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 Videos

Lightweight Ensemble Learning Based on Post-Hoc Probability Fusion with Its Application to Lung CT Image

Yuqian Feng¹, Yang Qu²

¹Department of Respiratory and Critical Care Medicine, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China.

Current Medical Imaging

|July 16, 2026

Summary

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

Prognostic value of the systemic immune-inflammation index in gastrointestinal cancers treated with immune checkpoint inhibitors: a systematic review and meta-analysis.

BMC gastroenterology·2026

Same author

Gasdermin-Mediated Pyroptosis: Novel Strategies Against Colorectal Cancer.

Cancer science·2026

Same author

Associations of general and abdominal adiposity with incident elevated blood pressure among Tianjin adolescents: a school-based longitudinal study.

BMC public health·2026

Same author

Prediction of root and alveolar bone position during orthodontic therapy without additional radiation: A comparative validation study.

American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics·2026

Same author

Progress of Multimodal Imaging: Bridging Orthodontics to Comprehensive Oral Multidisciplinary Care.

International dental journal·2026

Same author

An antifungal effector from a plant-parasitic nematode modulates host fungal community composition and supports ecological fitness.

NPJ biofilms and microbiomes·2026

This study introduces a lightweight ensemble learning fusion method using weighted averaging to enhance medical image classification accuracy. The optimized model achieved superior performance in distinguishing pneumonia from lung cancer on CT scans.

Area of Science:

Medical Imaging Analysis
Deep Learning
Ensemble Learning

Background:

Model fusion in ensemble learning improves performance but parameter optimization is challenging.
This study proposes a lightweight fusion method using post-hoc weighted averaging of predicted probabilities.

Purpose of the Study:

To investigate an optimal fusion strategy by adjusting fusion weight coefficients and decision thresholds.
To enhance performance metrics like accuracy, precision, recall, and F1 score.
To apply the method to a medical classification task distinguishing pneumonia and lung cancer using CT images.

Main Methods:

Evaluated nine deep learning architectures (VGG and ResNet families) on 859 lung CT images.
Selected ResNet34 and ResNeXt50 models based on superior performance.

Keywords:

Computed tomography imaging Lightweight ensemble learning Model integration Pulmonary disease classification Weighted probability fusion

Related Experiment Videos

Applied a lightweight weighted probability fusion strategy to integrate the selected models.

Main Results:

The optimized fusion model achieved 96.67% accuracy, 94.68% precision, 98.88% recall, and 96.74% F1 score.
Outperformed individual deep learning models across all evaluation metrics.
Demonstrated effectiveness in classifying visually similar diseases.

Conclusions:

The lightweight ensemble learning method enhances classification accuracy and decision robustness.
Weighted probability fusion is effective for medical image analysis tasks with inter-class visual similarity.
Provides a feasible strategy balancing performance and computational efficiency in medical image analysis.