This study was conducted to retrospectively evaluate the variation of CAD performance utilizing two different FFDM systems in normal clinical cases.

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.

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.

Computer-aided diagnosis (CAD) systems usually require information about regions of interest in images, like: lungs (for nodule detection), colon (for identifying polyps), etc. Many times, it is computationally intensive to process large data sets as in CT to find these areas of interest. A fast and accurate recognition of the different regions of interest in the human body from images is therefore necessary. In this paper we propose a fast and efficient algorithm that can detect the organs of interest in a CT volume and estimate their sizes. Instead of analyzing the whole 3D volume; which is computationally expensive, a binary search technique is adapted to search in a few slices. The slices selected in the search process is segmented and different regions are labeled. Decision over whether the image belongs to a lung or colon or both is based on the count of lung/colon pixels in the slice. Once the detection is done we look for the start and end slice of the body part to have an estimate of their sizes. The algorithm involves certain search decisions based on some predefined threshold values which are empirically chosen from a training data set. The effectiveness of our technique is confirmed by applying it on an independent test data set. Detection accuracy of 100% is obtained on a test set. This algorithm can be integrated in a CAD system for running the right application, or can be used in pre-sets for visualization purposes and other post-processing like image registration etc.

Advances in medical technology have greatly increased information density for imaging studies. This may result from increased spatial resolution facilitating greater anatomical detail, increased contrast resolution allowing evaluation of more subtle structures than previously possible, or increased temporal image acquisition rate. However, such technological advances, while potentially improving the diagnostic benefits of a study, may result in ―data overload‖ while processing this information. This often manifests as increased total study time, defined as the combination of acquisition, processing and interpretation times; even more critically, the vast increase in data does not always translate to improved diagnosis/treatment selection. This paper describes a related series of clinically motivated data mining products that extract the key, actionable information from the vast amount of imaging data in order to ensure an improvement in patient care (via more accurate/early diagnosis) and a simultaneous reduction in total study time. Several thousand units of the products described in this paper have been commercially deployed in hospitals around the world since 2004. While each application targets a specific clinical task, they share the common methodology of transforming raw imaging data, through knowledge-based data mining algorithms, into clinically relevant information. This enables users to spend less time interacting with an image volume to extract the clinical information it contains, while supporting improved diagnostic accuracy. Although image processing plays an equally critical role in these software, this paper focuses primarily on the data mining challenges involved in developing commercial products. General Terms Algorithms, Measurement, Performance, Experimentation.

Chest X-ray (CXR) data is a 2D projection image. The main drawback of such an image is that each pixel of it represents a volumetric integration. This poses a challenge in detection and estimation of nodules and their characteristics. Due to human anatomy there are a lot of lung structures which can be falsely identified as nodules in a projection data. Detection of nodules with a large number of false positives (FP) adds more work for the radiologists. With the help of CAD algorithms we aim to identify regions which cause higher FP readings or provide additional information for nodule detection based on the human anatomy. Different lung regions have different image characteristics we take advantage of this and propose an automatic lung partitioning into vessel, apical, basal and exterior pulmonary regions. Anatomical landmarks like aortic arch and end of cardiac-notch along-with inter intra-rib width and their shape characteristics were used for this partitioning. Likelihood of FPs is more in vessel, apical and exterior pulmonary regions due to rib-crossing, overlap of vessel with rib and vessel branching. For each of these three cases, special features were designed based on histogram of rib slope and the structural properties of rib segments information. These features were assigned different weights based on the partitioning. An experiment was carried out using a prototype CAD system 150 routine CXR studies were acquired from three institutions (24 negatives, rest with one or more nodules). Our algorithm provided a sensitivity of 70.4% with 5 FP/image for cross-validation without partition. Inclusion of the proposed techniques increases the sensitivity to 78.1% with 4.1 FP/image.

Chest X-ray (CXR) data is a projection image where each pixel of it represents a volumetric integration. Consequently identification of nodules and their characteristics is a difficult task in such images. Using a novel application of random process-based fractal image processing technique we extract features for nodule characterization. The uniqueness of the proposed technique lies in the fact that instead of relying on apriori information from user as in other random process inspired measures, we translate the random walk process into a feature which is based on its realization values. The Normalized Fractional Brownian Motion (NFBM) Model is derived from the random walk process. Using neighborhood region information in an incremental manner we can characterize the smoothness or roughness of a surface. The NFBM system gives a measure of roughness of a surface which in our case is a suspicious region (probable nodule). A classification procedure uses this measure to categorize nodule and non-nodule structures in the lung. The NFBM feature set is integrated in a prototype CAD system for nodule detection in CXR. Our algorithm provided a sensitivity of 75.9% with 3.1 FP/image on an independent test set of 50 CXR studies.

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.

A novel method called local shape controlled voting has been developed for spherical object detection in 3D voxel images. By introducing local shape properties into the voting procedure of normal overlap, the proposed method improves the capability of differentiating spherical objects from other structures, as the normal overlap technique only measures the `density' of normal overlapping, while how the normals are distributed in 3D is not discovered. The proposed method was applied to computer aided detection of pulmonary nodules based on helical CT images. Experiments showed that this method attained a better performance compared to the original normal overlap technique.

Alzheimer’s disease is the most frequent type of dementia for elderly patients. Due to aging populations, the occurrence of this disease will increase in the next years. Early diagnosis is crucial to be able to develop more powerful treatments. Brain perfusion changes can be a marker for Alzheimer’s disease. In this article, we study the use of SPECT perfusion imaging for the diagnosis of Alzheimer’s disease differentiating between images from healthy subjects and images from Alzheimer’s disease patients. Our classification approach is based on a linear programming formulation similar to the 1-norm support vector machines. In contrast with other linear hyperplane-based methods that perform simultaneous feature selection and classification, our proposed formulation incorporates proximity information about the features and generates a classifier that does not just select the most relevant voxels but the most relevant “areas” for classification resulting in more robust classifiers that are better suitable for interpretation. This approach is compared with the classical Fisher linear discriminant (FLD) classifier as well as with statistical parametric mapping (SPM). We tested our method on data from four European institutions. Our method achieved sensitivity of 84.4% at 90.9% specificity, this is considerable better the human experts. Our method also outperformed the FLD and SPM techniques. We conclude that our approach has the potential to be a useful help for clinicians.