UNLIMITED
Why and how should pathologists keep up with AI? w/ David Harrison, University of St. Andrews by Digital Pathology PodcastUNLIMITED
41: Digital Pathology for Dermatologists. How Pathology Watch managed to incorporate digital pathology in dermatology practices across the US w/ Dan L…
UNLIMITED
41: Digital Pathology for Dermatologists. How Pathology Watch managed to incorporate digital pathology in dermatology practices across the US w/ Dan L…
ratings:
Length:
23 minutes
Released:
Apr 25, 2022
Format:
Podcast episode
Description
Digital pathology is supposed to help pathologists provide better patient care and make their lives easier, but what about other doctors, do they even care? Maybe radiologists? Oncologists? Nope…Dermatologists! They do care!And they are the clients of Pathology Watch – a CLIA lab specializing in dermatopathology, that is currently servicing samples from over 65 dermatology clinics in the USA. Pathology Watch provides an end-to-end digital pathology solution for dermatologists. From processing the samples sent by the dermatologists, through the dermatopathology report to the whole slide image of the diagnosed sample, and all this browser-based and integrated with the dermatology clinic’s electronic medical record (EMR) systems. This provides a completely non-disruptive workflow. Pathology Watch is providing a true end-to-end solution built around dermatologists. The EMR integration saves the dermatologists time (25h/ month!!! Who would not want to have that?!?) and whole slide images build the bridge between and improve the communication on the “patient-dermatologist-pathologist” line. Dermatologists can show the images of the cases to the patients, and they can see the highlighted areas used by the pathologist when diagnosing the case. Once the digitization and intersystem integration take care of the time savings it’s time to step up the game! The next step is using artificial intelligence for better dermatopathology diagnostics and to gain even more time savings. Pathology Watch designed its AI pipeline specifically to bypass the known industry problem of generalizability of AI models. It is extremely difficult to train generalizable models on samples from different institutions, but if the samples are processed in just one lab in a very controlled environment, using automated equipment and performing rigorous quality control, the pre-analytical variability causing a lack of generalizability is taken care of. As in any digital pathology operation, troubleshooting is part of the business. What do you do when your scanner breaks down? How do you store the digital pathology images effectively in a cost-efficient way? And how do you deliver the slides in the browser FAST? It took the Pathology Watch team a few years to solve those and other challenges and come up with good mitigation strategies. Do you want to know how they did it? Listen to the full episode to learn more from Dan Lambert, the CEO of Pathology Watch. This Episodes resourcesPathology Watch website Get your "Digital Pathology Beginners Guide" E-book for free! Sign up for the waiting list here.
Released:
Apr 25, 2022
Format:
Podcast episode
Titles in the series (100)
- 31 min listen