Search research articles

Related Concept Videos

Methods of Medium Optimization

Methods of Medium Optimization

Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...

You might also read

Related Articles

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

Sort by

Same author

Design and experimental study of a rigid-flexible coupled back rehabilitation robot.

Frontiers in bioengineering and biotechnology·2026

Same author

PH2ST: Prompt-guided hypergraph learning for spatial transcriptomics prediction in whole slide images.

Medical image analysis·2026

Same author

Porcine-derived amelogenin P148 in a layer-by-layer chitosan/hyaluronic acid coating for enhanced implant osseointegration.

Colloids and surfaces. B, Biointerfaces·2026

Same author

Polyethylene with Good Elasticity Synthesized by Anilinotropone Nickel Catalysts.

Inorganic chemistry·2026

Same author

ProGIS: Prototype-Guided Interactive Segmentation for Pathological Images.

IEEE transactions on medical imaging·2025

Same author

StaDis: Stability distance to detecting out-of-distribution data in computational pathology.

Medical image analysis·2025

Same journal

Long-term outcomes of adjuvant metronomic capecitabine in locoregionally advanced nasopharyngeal carcinoma: a randomized, controlled, multicenter, phase 3 study.

Nature cancer·2026

Same journal

Inhibition of ADSS2-mediated de novo AMP biosynthesis re-sensitizes acute myeloid leukemia to BH3 mimetics.

Nature cancer·2026

Same journal

GABA signaling activation drives glioblastoma progression in female mice through myeloid-derived suppressor cells.

Nature cancer·2026

Same journal

GABA shapes GBM immune responses in a sex-dependent manner.

Nature cancer·2026

Same journal

The future of tertiary lymphoid structures in cancer immunotherapy as biomarkers and therapeutic targets.

Nature cancer·2026

Same journal

Targeting PID1 generates oxysterols to switch macrophage cell fates for improved antitumor immunity.

Nature cancer·2026

See all related 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

Search research articles

Related Experiment Video

Updated: May 6, 2026

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

SMMILe enables accurate spatial quantification in digital pathology using multiple-instance learning.

Zeyu Gao^1,2, Anyu Mao³, Yuxing Dong³

¹Department of Oncology, University of Cambridge, Cambridge, UK.

|November 19, 2025

Summary

This summary is machine-generated.

This study introduces SMMILe, a novel computational pathology method that enhances spatial quantification in whole-slide images without sacrificing classification accuracy. SMMILe improves both diagnostic predictions and spatial awareness in digital pathology.

More Related Videos

Semi-Automated Planimetric Quantification of Dental Plaque Using an Intraoral Fluorescence Camera

Semi-Automated Planimetric Quantification of Dental Plaque Using an Intraoral Fluorescence Camera

Published on: January 27, 2023

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

Related Experiment Videos

Last Updated: May 6, 2026

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

Semi-Automated Planimetric Quantification of Dental Plaque Using an Intraoral Fluorescence Camera

Semi-Automated Planimetric Quantification of Dental Plaque Using an Intraoral Fluorescence Camera

Published on: January 27, 2023

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

Area of Science:

Computational pathology
Digital pathology
Machine learning in medicine

Background:

Spatial quantification is crucial for computational pathology but often lost in multiple-instance learning (MIL) models.
Existing MIL methods predict whole-slide image labels but lack spatial awareness, limiting clinical applications.
Manual annotations are time-consuming and hinder scalability in pathology image analysis.

Purpose of the Study:

To develop a computational pathology method that achieves accurate whole-slide image (WSI) prediction and superior spatial quantification.
To mathematically prove that instance-level aggregation can improve spatial awareness in MIL models.
To introduce and validate a superpatch-based measurable multiple-instance learning (SMMILe) method.

Main Methods:

Developed a superpatch-based measurable multiple-instance learning (SMMILe) framework.
Mathematically demonstrated the benefits of instance-level aggregation for spatial quantification in MIL.
Evaluated SMMILe on 3,850 whole-slide images across 6 cancer types and 3 classification tasks.
Benchmarked SMMILe against nine existing methods using two distinct encoders (ImageNet-pretrained and pathology-specific).

Main Results:

SMMILe matched or exceeded state-of-the-art WSI classification performance across all evaluated tasks.
The method demonstrated outstanding spatial quantification capabilities.
Performance was consistent regardless of the encoder used (ImageNet or pathology-specific foundation model).

Conclusions:

SMMILe effectively integrates spatial quantification with high-performance WSI classification.
The proposed instance-level aggregation approach overcomes limitations of traditional MIL methods.
SMMILe offers a powerful tool for advancing computational pathology and digital diagnostics.