. We aimed to assess the sensitivity and specificity of ex vivo CLSM in detecting malignant features, to validate its reliability in identifying various skin tumours based on a combination of confocal features and to evaluate the digital staining mode (DS). One-hundred twenty freshly excised skin samples from 91 patients were evaluated. Each lesion was screened for the presence of 23 predefined confocal criteria with ex vivo CLSM, followed by a histopathological examination. The diagnostic agreement between ex vivo CLSM and histology was 89.2%. The diagnostic accuracy of ex vivo CLSM in detecting malignancy reached a sensitivity of 98% and a specificity of 76%. Ex vivo CLSM enabled a rapid identification of the most common skin tumours, the tumour dignity and cytological features. The DS demonstrated a close resemblance to conventional histopathology.

Visualization of energy-based device-induced thermal tissue alterations using bimodal ex-vivo confocal microscopy with digital staining. A proof-of-concept study

BACKGROUND

Ex-vivo confocal microscopy (EVCM) enables examination of tissue alterations immediately after treatment with energy-based devices (EBDs). This proof-of-concept study aimed to describe EBD-induced tissue effects in ex-vivo porcine skin after treatment with microneedle radiofrequency (MNRF) and ablative fractional CO₂ -laser (AFL) using EVCM.

MATERIALS AND METHODS

Ex-vivo porcine skin was treated with MNRF and AFL. Three cryosections from each intervention were stained with acridine orange (AO) and scanned with EVCM. Reflectance confocal microscopy (RCM, 638 nm) and fluorescence confocal microscopy (FCM, 488 nm) images were captured and evaluated individually, after image fusion, and after digital hematoxylin and eosin (H&E) staining.

RESULTS

Bimodal EVCM was able to visualize EBD-induced thermal alterations in porcine skin. In RCM mode, the full width and depth of the vertically aligned microscopic treatment zones (MTZs) were displayed with clear demarcation to surrounding intact skin. In FCM mode, the ablation of the epidermis after AFL was prominent in contrast with the almost intact epidermis observed in MNRF treated skin. In fusion mode, fluorescence signal from AO marked the surrounding coagulation zone (CZ) from both interventions, with enhanced discrimination between ablation and coagulation. Digitally H&E-stained images closely resembled conventional histopathology but proved superior in terms of visualization of the CZ.

CONCLUSION

Bimodal EVCM with digital H&E-staining facilitates the identification and qualitative evaluation of thermal alterations induced by treatment with EBD. By providing high-resolution images comparable to standard histology, EVCM is a useful tool in the research and development of EBD to visualize and evaluate device-tissue interactions.

Machine Learning Based Prediction of Squamous Cell Carcinoma in Ex Vivo Confocal Laser Scanning Microscopy

Image classification with convolutional neural networks (CNN) offers an unprecedented opportunity to medical imaging. Regulatory agencies in the USA and Europe have already cleared numerous deep learning/machine learning based medical devices and algorithms. While the field of radiology is on the forefront of artificial intelligence (AI) revolution, conventional pathology, which commonly relies on examination of tissue samples on a glass slide, is falling behind in leveraging this technology. On the other hand, ex vivo confocal laser scanning microscopy (ex vivo CLSM), owing to its digital workflow features, has a high potential to benefit from integrating AI tools into the assessment and decision-making process. Aim of this work was to explore a preliminary application of CNN in digitally stained ex vivo CLSM images of cutaneous squamous cell carcinoma (cSCC) for automated detection of tumor tissue. Thirty-four freshly excised tissue samples were prospectively collected and examined immediately after resection. After the histologically confirmed ex vivo CLSM diagnosis, the tumor tissue was annotated for segmentation by experts, in order to train the MobileNet CNN. The model was then trained and evaluated using cross validation. The overall sensitivity and specificity of the deep neural network for detecting cSCC and tumor free areas on ex vivo CLSM slides compared to expert evaluation were 0.76 and 0.91, respectively. The area under the ROC curve was equal to 0.90 and the area under the precision-recall curve was 0.85. The results demonstrate a high potential of deep learning models to detect cSCC regions on digitally stained ex vivo CLSM slides and to distinguish them from tumor-free skin.

[Ex vivo confocal laser scanning microscopy for melanocytic lesions and autoimmune diseases]

BACKGROUND

Ex vivo confocal laser scanning microscopy (CLSM) enables bedside histology and offers the surgeon a direct intraoperative tissue examination.

OBJECTIVES

To determine whether this innovative, ultra-fast diagnostic tool can be expanded beyond nonmelanoma skin cancer, particularly basal cell carcinoma, to other indications including melanocytic lesions and autoimmune diseases.

MATERIALS AND METHODS

Review of literature and summary of the current knowledge and experience of the use of ex vivo CLSM in melanocytic lesions and in autoimmune diseases.

RESULTS

Up to date experience of the use of ex vivo CLSM in melanocytic lesions and in autoimmune diseases is limited but promising. Current knowledge on melanocytic lesions in ex vivo CLSM and their examples together with classic ex vivo CLSM features are presented. Previous results on the use of ex vivo CLSM in autoimmune dermatoses are presented, and future application possibilities of ex vivo CLSM are discussed.

CONCLUSIONS

The method is particularly suitable for the rapid examination of basal cell carcinomas during Mohs surgery but could also be used in the future for the intraoperative examination of melanocytic and autoimmune skin lesions.

Classification of Basal Cell Carcinoma in Ex Vivo Confocal Microscopy Images from Freshly Excised Tissues Using a Deep Learning Algorithm

Ex vivo confocal microscopy (EVCM) generates digitally colored purple-pink images similar to H&E without time-consuming tissue processing. It can be used during Mohs surgery for rapid detection of basal cell carcinoma (BCC); however, reading EVCM images requires specialized training. An automated approach using a deep learning algorithm for BCC detection in EVCM images can aid in diagnosis. A total of 40 BCCs and 28 negative (not-BCC) samples were collected at Memorial Sloan Kettering Cancer Center to create three training datasets: (i) EVCM image dataset (663 images), (ii) H&E image dataset (516 images), and (iii) a combination of the two datasets. A total of seven BCCs and four negative samples were collected to create an EVCM test dataset (107 images). The model trained with the EVCM dataset achieved 92% diagnostic accuracy, similar to the H&E model (93%). The area under the receiver operator characteristic curve was 0.94, 0.95, and 0.94 for EVCM-, H&E-, and combination-trained models, respectively. We developed an algorithm for automatic BCC detection in EVCM images (comparable accuracy to dermatologists). This approach could be used to assist with BCC detection during Mohs surgery. Furthermore, we found that a model trained with only H&E images (which are more available than EVCM images) can accurately detect BCC in EVCM images.