The development of computer-aided diagnostic (CAD) systems requires an initial establishment of "truth" by
expert human observers. Potential inconsistencies in the "truth" data must be identified and corrected before investigators can rely on this data. We developed a quality assurance model to supplement the "truth" collection process for lung nodules on CT scans. A two-phase process was established for the interpretation of CT scans by four radiologists. During the initial "blinded read," radiologists independently assigned lesions they identified into one of
three categories: "nodule ⩾ 3mm," "nodule < 3mm," or "non-nodule ⩾ 3mm." During the subsequent "unblinded read,"
the blinded read results of all radiologists were revealed. The radiologists then independently reviewed their marks
along with their colleague's marks; a radiologist's own marks could be left unchanged, deleted, switched in terms of
lesion category, or additional marks could be added. The final set of marks underwent quality assurance, which
consisted of identification of potential errors that occurred during the reading process and error correction. All marks
were visually grouped into discrete nodules. Six categories of potential error were defined, and any nodule with a mark
that satisfied the criterion for one of these categories was referred to the radiologist who assigned the mark in question.
The radiologist either corrected the mark or confirmed that the mark was intentional. A total of 829 nodules were
identified by at least one radiologist in 100 CT scans through the two-phase process designed to capture "truth." The
quality assurance process yielded 81 nodules with potential errors. The establishment of "truth" must incorporate a
quality assurance model to guarantee the integrity of the "truth" that will provide the basis for the training and testing of
CAD systems.
Size is an important metric for pulmonary nodule
characterization. Furthermore, it is an important parameter in
measuring the performance of computer aided detection systems since
they are always qualified with respect to a given size range of
nodules. The first 120 whole-lung CT scans documented by the Lung Image
Database Consortium using their protocol for nodule evaluation
were used in this study. For documentation, each inspected lesion was
reviewed independently by four expert radiologists and, when a lesion
was considered to be a nodule larger than 3mm, the radiologist
provided boundary markings in each image in which the nodule was
contained. Three size metrics were considered: a uni-dimensional and
a bi-dimensional measure on a single image slice and a volumetric
measurement based on all the image slices. In this study we analyzed
the boundary markings of these nodules in the context of these three
size metrics to characterize the inter-radiologist variation and to
examine the difference between these metrics. A data set of 63 nodules
each having four observations was analyzed for inter-observer
variation and an extended set of 252 nodules each having at least one
observation was analyzed for the difference between the metrics. A
very high inter-observer variation was observed for all these metrics
and also a very large difference among the metrics was observed.
M. McNitt-Gray, S. Armato, C. Meyer, A. Reeves, G. McLennan, R. Pais, J. Freymann, M. Brown, R. Engelmann, P. Bland, G. Laderach, C. Piker, J. Guo, D. Qing, D. Yankelevitz, D. Aberle, E. van Beek, H. MacMahon, E. Kazerooni, B. Croft, L. Clarke
KEYWORDS: Data processing, Image processing, Databases, Lung, Medical imaging, Computed tomography, Telecommunications, Data communications, Computer aided diagnosis and therapy, Medical research
The LIDC is developing a publicly available database of thoracic computed tomography (CT) scans as a medical imaging research resource. A unique multi-center data collection process and communication system were developed to share image data and to capture the location and spatial extent of lung nodules as marked by expert radiologists. A two-phase data collection process was designed to allow multiple radiologists at different centers to asynchronously review and annotate each CT image series. Four radiologists reviewed each case using this process. In the first or "blinded" phase, each radiologist reviewed the CT series independently. In the second or "unblinded" review phase, the results from all four blinded reviews are compiled and presented to each radiologist for a second review. This allows each radiologist to review their own annotations along with those of the other radiologists. The results from each radiologist's unblinded review were compiled to form the final unblinded review. There is no forced consensus in this process. An XML-based message system was developed to communicate the results of each reading. This two-phase data collection process was designed, tested and implemented across the LIDC. It has been used for more than 130 CT cases that have been read and annotated by four expert readers and are publicly available at (http://ncia.nci.nih.gov). A data collection process was developed, tested and implemented that allowed multiple readers to review each case multiple times and that allowed each reader to observe the annotations of other readers.
The National Cancer Institute (NCI) is interested in supporting the development of an image database for lung cancer screening using spiral x-ray CT. A cooperative agreement is envisioned that will involve applications from investigators who are interested in joining a consortium of institutions to construct such a database as a public resource. The intent is to develop standards for generating the database resource and to allow this database to be used for evaluating computer aided diagnostic (CAD) software methods. Initial interest is focused on spiral CT of the lung because of the recent interest in using this imaging modality for lung cancer screening for patients at high risk, where early intervention may significantly reduce cancer mortality rates. The use of CAD methods is rapidly emerging for this large-scale cancer screening application as these methods have the potential of improving the efficiency of screening. Lung imaging is a good physical model in that it involves the use of 3D CAD methods that require critical software optimization for both detection and classification. In addition, the detection of change in the CT images over time, or changes in lung nodule size, has the potential to provide either improved early cancer detection or improved classification.
A new CAD mass detection system was developed using adaptive and multi-scale processing methods for improving detection sensitivity/specificity, and its robustness to the variation in mammograms. The major techniques developed in system design include: (1) image standardization by applying a series of preprocessing to remove extrinsic signal, extract breast area, and normalize the image intensity; (2) multi- mode processing by decomposing image features using directional wavelet transform and non-linear multi-scale representation using anisotropic diffusion; (3) adaptive processing in image segmentation using localized adaptive thresholding and adaptive clustering; and (4) combined `hard'-`soft' classification by using a modified fuzzy decision tree and committee decision-making method. Evaluations and comparisons were taken with a training dataset containing 30 normal and 47 abnormal mammograms with totally 70 masses, and an independent testing dataset consisting of 100 normal images, 39 images with 48 minimal cancers and 25 images with 25 benign masses. A high detection performance of sensitivity TP equals 93% with false positive rate FP equals 3.1 per image and a good generalizability with TP equals 80% and FP equals 2.0 per image are obtained.
Softcopy reading and CAD in mammography are both dependent upon the characteristics of the source of the digital data, either direct digital mammography or digitized screen-film mammography. In this work, a standardization is proposed based on geometric and intensity transformation that are discovered using a set of calibration images. A genetic algorithm is used to search for the best transformations. Results indicate that standardization for display can be achieved, but that CAD performance varies even after standardization: both sensitivity and false-positive rates appear to be reduced.
Multiresolution and multiorientation wavelet transforms (WTs), as the key CAD modules, were used in our previous study of CAD mass detection. The objective of this paper is to evaluate the roles of these WTs modules in the proposed CAD approach. A statistical analysis of the effects of WTs on image feature extraction for mass detection is taken including the effects of WTs on mass segmentation and a comparative study of discrimination ability of features extracted with WTs based and non-WTs based segmentation method. Three indexes are proposed to asses the segmentation. The effects of WTs on feature extraction are evaluated using ROC analysis of the feature discrimination ability. The statistical analysis demonstrates that the use of WTs modules results in a significant improvement in feature extraction for the previously proposed CAD mass detection method. The improvement, however, depends on the feature characteristics, large for boundary-related features while small for intensity-related features.
The development and evaluation of a new class of algorithms for computer assisted diagnostic (CAD) methods for segmentation and detection of masses in digitized mammograms is reported. Both non-adaptive and adaptive methods are reported that employ two key novel CAD modules, specifically tailored for digital mammography, namely: (a) a multiorientation directional wavelet transform for removal of directional features and for the direct detection of speculations for spiculated lesions, and (b) a multiresolution wavelet transform for image enhancement to improve the segmentation of suspicious areas. The aim of the work is to provide a brief overview of both the non-adaptive and adaptive methods and comparison of their performance using computer ROC curves. An image data base containing regions of interest (ROI), enclosing all mass types and normal tissues, was used for the relative comparison of the performance, where electronic ground truth was established. The result confirm the importance of using adaptive CAD methods that should potentially allow a more generalized and robust application for larger image data bases, images generated from different sensors, or direct X-ray detection, as required for clinical trials and teleradiology applications.
The goal of this project was the development of a workstation-user interface for evaluating computer assisted diagnosis (CAD) methods for digital mammography in receiver operating characteristic (ROC) experiments. Digital mammography poses significant and unique difficulties in the design and implementation of such an interface because multiple, large size images need to be handled at high- speeds. Furthermore, controls such as contrast, pan and zoom, and tools such as reporting forms, case information, and analysis of results need to be included. The software and hardware used to develop such a workstation and interface were based on Sun platforms and the Unix operating system. The software was evaluated by radiologists, and found to be user friendly, and comparable to standard mammography film reading in terms of display layout and speed. The software, as designed, will work on entry level workstations as well as high-end workstations with specialized hardware, thus being usable in either an educational, training, or clinical environment for annotation purposes using CAD techniques as well as primary diagnosis.
Film digitalization is the process of mapping the optical densities of a radiographic film into a digital matrix. In this work, a film digitizer based on charge-coupled device was evaluated and optimized for digital mammography applications. The characteristics of the digital output were determined for various spatial resolutions and dynamic ranges. Furthermore, the reproducibility of the system was tested as needed for computer assisted diagnosis (CAD) applications. Practical and relevant to the application quality control procedures were established for the system that will allow early troubleshooting and close monitoring of image quality for consistent performance. Overall, the characteristics of the scanner matched the properties of the tested screen/films and its performance generally met digital mammography and CAD requirements.
The morphology and distribution of mammographic calcifications and the way these elements vary within a cluster are valuable in distinguishing between benign and malignant calcifications. The specific aims of this study were (a) the development of an automatic tool that differentiates between benign and malignant clustered calcifications based on their morphological properties and (b) the determination of the effects of image spatial resolution on the classification process. The long term aim of the project is to use this tool to categorize detected clusters into the various types described in the breast imaging reporting and data systems of the American College of Radiology and assist the radiologists in their diagnosis.
The theoretical basis for an adaptive multiresolution and multiorientation wavelet transform methods for image preprocessing is described for improved CAD performance in breast cancer screening using digital maniinography. The method is an extension of an earlier method reported that uses fixed parameters for the multiorientation wavelet transforms. Simulation results are described to demonstrate the importance of using higher order transforms. The computed FROC results are summarized for the previously reported non-adaptive methods, compare well to that reported in the literature, to demonstrate the potential improvement if adaptive methods are used.
This paper is part of a feasibility study of using an image segmentation method to automatically identify the tumor or target boundaries in each axial slice or to assist an expert physician to manually draw these boundaries.A two-stage segmentation method is proposed. In the first step, the outlying bone structure is removed from the raw CT data and the brain parenchymal area is extracted. Then a VQ-based method is applied for the segmentation of the soft tissue inside the brain area. Representative results for two sets of x-ray CT axial slice images from tow patients are presented. Problems and further modifications are discussed.
Lung nodule (LN) detection using computer assisted diagnostic (CAD) methodology in chest radiolographs is generally composed of two steps, i.e., suspicious area (SA) location and differentiation of 'true' nodules from 'false' nodules among located SAs. The first step is related to computer image processing techniques, such as image enhancement and segmentation methods. The second step uses pattern classification techniques, such as statistical classifiers and artificial neural networks (ANN). This paper will address only the first step of the CAD lung nodule detection. We have designed a novel fractional dimension filtering (FDF) algorithm for the extraction of lung nodule patterns, which generally appear as circular bright areas in the chest radiograph. The FDF provides an improved performance of discriminating circular pattern from other patterns in the presence of overlapping structures. A multiscale analysis has also been introduced to locate multiscale nodules and eliminate false positives. A computed ROC analysis has been performed to show the improvement of discriminating performance of the FDF by using simulated patterns. A computed FROC analysis has also been conducted for analyzing the performance of the proposed location scheme with and without the multiscale analysis.
Magnetic resonance images (MRI) of the brain are segmented into tumor and non-tumor to provide an objective means for measuring the response of a tumor to therapy. This paper focuses on automatic feature extraction to improve brain tumor segmentation using genetic algorithms (GAs). Using the discovered features, a significant increase in accuracy of tumor segmentation is seen. Moreover, this improvement is consistent over a tumor volume outside the training data.
A neural-network-based algorithm is proposed for the restoration of nuclear medicine images as required for antibody therapy. The method was designed to address the particular problem of restoration of planar and tomographic bremsstrahlung data acquired with a gamma camera. Restoration was achieved by minimizing the energy function of the Hopfield network using a maximum entropy constraint. The performance of the proposed algorithm was tested on simulated data and planar gamma camera images of pure p-emitting radionuclides used in radioimmunotherapy. The results were compared with those of previously reported restoration techniques based on neural networks or traditional filters. Qualitative and quantitative analysis of the data suggested that the neural network with the maximum entropy constraint has good overall restoration performance; it is stable and robust even in cases where the signal-to-noise ratio is poor and scattering effects are significant. This behavior is particularly important in imaging therapeutic doses of pure β emitters such as yttrium-90 in order to provide accurate in vivo estimates of the radiation dose to the target and/or the critical organs.
Computer aided diagnosis (CADx) is a promising technology for the detection of breast cancer in screening mammography. A number of different approaches have been developed for CADx research that have achieved significant levels of performance. Research teams now recognize the need for a careful and detailed evaluation study of approaches to accelerate the development of CADx, to make CADx more clinically relevant and to optimize the CADx algorithms based on unbiased evaluations. The results of such a comparative study may provide each of the participating teams with new insights into the optimization of their individual CADx algorithms. This consortium of experienced CADx researchers is working as a group to compare results of the algorithms and to optimize the performance of CADx algorithms by learning from each other. Each institution will be contributing an equal number of cases that will be collected under a standard protocol for case selection, truth determination, and data acquisition to establish a common and unbiased database for the evaluation study. An evaluation procedure for the comparison studies are being developed to analyze the results of individual algorithms for each of the test cases in the common database. Optimization of individual CADx algorithms can be made based on the comparison studies. The consortium effort is expected to accelerate the eventual clinical implementation of CADx algorithms at participating institutions.
Individual cluster validation has not received as much attention as partition validation. This paper presents two measures for evaluating individual clusters in a fuzzy partition. They both account for properties of the fuzzy memberships as well as the structure of the data. The first measure is a ratio between compactness and separation of the fuzzy clusters; the second is based on counting a contradiction between properties of the fuzzy memberships and the stucture of the data. These two measures are applied and compared in evaluating fuzzy clusters generated by the fuzzy c-means algorithm for segmentation of magnetic resonance images of the brain.
Unsupervised fuzzy methods are proposed for segmentation of 3D Magnetic Resonance images of the brain. Fuzzy c-means (FCM) has shown promising results for segmentation of single slices. FCM has been investigated for volume segmentations, both by combining results of single slices and by segmenting the full volume. Different strategies and initializations have been tried. In particular, two approaches have been used: (1) a method by which, iteratively, the furthest sample is split off to form a new cluster center, and (2) the traditional FCM in which the membership grade matrix is initialized in some way. Results have been compared with volume segmentations by k-means and with two supervised methods, k-nearest neighbors and region growing. Results of individual segmentations are presented as well as comparisons on the application of the different methods to a number of tumor patient data sets.
The development of an extensive array of algorithms for both image enhancement and feature extraction for microcalcification cluster detection is reported. Specific emphasis is placed on image detail preservation and automatic or operator independent methods to enhance the sensitivity and specificity of detection and that should allow standardization of breast screening procedures. Image enhancement methods include both novel tree structured non-linear filters with fixed parameters and adaptive order statistic filters designed to further improve detail preservation. Novel feature extraction methods developed include both two channel tree structured wavelet transform and three channel quadrature mirror filter banks with multiresolution decomposition and reconstruction specifically tailored to extract MCC's. These methods were evaluated using fifteen representative digitized mammograms where similar sensitivity (true positive (TP) detection rate 100%) and specificity (0.1 - 0.2 average false positive (FP) MCC's/image) was observed but with varying degrees of detail preservation important for characterization of MCC's. The image enhancement step proved to be very critical to minimize image noise and associated FP detection rates for MCC's or individual microcalcifications.
Computer detection of microcalcifications in mammographic images will likely require a multi-stage algorithm that includes segmentation of possible microcalcifications, pattern recognition techniques to classify the segmented objects, a method to determine if a cluster of calcifications exists, and possibly a method to determine the probability of malignancy. This paper will focus on the classification of segmented objects as being either (1) microcalcifications or (2) non-microcalcifications. Six classifiers (2 Bayesian, 2 dynamic neural networks, a standard backpropagation network, and a K-nearest neighbor) are compared. Methods of segmentation and feature selection are described, although they are not the primary concern of this paper. A database of digitized film mammograms is used for training and testing. Detection accuracy is compared across the six methods.
Partial supervision is introduced to the unsupervised fuzzy c-means algorithm (FCM). The resulting algorithm is called semi-supervised fuzzy c-means (SFCM). Labeled data are used as training information to improve FCM's performance. Training data are represented as training columns in SFCM's membership matrix (U), and are allowed to affect the cluster center computations. The degree of supervision is monitored by choosing the number of copies of the training set to be used in SFCM. Preliminary results of SFCM (applied to MRI segmentation) suggest that FCM finds the clusters of most interest to the user very accurately when training data is used to guide it.
A conventional gamma camera is used for the external imaging of bremsstrahlung generated from pure beta-emitters such as phosphorous-32 (32P). Tomographic images of a cylindrical phantom filled with water and containing four cylindrical sources of varying diameter are recorded using two collimators with symmetrical aperture configuration but different bore-lengths. The resolution of the system is comparable to single photon emitters for both collimaters; FWHM approximately 1.8 cm and FWTM approximately 2.9 cm. An effective linear attenuation coefficient of 0.14 cm-1 for 32P, calculated from isolated spherical sources in water, is used with the post-reconstruction Chang algorithm to correct the tomographic images. The use of a broad energy window and the symmetric apertures of the collimators yields an approximately radially symmetric, shift invariant, and stationary point-spread-function with distance from the collimator face as required for the use of image restoration filters. A new filter is proposed which shares the advantages of both neural network for deconvolution and advanced nonlinear filtering for noise removal and edge enhancement. The new filter compares favorably with the Wiener for image restoration and improves the conditions for quantitative measurements with the gamma camera. In addition, its application for image restoration does not require the knowledge of the object and noise power spectra and the serious problems (ring effects and noise overriding) associated with the inverse operation encountered in the Wiener filter are avoided.
A computer assisted method for the quantification and classification of mammographic parenchymal patterns (MPP) is proposed. Enhancement of mammographic images is performed using order statistic filtering, a superior method compared to median filtering techniques previously reported. Two complementary methods are proposed for quantification and classification of MPP, a local thresholding technique and an edge detection method, respectively. The latter method is based on non-linear filtering which uses order statistics or linear combination of order statistics filter specifically tailored to identify the boundaries and fine details of MPP. The edge detection method proved to be useful for the difficult differentiation of Wolfe's P2 and DY MPP that have similar breast density and common characteristics. The results suggest that the methods proposed are potentially useful for identification and quantitation of MPPs as required for mass screening of breast cancer.
The use of image intensity based segmentation techniques are proposed to improve MRI contrast and provide greater confidence levels in 3-D visualization of pathology. Pattern recognition methods are proposed using both supervised and unsupervised methods. This paper emphasizes the practical problems in the selection of training data sets for supervised methods that result in instability in segmentation. An unsupervised method, namely fuzzy c- means, that does not require training data sets and produces comparable results is proposed.
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.