Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Neural Regulation

Neural Regulation

Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Chromatin landscape and epigenetic heterogeneity of acute myeloid leukaemia.

Nature·2026

Same author

Total Bone Uptake as a Quantitative Imaging Biomarker for Prostate Cancer With Bone Metastases.

Cancer diagnosis & prognosis·2026

Same author

Enfortumab vedotin demonstrates consistent efficacy in platinum- and ICI-refractory metastatic urothelial carcinoma patients irrespective of prior response: a multicenter real-world study.

Central European journal of urology·2026

Same author

CRISPR-Cas9 disruption of flavanone 3-hydroxylase produces a green phenotype and alters flavone metabolites in allotetraploid perilla.

Frontiers in plant science·2026

Same author

Accuracy of Kampo Diagnostic Support System: Comparison With Certified Physicians of the Japan Society for Oriental Medicine.

The Tokai journal of experimental and clinical medicine·2026

Same author

Urinary Lipid Profiling for Biomarker Discovery in Clear Cell Renal Cell Carcinoma.

Anticancer research·2026

Search research articles

Related Experiment Video

Updated: Feb 28, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Patch-level phenotype identification via weakly supervised neuron selection in sparse autoencoders for CLIP-derived

Keita Tamura¹, Yao-Zhong Zhang², Yohei Okubo³

¹School of Medicine, Hiroshima University, Hiroshima, 734-8553, Japan.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing

|February 27, 2026

Summary

This summary is machine-generated.

This study introduces a weakly supervised method for neuron selection in pathology foundation models, enabling accurate tumor identification from whole slide images (WSIs) with enhanced explainability.

More Related Videos

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Related Experiment Videos

Last Updated: Feb 28, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Area of Science:

Computational pathology
Artificial intelligence in medicine
Digital pathology

Background:

Computer-aided analysis of whole slide images (WSIs) is rapidly advancing.
Multi-modal pathology foundation models offer new possibilities for WSI analysis.

Purpose of the Study:

To propose a weakly supervised neuron selection approach for extracting disentangled representations from CLIP-derived pathology foundation models.
To leverage the interpretability of sparse autoencoders for enhanced WSI analysis.
To enable effective patch-level phenotype identification using selected neurons.

Main Methods:

A weakly supervised neuron selection approach using whole-slide level labels within a multiple instance learning (MIL) framework.
Investigation of pre-trained image embeddings from general and pathology images.
Utilizing sparse autoencoders for disentangled representation extraction.

Main Results:

A single selected neuron effectively enables patch-level phenotype identification.
Demonstrated effectiveness and explainability on Camelyon16 and PANDA datasets.
Showcased generalization ability for tumor patch identification.

Conclusions:

The proposed weakly supervised neuron selection method enhances the interpretability and effectiveness of pathology foundation models.
This approach facilitates accurate tumor identification and phenotype analysis in digital pathology.
The method shows strong generalization capabilities across different datasets.