16963 FFDM cases (280 cancers), were culled retrospectively and run with a CAD algorithm. Instead of using CAD as a "second reader", the study investigates the feasibility of using CAD for prescreening, allowing cases with no CAD prompts to bypass review, thereby decreasing the workload. The study also investigates the outcome of presorting all cases with matching CAD marks of the same type in both views, to enrich the case mix, thereby enhancing the reader’s willingness to accept true CAD prompts. The sensitivity of the CAD algorithm was 83.4% and the mean false mark rate generated by CAD per case was 1.15. It was found that prescreening decreases the workload by about 42%, but is not feasible since 6.4% of the cancers would be missed. Using presorting, 73.2 % of the cancers and only 14.2% of the normals would be prioritized for interpretation, enriching the case mix by 5 times.

234 pathology-proven FFDM malignant cases and 3872 normal cases were culled retrospectively from 6 screening facilities. For malignant cases, location and size of the biopsied finding and breast density were recorded. All cases were run with a prototype CAD algorithm (Siemens) to evaluate the impact of breast density, lesion size and lesion pathology on CAD performance. The overall CAD sensitivity was 84.2

This paper deals with learning spiculation scores of masses in a supervised manner. Three spiculation score prediction models treating the score either as a continuous or ordinary variable are presented. These models were compared on a data-set of 255 masses.

This study evaluates the performance of an advanced CAD algorithm that is capable of filtering detection marks by level-of-suspicion. The detection of small invasive cancers, which has the greatest impact on breast cancer survival, was investigated. The advanced algorithm (Siemens) permits the radiologist to toggle back and forth between different levels of filtering, and focus on the detection marks that appear or disappear as findings with lower or higher levels of suspicion are displayed. The performance of the algorithm at three levels of filtering was evaluated, by lesion size and breast composition. 149 malignant cases with 151 masses (60 small masses) and 528 normal cases were analyzed. When the highest level of filtering was applied, and only findings most indicative of malignancy were displayed, the number of false masses was markedly reduced by 37.8%, while the detection sensitivity for masses was slightly reduced from 84.8% to 80.1%, and similarly, the detection sensitivity for small masses in dense breast decreased from 69.6% to 65.2%. In conclusion, when using an algorithm with filtering capabilities, designed to draw radiologists' attention to prompts most indicative of malignancy, the substantial reduction in false marks offsets the slight reduction in the detection sensitivity. Reducing the false mark rate by altering the level of filtering of the CAD prompts, does not have a selectively adverse impact on the detection sensitivity of small masses.

This study evaluates the performance of a new generation algorithm designed to both increase detection sensitivity of cancers and to markedly reduce the false mark rate. In the advanced algorithm, several improvements were implemented. The algorithm for the initial detection of potential mass candidates was upgraded to ignore dense areas that do not represent masses. For the initial detection of potential clusters candidates, the advanced algorithm considers interdependence between various stages of the parametric clusterization process and implements automatic performance optimization. Moreover, the advanced algorithm includes a one-step global classification model, which assigns a score to each candidate lesion, instead of sequential multi-step filtration at various steps of the algorithm. Both the advanced and the previous algorithm were run on 83 malignant cases, with proven pathology, and on 523 normal screening cases that were consecutively culled from 4 clinical sites. The overall sensitivity of the advanced algorithm was 86%, compared to a sensitivity of 84% for the previous one. The false mark (FM) rate per case, decreased from 3.20 for the previous algorithm, to 1.39 for the advanced one. The advanced algorithm reduced both mass FMs and cluster FMs. In conclusion, the new algorithm outperforms the old one with a slight increase in sensitivity and with a substantial reduction in false mark rate for both masses and clusters.

We propose a novel multiple-instance learning (MIL) algorithm for designing classifiers for use in computer aided detection (CAD). The proposed algorithm has 3 advantages over classical methods. First, unlike traditional learning algorithms that minimize the candidate level misclassification error, the proposed algorithm directly optimizes the patient-wise sensitivity. Second, this algorithm automatically selects a small subset of statistically useful features. Third, this algorithm is very fast, utilizes all of the available training data (without the need for cross-validation etc.), and requires no human hand tuning or intervention. Experimentally the algorithm is more accurate than state of the art support vector machine (SVM) classifier, and substantially reduces the number of features that have to be computed.

The purpose of this study was to investigate feasibility of computer-aided detection of masses and calcification clusters in breast tomosynthesis images and obtain reliable estimates of sensitivity and false positive rate on an independent test set. Automatic mass and calcification detection algorithms developed for film and digital mammography images were applied without any adaptation or retraining to tomosynthesis projection images. Test set contained 36 patients including 16 patients with 20 known malignant lesions, 4 of which were missed by the radiologists in conventional mammography images and found only in retrospect in tomosynthesis. Median filter was applied to tomosynthesis projection images. Detection algorithm yielded 80% sensitivity and 5.3 false positives per breast for calcification and mass detection algorithms combined. Out of 4 masses missed by radiologists in conventional mammography images, 2 were found by the mass detection algorithm in tomosynthesis images.

Computer aided detection systems for mammography typically use standard classification algorithms from machine learning for detecting lesions. However, these general purpose learning algorithms make implicit assumptions that are commonly violated in CAD problems. We propose a new ensemble algorithm that explicitly accounts for the small fraction of outlier images which tend to produce a large number of false positives. A bootstrapping procedure is used to ensure that the candidates from these outlier images do not skew the statistical properties of the training samples. Experimental studies on the detection of clusters of micro-calcifications indicate that the proposed method significantly outperforms a state-of-the-art general purpose method for designing classifiers (SVM), in terms of FROC curves on a hold out test set.