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.
Features calculated from different dimensions of images capture quantitative information of the lung nodules through
one or multiple image slices. Previously published computer-aided diagnosis (CADx) systems have used either twodimensional
(2D) or three-dimensional (3D) features, though there has been little systematic analysis of the relevance of
the different dimensions and of the impact of combining different dimensions. The aim of this study is to determine the
importance of combining features calculated in different dimensions. We have performed CADx experiments on 125
pulmonary nodules imaged using multi-detector row CT (MDCT). The CADx system computed 192 2D, 2.5D, and 3D
image features of the lesions. Leave-one-out experiments were performed using five different combinations of features
from different dimensions: 2D, 3D, 2.5D, 2D+3D, and 2D+3D+2.5D. The experiments were performed ten times for
each group. Accuracy, sensitivity and specificity were used to evaluate the performance. Wilcoxon signed-rank tests
were applied to compare the classification results from these five different combinations of features. Our results showed
that 3D image features generate the best result compared with other combinations of features. This suggests one
approach to potentially reducing the dimensionality of the CADx data space and the computational complexity of the
system while maintaining diagnostic accuracy.
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 (κ=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.
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.
KEYWORDS: Video, Video compression, Video coding, Resolution enhancement technologies, Video processing, Control systems, Semantic video, Quantization, Computer programming, Process control
In this paper we outline a post-processing system for compressed video sources, aimed at reducing the visibility of coding artifacts. To achieve optimal video quality for compressed sources, it addresses artifact reduction and video enhancement functions as well as their interdependency. The system is based on the Unified Metric for Digital Video Processing (UMDVP), a quality metric that estimates the level of coding artifacts on a per-pixel basis. Experiments on MPEG-2 encoded video sequences showed significant improvement in picture quality compared to systems that do not have UMDVP control or that do not consider the interdependency between artifact reduction and video enhancement.
KEYWORDS: Video, Video processing, Video compression, Resolution enhancement technologies, Control systems, Video coding, Semantic video, Computer programming, Quantization, Algorithm development
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.
KEYWORDS: Video, Video processing, Resolution enhancement technologies, Digital filtering, Video coding, Algorithm development, Quantization, Linear filtering, Wavelets, Edge detection
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.
Image sequence quality enhancement is required in many different application areas, like restoration of old, damaged films, or displaying compressed sequences in higher spatial and/or temporal resolution using MC (motion- compensated) interpolation. Image sequence interpolation is the process of increasing the frame rate of a video signal by computing intermediate images between two or more known ones. It is used in a wide range of applications from low bitrate video conferencing till standard format conversion. The pixel values of the unknown frames have to be interpolated along the motion trajectories. First, correspondence must be established between the known images using a motion estimation algorithm, than this motion information is used to compute the interpolated image (or images) between the known ones. Interpolation of pixel values is done by a linear interpolation filter along the calculated motion trajectories. In our contribution experimental comparison of different motion models is given using artificial image sequences. The sequences have been generated by moving natural images along different trajectories. In the experiments presented in this paper the motion parameters are calculated from the known trajectories, and these parameters are passed to the interpolation algorithm. In other experiments, using real- life sequences, motion estimation should be used. It is in our case a multiresolution pel-recursive motion estimation algorithm.
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.
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.
In this paper adaptive algorithms for pel-recursive displacement estimation are introduced. The proposed algorithms are similar in form to the original Wiener-based algorithm, where the extensions are the appropriate tuning of the so-called damping parameter and the use of a linear search technique. The proposed techniques 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 the computational complexity. The application of a bi-section linear search technique is the most effective extension, but the most computational intensive too.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.