Related Experiment Video
Updated: Jul 22, 2026
06:08
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
Published on: March 21, 2025
Computer-aided detection of prostate cancer
Rafael Llobet1, Juan C Pérez-Cortés, Alejandro H Toselli
1Instituto Tecnológico de Informática, Ciudad Politécnica de la Innovatión, Universidad Politécnica de Valencia, Camino de Vera s/n, 46022 Valencia, Spain. rllobet@iti.upv.es
International Journal of Medical Informatics
|April 20, 2006
Summary
Computer-aided diagnosis for prostate cancer shows potential, improving inexperienced user accuracy on ultrasound images. However, the system needs further development for clinical application.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Oncology
Background:
- Prostate cancer is a leading cause of male mortality globally.
- Early detection of prostate carcinoma is vital for effective treatment.
- Transrectal ultrasound is a key imaging modality for prostate cancer diagnosis.
Purpose of the Study:
- To evaluate a computer-aided diagnosis (CAD) system for prostate cancer detection using transrectal ultrasound images.
- To compare the performance of k-nearest neighbors and Hidden Markov models classifiers.
- To assess the impact of the CAD system on the diagnostic accuracy of users with varying experience levels.
Main Methods:
- Analysis of 4944 transrectal ultrasound images from 303 patients.
- Implementation and comparison of k-nearest neighbors and Hidden Markov model classifiers.
- Experimental testing of the CAD system with human evaluators of different expertise.
Main Results:
- The best classification model achieved an area under the ROC curve of 61.6%.
- The CAD system provided a slight improvement in diagnostic capacity for expert urologists.
- Inexperienced users showed improved diagnostic performance with the aid of the computer-aided system.
Conclusions:
- Discrimination between cancerous and non-cancerous prostate tissue is achievable to some extent.
- The CAD system demonstrates utility in assisting less experienced diagnosticians.
- Further enhancements are required for the CAD system's practical clinical implementation.
