Related Experiment Video
Updated: May 30, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.6K
Improved early detection accuracy for breast cancer using a deep learning framework in medical imaging
Richa1, Bachu Dushmanta Kumar Patro1
1Department of Computer Science and Engineering, Rajkiya Engineering College, Kannauj, India; Affiliated with Abdul Kalam Technical University(AKTU), Jankipuram Vistar, Lucknow, Uttar Pradesh, 226031, India.
Computers in Biology and Medicine
|January 30, 2025
Summary
A new deep learning framework accurately detects breast cancer (BC) in medical images. This AI approach improves early diagnosis, potentially reducing mortality rates through enhanced precision.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Breast cancer (BC) is the most common cancer in women, necessitating early detection for effective treatment.
- Medical imaging techniques are crucial for early BC detection but often require accuracy corrections.
Purpose of the Study:
- To introduce a novel deep learning approach for the early detection of breast cancer (BC) using medical images.
- To enhance BC detection accuracy by combining Convolutional Neural Networks (CNNs) with feature selection and fusion methods.
Main Methods:
- A Deep Learning Framework (DLF) employing multi-level artificial neural networks for BC image classification.
- Integration of CNNs with feature selection and fusion techniques for improved diagnostic precision.
Main Results:
- The DLF achieved high performance metrics: 94.93% accuracy, 93.66% precision, 89.21% recall, and 98.86% F1-score.
- The method demonstrated increased scalability for convolutional recurrent networks.
- Accurate detection of cancer tumors in specific locations was achieved.
Conclusions:
- The proposed DLF automates feature learning and extraction, outperforming traditional methods reliant on manual feature selection.
- This automated approach offers a more robust and accurate solution for early breast cancer detection.
