Yusuf Artan

Prostate Cancer Localization With Multispectral MRI Using Cost-Sensitive Support Vector Machines and Conditional Random Fields

Prostate cancer is a leading cause of cancer death for men in the United States. Fortunately, the survival rate for early diagnosed patients is relatively high. Therefore, in vivo imaging plays an important role for the detection and treatment of the disease. Accurate prostate cancer localization with noninvasive imaging can be used to guide biopsy, radiotheraphy, and surgery as well as to monitor disease progression. Magnetic resonance imaging (MRI) performed with an endorectal coil provides higher prostate cancer localization accuracy, when compared to transrectal ultrasound (TRUS). However, in general, a single type of MRI is not sufficient for reliable tumor localization. As an alternative, multispectral MRI, i.e., the use of multiple MRI-derived datasets, has emerged as a promising noninvasive imaging technique for the localization of prostate cancer; however almost all studies are with human readers. There is a significant inter and intraobserver variability for human readers, and it is substantially difficult for humans to analyze the large dataset of multispectral MRI. To solve these problems, this study presents an automated localization method using cost-sensitive support vector machines (SVMs) and shows that this method results in improved localization accuracy than classical SVM. Additionally, we develop a new segmentation method by combining conditional random fields (CRF) with a cost-sensitive framework and show that our method further improves cost-sensitive SVM results by incorporating spatial information. We test SVM, cost-sensitive SVM, and the proposed cost-sensitive CRF on multispectral MRI datasets acquired from 21 biopsy-confirmed cancer patients. Our results show that multispectral MRI helps to increase the accuracy of prostate cancer localization when compared to single MR images; and that using advanced methods such as cost-sensitive SVM as well as the proposed cost-sensitive CRF can boost the performance significantly when compared to SVM.

Prostate Cancer Localization Using Multiparametric MRI based on Semisupervised Techniques With Automated Seed Initialization

In this paper, we propose a novel and efficient semisupervised technique for automated prostate cancer localization using multiparametric magnetic resonance imaging (MRI). This method can be used in guiding biopsy, surgery, and therapy. We systematically present a new segmentation technique by developing a multiparametric graph-based random walker (RW) algorithm with automated seed initialization to perform prostate cancer segmentation using multiparametric MRI. RW algorithm has proved to be accurate and fast in segmentation applications; however, it requires a set of (user provided) seed points in order to perform segmentation. In this study, we first developed a novel RW method, which can be used with multiparametric MR images and then devised alternative methods that can determine seed points in an automated manner using discriminative classifiers such as support vector machines (SVM). Proposed RW method with automated seed initialization is able to produce improved segmentation results by assigning more weights to the images with more discriminative power. We applied the proposed method to a multiparametric dataset obtained from biopsy confirmed prostate cancer patients. Proposed method produces a sensitivity/specificity rate of 0.76 and 0.86, respectively. Both visual, quantitative as well as statistical results are presented to show the significant performance improvements. Fisher sign test is used to demonstrate the statistical significance of our results by achieving p-values less than 0.05. This method outperforms available RW- and SVM-based methods by achieving a high-specificity rate, while not reducing sensitivity.

Driver Cell Phone Usage Detection from HOV/HOT NIR Images

Distracted driving due to cell phone usage is an increasingly costly problem in terms of lost lives and damaged property. Motivated by its impact on public safety and property, several state and federal governments have enacted regulations that prohibit driver mobile phone usage while driving. These regulations have created a need for cell phone usage detection for law enforcement. In this paper, we propose a computer vision based method for determining driver cell phone usage using a near infrared (NIR) camera system directed at the vehicles front windshield. The developed method consists of two stages, first, we localize the drivers face region within the front windshield image using the deformable part model (DPM). Next, we utilize a local aggregation based image classification technique to classify a region of interest (ROI) around the drivers face to detect the cell phone usage. We propose two classification architectures by using full face and half face images for classification and compare their performance in terms of accuracy, specificity, and sensitivity. We also present a comparison of various local aggregation-based image classification methods using bag-of-visual-words (BOW), vector of locally aggregated descriptors (VLAD) and Fisher vectors (FV). A data set of 1500 images was collected on a public roadway and is used to perform the experiments.

Interactive Image Segmentation Using Machine Learning Techniques

Image segmentation is an important and challenging task in image processing. Recently, semi-supervised segmentation methods have received a considerable attention due to their fast and reliable performance. There exist many semi-supervised classification algorithms in machine learning literature such as low density separation (LDS) and Transductive SVM (TSVM). However, most of these are not directly applicable to image segmentation problem due to heavy computational demands. Super pixels substantially reduce the computational requirements of the semi-supervised algorithms, hence, making them applicable to general image segmentation tasks. In this study, we introduce a semi-supervised image segmentation method using machine learning techniques and super pixels. The proposed method yields superior segmentation results over several semi-supervised methods including the popular random walker algorithm. We present experimental evidence suggesting that this interactive image segmentation framework performs well for a broad variety of images.

Prostate cancer segmentation with multispectral MRI using cost-sensitive Conditional Random Fields

Prostate cancer is a leading cause of cancer death for men in the United States. There is currently no widely adopted accurate noninvasive method for localizing prostate cancer using imaging. If such as technique were available it could be used to guide biopsy, radiotheraphy and surgery. However, current imaging techniques are limited due to inability to detect cancers, intensity changes related to non-malignant pathologies and interobserver variability. Recently, multispectral magnetic resonance imaging (MRI) has emerged as a promising noninvasive method for the localization of prostate cancer alternative to transrectal ultrasound (TRUS). This paper develops automated methods for prostate cancer localization with conditional random fields using multispectral MRI. We propose to combine cost-sensitive Support Vector Machines with Conditional Random Fields and show that this method results in higher accuracy of localization compared to other common methods. Our results also show that multispectral modality images helps to increase the accuracy of prostate cancer localization. Using multispectral MR images, we demonstrate the effectiveness of each algorithm by testing them on real data sets and compare them to recently proposed SVMstruct and Conditional Random Fields.

Graph-based active contours using shape priors for prostate segmentation with MRI

Prostate segmentation based on magnetic resonance images is a challenging and important task in medical imaging with applications of guiding biopsy, surgery and therapy. While a fully automated method is highly desired for this application, it can be a very difficult task due to the structure and surrounding tissues of the prostate gland. Recently, graph based interactive (semi-automatic) segmentation methods have emerged as a useful substitute to fully automated segmentation for many medical imaging tasks. A small amount of user input often resolves ambiguous decisions on the part of these algorithms. In this study, we propose to use graph-based active contours to segment prostate from a given magnetic resonance image (MRI). Traditional graph-based active contours are typically quite successful for piecewise constant images, but they may fail in cases where magnetic resonance image has diffuse edges, or multiple similar objects (e.g., bladder close to prostate) within close proximity. In order to mitigate these problems, we incorporate a shape prior in our graph-based prostate extraction scheme. Using real world prostate MR images from a well-known database, we show the effectiveness of the proposed method and compare it to results without the shape prior.

Improved random walker algorithm for image segmentation

General purpose image segmentation is one of the important and challenging problems in image processing. Objective of image segmentation is to group regions with coherent cues such as intensity, texture, color and shape together. Most of the earlier studies on this issue are based on supervised and unsupervised learning methods. In this paper, we develop a semi-supervised image segmentation technique for images using filter bank responses as features. This study utilizes a graph based semi-supervised random walker algorithm to perform segmentation task. Filter bank response driven random walker algorithm has not been considered in the past. We present segmentation results using a variety of images to demonstrate the effectiveness of the proposed technique.

A Machine Learning Approach to Vehicle Occupancy Detection

To manage ever increasing traffic volume on modern highways, transportation agencies have introduced special managed lanes where only vehicles with a certain occupancy level are allowed. This encourages highway users to ride together, thus, in theory, more efficiently transporting people through the highway system. In order to be effective, however, adherence to the vehicle occupancy rules has to be enforced. Recent studies have shown that the traditional approach of dispatching traffic law enforcement officers to perform roadside visual inspections is not only expensive and dangerous, but also ineffective for managed lane enforcement. In this paper, we describe an image-based machine learning approach for automatic or semi-automatic vehicle occupancy detection. Our method localizes windshield regions by constructing an elastic deformation model from sets of uniquely defined landmark points along the front windshield. From the localized windshield region, the method calculates image-level feature representations, which are then applied to a trained classifier for classifying the vehicle into violator and non-violator classes.

Semi-supervised prostate cancer segmentation with multispectral MRI

Prostate cancer is one of the leading causes of cancer related death for men in the United States. Recently, multispectral magnetic resonance imaging (MRI) has emerged as a promising noninvasive method for the localization of prostate cancer alternative to transrectal ultrasound (TRUS). This paper develops a semi-supervised method for prostate cancer localization using multispectral MRI. Patient-specific contrast can be utilized in this method for improved performance. We also propose to use an anisotropic filtering scheme to suppress the noise in the images. Using multispectral MR images, we demonstrate the effectiveness of this algorithm by testing it on real data sets and compare it to the results of a fully-automated method as well as to the earlier results. Both visual and quantitative comparisons are provided, illlustrating the success of the proposed method.

Comparison of face detection and image classification for detecting front seat passengers in vehicles

Due to the high volume of traffic on modern roadways, transportation agencies have proposed High Occupancy Vehicle (HOV) lanes and High Occupancy Tolling (HOT) lanes to promote car pooling. However, enforcement of the rules of these lanes is currently performed by roadside enforcement officers using visual observation. Manual roadside enforcement is known to be inefficient, costly, potentially dangerous, and ultimately ineffective. Violation rates up to 50%-80% have been reported, while manual enforcement rates of less than 10% are typical. Therefore, there is a need for automated vehicle occupancy detection to support HOV/HOT lane enforcement. A key component of determining vehicle occupancy is to determine whether or not the vehicles front passenger seat is occupied. In this paper, we examine two methods of determining vehicle front seat occupancy using a near infrared (NIR) camera system pointed at the vehicles front windshield. The first method examines a state-of-the-art deformable part model (DPM) based face detection system that is robust to facial pose. The second method examines state-of-the-art local aggregation based image classification using bag-of-visual-words (BOW) and Fisher vectors (FV). A dataset of 3000 images was collected on a public roadway and is used to perform the comparison. From these experiments it is clear that the image classification approach is superior for this problem.