No abstract

Mammography is considered the most effective method for early detection of breast cancers. However, it is difficult for radiologists to detect microcalcification clusters. Therefore, we have developed a computerized scheme for detecting early-stage microcalcification clusters in mammograms. We first developed a novel filter bank based on the concept of the Hessian matrix for classifying nodular structures and linear structures. The mammogram images were decomposed into several subimages for second difference at scales from 1 to 4 by this filter bank. The subimages for the nodular component (NC) and the subimages for the nodular and linear component (NLC) were then obtained from analysis of the Hessian matrix. Many regions of interest (ROIs) were selected from the mammogram image. In each ROI, eight features were determined from the subimages for NC at scales from 1 to 4 and the subimages for NLC at scales from 1 to 4. The Bayes discriminant function was employed for distinguishing among abnormal ROIs with a microcalcification cluster and two different types of normal ROIs without a microcalcification cluster. We evaluated the detection performance by using 600 mammograms. Our computerized scheme was shown to have the potential to detect microcalcification clusters with a clinically acceptable sensitivity and low false positives.

No abstract

The histological classification of clustered microcalcifications on mammograms can be difficult, and thus often require biopsy or follow-up. Our purpose in this study was to develop a computer-aided diagnosis scheme for identifying the histological classification of clustered microcalcifications on magnification mammograms in order to assist the radiologists' interpretation as a "second opinion." Our database consisted of 58 magnification mammograms, which included 35 malignant clustered microcalcifications (9 invasive carcinomas, 12 noninvasive carcinomas of the comedo type, and 14 noninvasive carcinomas of the noncomedo type) and 23 benign clustered microcalcifications (17 mastopathies and 6 fibroadenomas). The histological classifications of all clustered microcalcifications were proved by pathologic diagnosis. The clustered microcalcifications were first segmented by use of a novel filter bank and a thresholding technique. Five objective features on clustered microcalcifications were determined by taking into account subjective features that experienced the radiologists commonly use to identify possible histological classifications. The Bayes decision rule with five objective features was employed for distinguishing between five histological classifications. The classification accuracies for distinguishing between three malignant histological classifications were 77.8% (7/9) for invasive carcinoma, 75.0% (9/12) for noninvasive carcinoma of the comedo type, and 92.9% (13/14) for noninvasive carcinoma of the noncomedo type. The classification accuracies for distinguishing between two benign histological classifications were 94.1% (16/17) for mastopathy, and 100.0% (6/6) for fibroadenoma. This computerized method would be useful in assisting radiologists in their assessments of clustered microcalcifications.

Recent psychophysical studies have demonstrated that periodic attention in the 4-8 Hz range facilitates performance on visual detection. The present study examined the periodicity of feature binding, another major function of attention, in human observers (3 females and 5 males for behavior, with 7 males added for the EEG experiment). In a psychophysical task, observers reported a synchronous pair of brightness (light/dark) and orientation (clockwise/counterclockwise) patterns from two combined brightness-orientation pairs presented in rapid succession. We found that temporal binding performance exhibits periodic oscillations at ϳ8 Hz as a function of stimulus onset delay from a self-initiated button press in conditions where brightness-orientation pairs were spatially separated. However, as one would expect from previous studies on pre-attentive binding, significant oscillations were not apparent in conditions where brightnessorientation pairs were spatially superimposed. EEG results, while fully compatible with behavioral oscillations, also revealed a significant dependence of binding performance across trials on prestimulus neural oscillatory phases within the corresponding band. The peak frequency of this dependence was found to be correlated with intertrial phase coherence (ITPC) around the timing of button press in parietal sensors. Moreover, the peak frequency of the ITPC was found to predict behavioral frequency in individual observers. Together, these results suggest that attention operates periodically (at ϳ8 Hz) on the perceptual binding of multimodal visual information and is mediated by neural oscillations phase-locked to voluntary action.