Search

Purpose To assess the likelihood of malignancy among a subset of nodules in the National Lung Screening Trial (NLST) by using a risk calculator based on nodule and patient characteristics. Materials and Methods All authors received approval for use of NLST data. An institutional review board exemption and a waiver for informed consent were granted to the author with an academic appointment. Nodule characteristics and patient attributes with regard to benign and malignant nodules in the NLST were applied to a nodule risk calculator from a group in Vancouver, Canada. Patient populations and their nodule characteristics were compared between the NLST and Vancouver cohorts. Multiple thresholds were tested to distinguish benign nodules from malignant nodules. An optimized threshold value was used to determine positive and negative predictive values, and a full logistic regression model was applied to the NLST data set. Results Sufficient data were available for 4431 nodules (4315 benign nodules and 116 malignant nodules) from the NLST data set. The NLST and Vancouver data sets differed in that the former included fewer nodules per study, fewer nonsolid nodules, and more nodule spiculation and emphysema. A composite risk score threshold of 10% was determined to be optimal, demonstrating sensitivity, specificity, positive predictive value, and negative predictive value of 85.3%, 93.9%, 27.4%, and 99.6%, respectively. The receiver operating characteristic curve for the full regression model applied to the NLST database demonstrated an area under the receiver operating characteristic curve of 0.963 (95% confidence interval: 0.945, 0.974). Conclusion Application of an NLST data subset to the Vancouver risk calculator yielded a high discriminant value, which supports the use of a risk calculator method as a valuable approach to distinguish between benign and malignant nodules.

Objective: Accurate classification methods are critical in computer-aided diagnosis (CADx) and other clinical decision support systems. Previous research has reported on methods for combining genetic algorithm (GA) feature selection with ensemble classifier systems in an effort to increase classification accuracy. In this study, we describe a CADx system for pulmonary nodules using a two-step supervised learning system combining a GA with the random subspace method (RSM), with the aim of exploring algorithm design parameters and demonstrating improved classification performance over either the GA or RSM-based ensembles alone. Methods and materials: We used a retrospective database of 125 pulmonary nodules (63 benign; 62 malignant) with CT volumes and clinical history. A total of 216 features were derived from the segmented image data and clinical history. Ensemble classifiers using RSM or GA-based feature selection were constructed and tested via leave-one-out validation with feature selection and classifier training executed within each iteration. We further tested a two-step approach using a GA ensemble to first assess the relevance of the features, and then using this information to control feature selection during a subsequent RSM step. The base classification was performed using linear discriminant analysis (LDA). Results: The RSM classifier alone achieved a maximum leave-one-out Az of 0.866 (95% confidence interval: 0.794-0.919) at a subset size of s=36 features. The GA ensemble yielded an Az of 0.851 (0.775-0.907). The proposed two-step algorithm produced a maximum Az value of 0.889 (0.823-0.936) when the GA ensemble was used to completely remove less relevant features from the second RSM step, with similar results obtained when the GA-LDA results were used to reduce but not eliminate the occurrence of certain features. After accounting for correlations in the data, the leave-one-out Az in the two-step method was significantly higher than in the RSM and the GA-LDA. Conclusions: We have developed a CADx system for evaluation of pulmonary nodule based on a two-step feature selection and ensemble classifier algorithm. We have shown that by combining classifier ensemble algorithms in this two-step manner, it is possible to predict the malignancy for solitary pulmonary nodules with a performance exceeding that of either of the individual steps.

Objective Computer-aided diagnosis (CADx) systems can be utilized to estimate the likelihood of malignancy of pulmonary nodules detected on CT scans. Such systems often require an initial segmentation step. We report on the impact of segmentation variations on the CADx output and describe methods for reducing this effect.

The recently published Vancouver model for lung nodule malignancy prediction holds great promise as a practically feasible tool to mitigate the clinical decision problem of how to act on a lung nodule detected at baseline screening. It provides a formula to compute a probability of malignancy from only nine clinical and radiologic features. The feature values are provided by user interaction but in principle could also be automatically pre-filled by appropriate image processing algorithms and RIS requests. Nodule diameter is a feature with crucial influence on the predicted malignancy, and leads to uncertainty caused by inter-reader variability. The purpose of this paper is to analyze how strongly the malignancy prediction of a lung nodule found with CT screening is affected by the inter-reader variation of the nodule diameter estimation. To this aim we have estimated the magnitude of the malignancy variability by applying the Vancouver malignancy model to the LIDC-IDRI database which contains independent delineations from several readers. It can be shown that using fully automatic nodule segmentation can significantly lower the variability of the estimated malignancy, while demonstrating excellent agreement with the expert readers.

We propose a feature subset selection method based on genetic algorithms to improve the performance of false positive reduction in lung nodule computer-aided detection (CAD). It is coupled with a classifier based on support vector machines. The proposed approach determines automatically the optimal size of the feature set, and chooses the most relevant features from a feature pool. Its performance was tested using a lung nodule database (52 true nodules and 443 false ones) acquired by multislice CT scans. From 23 features calculated for each detected structure, the suggested method determined ten to be the optimal feature subset size, and selected the most relevant ten features. A support vector machine classifier trained with the optimal feature subset resulted in 100% sensitivity and 56.4% specificity using an independent validation set. Experiments show significant improvement achieved by a system incorporating the proposed method over a system without it. This approach can be also applied to other machine learning problems; e.g. computer-aided diagnosis of lung nodules.

In this paper, we propose a machine learning approach to reduce false positive lung nodules identified in multi-slice CT scans by CAD algorithms. From a pool of features computed from the thin-slice scans, a genetic algorithm is used to determine an optimal feature subset for training a classifier that will eliminate as many of the false positives as possible while retaining the true nodules. We use support vector machines as the classifier for its superior performance. The experiment was conducted on a database of 66 true nodules and 123 false ones. From 15 features calculated for each nodule our approach selected 9 as the optimal feature subset size and the resulting classifier trained with a selected set of 9 features was able to achieve 98.5% sensitivity and 82.9% specificity using leave-one-out cross validation.

In this paper a comparative analysis of MPEG-2 and Motion-JPEG (M-JPEG) video coding is given, and the performance of these methods is compared via experiments. At first, the algorithmic differences are discussed, then results of the experiments are shown for various video sources with different image sizes and frame rates; the bit rates ranged from 1 to 8 Mbits/sec. The results also show that MPEG-2 intraframe only (I-only) and intra- and predictive-frame (IP) encoding achieve higher picture quality at the same bit rate, or equivalent picture quality at a lower bit rate, than M-JPEG. This quantitative comparison as well as the subjective picture quality evaluation can trigger the use of MPEG-2 video coding instead of M-JPEG at low bit rates.

Ultrasound lesion segmentation is an important and challenging task. Comparing with other methods, region-based level set has many advantages, but still requires considerable improvement to deal with the characteristic of lesions in the ultrasound modality such as shadowing, speckle and heterogeneity. In the clinical workflow, the physician would usually denote long and short axes of a lesion for measurement purpose yielding four markers in an image. Inspired by this workflow, a constrained level set method is proposed to fully utilize these four markers as prior knowledge and global constraint for the segmentation. First, the markers are detected using template-matching algorithm and B-Spline is applied to fit four markers as the initial contour. Then four-marker constrained energy is added to the region-based local level set to make sure that the contour evolves without deviation from the four markers. Finally the algorithm is implemented in a multi-resolution scheme to achieve sufficient computational efficiency. The performance of the proposed segmentation algorithm was evaluated by comparing our results with manually segmented boundaries on 308 ultrasound images with breast lesions. The proposed method achieves Dice similarity coefficient 89.49 ± 4.76% and could be run in real-time.

The purpose of this article is to evaluate the performance of radiologists using a prototype clinical decision support system to diagnose and manage patients with breast cancer based on dynamic contrast-enhanced MRI studies.The study was conducted with three breast radiologists and two breast imaging fellows who gave patient treatment recommendations and confidence ratings, both without and with computer aid. The computer aid presented similar cases from a retrieval database of 192 lesions (96 malignant and 96 benign) for a test set of 97 mass lesions (46 malignant and 51 benign). The performance of each observer was quantified by receiver operating characteristic analysis. The radiologists' confidence in their recommendations was analyzed with respect to the query case pathologic diagnosis, perceived usefulness of the similar cases, and the accuracy of the computer in retrieving cases of the correct diagnosis. The statistical significance in the performance measure differences was determined by using a two-tailed Student t test for paired data.For each observer, the area under the receiver operating characteristic curve did not change significantly with the use of the computer aid (from a mean of 0.8 to a mean of 0.8; p = 0.61). The average confidence of three of the five observers increased significantly with the computer aid (from 5.9 to 6.3 [p0.001], from 7.0 to 7.2 [p = 0.04], and from 4.4 to 5.4 [p0.001], respectively). The confidence change of the radiologists was more frequent and larger for malignant lesions where the computer was correct. However, for benign lesions, even when the computer was correct, the confidence of the radiologists did not necessarily change.The presentation of similar cases reinforced radiologists' confidence rating in the diagnosis of malignant lesions; however, it did not change their confidence rating for benign lesions or reduce the number of unnecessary biopsies in managing patients with breast cancer using dynamic contrast-enhanced MRI under the limited study conditions.

Accurate classification methods are critical in computer-aided diagnosis and other clinical decision support systems. Previous research has studied methods for combining genetic algorithms for feature selection with ensemble classifier systems in an effort to increase classification accuracy. We propose a two-step approach that first uses genetic algorithms to reduce the number of features used to characterize the data, then applies the random subspace method on the remaining features to create a set of diverse but high performing classifiers. These classifiers are combined using ensemble learning techniques to yield a final classification. We demonstrate this approach for computer-aided diagnosis of solitary pulmonary nodules from CT scans, in which the proposed method outperforms several previously described methods.

One challenge facing radiologists is the characterization of whether a pulmonary nodule detected in a CT scan is likely to be benign or malignant. We have developed an image processing and machine learning based computer-aided diagnosis (CADx) method to support such decisions by estimating the likelihood of malignancy of pulmonary nodules. The system computes 192 image features which are combined with patient age to comprise the feature pool. We constructed an ensemble of 1000 linear discriminant classifiers using 1000 feature subsets selected from the feature pool using a random subspace method. The classifiers were trained on a dataset of 125 pulmonary nodules. The individual classifier results were combined using a majority voting method to form an ensemble estimate of the likelihood of malignancy. Validation was performed on nodules in the Lung Imaging Database Consortium (LIDC) dataset for which radiologist interpretations were available. We performed calibration to reduce the differences in the internal operating points and spacing between radiologist rating and the CADx algorithm. Comparing radiologists with the CADx in assigning nodules into four malignancy categories, fair agreement was observed (K=0.381) while binary rating yielded an agreement of (κ=0.475), suggesting that CADx can be a promising second reader in a clinical setting.

Dans cet article, les auteurs analysent un algorithme d’estimation du mouvement, recursif au niveau des pixels et base sur une methode de Wiener. Ils presentent des techniques d’estimation precises et ensuite etablissent certaines methodes de calcul des parametres de l’algorithme. Une etude theorique de la convergence est presentee. Des resultats de simulations illustrent les proprietes de convergence.

Computer-aided detection (CAD) algorithms 'automatically' identify lung nodules on thoracic multi-slice CT scans (MSCT) thereby providing physicians with a computer-generated 'second opinion'. While CAD systems can achieve high sensitivity, their limited specificity has hindered clinical acceptance. To overcome this problem, we propose a false positive reduction (FPR) system based on image processing and machine learning to reduce the number of false positive lung nodules identified by CAD algorithms and thereby improve system specificity. To discriminate between true and false nodules, twenty-three 3D features were calculated from each candidate nodule's volume of interest (VOI). A genetic algorithm (GA) and support vector machine (SVM) were then used to select an optimal subset of features from this pool of candidate features. Using this feature subset, we trained an SVM classifier to eliminate as many false positives as possible while retaining all the true nodules. To overcome the imbalanced nature of typical datasets (significantly more false positives than true positives), an intelligent data selection algorithm was designed and integrated into the machine learning framework, thus further improving the FPR rate. Three independent datasets were used to train and validate the system. Using two datasets for training and the third for validation, we achieved a 59.4% FPR rate while removing one true nodule on the validation datasets. In a second experiment, 75% of the cases were randomly selected from each of the three datasets and the remaining cases were used for validation. A similar FPR rate and true positive retention rate was achieved. Additional experiments showed that the GA feature selection process integrated with the proposed data selection algorithm outperforms the one without it by 5%-10% FPR rate. The methods proposed can be also applied to other application areas, such as computer-aided diagnosis of lung nodules.

In this paper we propose a novel, post-processing system for compressed video sources. The proposed system explores the interaction between artifact reduction and sharpness/resolution enhancement to achieve optimal video quality for compressed (e.g. MPEG-2) sources. It is based on the Unified Metric for Digital Video Processing (UMDVP), which adaptively controls the post-processing algorithms according to the coding characteristics of the decoded video. The experiments carried out on several MPEG-2 encoded video sequences have shown significant improvement in picture quality compared to a system without the UMDVP control and to a system that did not exploit the interaction between artifact reduction and video enhancement. The UMDVP as well the proposed post-processing system can be easily adapted for different coding standard, such as MPEG-4, H.26x.

In this paper we propose a new deringing algorithm for MPEG-2 encoded video. It is based on a Unified Metric for Digital Video Processing (UMDVP) and therefore directly linked to the coding characteristics of the decoded video. Experiments carried out on various video sequences have shown noticeable improvement in picture quality and the proposed algorithm outperforms the deringing algorithm described in the MPEG-4 video standard. Coding artifacts, particularly ringing artifacts, are especially annoying on large high-resolution displays. To prevent the enlargement and enhancement of the ringing artifacts, we have applied the proposed deringing algorithm prior to resolution enhancement. Experiments have shown that in this configuration, the new deringing algorithm has significant positive impact on picture quality.

This paper presents two novel methods to encode HD (High Definition) video at low bitrates (~5 Mbps) using the MPEG-2 Main Profile@Main Level standard (be compatible with current digital video devices; e.g., DVD players, digital video recorders, etc.) with the embedded HD-relevant information (E-data) in the bitstream. Due to the low bitrate constraint, traditional coding based approaches (e.g., MPEG-2 layered coding or scalable coding) cannot satisfy this requirement. Therefore, we developed our system from the video-enhancement point of view. At first, the HD video is down converted to SD (Standard Definition). During the down-conversion, extra data (E-data) is saved. This E-data is used to re-create HD effects when the encoded SD is upconverted prior to the display. For HD re-creation, we developed a novel multilevel resolution-enhancement method that makes an upconverted image emulate the quality of the original HD picture. Further, we designed a visual-based fine detail injection method to add more details into the picture to achieve near HD quality. Based on several test video sequences, we conclude that our approaches have the potential to create HD visual effect on the upconverted SD video.© (2003) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Frame rate conversion requires interpolation of image frames at time instances, where the original sequence has not been sampled. This can be done in high quality only by means of motion-compensated algorithms, therefore the knowledge of motion present in the sequence is essential. This motion information has to be determined from the image sequence itself. In this paper a motion-based image segmentation algorithm is proposed, and its application for motion- compensated (MC) frame rate conversion is presented. The segmentation algorithm that can trace multiple rigid objects with translational movement, is based on vector quantization of the estimated motion field determining a set of global motion vectors and segmenting the images into multiple moving areas. Then, the spatial order of the objects (which one is in front of the other) is determined. Interpolation is performed based on the results of the segmentation, the set of motion vectors, and the proper handling of covered and uncovered areas. Furthermore, an accelerated motion model developed previously by the authors is applied, in order to further improve the performance of the MC frame rate converter.

In motion-compensated processing of image sequences, e.g. in frame interpolation, frame rate conversion, deinterlacing, motion blur correction, image sequence restoration, slow-motion replay, etc., the knowledge of motion is essential. In these applications motion information has to be determined from the image sequence. Most motion estimation algorithms use only a simple motion model, and assume linear constant speed motion. The contribution of our paper is the development of an algorithm for modeling and estimation of accelerated motion trajectories, based on a second order motion model. This model is more general and much closer to the real motion present in natural image sequences. The parameters of the accelerated motion are determined from two consecutive motion fields, that has been estimated from three consecutive image frames using a multiresolution pel-recursive Wiener-based motion estimation algorithm. The proposed algorithm was successfully tested on artificial image sequences with synthetic motion as well as on natural real-file videophone and videoconferencing sequences in a frame interpolation environment.© (1996) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

In many video coding schemes, especially at low bitrates, a temporal subsampling of the input image sequence is considered. It is realized by skipping images at the transmitter, and these frames must be reconstructed at the receiver side. In order to prevent jerkiness or blurring in the moving areas, motion-compensated interpolation has to be applied. Frame interpolation algorithms usually consider two consecutively transmitted frames and assume constant velocity linear motion between these frames. The algorithm proposed in our paper assumes constant acceleration -- instead of constant speed -- that is estimated based on three consecutively transmitted images and two corresponding motion fields. This approach is much closer to the real situation than the previous methods taking into account only constant speed motion. The proposed interpolation algorithm results in smoother movement in the final interpolated video sequence. Experiments carried out using real-life image sequences confirm the applicability of the proposed method for low and very low bitrate video coding.© (1995) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

This paper presents a novel multiresolution wavelet-based algorithm for filtering SAR images in order to remove speckle noise. The basic idea is to apply to the wavelet coefficients a size-decreasing half-interpolated median filter. The size of the median filter is adapted to the noise energy reduction between the image pyramid levels and different filter shapes are used in each wavelet subbands according to the dominant frequencies. Experimental results showed, that the proposed algorithm results in significant noise removal while the edges are preserved in the images.

In this paper adaptive algorithms for pel-recursive displacement estimation are introduced. The proposedalgorithms are similar in form to the original Wiener-based algorithm, where the extensions are the appro-priate tuning of the so-called damping parameter and the use of a linear search technique. The proposedtechniques maintain the order of complexity of the original Wiener-based displacement estimator but they are more robust and exhibit a higher rate of convergence. The adaption of the damping parameter in a Total Least Squares sense improves the performance of the estimator with only a modest increase in thecomputational complexity. The application of a bi-section linear search technique is the most effectiveextension, but the most computational intensive too. 1. INTRODUCTION Research in the field of motion estimation is concerned with the extraction of motion information cor-responding to object or camera movements from a sequence of time-varying images. The estimation ofmotion information from a sequence of images has its importance in the field of image sequence processing.Particularly in image sequence coding, motion estimation is a key issue since the coding efficiency can beimproved by exploiting the temporal correlation between the intensities in image sequences along the so-called motion trajectories [1]. In this paper, the motion is represented by a so-called motion field which isthe projection onto the image plane of 3-D object movement. The determination of each vector individuallyfrom the local time-varying intensities is an ill-posed problem since one temporal intensity variation is notsufficient to reveal the two unknown components of the corresponding motion field vector. In image cod-ing, motion estimation techniques are based mainly on such local 2-D translational motion models and twoclasses of commonly used techniques are block-matching and pel-recursive algorithms [1] .Inblock-matchingthe ill-posedness is circumvented by assigning one displacement vector to a block of pel-locations and inthe pel-recursive algorithms by using a specific recursion technique. This paper exclusively deals with thepel-recursive techniques since they provide, as opposed to block-matching, a full-resolution motion fieldwith fractional-pel accuracy.Pel-recursive techniques are based on a predictor/update form that is applied recursively along each scan-line. Research in this field has been focussing on motion detection techniques, vector prediction formulas andupdating strategies. The results presented in this paper fall in the third category. The update part mainlydetermines the rate of convergence and the estimation accuracy. Update equations presented in literature