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

Quantifying Heat

Quantifying Heat

Thermal Energy Microscopically, thermal energy is the kinetic energy associated with the random motion of atoms and molecules. Temperature is a quantitative measure of “hot” or “cold”, which depends on the amount of thermal energy. When the atoms and molecules in an object are moving or vibrating quickly, they have a higher average kinetic energy (KE) (or higher thermal energy), and the object is perceived as “hot”, or it is described as being at a...

You might also read

Related Articles

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

Sort by

Same author

Molecular Epidemiology to Decipher the Transmission Networks of MPOX in an Outbreak Scenario: Applications in Thailand during the 2023 Global Health Emergency.

The Journal of infectious diseases·2026

Same author

Authors reply: "Development and internal validation of machine learning in predicting prognosis of acute kidney injury patients in resource-limited setting".

Journal of critical care·2026

Same author

The Phase Ib IMPACT Trial of Intramuscular Personalized Neoantigen Synthetic Long Peptide Vaccines in Patients with Advanced Melanoma and Renal Cell Carcinoma.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026

Same author

Correction: Analytical validation of a metagenomic next-generation diagnostic platform for urinary tract infection in a Thai tertiary hospital setting: a BI-Biotia UTI cohort study.

Frontiers in cellular and infection microbiology·2026

Same author

Analytical validation of a metagenomic next-generation diagnostic platform for urinary tract infection in a Thai tertiary hospital setting: a BI-Biotia UTI cohort study.

Frontiers in cellular and infection microbiology·2026

Same author

Development and internal validation of machine learning in predicting prognosis of acute kidney injury patients in resource-limited setting.

Journal of critical care·2026

Same journal

Topological skeleton analysis for network-based shape representation in biology and beyond.

iScience·2026

Same journal

Condition-specific neural signatures of reactivation during post-retrieval rest: An EEG study.

iScience·2026

Same journal

Multi-chaotic signal identification employing a causal cross-correlation neural network.

iScience·2026

Same journal

Repeated insertions at positions 261-280 in KPC-2 highlight a ceftazidime-avibactam resistance hotspot.

iScience·2026

Same journal

ROS inhibits microtubule dynamics and cell growth heterogeneity during Arabidopsis sepal morphogenesis.

iScience·2026

Same journal

Type 1 diabetes alters early macrophage-<i>Mycobacterium tuberculosis</i> transcriptional coordination during infection.

iScience·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 1, 2025

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

Improved image classification explainability with high-accuracy heatmaps.

Konpat Preechakul^1,2, Sira Sriswasdi^2,3,4, Boonserm Kijsirikul¹

¹Department of Computer Engineering, Chulalongkorn University, Pathum Wan, Bangkok 10330, Thailand.

|March 7, 2022

Summary

This summary is machine-generated.

Pyramid Localization Network (PYLON) enhances deep learning image classification by improving heatmap resolution for precise object localization. This method requires only image-level labels, making it valuable for medical imaging and small datasets.

Keywords:

Artificial intelligence Computer science Signal processing

More Related Videos

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

Related Experiment Videos

Last Updated: Oct 1, 2025

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Author Spotlight: Unlocking Insights into the Immune Cell Landscape of Tumors

Published on: August 18, 2023

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

Area of Science:

Computer Vision
Artificial Intelligence
Medical Imaging

Background:

Deep learning models are widely used for image classification.
Explaining model decisions is crucial, especially in medical imaging.
Current methods like Class Activation Maps (CAM) lack precise localization.

Purpose of the Study:

To introduce Pyramid Localization Network (PYLON) for improved localization explanation in deep learning.
To enhance the resolution and quality of heatmaps generated by CAM.
To enable precise object pinpointing without requiring expert location annotations.

Main Methods:

Developed PYLON, a deep learning model that increases heatmap resolution.
Applied PYLON to general and medical image datasets.
Utilized image-level labels for training, avoiding the need for object location annotations.

Main Results:

PYLON significantly improved heatmap quality compared to standard CAM.
The model excelled at pinpointing small objects.
PYLON demonstrated effective transfer learning for small datasets.

Conclusions:

PYLON offers precise, human-understandable explanations for deep learning image classification.
Its ability to train with image-level labels is critical for domains with limited annotations.
PYLON facilitates wider adoption of explainable AI in image analysis.