AI-assisted screening tool that reduces technologist average read time from 5 minutes to under 30 seconds.
Fecal Ova & Parasite Detector
Transforming the practice of pathology
Overview
CE-IVDD marked in Europe
Our O&P solution will classify and count the following objects (for a full list, see below):
Challenges & Solutions
Studies show that up to 95% of O&P cases are negative 1. Reading them requires skilled technologists that can be difficult to find and retain. It’s monotonous, and peering eight hours a day through a microscope can cause repetitive stress injuries.
Our solution helps technologists quickly eliminate negative samples using a computer monitor, allowing them to focus more on the positive cases.
How it works
4-step process:
Prepare slides
Lab tech preps slides using an Apacor Mini or Midi Parasep to concentrate the sample, then follow a standard Trichrome or Modified Acid Fast CDC staining protocol. Slides are then coverslipped for scanning.
Scan slides
Technicians load slides into the chosen scanner. Slides are then scanned and the resulting images are automatically uploaded to the Techcyte platform for AI analysis. Our Trichrome and modified acid fast (MAF) O&P fecal tests accept any good-quality 80x image from a compatible scanner (for a list of compatible scanners, see below). Our wet mount iodine solution is under development and will accept 40x images.
Process images
Our AI algorithm uses a convolutional neural network to identify differentiating features and determine which combinations indicate a certain ova, parasites, or other diagnostically significant objects. It then places them into the most likely classification for technologist review. This algorithm is deterministic, making the same classification every time it is shown the same image. The whole process is designed to take just minutes.
Review results
A technologist logs into Techcyte on any web-enabled device and reviews available samples, confirming presence of objects of interest and, if required, their prevalence. They can also add notes or request an additional consult.
Positive samples are manually reviewed by a technologist who confirms the assessment on the microscope and confirms results in their LIS.
Cells & Organisms Identified
- Blastocystis spp.
- Giardia duodenalis
- Combined D.frag, Ib, E.nana troph
- Dientamoeba fragilis
- Endolimax nana
- Iodamoeba buetschlii
- Entamoeba spp.
- Entamoeba coli
- Entamoeba polecki
- Entamoeba histolytica-complex (4 other morphologically similar species)
- Entamoeba hartmanni
- Chilomastix mesnili
- Cyclospora cayetanensis (advisory)
- White Blood Cells
- Red Blood Cells
- Cryptosporidium spp. oocysts
- Cyclospora cayetanensis oocysts
- Yeast
- Ascaris lumbricoides
- Balantioides coli
- Blastocystis spp.
- Chilomastix mesnili
- Clonorchis sinensis/Opisthorchis spp.
- Cyclospora spp.
- Cystoisospora belli
- Endolimax nana
- Entamoeba species
- Enterobius vermicularis
- Fasciola spp./Fasciolopsis buski
- Fish Tapeworm
- Giardia duodenalis
- Hookworm/Trichostrongylus
- Hymenolepis diminuta
- Iodamoeba buetschlii
- Misc Small Protozoans
- Chilomastix trophozoites
- Dientamoeba fragilis troph
- Endolimax nana troph
- Entamoeba hartmanni
- Iodamoeba buetschlii troph
- Paragonimus spp.
- Paracapillaria philippinensis
- Rodentolepsis nana
- Schistosoma mansoni
- Schistosoma japonicum/S. mekongi
- Strongyloides spp.
- Taenia spp.
- Trichuris trichiura
Supported scanners
Trichrome
Hamamatsu S360
3DHistech P250, P1000
Trichrome (under development)
Pramana M Pro, HT2, HT4
Modified Acid Fast (MAF)
3DHistech P250, P1000
Wet Mount Iodine (under development)
Hamamatsu S360, S20
Grundium Ocus 40
Features
- State-of-the-art platform
- AI-proposed images of parasites and objects of interest, grouped by class and sorted by confidence
- 30-second average read times
- Sensitivity 98.9%, slide-level specificity 98.1%*
- 5 serial dilutions are more sensitive when using Techcyte vs. manual examination*
- No daily cycle of fatigue, distraction, or confirmation bias
- Levels out sample and stain variations
- Excels at low-prevalence samples
- High volume, high reliability scanners produce 80x equivalent digital images
*These claims have not been examined by the FDA. These results are from a single study in a US based reference lab.
Benefits
Partners
Related Resources
-
Video
Mayo Clinic ‘Hot Topic’ – AI and Digital Slide Scanning: Detection of Intestinal Protozoa in Trichrome-Stained Stool Specimens
Sep 2023 -
Publications
JCM Article: Detection of Intestinal Protozoa in Trichrome-Stained Stool Specimens by Use of a Deep Convolutional Neural Network
May 2020 -
Publications
JCM Commentary: Computer Vision and Artificial Intelligence Are Emerging Diagnostic Tools for the Clinical Microbiologist
May 2020 -
Press Release
Techcyte announces the release of their second generation AI for Human Parasites
Jul 2022 -
Press Release
A Whole New Microscopic World: ARUP/Techcyte Publish First Peer-Reviewed Study on AI-based Ova and Parasite Detection Tool
Jun 2020 -
Press Release
ARUP Laboratories Deploys World’s First AI-Augmented Ova and Parasite Detection Tool
Aug 2019 -
Press Release
Techcyte and ARUP Laboratories partner to deliver AI-based Digital Diagnostics
Jan 2019