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

Search research articles

Related Experiment Video

Updated: Dec 26, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

A multi-context CNN ensemble for small lesion detection.

B Savelli¹, A Bria¹, M Molinara¹

¹Department of Electrical and Information Engineering, University of Cassino and L.M., Via G. Di Biasio 43, 03043 Cassino (FR), Italy.

Artificial Intelligence in Medicine

|March 8, 2020

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Safety of fertility preservation techniques before and after anticancer treatments in young women with breast cancer: a systematic review and meta-analysis.

Human reproduction (Oxford, England)·2022

Same author

The importance of early detection of calcifications associated with breast cancer in screening.

Breast cancer research and treatment·2017

Same author

Validity of the Italian version of Khalfa's questionnaire on hyperacusis.

Acta otorhinolaryngologica Italica : organo ufficiale della Societa italiana di otorinolaringologia e chirurgia cervico-facciale·2015

Same author

Learning from unbalanced data: a cascade-based approach for detecting clustered microcalcifications.

Medical image analysis·2013

Same author

Anatomic distribution of cancers and colorectal adenomas according to age and sex and relationship between proximal and distal neoplasms in an i-FOBT-positive average-risk Italian screening cohort.

International journal of colorectal disease·2013

Same author

Experience with early TEVAR treatment of uncomplicated type B aortic dissection.

The Journal of cardiovascular surgery·2013

Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026

Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026

Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026

Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026

Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026

Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026

See all related articles

This study introduces a new method using a multi-context ensemble of convolutional neural networks (CNNs) for improved detection of small lesions in medical images. The novel approach enhances diagnostic accuracy for conditions like microcalcifications and microaneurysms.

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Accurate detection of small lesions in medical images is crucial for early diagnosis.
Existing methods using convolutional neural networks (CNNs) face challenges in capturing multi-scale contextual information for small abnormality detection.

Purpose of the Study:

To propose a novel multi-context ensemble of CNNs for enhanced detection of small lesions in digital medical images.
To improve the performance of lesion detection by effectively learning diverse spatial contexts.

Main Methods:

Developed a multi-context ensemble of CNNs, integrating multiple-depth CNNs trained on image patches of varying dimensions.
Combined individual CNNs to create an ensemble capable of exploiting both local features and surrounding context for lesion identification.

Keywords:

Computer-aided detection (CADe)Convolutional neural networks Deep learning Ensemble classifier Mammograms Ocular fundus images

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Dec 26, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Evaluated the method on microcalcification detection in mammograms (INbreast dataset) and microaneurysm detection in fundus images (E-ophtha dataset).

Main Results:

The proposed ensemble method achieved statistically significant improvements in detection performance compared to existing literature approaches.
Demonstrated superior effectiveness in identifying and locating small abnormalities in both mammographic and ocular fundus images.
The multi-depth CNN ensemble successfully leveraged multi-scale contextual information for enhanced lesion detection.

Conclusions:

The novel multi-context ensemble of CNNs is an effective method for detecting small abnormalities in medical images.
This approach offers a significant advancement in medical image analysis, particularly for challenging detection tasks.
The findings highlight the potential of ensemble deep learning models in improving diagnostic accuracy for subtle pathologies.