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.

This study explores the advanced imaging of skin vasculature using Line-Field Confocal Optical Coherence Tomography (LC-OCT), which offers high-resolution, three-dimensional (3D) visualization of vascular structures, especially within skin tumors. The research aims to improve the understanding of tumor angiogenesis and the complex vascular morphology associated with malignancies. The methodology involves converting original image stacks into negative images, manually tracing vessels using the Simple Neurite Tracer (SNT) plugin, and creating smoothed binary masks to reconstruct 3D models. The study’s results highlight the ability to visualize serpiginous, corkscrew-like, and irregular vessels across various skin cancers, including melanoma, squamous cell carcinoma, and basal cell carcinoma. These visualizations provide insights into vessel morphology, spatial arrangements, and blood flow patterns, which are crucial for assessing tumor growth and potential therapeutic responses. The findings indicate that 3D reconstructions from LC-OCT can uncover vascular details previously undetectable by two-dimensional imaging techniques, making it a valuable tool in dermatology for both clinical diagnostics and research. This method allows for better monitoring of skin cancer treatment and understanding of the role of vascular polymorphism in tumor development.

Monitoring the tumor margins of basal cell carcinomas is still a challenge in everyday clinical practice. Usually, the clinical margins of the tumor are marked by the naked eye or, even better, with dermoscopy before surgery and then examined in detail after the operation using histological examination. In order to achieve tumor freedom, several surgical steps are sometimes necessary, meaning that patients spend longer periods in hospital and the healthcare system is burdened more as a result. One way to improve this is the one-stop shop method, which requires precise diagnostics and margin marking before and during surgery so that tumor freedom can be achieved after just one surgery. For this reason, the current status of the diagnosis and treatment of basal cell carcinomas before and after surgery is to be examined following extensive literature research using devices and methods that have already been tested in order to determine how a simplified process of tumor margin control of basal cell carcinomas can be made possible both in vivo and ex vivo.

To date, therapeutic responses in plaque psoriasis are evaluated with clinical scores. No objective examination has been established. A recently developed non-invasive imaging tool, line-field confocal optical coherence tomography (LC-OCT), enables the in vivo live imaging of skin changes in psoriasis under therapy. The aim of this study was to measure therapeutic response clinically and with LC-OCT, comparing the subjectively scored epidermal changes with an AI-supported analysis. This prospective, observational study included 12 patients with psoriasis starting a systemic treatment with IL-17 inhibitors (secukinumab, ixekizumab, and bimekizumab). LC-OCT and clinical assessment with a local psoriasis and severity index of the study plaque and a control area were performed before the initiation of therapy as well as after 4 and 12 weeks of treatment. A manual and AI-supported measurement of the thickness of epidermis, stratum corneum, and undulation of the dermo-epidermal junction was carried out. Acanthosis and hyperkeratosis showed a significant reduction under treatment. AI-supported calculations were compared to subjective measurements showing good reliability with high correlation. AI-supported analysis of vascular changes may serve as a prognostic and therapeutic response marker in the future.

Background/Objectives: Topical imiquimod is an established non-invasive treatment for superficial basal cell carcinoma (sBCC). However, data on treatment-associated changes in tumor microvascularization remain limited. This study investigated vascular changes before and after imiquimod therapy using multimodal non-invasive imaging. Methods: In this single-center, prospective observational study, 31 basal cell carcinomas in 20 patients were examined before and 12–16 weeks after topical imiquimod therapy (5%, five times weekly for six weeks) using dermoscopy, dynamic optical coherence tomography (D-OCT), and line-field confocal optical coherence tomography (LC-OCT). Analyses were performed as paired before-and-after comparisons. While approved for sBCC, a small number of thin nodular and infiltrative BCCs were included exploratorily; subgroup analyses were not powered. Results: Dermoscopy showed a nominally significant shift toward smaller vessel diameter categories after therapy (ATS = 8.183, df = 1, p = 0.004). D-OCT-derived parameters (vessel density, vessel diameter, and depth of the vascular plexus) did not show nominally significant changes. LC-OCT showed nominally lower apparent intratumoral flow scores (ATS = 13.285, df = 1, p < 0.001), reduced occurrence of vessel-wall-associated intraluminal structures showing a rolling-like motion pattern (86.7% before treatment versus 33.3% after treatment; ATS = 13.357; df = 1, p < 0.001), and a reduction in maximum vessel diameter (ATS = 6.110, df = 1, p = 0.013). The primary LC-OCT inferential analyses were performed at the lesion level without adjustment for within-patient clustering and should therefore be interpreted as exploratory. An additional patient-cluster-adjusted paired change-score sensitivity analysis for LC-OCT maximum vessel diameter yielded a directionally consistent estimate (−17.81 µm; 95% CI: −34.40 to −1.23; p = 0.037). The primary exploratory endpoints were LC-OCT–based apparent intratumoral flow and maximum vessel diameter; secondary endpoints included dermoscopic and D-OCT–based vascular parameters. In the exploratory response-stratified analysis, the change in LC-OCT-based maximum vessel diameter did not differ significantly among the assigned response groups (Kruskal–Wallis H = 3.870, df = 2, raw p = 0.144; BH-adjusted p = 0.753). Conclusions: LC-OCT detected several exploratory vascular changes between the pre-treatment examination and follow-up and may provide complementary information for the non-invasive assessment of BCC after imiquimod therapy. Given the exploratory design, limited sample size, and lack of systematic histological confirmation, these findings are hypothesis-generating and require validation in larger prospective studies.

Background/Objectives: Rapid optical assessment of freshly excised basal cell carcinoma (BCC) specimens may shorten the interval between excision and margin evaluation. This prospective pilot study estimated the diagnostic performance of ex vivo line-field confocal optical coherence tomography (LC-OCT) for detecting residual BCC at lateral surgical margins, using histopathology as the reference standard. Methods: Fifty-five clinically suspicious lesions from 48 patients were examined at two centers. Results were analyzed for the complete cohort and for a post-training inclusion phase comprising 32 lesions from 31 patients. Overall lesion-level consensus classifications were recorded separately from classifications of the four clock-face quadrants. Lesions with a negative overall LC-OCT assessment and at least one non-evaluable quadrant were classified as indeterminate and excluded from the primary lesion-level analysis. Thirteen lesions also underwent exploratory ex vivo fusion confocal microscopy (evFCM). Results: In the inclusion phase, 125 of 128 quadrants were evaluable. Thirteen true-positive, 106 true-negative, 2 false-negative, and 4 false-positive quadrant results yielded 86.7% sensitivity, 96.4% specificity, and 95.2% accuracy. At the lesion level, 2 of 32 results were indeterminate. Among the remaining 30 lesions, LC-OCT yielded 5 true-positive, 22 true-negative, 2 false-negative, and 1 false-positive results, corresponding to 71.4% sensitivity, 95.7% specificity, and 90.0% accuracy. The evFCM analysis was descriptive because the subset was small and nonconsecutive. Conclusions: Ex vivo LC-OCT showed promising specificity and overall accuracy for assessing lateral BCC margins after training. The limited number of margin-positive lesions, indeterminate results, clustered quadrant data, and absence of systematic deep-margin imaging require cautious interpretation. LC-OCT should not replace histopathological margin assessment on the basis of the present data.