Search Results for author:
Found 34 papers, 20 papers with code
A deep learning framework for efficient pathology image analysis
Artificial intelligence (AI) has transformed digital pathology by enabling biomarker prediction from high-resolution whole slide images (WSIs).
LLM Agents Making Agent Tools
Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components.
Abnormality-Driven Representation Learning for Radiology Imaging
To date, the most common approach for radiology deep learning pipelines is the use of end-to-end 3D networks based on models pre-trained on other tasks, followed by fine-tuning on the task at hand.
Medical Slice Transformer: Improved Diagnosis and Explainability on 3D Medical Images with DINOv2
We introduce the Medical Slice Transformer (MST) framework to adapt 2D self-supervised models for 3D medical image analysis.
Ranked #5 on
Lung Nodule Classification
on LIDC-IDRI
(AUC metric, using extra
training data)
Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning
Existing approaches for slide representation learning extend the principles of SSL from patch level learning to entire slides by aligning different augmentations of the slide or by utilizing multimodal data.
Pathologist-like explainable AI for interpretable Gleason grading in prostate cancer
The aggressiveness of prostate cancer, the most common cancer in men worldwide, is primarily assessed based on histopathological data using the Gleason scoring system.
Dermatologist-like explainable AI enhances melanoma diagnosis accuracy: eye-tracking study
Our findings reveal that XAI systems improved balanced diagnostic accuracy by 2. 8 percentage points relative to standard AI.
Large Language Models-Enabled Digital Twins for Precision Medicine in Rare Gynecological Tumors
Rare gynecological tumors (RGTs) present major clinical challenges due to their low incidence and heterogeneity.
Benchmarking foundation models as feature extractors for weakly-supervised computational pathology
Advancements in artificial intelligence have driven the development of numerous pathology foundation models capable of extracting clinically relevant information.
RadioRAG: Factual large language models for enhanced diagnostics in radiology using online retrieval augmented generation
We evaluate the diagnostic accuracy of various LLMs when answering radiology-specific questions with and without access to additional online information via RAG.
End-To-End Clinical Trial Matching with Large Language Models
Matching cancer patients to clinical trials is essential for advancing treatment and patient care.
On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction
Denoising diffusion models offer a promising approach to accelerating magnetic resonance imaging (MRI) and producing diagnostic-level images in an unsupervised manner.
Compute-Efficient Medical Image Classification with Softmax-Free Transformers and Sequence Normalization
The Transformer model has been pivotal in advancing fields such as natural language processing, speech recognition, and computer vision.
Autonomous Artificial Intelligence Agents for Clinical Decision Making in Oncology
We believe, that our work can serve as a proof-of-concept for more advanced LLM-agents in the medical domain.
In-context learning enables multimodal large language models to classify cancer pathology images
Medical image classification requires labeled, task-specific datasets which are used to train deep learning networks de novo, or to fine-tune foundation models.
Reducing self-supervised learning complexity improves weakly-supervised classification performance in computational pathology
Specifically, we analyzed the effects of adaptations in data volume, architecture, and algorithms on downstream classification tasks, emphasizing their impact on computational resources.
Joint multi-task learning improves weakly-supervised biomarker prediction in computational pathology
Deep Learning (DL) can predict biomarkers directly from digitized cancer histology in a weakly-supervised setting.
Unconditional Latent Diffusion Models Memorize Patient Imaging Data: Implications for Openly Sharing Synthetic Data
Collectively, our results emphasize the importance of carefully training generative models on private medical imaging datasets, and examining the synthetic data to ensure patient privacy before sharing it for medical research and applications.
LongHealth: A Question Answering Benchmark with Long Clinical Documents
However, all models struggled significantly in tasks requiring the identification of missing information, highlighting a critical area for improvement in clinical data interpretation.
From Whole-slide Image to Biomarker Prediction: A Protocol for End-to-End Deep Learning in Computational Pathology
Hematoxylin- and eosin (H&E) stained whole-slide images (WSIs) are the foundation of diagnosis of cancer.
Ranked #1 on
Classification
on TCGA
Benchmarking Pathology Feature Extractors for Whole Slide Image Classification
2) Which feature extractors are best for downstream slide-level classification?
Medical Foundation Models are Susceptible to Targeted Misinformation Attacks
We validate our findings in a set of 1, 038 incorrect biomedical facts.
Large Language Models Streamline Automated Machine Learning for Clinical Studies
A knowledge gap persists between machine learning (ML) developers (e. g., data scientists) and practitioners (e. g., clinicians), hampering the full utilization of ML for clinical data analysis.
Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images
In this study, we explored if SSL for pre-training on non-medical images can be applied to chest radiographs and how it compares to supervised pre-training on non-medical images and on medical images.
Cascaded Cross-Attention Networks for Data-Efficient Whole-Slide Image Classification Using Transformers
However, while the conventional transformer allows for a simultaneous processing of a large set of input tokens, the computational demand scales quadratically with the number of input tokens and thus quadratically with the number of image patches.
Fibroglandular Tissue Segmentation in Breast MRI using Vision Transformers -- A multi-institutional evaluation
Accurate and automatic segmentation of fibroglandular tissue in breast MRI screening is essential for the quantification of breast density and background parenchymal enhancement.
Regression-based Deep-Learning predicts molecular biomarkers from pathology slides
We tested our method for multiple clinically and biologically relevant biomarkers: homologous repair deficiency (HRD) score, a clinically used pan-cancer biomarker, as well as markers of key biological processes in the tumor microenvironment.
Fully transformer-based biomarker prediction from colorectal cancer histology: a large-scale multicentric study
Methods: In this study, we developed a new fully transformer-based pipeline for end-to-end biomarker prediction from pathology slides.
Medical Diagnosis with Large Scale Multimodal Transformers: Leveraging Diverse Data for More Accurate Diagnosis
Multimodal deep learning has been used to predict clinical endpoints and diagnoses from clinical routine data.
Collaborative Training of Medical Artificial Intelligence Models with non-uniform Labels
Due to the rapid advancements in recent years, medical image analysis is largely dominated by deep learning (DL).
Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation
Furthermore, we demonstrate that synthetic images can be used in a self-supervised pre-training and improve the performance of breast segmentation models when data is scarce (dice score 0. 91 vs. 0. 95 without vs. with synthetic data).
Image prediction of disease progression by style-based manifold extrapolation
We present a generic solution for this problem by a methodology that allows the prediction of progression risk and morphology in individuals using a latent extrapolation optimization approach.
Deep Learning for interpretable end-to-end survival prediction in gastrointestinal cancer histopathology
Digitized histopathology slides contain a wealth of information, only a fraction of which is being used in clinical routine.
