Observer studies involving detection and localization: modeling, analysis, and validation

Although the receiver operating characteristic (ROC) paradigm is the accepted method for evaluation of diagnostic imaging systems, it has some serious shortcomings inasmuch as it is restricted to one observer report per image. By contrast the free-response ROC (FROC) paradigm and associated analysis method allows the observer to report multiple abnormalities within each imaging study, and uses the location of reported abnormalities to improve the measurement. Because the ROC method cannot accommodate multiple responses or use location information, its statistical power will suffer. The FROC paradigm/analysis has not enjoyed widespread acceptance because of concern about whether responses made to the same diagnostic study can be treated as independent. We propose a new jackknife FROC analysis method (JAFROC) that does not make the independence assumption. The new analysis method combines elements of FROC and the Dorfman-Berbaum-Metz (DBM) methods. To compare JAFROC to an earlier free-response analysis method (specifically the alternative free-response, or AFROC method), and to the DBM method, which uses conventional ROC scoring, we developed a model for generating simulated FROC data. The simulation model is based on an eye-movement model of how experts evaluate images. It allowed us to examine null hypothesis (NH) behavior and statistical power of the different methods. We found that AFROC analysis did not pass the NH test, being unduly conservative. Both the JAFROC method and the DBM method passed the NH test, but JAFROC had more statistical power than the DBM method. The results of this comparison suggest that future studies of diagnostic performance may enjoy improved statistical power or reduced sample size requirements through the use of the JAFROC method.     

Operating characteristics predicted by models for diagnostic tasks involving lesion localization

In 1996 Swensson published an observer model that predicted receiver operating characteristic (ROC), localization ROC (LROC), free-response ROC (FROC) and alternative FROC (AFROC) curves, thereby achieving "unification" of different observer performance paradigms. More recently a model termed initial detection and candidate analysis (IDCA) has been proposed for fitting computer aided detection (CAD) generated FROC data, and recently a search model for human observer FROC data has been proposed. The purpose of this study was to derive IDCA and the search model based expressions for operating characteristics, and to compare the predictions to the Swensson model. For three out of four mammography CAD data sets all models yielded good fits in the high-confidence region, i.e., near the lower end of the plots. The search model and IDCA tended to better fit the data in the low-confidence region, i.e., near the upper end of the plots, particularly for FROC curves for which the Swensson model predictions departed markedly from the data. For one data set none of the models yielded satisfactory fits. A unique characteristic of search model and IDCA predicted operating characteristics is that the operating point is not allowed to move continuously to the lowest confidence limit of the corresponding Swensson model curves. This prediction is actually observed in the CAD raw data and it is the primary reason for the poor FROC fits of the Swensson model in the low-confidence region.     

Binary and multi-category ratings in a laboratory observer performance study: a comparison

The authors investigated radiologists, performances during retrospective interpretation of screening mammograms when using a binary decision whether to recall a woman for additional procedures or not and compared it with their receiver operating characteristic (ROC) type performance curves using a semi-continuous rating scale. Under an Institutional Review Board approved protocol nine experienced radiologists independently rated an enriched set of 155 examinations that they had not personally read in the clinic, mixed with other enriched sets of examinations that they had individually read in the clinic, using both a screening BI-RADS rating scale (recall/not recall) and a semi-continuous ROC type rating scale (0 to 100). The vertical distance, namely the difference in sensitivity levels at the same specificity levels, between the empirical ROC curve and the binary operating point were computed for each reader. The vertical distance averaged over all readers was used to assess the proximity of the performance levels under the binary and ROC-type rating scale. There does not appear to be any systematic tendency of the readers towards a better performance when using either of the two rating approaches, namely four readers performed better using the semi-continuous rating scale, four readers performed better with the binary scale, and one reader had the point exactly on the empirical ROC curve. Only one of the nine readers had a binary "operating point" that was statistically distant from the same reader's empirical ROC curve. Reader-specific differences ranged from -0.046 to 0.128 with an average width of the corresponding 95% confidence intervals of 0.2 and p-values ranging for individual readers from 0.050 to 0.966. On average, radiologists performed similarly when using the two rating scales in that the average distance between the run in individual reader's binary operating point and their ROC curve was close to zero. The 95% confidence interval for the fixed-reader average (0.016) was (-0.0206, 0.0631) (two-sided p-value 0.35). In conclusion the authors found that in retrospective observer performance studies the use of a binary response or a semi-continuous rating scale led to consistent results in terms of performance as measured by sensitivity-specificity operating points.     

Bilateral analysis based false positive reduction for computer-aided mass detection

We have developed a false positive (FP) reduction method based on analysis of bilateral mammograms for computerized mass detection systems. The mass candidates on each view were first detected by our unilateral computer-aided detection (CAD) system. For each detected object, a regional registration technique was used to define a region of interest (ROI) that is "symmetrical" to the object location on the contralateral mammogram. Texture features derived from the spatial gray level dependence matrices and morphological features were extracted from the ROI containing the detected object on a mammogram and its corresponding ROI on the contralateral mammogram. Bilateral features were then generated from corresponding pairs of unilateral features for each object. Two linear discriminant analysis (LDA) classifiers were trained from the unilateral and the bilateral feature spaces, respectively. Finally, the scores from the unilateral LDA classifier and the bilateral LDA asymmetry classifier were fused with a third LDA whose output score was used to distinguish true mass from FPs. A data set of 341 cases of bilateral two-view mammograms was used in this study, of which 276 cases with 552 bilateral pairs contained 110 malignant and 166 benign biopsy-proven masses and 65 cases with 130 bilateral pairs were normal. The mass data set was divided into two subsets for twofold cross-validation training and testing. The normal data set was used for estimation of FP rates. It was found that our bilateral CAD system achieved a case-based sensitivity of 70%, 80%, and 85% at average FP rates of 0.35, 0.75, and 0.95 FPs/image, respectively, on the test data sets with malignant masses. In comparison to the average FP rates for the unilateral CAD system of 0.58, 1.33, and 1.63, respectively, at the corresponding sensitivities, the FP rates were reduced by 40%, 44%, and 42% with the bilateral symmetry information. The improvement was statistically significance (p < 0.05) as estimated by JAFROC analysis.     

Characterization of mammographic masses using a gradient-based segmentation algorithm and a neural classifier

Computerized methods have recently shown a great potential in providing radiologists with a second opinion about the visual diagnosis of the malignancy of mammographic masses. The computer-aided diagnosis (CAD) system we developed for the mass characterization is mainly based on a segmentation algorithm and on the neural classification of several features computed on the segmented mass. Mass-segmentation plays a key role in most computerized systems. Our technique is a gradient-based one, showing the main characteristic that no free parameters have been evaluated on the data set used in this analysis, thus it can directly be applied to data sets acquired in different conditions without any ad hoc modification. A data set of 226 masses (109 malignant and 117 benign) has been used in this study. The segmentation algorithm works with a comparable efficiency both on malignant and benign masses. Sixteen features based on shape, size and intensity of the segmented masses are extracted and analyzed by a multi-layered perceptron neural network trained with the error back-propagation algorithm. The capability of the system in discriminating malignant from benign masses has been evaluated in terms of the receiver-operating characteristic (ROC) analysis. A feature selection procedure has been carried out on the basis of the feature discriminating power and of the linear correlations interplaying among them. The comparison of the areas under the ROC curves obtained by varying the number of features to be classified has shown that 12 selected features out of the 16 computed ones are powerful enough to achieve the best classifier performances. The radiologist assigned the segmented masses to three different categories: correctly-, acceptably- and non-acceptably-segmented masses. We initially estimated the area under ROC curve only on the first category of segmented masses (the 88.5% of the data set), then extending the classification to the second subclass (reaching the 97.8% of the data set) and finally to the whole data set, obtaining A(z)=0.805+/-0.030, 0.787+/-0.024 and 0.780+/-0.023, respectively.     

Maximum likelihood analysis of free-response receiver operating characteristic (FROC) data

Receiver operating characteristic (ROC) methodology is widely used in evaluating medical imaging modalities. While appropriate in some cases, it has several drawbacks when the detection task, e.g., nodule detection, involves localizing the abnormality. Free-response receiver operating characteristic (FROC) methodology offers a more natural framework to describe observer performance in such studies and has other advantages. Due to the lack of a statistical analysis procedure comparable to the maximum likelihood procedure (ROCFIT program) available for ROC studies, the FROC method has not gained widespread acceptance. This work presents and solves a two parameter model for the statistical analysis of FROC data. The model assumes that the probability density of the signal stimuli is normally distributed, as is the probability density for producing one or more false positives per image. A program (FROCFIT) is described for estimating the parameters and their uncertainties from experimental data. An index of performance is proposed to quantify observer performance in FROC experiments. Application of this methodology to several FROC data sets produced good to excellent fits.     

Determination of subjective similarity for pairs of masses and pairs of clustered microcalcifications on mammograms: comparison of similarity ranking scores and absolute similarity ratings

The presentation of images that are similar to that of an unknown lesion seen on a mammogram may be helpful for radiologists to correctly diagnose that lesion. For similar images to be useful, they must be quite similar from the radiologists' point of view. We have been trying to quantify the radiologists' impression of similarity for pairs of lesions and to establish a "gold standard" for development and evaluation of a computerized scheme for selecting such similar images. However, it is considered difficult to reliably and accurately determine similarity ratings, because they are subjective. In this study, we compared the subjective similarities obtained by two different methods, an absolute rating method and a 2-alternative forced-choice (2AFC) method, to demonstrate that reliable similarity ratings can be determined by the responses of a group of radiologists. The absolute similarity ratings were previously obtained for pairs of masses and pairs of microcalcifications from five and nine radiologists, respectively. In this study, similarity ranking scores for eight pairs of masses and eight pairs of microcalcifications were determined by use of the 2AFC method. In the first session, the eight pairs of masses and eight pairs of microcalcifications were grouped and compared separately for determining the similarity ranking scores. In the second session, another similarity ranking score was determined by use of mixed pairs, i.e., by comparison of the similarity of a mass pair with that of a calcification pair. Four pairs of masses and four pairs of microcalcifications were grouped together to create two sets of eight pairs. The average absolute similarity ratings and the average similarity ranking scores showed very good correlations in the first study (Pearson's correlation coefficients: 0.94 and 0.98 for masses and microcalcifications, respectively). Moreover, in the second study, the correlations between the absolute ratings and the ranking scores were also very high (0.92 and 0.96), which implies that the observers were able to compare the similarity of a mass pair with that of a calcification pair consistently. These results provide evidence that the concept of similarity for pairs of images is robust, even across different lesion types, and that radiologists are able to reliably determine subjective similarity for pairs of breast lesions.     

A method to improve visual similarity of breast masses for an interactive computer-aided diagnosis environment

The purpose of this study was to develop and test a method for selecting "visually similar" regions of interest depicting breast masses from a reference library to be used in an interactive computer-aided diagnosis (CAD) environment. A reference library including 1000 malignant mass regions and 2000 benign and CAD-generated false-positive regions was established. When a suspicious mass region is identified, the scheme segments the region and searches for similar regions from the reference library using a multifeature based k-nearest neighbor (KNN) algorithm. To improve selection of reference images, we added an interactive step. All actual masses in the reference library were subjectively rated on a scale from 1 to 9 as to their "visual margins speculations". When an observer identifies a suspected mass region during a case interpretation he/she first rates the margins and the computerized search is then limited only to regions rated as having similar levels of spiculation (within +/-1 scale difference). In an observer preference study including 85 test regions, two sets of the six "similar" reference regions selected by the KNN with and without the interactive step were displayed side by side with each test region. Four radiologists and five nonclinician observers selected the more appropriate ("similar") reference set in a two alternative forced choice preference experiment. All four radiologists and five nonclinician observers preferred the sets of regions selected by the interactive method with an average frequency of 76.8% and 74.6%, respectively. The overall preference for the interactive method was highly significant (p < 0.001). The study demonstrated that a simple interactive approach that includes subjectively perceived ratings of one feature alone namely, a rating of margin "spiculation," could substantially improve the selection of "visually similar" reference images.     

Maximum likelihood fitting of FROC curves under an initial-detection-and-candidate-analysis model

We have developed a model for FROC curve fitting that relates the observer's FROC performance not to the ROC performance that would be obtained if the observer's responses were scored on a per image basis, but rather to a hypothesized ROC performance that the observer would obtain in the task of classifying a set of "candidate detections" as positive or negative. We adopt the assumptions of the Bunch FROC model, namely that the observer's detections are all mutually independent, as well as assumptions qualitatively similar to, but different in nature from, those made by Chakraborty in his AFROC scoring methodology. Under the assumptions of our model, we show that the observer's FROC performance is a linearly scaled version of the candidate analysis ROC curve, where the scaling factors are just given by the FROC operating point coordinates for detecting initial candidates. Further, we show that the likelihood function of the model parameters given observational data takes on a simple form, and we develop a maximum likelihood method for fitting a FROC curve to this data. FROC and AFROC curves are produced for computer vision observer datasets and compared with the results of the AFROC scoring method. Although developed primarily with computer vision schemes in mind, we hope that the methodology presented here will prove worthy of further study in other applications as well.     

Application of the iris filter for automatic detection of pulmonary nodules on computed tomography images

We have developed a computer-aided diagnosis (CAD) system to detect pulmonary nodules on thin-slice helical computed tomography (CT) images. We have also investigated the capability of an iris filter to discriminate between nodules and false-positive findings. Suspicious regions were characterized with features based on the iris filter output, gray level and morphological features, extracted from the CT images. Functions calculated by linear discriminant analysis (LDA) were used to reduce the number of false-positives.The system was evaluated on CT scans containing 77 pulmonary nodules. The system was trained and evaluated using two completely independent data sets. Results for a test set, evaluated with free-response receiver operating characteristic (FROC) analysis, yielded a sensitivity of 80% at 7.7 false-positives per scan.     

Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers

OBJECTIVES: The aim of the present study is to define an optimally performing computer-aided diagnosis (CAD) architecture for the classification of liver tissue from non-enhanced computed tomography (CT) images into normal liver (C1), hepatic cyst (C2), hemangioma (C3), and hepatocellular carcinoma (C4). To this end, various CAD architectures, based on texture features and ensembles of classifiers (ECs), are comparatively assessed. MATERIALS AND METHODS: Number of regions of interests (ROIs) corresponding to C1-C4 have been defined by experienced radiologists in non-enhanced liver CT images. For each ROI, five distinct sets of texture features were extracted using first order statistics, spatial gray level dependence matrix, gray level difference method, Laws' texture energy measures, and fractal dimension measurements. Two different ECs were constructed and compared. The first one consists of five multilayer perceptron neural networks (NNs), each using as input one of the computed texture feature sets or its reduced version after genetic algorithm-based feature selection. The second EC comprised five different primary classifiers, namely one multilayer perceptron NN, one probabilistic NN, and three k-nearest neighbor classifiers, each fed with the combination of the five texture feature sets or their reduced versions. The final decision of each EC was extracted by using appropriate voting schemes, while bootstrap re-sampling was utilized in order to estimate the generalization ability of the CAD architectures based on the available relatively small-sized data set. RESULTS: The best mean classification accuracy (84.96%) is achieved by the second EC using a fused feature set, and the weighted voting scheme. The fused feature set was obtained after appropriate feature selection applied to specific subsets of the original feature set. CONCLUSIONS: The comparative assessment of the various CAD architectures shows that combining three types of classifiers with a voting scheme, fed with identical feature sets obtained after appropriate feature selection and fusion, may result in an accurate system able to assist differential diagnosis of focal liver lesions from non-enhanced CT images.     

Evaluating computer-aided detection algorithms

Computer-aided detection (CAD) has been attracting extensive research interest during the last two decades. It is recognized that the full potential of CAD can only be realized by improving the performance and robustness of CAD algorithms and this requires good evaluation methodology that would permit CAD designers to optimize their algorithms. Free-response receiver operating characteristic (FROC) curves are widely used to assess CAD performance, however, evaluation rarely proceeds beyond determination of lesion localization fraction (sensitivity) at an arbitrarily selected value of nonlesion localizations (false marks) per image. This work describes a FROC curve fitting procedure that uses a recent model of visual search that serves as a framework for the free-response task. A maximum likelihood procedure for estimating the parameters of the model from free-response data and fitting CAD generated FROC curves was implemented. Procedures were implemented to estimate two figures of merit and associated statistics such as 95% confidence intervals and goodness of fit. One of the figures of merit does not require the arbitrary specification of an operating point at which to evaluate CAD performance. For comparison a related method termed initial detection and candidate analysis was also implemented that is applicable when all suspicious regions are reported. The two methods were tested on seven mammography CAD data sets and both yielded good to excellent fits. The search model approach has the advantage that it can potentially be applied to radiologist generated free-response data where not all suspicious regions are reported, only the ones that are deemed sufficiently suspicious to warrant clinical follow-up. This work represents the first practical application of the search model to an important evaluation problem in diagnostic radiology. Software based on this work is expected to benefit CAD developers working in diverse areas of medical imaging.     

Computer-aided diagnosis in high resolution CT of the lungs

A computer-aided diagnosis (CAD) system is presented to automatically distinguish normal from abnormal tissue in high-resolution CT chest scans acquired during daily clinical practice. From high-resolution computed tomography scans of 116 patients, 657 regions of interest are extracted that are to be classified as displaying either normal or abnormal lung tissue. A principled texture analysis approach is used, extracting features to describe local image structure by means of a multi-scale filter bank. The use of various classifiers and feature subsets is compared and results are evaluated with ROC analysis. Performance of the system is shown to approach that of two expert radiologists in diagnosing the local regions of interest, with an area under the ROC curve of 0.862 for the CAD scheme versus 0.877 and 0.893 for the radiologists.     

Computer-aided detection of masses in digital tomosynthesis mammography: comparison of three approaches

The authors are developing a computer-aided detection (CAD) system for masses on digital breast tomosynthesis mammograms (DBT). Three approaches were evaluated in this study. In the first approach, mass candidate identification and feature analysis are performed in the reconstructed three-dimensional (3D) DBT volume. A mass likelihood score is estimated for each mass candidate using a linear discriminant analysis (LDA) classifier. Mass detection is determined by a decision threshold applied to the mass likelihood score. A free response receiver operating characteristic (FROC) curve that describes the detection sensitivity as a function of the number of false positives (FPs) per breast is generated by varying the decision threshold over a range. In the second approach, prescreening of mass candidate and feature analysis are first performed on the individual two-dimensional (2D) projection view (PV) images. A mass likelihood score is estimated for each mass candidate using an LDA classifier trained for the 2D features. The mass likelihood images derived from the PVs are backprojected to the breast volume to estimate the 3D spatial distribution of the mass likelihood scores. The FROC curve for mass detection can again be generated by varying the decision threshold on the 3D mass likelihood scores merged by backprojection. In the third approach, the mass likelihood scores estimated by the 3D and 2D approaches, described above, at the corresponding 3D location are combined and evaluated using FROC analysis. A data set of 100 DBT cases acquired with a GE prototype system at the Breast Imaging Laboratory in the Massachusetts General Hospital was used for comparison of the three approaches. The LDA classifiers with stepwise feature selection were designed with leave-one-case-out resampling. In FROC analysis, the CAD system for detection in the DBT volume alone achieved test sensitivities of 80% and 90% at average FP rates of 1.94 and 3.40 per breast, respectively. With the 2D detection approach, the FP rates were 2.86 and 4.05 per breast, respectively, at the corresponding sensitivities. In comparison, the average FP rates of the system combining the 3D and 2D information were 1.23 and 2.04 per breast, respectively, at 80% and 90% sensitivities. The difference in the detection performances between the 2D and the 3D approach, and that between the 3D and the combined approach were both statistically significant (p = 0.02 and 0.01, respectively) as estimated by alternative FROC analysis. The combined system is a promising approach to improving automated mass detection on DBTs.     

Improvement of computerized mass detection on mammograms: fusion of two-view information

Recent clinical studies have proved that computer-aided diagnosis (CAD) systems are helpful for improving lesion detection by radiologists in mammography. However, these systems would be more useful if the false-positive rate is reduced. Current CAD systems generally detect and characterize suspicious abnormal structures in individual mammographic images. Clinical experiences by radiologists indicate that screening with two mammographic views improves the detection accuracy of abnormalities in the breast. It is expected that the fusion of information from different mammographic views will improve the performance of CAD systems. We are developing a two-view matching method that utilizes the geometric locations, and morphological and textural features to correlate objects detected in two different views using a prescreening program. First, a geometrical model is used to predict the search region for an object in a second view from its location in the first view. The distance between the object and the nipple is used to define the search area. After pairing the objects in two views, textural and morphological characteristics of the paired objects are merged and similarity measures are defined. Linear discriminant analysis is then employed to classify each object pair as a true or false mass pair. The resulting object correspondence score is combined with its one-view detection score using a fusion scheme. The fusion information was found to improve the lesion detectability and reduce the number of FPs. In a preliminary study, we used a data set of 169 pairs of cranio-caudal (CC) and mediolateral oblique (MLO) view mammograms. For the detection of malignant masses on current mammograms, the film-based detection sensitivity was found to improve from 62% with a one-view detection scheme to 73% with the new two-view scheme, at a false-positive rate of 1 FP/image. The corresponding cased-based detection sensitivity improved from 77% to 91%.     

A constrained formulation for the receiver operating characteristic (ROC) curve based on probability summation

We propose a principled formulation of the ROC curve that is constrained in a realistic way by the mechanism of probability summation. The constrained and conventional ROC formulations were fitted to 150 separate sets of rating data taken from previous observer studies of 250 or 529 chest radiographs. A total of 20 different readers had used either discrete or continuous rating scales to evaluate those chest cases for likelihood of separate specified abnormalities: interstitial disease, pulmonary nodule, pneumothorax, alveolar infiltrate, or rib fracture. Both ROC formulations were fitted separately to every set of rating data using maximum-likelihood statistical procedures that specified each ROC curve by normally distributed latent variables with two scaling parameters, and estimated the area below the ROC curve (Az) with its standard error. The conventional and constrained binormal formulations usually fitted ROC curves that were nearly indistinguishable in form and in Az. But when fitted to asymmetric rating data that contained few false-positive cases, the conventional ROC curves often rose steeply, then flattened and extrapolated into an unrealistic upward "hook" at the higher false-positive rates. For those sets of rating data, the constrained ROC curves (without hooks) estimated larger values for Az with smaller standard errors. The constrained ROC formulation describes observers' ratings of cases at least as well as the conventional ROC, and always guarantees a realistic fitted curve for observer performance. Its estimated parameters are easy to interpret, and may also be used to predict observer accuracy in localizing the image abnormalities.     

Clinical evaluation of irreversible data compression for computed radiography of the chest

Efficient data compression is essential for practical daily operation of computed radiography (CR) systems. In this study the clinical applicability of type III irreversible high data compression using an FCR 9501 chest unit (Fuji Photo Film, Tokyo, Japan) was evaluated. Sixty-eight normal and 93 various abnormal cases, with an additional 15 cases of lung cancers with solitary lung nodules, were selected from the file. A pair of hard copies of original images and images reconstructed using type III compression was made for each case. Six radiologists evaluated the image quality by visual rating and receiver operating characteristic (ROC) curve analysis. For all five anatomic regions of normal cases, “original equal to compressed” was the most common response, followed by “original significantly better than compressed.” When abnormal cases were evaluated for diagnostic information, there was no significant difference between the compressed and original images. ROC curve analysis on lung nodules with lung cancer showed no significant difference between the two. Compressed CR images using the type III irreversible technique are clinically applicable and acceptable despite slight degradation of image quality.     

On comparing methods for discriminating between actually negative and actually positive subjects with FROC type data

The task of searching and detecting multiple abnormalities depicted on an image, or a series of images, is a common problem in different areas such as military target detection or diagnostic medical imaging. A free response receiver operating characteristic (FROC) approach for assessing performance in many of these scenarios entails marking the locations of suspected abnormalities and indicating a level of suspicion at each of the marked locations. One of the important characteristics of a system being evaluated under the FROC paradigm is its performance in the conventional ROC domain, namely classifying a subject (or a unit of interest) as "negative" or "positive" in regard to the presence of the abnormality (or any of the abnormalities) of interest. With FROC data we can compare subjects by specifying a function of multiple scores within a subject. This approach allows formulating subject-based ROC type indices that can be estimated using existing ROC concepts. In this article we focus on indices that reflect the ability of the system to discriminate between actually negative and actually positive subjects. We consider a previously proposed index that is based on the comparison of the highest scores on subjects and two new indices that are based on potentially more stable comparison functions, namely comparison of average scores and stochastic dominance. Based on these indices we develop nonparametric procedures for comparing subject-based discriminative ability of diagnostic systems being evaluated under the FROC paradigm. We also investigate the properties of the statistical procedures in a simulation study.     

A Metric for Reducing False Positives in the Computer-Aided Detection of Breast Cancer from Dynamic Contrast-Enhanced Magnetic Resonance Imaging Based Screening Examinations of High-Risk Women

Magnetic resonance imaging (MRI)-enabled cancer screening has been shown to be a highly sensitive method for the early detection of breast cancer. Computer-aided detection systems have the potential to improve the screening process by standardizing radiologists to a high level of diagnostic accuracy. This retrospective study was approved by the institutional review board of Sunnybrook Health Sciences Centre. This study compares the performance of a proposed method for computer-aided detection (based on the second-order spatial derivative of the relative signal intensity) with the signal enhancement ratio (SER) on MRI-based breast screening examinations. Comparison is performed using receiver operating characteristic (ROC) curve analysis as well as free-response receiver operating characteristic (FROC) curve analysis. A modified computer-aided detection system combining the proposed approach with the SER method is also presented. The proposed method provides improvements in the rates of false positive markings over the SER method in the detection of breast cancer (as assessed by FROC analysis). The modified computer-aided detection system that incorporates both the proposed method and the SER method yields ROC results equal to that produced by SER while simultaneously providing improvements over the SER method in terms of false positives per noncancerous exam. The proposed method for identifying malignancies outperforms the SER method in terms of false positives on a challenging dataset containing many small lesions and may play a useful role in breast cancer screening by MRI as part of a computer-aided detection system.     

Registration of central paths and colonic polyps between supine and prone scans in computed tomography colonography: pilot study

Computed tomography colonography (CTC) is a minimally invasive method that allows the evaluation of the colon wall from CT sections of the abdomen/pelvis. The primary goal of CTC is to detect colonic polyps, precursors to colorectal cancer. Because imperfect cleansing and distension can cause portions of the colon wall to be collapsed, covered with water, and/or covered with retained stool, patients are scanned in both prone and supine positions. We believe that both reading efficiency and computer aided detection (CAD) of CTC images can be improved by accurate registration of data from the supine and prone positions. We developed a two-stage approach that first registers the colonic central paths using a heuristic and automated algorithm and then matches polyps or polyp candidates (CAD hits) by a statistical approach. We evaluated the registration algorithm on 24 patient cases. After path registration, the mean misalignment distance between prone and supine identical anatomic landmarks was reduced from 47.08 to 12.66 mm, a 73% improvement. The polyp registration algorithm was specifically evaluated using eight patient cases for which radiologists identified polyps separately for both supine and prone data sets, and then manually registered corresponding pairs. The algorithm correctly matched 78% of these pairs without user input. The algorithm was also applied to the 30 highest-scoring CAD hits in the prone and supine scans and showed a success rate of 50% in automatically registering corresponding polyp pairs. Finally, we computed the average number of CAD hits that need to be manually compared in order to find the correct matches among the top 30 CAD hits. With polyp registration, the average number of comparisons was 1.78 per polyp, as opposed to 4.28 comparisons without polyp registration.