Vision-LSTM: xLSTM as Generic Vision Backbone

B Alkin, M Beck, K Pöppel, S Hochreiter… - arXiv preprint arXiv …, 2024 - arxiv.org
Transformers are widely used as generic backbones in computer vision, despite initially
introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) …

Foundational Models for Pathology and Endoscopy Images: Application for Gastric Inflammation

H Kerdegari, K Higgins, D Veselkov… - arXiv preprint arXiv …, 2024 - arxiv.org
The integration of artificial intelligence (AI) in medical diagnostics represents a significant
advancement in managing upper gastrointestinal (GI) cancer, a major cause of global …

PathAlign: A vision-language model for whole slide images in histopathology

F Ahmed, A Sellergren, L Yang, S Xu… - arXiv preprint arXiv …, 2024 - arxiv.org
Microscopic interpretation of histopathology images underlies many important diagnostic
and treatment decisions. While advances in vision-language modeling raise new …

HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis

G Jaume, P Doucet, AH Song, MY Lu… - arXiv preprint arXiv …, 2024 - arxiv.org
Spatial transcriptomics (ST) enables interrogating the molecular composition of tissue with
ever-increasing resolution, depth, and sensitivity. However, costs, rapidly evolving …

Prospector Heads: Generalized Feature Attribution for Large Models & Data

G Machiraju, A Derry, A Desai, N Guha… - arXiv preprint arXiv …, 2024 - arxiv.org
Feature attribution, the ability to localize regions of the input data that are relevant for
classification, is an important capability for machine learning models in scientific and …

Hibou: A Family of Foundational Vision Transformers for Pathology

D Nechaev, A Pchelnikov, E Ivanova - arXiv preprint arXiv:2406.05074, 2024 - arxiv.org
Pathology, the microscopic examination of diseased tissue, is critical for diagnosing various
medical conditions, particularly cancers. Traditional methods are labor-intensive and prone …