Florian Jaeckle

New AI Sees Gluten Damage Doctors Often Miss – And Diagnoses Celiac in Seconds Cambridge scientists have developed a powerful AI tool that can diagnose celiac disease from biopsy images with over 97% accuracy. Trained on thousands of samples from diverse sources, the algorithm o...

Another health breakthrough, this time from Cambridge University.

An AI tool can diagnose celiac disease from biopsy images with over 97% accuracy in seconds.

@campathology.bsky.social
@hugheshall.bsky.social
@uniofcam.bsky.social
@cuh.nhs.uk
@ai.cam.ac.uk

A big thank you to all of my amazing collaborators and all of our incredibly partners and funders who made this work possible
@coeliacuk.bsky.social
@innovateuk.bsky.social
@acceleratescience.bsky.social
@cambridgec2d3.bsky.social
@cambridgebrc.bsky.social
@nihr.bsky.social

We hope that our interpretable AI approach marks a significant first step toward software that could support faster, more accurate and consistent coeliac disease diagnosis. [5/5]

Evaluating the IEL-to-enterocyte (in the villi and the crypts) and villus-to-crypt ratios on a large independent test set from a previously unseen hospital, we observed statistically significant differences for all ratios between the normal and coeliac disease populations. [4/5]

We showed how the models can accurately predict the IEL-to-enterocyte ratio. An increased IEL-to-enterocyte ratio is a key indicator of coeliac disease. However, unlike pathologists who only have time to count a few cells, the AI model can detect 1000s of cells in the entire biopsy in seconds. [3/5]

We developed segmentation models that can identify villi, crypts, intraepithelial lymphocytes (IELs), and enterocytes in H&E-stained duodenal biopsies, the four key structures used by pathologist when diagnosing coeliac disease. [2/5]

Very excited to share our paper "Interpretable machine learning-­based detection of coeliac disease" published this week in BMJ Digital Health & AI (bmjdigitalhealth.bmj.com/content/1/1/...) @bmj.com.

Key findings below 👇 [1/5]

📢 New blog post! Find out how @florianjaeckle.bsky.social based at @campathology.bsky.social @cuh.nhs.uk @hugheshall.bsky.social is using AI to speed up diagnosis of coeliac disease developing an algorithm that correctly identified more than 95 cases out of 100.

Find out more: bit.ly/3Z3Q6C0

Figure 2. The Five Steps in Our Pipeline.

A machine learning model that diagnoses celiac disease from duodenal biopsy images demonstrates strong generalizability across multiple hospitals & has the potential to enhance diagnostic efficiency & reliability in clinical practice. nejm.ai/4iJz7fZ

#AI #MedSky @florianjaeckle.bsky.social

Machine Learning Achieves Pathologist-Level Celiac Disease Diagnosis The diagnosis of celiac disease (CD), an autoimmune disorder with an estimated global prevalence of around 1%, generally relies on the histologic examination of duodenal biopsies. However, interpat...

A new #ML model developed for #CeliacDisease diagnosis achieved accuracy, sensitivity, and specificity above 95%, matching or exceeding pathologist-level performance. By diagnosing CD from diverse biopsy samples, it has the potential to reduce diagnostic time and support more reliable diagnoses.

@campathology.bsky.social, @hugheshall.bsky.social, @uniofcam.bsky.social, @nejm.org, @ai.nejm.org, @cuhnhs.bsky.social, @ai.cam.ac.uk

A big thank you to all of my amazing collaborators and all of our incredibly partners and funders who made this work possible
@coeliacuk.bsky.social,
@innovateuk.bsky.social,
@acceleratescience.bsky.social,
@cambridgec2d3.bsky.social,
@cambridgebrc.bsky.social

If you would like to read more please see our paper (ai.nejm.org/stoken/defau...), or if you prefer a less technical article see this Guardian article (www.theguardian.com/science/2025...), or this report written by the University Comms team (www.cam.ac.uk/stories/AI-a...)

We compared diagnoses from four experienced pathologists with those from our AI model. The result: average agreement between any two pathologists was identical (90%) to the agreement between each pathologist and the AI model.
The takeaway: the AI matches expert-level accuracy.

Our model was trained and validated on 3,000+ cases from 4 hospitals using 5 different scanners.
When tested on 600+ cases from a completely unseen hospital, it maintained high accuracy across all adult patient subgroups, demonstrating strong generalisability in real-world settings.

Our model pipeline looks as follows:
i) remove artefacts + separate tissue from background
ii) break down biopsy image into 256x256 pixel sub-patches
iii) apply stain normalisation
iv) train a ResNet model with multiple-instance learning
v) run inference + generate heatmaps to visualise prediction

Very excited to share our latest work published yesterday in NEJM AI @ai.nejm.org. We developed an AI model that diagnoses coeliac disease at the same level of accuracy as experienced pathologists.
The paper is available to read here:
ai.nejm.org/stoken/defau...

@campathology.bsky.social @hugheshall.bsky.social @uniofcam.bsky.social @nejm.org @ai.nejm.org @cuhnhs.bsky.social @ai.cam.ac.uk

If you would like to read more please see our paper (ai.nejm.org/stoken/defau...), or if you prefer a less technical article see this Guardian article (www.theguardian.com/science/2025...), or this report written by the brilliant University Comms team (www.cam.ac.uk/stories/AI-a...)

We compared diagnoses from four experienced pathologists with those from our AI model. The result: average agreement between any two pathologists was identical (90%) to the agreement between each pathologist and the AI model.
The takeaway: the AI matches expert-level accuracy.

Our model was trained and validated on 3,000+ cases from 4 hospitals using 5 different scanners.
When tested on 600+ cases from a completely unseen hospital, it maintained high accuracy across all adult patient subgroups, demonstrating strong generalisability in real-world settings.

Our model pipeline looks as follows:
i) remove artefacts + separate tissue from background
ii) break down biopsy image into 256x256 pixel sub-patches
iii) apply stain normalisation
iv) train a ResNet model with multiple-instance learning
v) run inference + generate heatmaps to visualise prediction

A big thank you to all of my amazing collaborators and all of our incredibly partners and funders who made this work possible @coeliacuk.bsky.social @innovateuk.bsky.social @acceleratescience.bsky.social @cambridgec2d3.bsky.social @cambridgebrc.bsky.social

Exciting developments in this field - congratulations to @florianjaeckle.bsky.social who is co-author of this important research.🌟

Machine Learning Achieves Pathologist-Level Celiac Disease Diagnosis Mar 27, 2025 Original Article by F. Jaeckle and Others

A machine learning model that diagnoses celiac disease from duodenal biopsy images demonstrates strong generalizability across multiple hospitals and has the potential to enhance diagnostic efficiency and reliability in clinical practice. #NEJMAI #OriginalArticle

Researchers develop AI tool that could speed up coeliac disease diagnosis Cambridge study finds algorithm is as effective as a pathologist in detecting disease – and much quicker AI could speed up the diagnosis of coeliac disease, according to research. Coeliac disease is an autoimmune condition affecting just under 700,000 people in the UK, but getting an accurate diagnosis can take years. Continue reading...

Researchers develop AI tool that could speed up coeliac disease diagnosis

AI is as good as pathologists at diagnosing coeliac disease, study finds - Hughes Hall A machine learning algorithm developed by Cambridge scientists was able to correctly identify in 97 cases out of 100 whether or not an individual had coeliac disease based on their biopsy, new…

An #AI tool developed by @uniofcam.bsky.social scientists could help accelerate coeliac diagnosis.

"This is the first time AI has been shown to diagnose as accurately as an experienced pathologist whether an individual has coeliac or not" Dr Florian Jaeckle