Comparing Ensembles of Learners: Detecting Prostate Cancer from High Resolution MRI
نویسندگان
چکیده
While learning ensembles have been widely used for various pattern recognition tasks, surprisingly, they have found limited application in problems related to medical image analysis and computer-aided diagnosis (CAD). In this paper we investigate the performance of several state-of-the-art machine-learning methods on a CAD method for detecting prostatic adenocarcinoma from high resolution (4 Tesla) ex vivo MRI studies. A total of 14 different feature ensemble methods from 4 different families of ensemble methods were compared: Bayesian learning, Boosting, Bagging, and the k-Nearest Neighbor (kNN) classifier. Quantitative comparison of the methods was done on a total of 33 2D sections obtained from 5 different 3D MRI prostate studies. The tumor ground truth was determined on histologic sections and the regions manually mapped onto the corresponding individual MRI slices. All methods considered were found to be robust to changes in parameter settings and showed significantly less classification variability compared to inter-observer agreement among 5 experts. The kNN classifier was the best in terms of accuracy and ease of training, thus validating the principle of Occam’s Razor. The success of a simple non-parametric classifier requiring minimal training is significant for medical image analysis applications where large amounts of training data are usually unavailable.
منابع مشابه
بررسی ارزش Diffusion Weighted Imaging در تصاویر MRI برای تشخیص سرطان پروستات
Background: Prostate cancer is the third leading cause of death and is the most common cause of cancer in elderly men. Regarding to the low accuracy of screening methods such as prostate-specific antigen (PSA), Digital Rectal Examination (DRE) and trans rectal ultrasound (TRUS) in detection and localization of tumor, Magnetic Resonance Imaging (MRI) and Diffusion Weighted Imaging (DWI) attracte...
متن کاملSusceptibility Weighted Imaging: A New Tool in the Diagnosis of Prostate Cancer and Detection of Prostatic Calcification
BACKGROUND Susceptibility weighted imaging (SWI) is a new MRI technique which has been proved very useful in the diagnosis of brain diseases, but few study was performed on its value in prostatic diseases. The aim of the present study was to investigate the value of SWI in distinguishing prostate cancer from benign prostatic hyperplasia and detecting prostatic calcification. METHODOLOGY/PRINC...
متن کاملThe Role of MRSI in Target Volume Definition for Radiation Therapy of Prostate Cancer
Introduction: Recently, magnetic resonance spectroscopic imaging (MRSI), as a functional imaging method, has been used for clinical target volume definition. In this study, we used this method to define the target volume in prostate radiotherapy. Material and Method: In this study, we used images of 20 prostate cancer cases. MRSI and MRI images were fused with CT images. Then, treatment plannin...
متن کاملEvaluation of the accuracy of dynamic contrast enhanced MRI in the diagnosis of invasive prostate neoplasm using pathological findings
Background: Prostate cancer is the most common malignancy in men and the second leading cause of death in all countries of the world. The exact mechanism of prostate cancer is not known. On the other hand, early detection of prostate cancer can lead to a complete cure. Several clinical experiments including Digital Rectum Examination (DRE), biochemistry such as Prostate Specific Antigen (PSA), ...
متن کاملAutomatic Prostate Cancer Segmentation Using Kinetic Analysis in Dynamic Contrast-Enhanced MRI
Background: Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) provides functional information on the microcirculation in tissues by analyzing the enhancement kinetics which can be used as biomarkers for prostate lesions detection and characterization.Objective: The purpose of this study is to investigate spatiotemporal patterns of tumors by extracting semi-quantitative as well as w...
متن کامل