AI-assisted ova, cyst, and parasite screening tool designed to improve the accuracy and efficiency of an O&P test.ย
Fusion Parasitology Suite
Overview
The solution will classify and count the following objects (for a full list see below):
Challenges & Solutions
Laboratory technologists analyzing wet mount iodine-stained slides for parasites face a difficult task. Most of the samples are negative, it takes a high amount of specialized training, and looking through a microscope all day can be laborious.
The Techcyte solution digitizes the samples and uses AI-powered analysis to enhance diagnostic accuracy, streamline the reporting process, and improve the working conditions of the medical technologists performing the reads.
How it works
4-step process:
Prepare slides
Lab techs prepare the slides using a fecal concentration device. The Apacor Mini or Midi Parasep are recommended. A specialized mounting media is added to the slide to lengthen slide life to two hours and improve the visibility of the parasites. Slides are then coverslipped for scanning.
Scan slides
Technicians load slides into a supported scanner. The scanner scans the slide and produces a high-quality 40x image, which is automatically uploaded to the Techcyte platform for AI analysis.
Process images
The AI algorithm uses a convolutional neural network to find ova, parasites, and other diagnostically significant objects. It classifies and presents them for technologist review. The scanning and processing only takes a few minutes.
Review results
Technologists log into Techcyte on a web browser and review the scanned images, confirming the presence of objects of interest and, if required, their prevalence and size. They can also add notes or request an additional consultation.
Positive samples are manually reviewed by technologists who confirm the assessment on the microscope and report their results in their LIS.
Cells & Organisms Identified
- Ascaris lumbricoides
- Clonorchis sinensis/Opisthorchis spp.
- Enterobius vermicularis
- Fasciola spp./Fasciolopsis buski
- Fish Tapeworm
- Hookworm/Trichostrongylus
- Hymenolepis diminuta
- Paragonimus spp.
- Paracapillaria philippinensis
- Rodentolepsis nana
- Schistosoma mansoni
- Schistosoma japonicum/S. mekongi
- Strongyloides spp.
- Taenia spp.
- Trichuris trichiura
- Balantioides coli
- Blastocystis spp.
- Chilomastix mesnili
- Cyclospora spp.
- Cystoisospora belli
- Endolimax nana
- Entamoeba species
- Entamoeba coli
- Entamoeba histolytica/dispar
- Entamoeba polecki
- Giardia duodenalis
- Iodamoeba buetschlii
- Misc Small Protozoans
- Chilomastix trophozoites
- Dientamoeba fragilis troph
- Endolimax nana troph
- Entamoeba hartmanni
- Iodamoeba buetschlii troph
Supported Scanners
Hamamatsu S360, S20
Grundium Ocus 40
Pramana M Pro, HT2, HT4
Features
-
Unified Pathology
Integrated digital workflow and AI platform -
AI-assisted
AI-proposed images of parasites & objects of interest, grouped by class, and sorted by confidence -
Multi-scan
Multi-scan review can combine Trichrome and Wet Mount slides into a single patient case -
Whole slide imaging
Scanners produce 80x equivalent digital images -
Parasitology Suite
Complements Techcyte’s Trichrome and Modified Acid Fast solutions to find additional parasites -
Single site study
Validation studies showed an average read time of 15 – 30 seconds**These claims have not been examined by the FDA. -
Improved sample preparation
Special stain increases the life of the slide and the clarity of the parasites
Benefits
Partners
Transforming the practice of pathology
Overview
CE-IVDD marked in Europe
The solution will classify, count and present the following objects for confirmation by a technologist (for a full list, see below):
Challenges & Solutions
Studies show that up to 98% of Trichrome-stained slides are negative 1.Reading them requires skilled technologists who can be difficult to find and retain. It’s difficult and monotonous, and looking eight hours a day through a microscope can cause repetitive stress injuries.
The solution is designed to help technologists quickly eliminate negative samples using a web browser on a computer monitor, allowing them to focus on the positive cases.
How it works
4-step process:
Prepare slides
Scan slides
Technicians load slides into a compatible scanner. Slides are scanned and the resulting images are automatically uploaded to the Techcyte platform for AI analysis. The Trichrome solution uses 40x images from compatible scanners. (for a list of compatible scanners, see below).
Process images
The AI algorithm uses a convolutional neural network to find ova, parasites, and other diagnostically significant objects. It classifies and presents them for technologist review. The scanning and processing only takes a few minutes.
Review results
Technologists log into Techcyte on a web browser and review the scanned images, confirming the presence of objects of interest and, if required, their prevalence and size. They can also add notes or request an additional consult.
Positive samples are manually reviewed by technologists who confirm the assessment on the microscope and report their results in their LIS
Cells & Organisms Identified
- Blastocystis sp.
- Giardia duodenalis
- Combined D.frag, Ib, E.nana troph
- Dientamoeba fragilis
- Endolimax nana
- Iodamoeba buetschlii
- Entamoeba hartmanni
- Entamoeba sp.
- 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
Supported scanners
Trichrome
Hamamatsu S360
3DHistech P250, P1000
Pramana M Pro, HT2, HT4
Features
-
Unified Platform
Integrated digital workflow and AI platform -
AI-assisted
AI-proposed images of parasites & objects of interest, grouped by class, and sorted by confidence -
Multi-scan review
Multi-scan review can combine Trichrome and Wet Mount slides into a single patient case -
Negative review times
Validation studies showed an average read time of 15 – 30 seconds for negative slides* -
Single site study
Preliminary results from a single-site study indicate a sensitivity of 98.9% and a slide-level specificity of 98.1%* -
Whole slide imaging
Scanners produce 80x equivalent digital images
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
Overview
The solution will classify, count and present the following objects: