Related Experiment Video
Updated: Aug 11, 2025
06:08
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
Published on: March 21, 2025
329
Diagnosis of Prostate Cancer Using GLCM Enabled KNN Technique by Analyzing MRI Images
L Anand1, Shivlal Mewada2, WameedDeyah Shamsi3
1Department of Networking and Communications, SRM Institute of Science and Technology, Chennai, India.
Biomed Research International
|February 3, 2023
Summary
This study introduces an efficient machine learning approach using MRI scans for early prostate cancer detection. The method enhances image quality and extracts features for accurate classification, improving diagnostic speed and precision.
Area of Science:
- Medical imaging analysis
- Machine learning in oncology
- Prostate cancer diagnostics
Background:
- Cancer significantly impacts adult mortality rates, necessitating rapid and accurate diagnosis.
- Manual interpretation of medical images for cancer detection is time-consuming and prone to interobserver variability.
- Prostate cancer affects a substantial portion of the male population, with rising mortality rates.
Purpose of the Study:
- To develop an effective and efficient strategy for image processing and feature extraction for machine learning-based prostate cancer detection.
- To improve the accuracy, precision, and speed of computer-aided diagnosis (CAD) systems for early cancer identification.
- To leverage MRI scans and machine learning for the early detection of prostate cancer.
Main Methods:
- Preliminary image processing using histogram equalization to enhance MRI scan quality.
- Image segmentation utilizing the fuzzy C-means approach.
- Feature extraction via the Gray Level Cooccurrence Matrix (GLCM).
- Classification using K-Nearest Neighbors (KNN), random forest, and AdaBoost algorithms.
Main Results:
- The proposed strategy effectively processes MRI images and extracts relevant features for machine learning.
- The combination of image processing techniques and machine learning algorithms shows promise for accurate prostate cancer detection.
- The study demonstrates the utility of CAD technology in improving diagnostic capabilities.
Conclusions:
- The developed approach offers an efficient and effective method for early prostate cancer detection using MRI and machine learning.
- This research contributes to advancing CAD systems for more precise and rapid oncological diagnoses.
- The findings highlight the potential of integrating advanced image processing and machine learning for improved patient outcomes in prostate cancer care.
