No abstract

Introduction There is an emerging need for telecytology in Colombia as the demand for cytopathology has increased. However, due to economic and technological constraints telecytology services are limited. Our aim was to evaluate the diagnostic feasibility of using whole slide imaging with and without Z‐stacking for telecytology in Colombia, South America. Methods Archival glass slides from 17 fine needle aspiration smears were digitized employing whole slide imaging (WSI) (Nanozoomer 2.0 HT, Hamamatsu) in one Z‐plane at 40x, and panoramic digital imaging (Panoptiq system, ViewsIQ) combining low‐magnification digital maps with embedded 40x Z‐stacks of representative regions of interest. Fourteen Colombian pathologists reviewed both sets of digital images. Diagnostic concordance, time to diagnosis, image quality (scale 1–10), usefulness of Z‐stacking, and technical difficulties were recorded. Results Image quality scored by pathologists was on average 8.3 for WSI and 8.7 for panoramic images with Z‐stacks (P = .03). However, diagnostic concordance was not impacted by image quality ranking. In the majority of cases (72.4%) pathologists deemed Z‐stacking to be diagnostically helpful. Technical issues related to Z‐stack video performance constituted only a minor proportion of technical problems reported. Slow downloads and crashing of files while viewing were mostly experienced with larger WSI files. Conclusion This study demonstrated that international telecytology for diagnostic purposes is feasible. Panoramic images had to be acquired manually, but were of suitable diagnostic quality and generated smaller image files associated with fewer technical errors. Z‐stacking proved to be useful in the majority of cases and is thus recommended for telecytology.

No abstract

The rise of Artificial Intelligence (AI) has shown promising performance as a support tool in clinical pathology workflows. In addition to the well-known interobserver variability between dermatopathologists, melanomas present a significant challenge in their histological interpretation. This study aims to analyze all previously published studies on whole-slide images of melanocytic tumors that rely on deep learning techniques for automatic image analysis. Embase, Pubmed, Web of Science, and Virtual Health Library were used to search for relevant studies for the systematic review, in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. Articles from 2015 to July 2022 were included, with an emphasis placed on the used artificial intelligence methods. Twenty-eight studies that fulfilled the inclusion criteria were grouped into four groups based on their clinical objectives, including pathologists versus deep learning models (n = 10), diagnostic prediction (n = 7); prognosis (n = 5), and histological features (n = 6). These were then analyzed to draw conclusions on the general parameters and conditions of AI in pathology, as well as the necessary factors for better performance in real scenarios.