Related Experiment Video
Updated: Jan 6, 2026
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.3K
Lightweight-CancerNet: a deep learning approach for brain tumor detection.
Asif Raza1, Muhammad Javed Iqbal1
1Department of Computer Science, University of Engineering and Technology Taxila, Taxila, Punjab, Pakistan.
Peerj. Computer Science
|March 10, 2025
Summary
A new deep learning model, Lightweight-CancerNet, efficiently detects brain tumors in medical images. This accurate and fast model aids real-time diagnosis, improving patient care and surgical decisions.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Accurate and rapid brain tumor detection is crucial for patient outcomes.
- Current deep learning models for medical image analysis are computationally intensive.
- There is a need for efficient and accurate deep learning frameworks for brain tumor diagnosis.
Purpose of the Study:
- To introduce Lightweight-CancerNet, a novel deep learning architecture for efficient and accurate brain tumor detection.
- To address the computational demands of existing deep learning models in medical imaging.
- To develop a reliable framework for real-time object detection of brain tumors.
Main Methods:
- Developed Lightweight-CancerNet using MobileNet architecture and NanoDet.
- Optimized the model for reduced computation time without sacrificing accuracy.
- Validated the framework on two magnetic resonance imaging (MRI) datasets, including images with distortions.
Main Results:
- Achieved a mean average precision (mAP) of 93.8% and an accuracy of 98%.
- Demonstrated significant reduction in computing time, enabling real-time applications.
- Confirmed the model's resilience and reliability across diverse MRI data.
Conclusions:
- Lightweight-CancerNet offers an efficient and accurate solution for brain tumor detection in medical imaging.
- The model's real-time capabilities can enhance clinical decision-making in neurosurgery.
- This research contributes to advancing deep learning applications in medical diagnostics.
