Testing the MitProfiler tool for detecting and counting dividing cells in stained tissue samples
| ISRCTN | ISRCTN16858627 |
|---|---|
| DOI | https://doi.org/10.1186/ISRCTN16858627 |
| IRAS number | 342246 |
| Secondary identifying numbers | MitPro Study Protocol 2.4 |
- Submission date
- 13/08/2025
- Registration date
- 19/09/2025
- Last edited
- 19/09/2025
- Recruitment status
- No longer recruiting
- Overall study status
- Completed
- Condition category
- Cancer
Plain English summary of protocol
Background and study aims
MitProfiler is a computer algorithm which uses machine learning, a form of artificial intelligence, to train computers to recognise mitotic figures in pathology samples (that is, samples of human or animal tissue prepared for microscopic examination). Mitotic figures are seen in cells which are dividing. They are the chromosomes in the cells which can be seen preparing to divide and separating into the daughter cells as the cells divide. They are an important feature of normal tissue biology (e.g. in growing regenerating tissue) and diseases such as cancer (where cells grow and divide in an uncontrolled manner). Pathologists see and count mitotic figures routinely in their work. Having the computer do this task saves time, reduces fatigue in pathologists and should deliver more consistent results as observations between individual human pathologists vary to some extent. By getting human pathologists and the MitProfiler algorithm to count mitoses in the same samples, this study aims to measure how the MitProfiler algorithm performs in comparison to human pathologists.
Who can participate?
Patients with haematoxylin and eosin-stained tissue sections from various tumour types
What does the study involve?
This study involves comparing the human pathologists' counts of mitotic figures in stained tissue sections with an automated mitotic counting algorithm.
What are the possible benefits and risks of participating?
If the results are as good or better than human pathologists, the data derived will be used to support the regulatory approval of the device through the Medicines and Healthcare Regulatory Authority.
Where is the study run from?
Histofy Ltd (UK)
When is the study starting and how long is it expected to run for?
February 2025 to September 2025
Who is funding the study?
Innovate UK
Who is the main contact?
Prof. David Snead, david.snead@uhcw.nhs.uk
Contact information
Public, Scientific, Principal investigator
Histofy
Venture centre
Sir William Lyons Rd
West Midlands
CV4 7AL
United Kingdom
 ORCID ID |
0000-0002-0766-9650 |
|---|---|
| Phone | +44 (0)2476968649 |
| d.snead@histofy.ai |
Study information
| Study design | Observational cohort study |
|---|---|
| Primary study design | Observational |
| Secondary study design | Cohort study |
| Study setting(s) | Laboratory |
| Study type | Diagnostic |
| Scientific title | Validation of the MitProfiler algorithm for the detection and quantification of mitotic figures in haematoxylin and eosin-stained tissue sections |
| Study acronym | MitPro validation study |
| Study objectives | MitProfiler is a computer algorithm which uses machine learning, a form of artificial intelligence, to train computers to recognise mitotic figures in pathology samples (that is, samples of human or animal tissue prepared for microscopic examination). Mitotic figures are seen in cells which are dividing. They are the chromosomes in the cells which can be seen preparing to divide and separating into the daughter cells as the cells actually divide. They are an important feature of normal tissue biology (e.g. in growing regenerating tissue) and diseases such as cancer (where cells grow and divide in an uncontrolled manner). Pathologists see and count mitotic figures routinely in their work. Having the computer do this task saves time, reduces fatigue in pathologists and should deliver more consistent results as observations between individual human pathologists vary to some extent. By getting human pathologists and the MitProfiler algorithm to count mitoses in the same samples, this study aims to measure how closely the MitProfiler algorithm performs in comparison to human pathologists. If the results are as good or better than human pathologists, the data derived will be used to support the regulatory approval of the device through the Medicines and Healthcare Regulatory Authority. |
| Ethics approval(s) |
Approved 20/02/2025, London - Fulham Research Ethics Committee (2 Redman Place, Stratford, London, E20 1JQ, United Kingdom; +44 (0)207 104 8084, (0)207 104 8286, (0)207 104 8109; fulham.rec@hra.nhs.uk), ref: 25/LO/0158 |
| Health condition(s) or problem(s) studied | Sarcoma, melanoma, carcinoma, carcinoid |
| Intervention | This observational study involves comparing the blinded counts of mitotic figures in archived hematoxylin and eosin (H&E) sections with an automated mitotic counting algorithm. |
| Intervention type | Device |
| Pharmaceutical study type(s) | Not Applicable |
| Phase | Not Applicable |
| Drug / device / biological / vaccine name(s) | MitPro |
| Primary outcome measure | Interobserver variation of mitotic counts measured using data generated by the MitProfiler algorithm and human pathologists at one timepoint |
| Secondary outcome measures | Time taken to produce mitotic counts measured using data generated by the MitProfiler algorithm and human pathologists at one timepoint |
| Overall study start date | 20/02/2025 |
| Completion date | 30/09/2025 |
Eligibility
| Participant type(s) | Patient |
|---|---|
| Age group | Mixed |
| Lower age limit | 1 Year |
| Upper age limit | 100 Years |
| Sex | All |
| Target number of participants | 500 |
| Key inclusion criteria | Patients with haematoxylin and eosin-stained tissue sections from tumour types: 1. Breast cancer 2. Neuroendocrine tumour 3. Melanoma (including uveal melanoma) 4. Soft tissue sarcoma 5. Leiomyoma 6. Lung cancer 7. Glioblastoma 8. Meningioma 9. Thyroid cancer 10. Retinoblastoma |
| Key exclusion criteria | Haematoxylin and eosin-stained tissue section slides are unavailable |
| Date of first enrolment | 13/08/2025 |
| Date of final enrolment | 20/09/2025 |
Locations
Countries of recruitment
- England
- United Kingdom
Study participating centre
Holdforth Road
Hartlepool
TS24 9AH
United Kingdom
Sponsor information
Industry
The Venture Centre
Sir William Lyons Road
Coventry
CV4 7EZ
England
United Kingdom
| Website | https://histofy.ai/ |
|---|
Funders
Funder type
Government
Government organisation / National government
- Alternative name(s)
- UK Research and Innovation Innovate UK, innovateuk
- Location
- United Kingdom
Results and Publications
| Intention to publish date | 31/10/2025 |
|---|---|
| Individual participant data (IPD) Intention to share | No |
| IPD sharing plan summary | Data sharing statement to be made available at a later date |
| Publication and dissemination plan | Planned publication in a peer-reviewed journal |
| IPD sharing plan | The data sharing plans for the current study are unknown and will be made available at a later date |
Study outputs
| Output type | Details | Date created | Date added | Peer reviewed? | Patient-facing? |
|---|---|---|---|---|---|
| Protocol file | version 2.4 | 21/08/2025 | No | No |
Additional files
Editorial Notes
13/08/2025: Study's existence confirmed by Health Research Authority (HRA) (UK).
