Applying modular classifiers to mammographic mass classification.

Classification is the last step in the computer aided diagnosis (CAD) system for determining whether a breast mass segmented from a digital mammogram is malignant or benign. Hence it is important to improve sensitivity at this stage. This work investigates the use of modular classifier (MoC) schemes, namely bagging and adaboost algorithms, for automated classification of mammographic masses. CAD systems containing a MoC are compared to CAD systems that contain traditional classifiers (TrC), for example single nearest mean or maximum likelihood classifiers. This study included 200 digitized mammograms, each manually segmented by a radiologist. In order to test the MoC and TrC approaches, conventional shape based features were extracted from the segmented masses. These features were then optimized using Fischer's linear discriminant analysis (LDA). When no LDA was utilized, it was observed that MoC schemes increased the sensitivity from 74% to 83% over the TrC approaches. After performing LDA, the sensitivity increased from 83% to 88% for TrC and MoC schemes, respectively.

Blunt renal artery injury: incidence, diagnosis, and management.

Renal artery injury is a rare complication of blunt abdominal trauma. Increasing use of CT scans to evaluate blunt abdominal trauma identifies more blunt renal artery injuries (BRAIs) that may have otherwise been missed. We identified patients with BRAI to examine the incidence and to evaluate the current diagnosis and management strategies. Patients admitted from 1986 to 2000 at a regional Level I trauma center sustaining BRAI were evaluated. Patients undergoing revascularization or nonoperative management were followed for renovascular hypertension. Twenty-eight patients with BRAI were identified out of 36,938 blunt trauma admissions between 1986 and 2000 (incidence 0.08%). Most renal artery injuries were diagnosed by CT scans (93%) with seven confirmatory angiograms. Nine patients had nephrectomy (one bilateral), and three patients with unilateral injuries were revascularized. Sixteen were managed nonoperatively including one patient who had endovascular stent placement. Three patients died from shock and sepsis. Follow-up for all patients ranged from one month to 8 years. Two patients developed hypertension: one who was revascularized (33%) and one was managed nonoperatively (6%). The frequency of diagnosis of BRAI is increasing because of the increased use of CT. Nonoperative management of unilateral injuries can be successful with a 6 per cent risk for developing renovascular hypertension. The role of endovascular stenting is promising, and further study is necessary.

Classifying mammographic mass shapes using the wavelet transform modulus-maxima method.

In this article, multiresolution analysis, specifically the discrete wavelet transform modulus-maxima (mod-max) method, is utilized for the extraction of mammographic mass shape features. These shape features are used in a classification system to classify masses as round, nodular, or stellate. The multiresolution shape features are compared with traditional uniresolution shape features for their class discriminating abilities. The study involved 60 digitized mammographic images. The masses were segmented manually by radiologists, prior to introduction to the classification system. The uniresolution and multiresolution shape features were calculated using the radial distance measure of the mass boundaries. The discriminating power of the shape features were analyzed via linear discriminant analysis (LDA). The classification system utilized a simple Euclidean metric to determine class membership. The system was tested using the apparent and leave-one-out test methods. The classification system when using the multiresolution and uniresolution shape features resulted in classification rates of 83% and 80% for the apparent and leave-one-out test methods, respectively. In comparison, when only the uniresolution shape features were used, the classification rates were 72 and 68% for the apparent and leave-one-out test methods, respectively.

Beliefs in realistic and unrealistic control: assessment and implications.

Scales were constructed to measure perceived control over controllable events (realistic control) and perceived control over uncontrollable events (unrealistic control). Internal reliability, test-retest reliability, and discriminant validity of both scales were adequate. Study 1 measured perceived personal control over hassles that judges rated on general controllability. For hassles very high in controllability, perceived personal control was related to belief in realistic control but not to belief in unrealistic control; for hassles very low in controllability, perceived personal control was related to belief in unrealistic control but not to belief in realistic control. Study 2 showed that participants high in unrealistic control belief (but not those high in realistic control belief) persevered more on a task that was in part uncontrollable. Study 3 showed that the combination of low realistic control belief and high unrealistic control belief predicted poorer future health, particularly for participants who have reported the experience of many negative events and/or hassles. The conditions under which unrealistic control results in maladaptive outcomes are discussed.

Effect of fixation time on measurement of 2'-deoxyribonucleoside 5'-triphosphate pools in the rat embyro.

Values for the concentrations of deoxyribonucleoside triphosphates in rat embryos on day 12 of gestation, determined by high-pressure liquid chromatography, were artifactually two to three times as high in embryos fixed by cooling in ice/water followed by freezing on solid CO2, in 20s, as in those more rapidly/fixed in liquid N2, in 1 s.