Knowledge-based computer-aided detection of masses on digitized mammograms: a preliminary assessment

A New GLLD Operator for Mass Detection in Digital Mammograms

During the last decade, several works have dealt with computer automatic diagnosis (CAD) of masses in digital mammograms. Generally, the main difficulty remains the detection of masses. This work proposes an efficient methodology for mass detection based on a new local feature extraction. Local binary pattern (LBP) operator and its variants proposed by Ojala are a powerful tool for textures classification. However, it has been proved that such operators are not able to model at their own texture masses. We propose in this paper a new local pattern model named gray level and local difference (GLLD) where we take into consideration absolute gray level values as well as local difference as local binary features. Artificial neural networks (ANNs), support vector machine (SVM), and k-nearest neighbors (kNNs) are, then, used for classifying masses from nonmasses, illustrating better performance of ANN classifier. We have used 1000 regions of interest (ROIs) obtained from the Digital Database for Screening Mammography (DDSM). The area under the curve of the corresponding approach has been found to be A(z) = 0.95 for the mass detection step. A comparative study with previous approaches proves that our approach offers the best performances.

Automated breast mass detection in 3D reconstructed tomosynthesis volumes: a featureless approach

The purpose of this study was to propose and implement a computer aided detection (CADe) tool for breast tomosynthesis. This task was accomplished in two stages-a highly sensitive mass detector followed by a false positive (FP) reduction stage. Breast tomosynthesis data from 100 human subject cases were used, of which 25 subjects had one or more mass lesions and the rest were normal. For stage 1, filter parameters were optimized via a grid search. The CADe identified suspicious locations were reconstructed to yield 3D CADe volumes of interest. The first stage yielded a maximum sensitivity of 93% with 7.7 FPs/breast volume. Unlike traditional CADe algorithms in which the second stage FP reduction is done via feature extraction and analysis, instead information theory principles were used with mutual information as a similarity metric. Three schemes were proposed, all using leave-one-case-out cross validation sampling. The three schemes, A, B, and C, differed in the composition of their knowledge base of regions of interest (ROIs). Scheme A's knowledge base was comprised of all the mass and FP ROIs generated by the first stage of the algorithm. Scheme B had a knowledge base that contained information from mass ROIs and randomly extracted normal ROIs. Scheme C had information from three sources of information-masses, FPs, and normal ROIs. Also, performance was assessed as a function of the composition of the knowledge base in terms of the number of FP or normal ROIs needed by the system to reach optimal performance. The results indicated that the knowledge base needed no more than 20 times as many FPs and 30 times as many normal ROIs as masses to attain maximal performance. The best overall system performance was 85% sensitivity with 2.4 FPs per breast volume for scheme A, 3.6 FPs per breast volume for scheme B, and 3 FPs per breast volume for scheme C.

Selection of examples in case-based computer-aided decision systems

Case-based computer-aided decision (CB-CAD) systems rely on a database of previously stored, known examples when classifying new, incoming queries. Such systems can be particularly useful since they do not need retraining every time a new example is deposited in the case base. The adaptive nature of case-based systems is well suited to the current trend of continuously expanding digital databases in the medical domain. To maintain efficiency, however, such systems need sophisticated strategies to effectively manage the available evidence database. In this paper, we discuss the general problem of building an evidence database by selecting the most useful examples to store while satisfying existing storage requirements. We evaluate three intelligent techniques for this purpose: genetic algorithm-based selection, greedy selection and random mutation hill climbing. These techniques are compared to a random selection strategy used as the baseline. The study is performed with a previously presented CB-CAD system applied for false positive reduction in screening mammograms. The experimental evaluation shows that when the development goal is to maximize the system's diagnostic performance, the intelligent techniques are able to reduce the size of the evidence database to 37% of the original database by eliminating superfluous and/or detrimental examples while at the same time significantly improving the CAD system's performance. Furthermore, if the case-base size is a main concern, the total number of examples stored in the system can be reduced to only 2-4% of the original database without a decrease in the diagnostic performance. Comparison of the techniques shows that random mutation hill climbing provides the best balance between the diagnostic performance and computational efficiency when building the evidence database of the CB-CAD system.

Decision optimization of case-based computer-aided decision systems using genetic algorithms with application to mammography

This paper presents an optimization framework for improving case-based computer-aided decision (CB-CAD) systems. The underlying hypothesis of the study is that each example in the knowledge database of a medical decision support system has different importance in the decision making process. A new decision algorithm incorporating an importance weight for each example is proposed to account for these differences. The search for the best set of importance weights is defined as an optimization problem and a genetic algorithm is employed to solve it. The optimization process is tailored to maximize the system's performance according to clinically relevant evaluation criteria. The study was performed using a CAD system developed for the classification of regions of interests (ROIs) in mammograms as depicting masses or normal tissue. The system was constructed and evaluated using a dataset of ROIs extracted from the Digital Database for Screening Mammography (DDSM). Experimental results show that, according to receiver operator characteristic (ROC) analysis, the proposed method significantly improves the overall performance of the CAD system as well as its average specificity for high breast mass detection rates.

Information-theoretic CAD system in mammography: Entropy-based indexing for computational efficiency and robust performance

We have previously presented a knowledge-based computer-assisted detection (KB-CADe) system for the detection of mammographic masses. The system is designed to compare a query mammographic region with mammographic templates of known ground truth. The templates are stored in an adaptive knowledge database. Image similarity is assessed with information theoretic measures (e.g., mutual information) derived directly from the image histograms. A previous study suggested that the diagnostic performance of the system steadily improves as the knowledge database is initially enriched with more templates. However, as the database increases in size, an exhaustive comparison of the query case with each stored template becomes computationally burdensome. Furthermore, blind storing of new templates may result in redundancies that do not necessarily improve diagnostic performance. To address these concerns we investigated an entropy-based indexing scheme for improving the speed of analysis and for satisfying database storage restrictions without compromising the overall diagnostic performance of our KB-CADe system. The indexing scheme was evaluated on two different datasets as (i) a search mechanism to sort through the knowledge database, and (ii) a selection mechanism to build a smaller, concise knowledge database that is easier to maintain but still effective. There were two important findings in the study. First, entropy-based indexing is an effective strategy to identify fast a subset of templates that are most relevant to a given query. Only this subset could be analyzed in more detail using mutual information for optimized decision making regarding the query. Second, a selective entropy-based deposit strategy may be preferable where only high entropy cases are maintained in the knowledge database. Overall, the proposed entropy-based indexing scheme was shown to reduce the computational cost of our KB-CADe system by 55% to 80% while maintaining the system's diagnostic performance.

False positive reduction in mammographic mass detection using local binary patterns

In this paper we propose a new approach for false positive reduction in the field of mammographic mass detection. The goal is to distinguish between the true recognized masses and the ones which actually are normal parenchyma. Our proposal is based on Local Binary Patterns (LBP) for representing salient micro-patterns and preserving at the same time the spatial structure of the masses. Once the descriptors are extracted, Support Vector Machines (SVM) are used for classifying the detected masses. We test our proposal using a set of 1792 suspicious regions of interest extracted from the DDSM database. Exhaustive experiments illustrate that LBP features are effective and efficient for false positive reduction even at different mass sizes, a critical aspect in mass detection systems. Moreover, we compare our proposal with current methods showing that LBP obtains better performance.

Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis

Computer-aided diagnostic (CAD) schemes have been developed to assist radiologists detect various lesions in medical images. In CAD schemes, classifiers play a key role in achieving a high lesion detection rate and a low false-positive rate. Although many popular classifiers such as linear discriminant analysis and artificial neural networks have been employed in CAD schemes for reduction of false positives, a rule-based classifier has probably been the simplest and most frequently used one since the early days of development of various CAD schemes. However, with existing rule-based classifiers, there are major disadvantages that significantly reduce their practicality and credibility. The disadvantages include manual design, poor reproducibility, poor evaluation methods such as resubstitution, and a large overtraining effect. An automated rule-based classifier with a minimized overtraining effect can overcome or significantly reduce the extent of the above-mentioned disadvantages. In this study, we developed an "optimal" method for the selection of cutoff thresholds and a fully automated rule-based classifier. Experimental results performed with Monte Carlo simulation and a real lung nodule CT data set demonstrated that the automated threshold selection method can completely eliminate overtraining effect in the procedure of cutoff threshold selection, and thus can minimize overall overtraining effect in the constructed rule-based classifier. We believe that this threshold selection method is very useful in the construction of automated rule-based classifiers with minimized overtraining effect.

Computer aid for decision to biopsy breast masses on mammography: validation on new cases

RATIONALE AND OBJECTIVES

The purpose of this study was to validate the performance of a previously developed computer aid for breast mass classification for mammography on a new, independent database of cases not used for algorithm development.

MATERIALS AND METHODS

A computer aid (classifier) based on the likelihood ratio (LRb) was previously developed on a database of 670 mass cases. The 670 cases (245 malignant) from one medical institution were described using 16 features from the American College of Radiology Breast Imaging-Reporting and Data System lexicon and patient history findings. A separate database of 151 (43 malignant) validation cases were collected that were previously unseen by the classifier. These new validation cases were evaluated by the classifier without retraining. Performance evaluation methods included Receiver Operating Characteristic (ROC), round-robin, and leave-one-out bootstrap sampling.

RESULTS

The performance of the classifier on the training data yielded an average ROC area of 0.90 +/- 0.02 and partial ROC area (0.90AUC) of 0.60 +/- 0.06. The exact nonparametric performance on the validation set of 151 cases yielded a ROC area of 0.88 and 0.90AUC of 0.57. Using a 100% sensitivity cutoff threshold established on the training data (100% negative predictive value), the classifier correctly identified 100% of the malignant masses in the validation test set, while potentially obviating 26% of the biopsies performed on benign masses.

CONCLUSION

The LRb classifier performed consistently on new data that was not used for classifier development. The LRb classifier shows promise as a potential aid in reducing the number of biopsies performed on benign masses.

Tolerance to missing data using a likelihood ratio based classifier for computer-aided classification of breast cancer

While mammography is a highly sensitive method for detecting breast tumours, its ability to differentiate between malignant and benign lesions is low, which may result in as many as 70% of unnecessary biopsies. The purpose of this study was to develop a highly specific computer-aided diagnosis algorithm to improve classification of mammographic masses. A classifier based on the likelihood ratio was developed to accommodate cases with missing data. Data for development included 671 biopsy cases (245 malignant), with biopsy-proved outcome. Sixteen features based on the BI-RADS lexicon and patient history had been recorded for the cases, with 1.3 +/- 1.1 missing feature values per case. Classifier evaluation methods included receiver operating characteristic and leave-one-out bootstrap sampling. The classifier achieved 32% specificity at 100% sensitivity on the 671 cases with 16 features that had missing values. Utilizing just the seven features present for all cases resulted in decreased performance at 100% sensitivity with average 19% specificity. No cases and no feature data were omitted during classifier development, showing that it is more beneficial to utilize cases with missing values than to discard incomplete cases that cannot be handled by many algorithms. Classification of mammographic masses was commendable at high sensitivity levels, indicating that benign cases could be potentially spared from biopsy.

Incorporation of an iterative, linear segmentation routine into a mammographic mass CAD system

In previous research, we have developed a computer-aided detection (CAD) system designed to detect masses in mammograms. The previous version of our system employed a simple but imprecise method to localize the masses. In this research, we present a more robust segmentation routine for use with mammographic masses. Our hypothesis is that by more accurately describing the morphology of the masses, we can improve the CAD system's ability to distinguish masses from other mammographic structures. To test this hypothesis, we incorporated the new segmentation routine into our CAD system and examined the change in performance. The developed iterative, linear segmentation routine is a gray level-based procedure. Using the identified regions from the previous CAD system as the initial seeds, the new segmentation algorithm refines the suspicious mass borders by making estimates of the interior and exterior pixels. These estimates are then passed to a linear discriminant, which determines the optimal threshold between the interior and exterior pixels. After applying the threshold and identifying the object's outline, two constraints on the border are applied to reduce the influence of background noise. After the border is constrained, the process repeats until a stopping criterion is reached. The segmentation routine was tested on a study database of 183 mammographic images extracted from the Digital Database for Screening Mammography. Eighty-three of the images contained 50 malignant and 50 benign masses; 100 images contained no masses. The previously developed CAD system was used to locate a set of suspicious regions of interest (ROIs) within the images. To assess the performance of the segmentation algorithm, a set of 20 features was measured from the suspicious regions before and after the application of the developed segmentation routine. Receiver operating characteristic (ROC) analysis was employed on the ROIs to examine the discriminatory capabilities of each individual feature before and after the segmentation routine. A statistically significant performance increase was found in many of the individual features, particularly those describing the mass borders. To examine how the incorporation of the segmentation routine affected the performance of the overall CAD system, free-response ROC (FROC) analysis was employed. When considering only malignant masses, the FROC performance of the system with the segmentation routine appeared better than the previous system. When detecting 90% of the malignant masses, the previous system achieved 4.9 false positives per image (FPpI) compared to the post-segmentation system's 4.2 FPpI. At 80% sensitivity, the respective FPpI were 3.5 and 1.6.

Computer-assisted detection of mammographic masses: a template matching scheme based on mutual information

The purpose of this study was to develop a knowledge-based scheme for the detection of masses on digitized screening mammograms. The computer-assisted detection (CAD) scheme utilizes a knowledge databank of mammographic regions of interest (ROIs) with known ground truth. Each ROI in the databank serves as a template. The CAD system follows a template matching approach with mutual information as the similarity metric to determine if a query mammographic ROI depicts a true mass. Based on their information content, all similar ROIs in the databank are retrieved and rank-ordered. Then, a decision index is calculated based on the query's best matches. The decision index effectively combines the similarity indices and ground truth of the best-matched templates into a prediction regarding the presence of a mass in the query mammographic ROI. The system was developed and evaluated using a database of 1465 ROIs extracted from the Digital Database for Screening Mammography. There were 809 ROIs with confirmed masses (455 malignant and 354 benign) and 656 normal ROIs. CAD performance was assessed using a leave-one-out sampling scheme and Receiver Operating Characteristics analysis. Depending on the formulation of the decision index, CAD performance as high as A(zeta) = 0.87 +/- 0.01 was achieved. The CAD detection rate was consistent for both malignant and benign masses. In addition, the impact of certain implementation parameters on the detection accuracy and speed of the proposed CAD scheme was studied in more detail.

Performance gain in computer-assisted detection schemes by averaging scores generated from artificial neural networks with adaptive filtering

The authors investigated a new method to optimize artificial neural networks (ANNs) with adaptive filtering used in computer-assisted detection schemes in digitized mammograms and to assess performance changes when averaging classification scores from three sets of optimized schemes. Two independent training and testing image databases involving 978 and 830 digitized mammograms, respectively, were used in this study. In the training data set, initial filtering and subtraction resulted in the identification of 592 mass regions and 3790 suspicious, but actually negative regions. These regions (including both true-positive and negative regions) were segmented into three subsets three times based on the calculation of the values of three features as segmentation indices. The indices were "mass" size multiplied by their digital value contrast, conspicuity, and circularity. Nine ANN-based classifiers were separately optimized using a genetic algorithm for each subset of regions. Each region was assigned three classification scores after applying the three adaptive ANNs. The performance gain of the CAD scheme after averaging the three scores for each suspicious region was tested using an independent data set and a ROC methodology. The experimental results showed that the areas under ROC curves (Az) for the testing database using three sets of optimized ANNs individually were 0.84+/-0.01, 0.83+/-0.01, and 0.84+/-0.01, respectively. The between-index correlations of three A values were 0.013, -0.007, and 0.086. Similar to averaging diagnostic ratings from independent observers, by averaging three ANN-generated scores for each testing region, the performance of the CAD scheme was significantly improved (p<0.001) with Az value of 0.95+/-0.01.