Lightnews — Scholar-powered news

Florian Jaeckle @florianjaeckle.bsky.social · 2d

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

Florian Jaeckle @florianjaeckle.bsky.social · 2d

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

1

Florian Jaeckle @florianjaeckle.bsky.social · 2d

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]

1

Florian Jaeckle @florianjaeckle.bsky.social · 2d

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]

1

Florian Jaeckle @florianjaeckle.bsky.social · 2d

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]

1

Florian Jaeckle @florianjaeckle.bsky.social · 2d

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]

1

Florian Jaeckle @florianjaeckle.bsky.social · 2d

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]

1 4

Reposted by Florian Jaeckle

Accelerate Programme for Scientific Discovery @acceleratescience.bsky.social · May 30

📢 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

2 3

Reposted by Florian Jaeckle

NEJM AI @ai.nejm.org · May 1

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

Figure 2. The Five Steps in Our Pipeline.

1 3

Reposted by Florian Jaeckle

Johannah Ruddy @johannahruddy.bsky.social · Apr 9

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.

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...

ai.nejm.org

1 2

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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

1

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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

1 3

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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...)

1

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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.

1

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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.

1

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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

1

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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...

1 2 9

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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

1 1

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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...)

1

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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.

1

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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.

1

Florian Jaeckle @florianjaeckle.bsky.social · Mar 28

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

1

Reposted by Florian Jaeckle

Hughes Hall, University of Cambridge @hugheshall.bsky.social · Mar 28

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

The Guardian @theguardian.com · Mar 27

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...

www.theguardian.com

1 3

Reposted by Florian Jaeckle

Med AI Media @medaimedia.bsky.social · Mar 27

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

Machine Learning Achieves Pathologist-Level Celiac Disease Diagnosis

Mar 27, 2025 Original Article by F. Jaeckle and Others

ai.nejm.org

2 2