Florian Jaeckle
YOU?
Author Swipe
View article: The comparative pathology workbench: An update
The comparative pathology workbench: An update Open
The Comparative Pathology Workbench (CPW) is a web-browser-based visual analytics platform providing shared access to an interactive "spreadsheet" style presentation of image data and associated analysis data. The software was developed to…
View article: Interpretable machine learning-based detection of coeliac disease
Interpretable machine learning-based detection of coeliac disease Open
Objective Coeliac disease, an autoimmune disorder affecting approximately 1% of the global population, is typically diagnosed on duodenal biopsy. However, interpathologist agreement on coeliac disease diagnosis is only 80%. Existing machin…
View article: Duodenal Biopsy Audit: Relative Frequency of Diagnoses, Key Words on Request Forms Indicating Severe Pathology, and Potential Diagnoses for Intraepithelial Lymphocytosis, as a Foundation for Developing Artificial Intelligence Diagnostic Approaches
Duodenal Biopsy Audit: Relative Frequency of Diagnoses, Key Words on Request Forms Indicating Severe Pathology, and Potential Diagnoses for Intraepithelial Lymphocytosis, as a Foundation for Developing Artificial Intelligence Diagnostic Approaches Open
Background/Objectives: Understanding the diagnostic landscape is essential prior to developing artificial intelligence (AI)-based diagnostic strategies for automating the diagnosis of duodenal biopsies. This study aims to (1) determine the…
View article: Determination of the Relative Frequencies of Expected Diagnoses in Duodenal Biopsies: An Essential Step in Developing an Artificial Intelligence Approach to Diagnostic Classification
Determination of the Relative Frequencies of Expected Diagnoses in Duodenal Biopsies: An Essential Step in Developing an Artificial Intelligence Approach to Diagnostic Classification Open
Understanding the diagnostic landscape prior to developing novel diagnostic strategies is key to managing expectations and authenticating results. In considering the possibility of developing alternate diagnostic approaches for coeliac dis…
View article: Machine Learning Achieves Pathologist-Level Celiac Disease Diagnosis
Machine Learning Achieves Pathologist-Level Celiac Disease Diagnosis Open
Our model achieved pathologist-level performance in diagnosing the presence or absence of coeliac disease from a representative set of duodenal biopsies, representing a significant advancement towards the adoption of machine learning in cl…
View article: Interpretable Machine Learning based Detection of Coeliac Disease
Interpretable Machine Learning based Detection of Coeliac Disease Open
Background Coeliac disease, an autoimmune disorder affecting approximately 1% of the global population, is typically diagnosed on duodenal biopsy. However, inter-pathologist agreement on coeliac disease diagnosis is only 80%. Existing mach…
View article: CD, or not CD, that is the question: a digital interobserver agreement study in coeliac disease
CD, or not CD, that is the question: a digital interobserver agreement study in coeliac disease Open
Objective Coeliac disease (CD) diagnosis generally depends on histological examination of duodenal biopsies. We present the first study analysing the concordance in examination of duodenal biopsies using digitised whole-slide images (WSIs)…
View article: Rapid artefact removal and H&E-stained tissue segmentation
Rapid artefact removal and H&E-stained tissue segmentation Open
View article: Bang and the Artefacts are Gone! Rapid Artefact Removal and Tissue Segmentation in Haematoxylin and Eosin Stained Biopsies
Bang and the Artefacts are Gone! Rapid Artefact Removal and Tissue Segmentation in Haematoxylin and Eosin Stained Biopsies Open
We present H&E Otsu thresholding, a scheme for rapidly detecting tissue in whole-slide images (WSIs) that eliminates a wide range of undesirable artefacts such as pen marks and scanning artefacts. Our method involves obtaining a bimodal re…
View article: Rapid Artefact Removal and H&E-Stained Tissue Segmentation
Rapid Artefact Removal and H&E-Stained Tissue Segmentation Open
We present an innovative method for rapidly segmenting hematoxylin and eosin (H&E)-stained tissue in whole-slide images (WSIs) that eliminates a wide range of undesirable artefacts such as pen marks and scanning artefacts. Our method invol…
View article: FastFill: Efficient Compatible Model Update
FastFill: Efficient Compatible Model Update Open
In many retrieval systems the original high dimensional data (e.g., images) is mapped to a lower dimensional feature through a learned embedding model. The task of retrieving the most similar data from a gallery set to a given query data i…
View article: Neural Network Branch-and-Bound for Neural Network Verification
Neural Network Branch-and-Bound for Neural Network Verification Open
Many available formal verification methods have been shown to be instances of a unified Branch-and-Bound (BaB) formulation. We propose a novel machine learning framework that can be used for designing an effective branching strategy as wel…
View article: Generating Adversarial Examples with Graph Neural Networks
Generating Adversarial Examples with Graph Neural Networks Open
Recent years have witnessed the deployment of adversarial attacks to evaluate the robustness of Neural Networks. Past work in this field has relied on traditional optimization algorithms that ignore the inherent structure of the problem an…
View article: Generating Adversarial Examples with Graph Neural Networks
Generating Adversarial Examples with Graph Neural Networks Open
Recent years have witnessed the deployment of adversarial attacks to evaluate the robustness of Neural Networks. Past work in this field has relied on traditional optimization algorithms that ignore the inherent structure of the problem an…
View article: On Recognising Nearly Single-Crossing Preferences
On Recognising Nearly Single-Crossing Preferences Open
If voters' preferences are one-dimensional, many hard problems in computational social choice become tractable. A preference profile can be classified as one-dimensional if it has the single-crossing property, which requires that the voter…