Comparative evaluation of support vector machine classification for computer aided detection of breast masses in mammography.

False positive (FP) marks represent an obstacle for effective use of computer-aided detection (CADe) of breast masses in mammography. Typically, the problem can be approached either by developing more discriminative features or by employing different classifier designs. In this paper, the usage of support vector machine (SVM) classification for FP reduction in CADe is investigated, presenting a systematic quantitative evaluation against neural networks, k-nearest neighbor classification, linear discriminant analysis and random forests. A large database of 2516 film mammography examinations and 73 input features was used to train the classifiers and evaluate for their performance on correctly diagnosed exams as well as false negatives. Further, classifier robustness was investigated using varying training data and feature sets as input. The evaluation was based on the mean exam sensitivity in 0.05-1 FPs on normals on the free-response receiver operating characteristic curve (FROC), incorporated into a tenfold cross validation framework. It was found that SVM classification using a Gaussian kernel offered significantly increased detection performance (P = 0.0002) compared to the reference methods. Varying training data and input features, SVMs showed improved exploitation of large feature sets. It is concluded that with the SVM-based CADe a significant reduction of FPs is possible outperforming other state-of-the-art approaches for breast mass CADe.

Clinical responses to ventricular assistance versus transplantation in a series of bridge to transplant patients.

Hemodynamic and peripheral organ responses to ventricular assistance were compared with transplantation in a cohort of patients bridged with the HeartMate 1000 IP left ventricular assist device (LVAD) (Thermo Cardiosystems Inc., Woburn, MA). The study population included 27 patients that were supported an average of 102 days (range, 15-324 days). Two hepatic (total bilirubin and serum glutamic oxaloacetic transaminase [SGOT]) and two renal (creatinine and blood urea nitrogen [BUN]) parameters were measured: 1) before LVAD insertion, 2) 30 and 60 days during ventricular assistance, 3) before transplantation while still on the VAD, and 4) 30 and 60 days after transplantation. Total bilirubin values were significantly greater just before LVAD implant (2.3 mg/dl) than before transplantation (0.7 mg/dl). Although there was no difference after 30 days of either treatment, the total bilirubin values were greater at 60 days after transplantation (1.1 mg/dl) than at an equivalent time on the LVAD (0.6 mg/dl). The SGOT values were also significantly reduced before transplantation. No differences at 30 and 60 days after either procedure were noticed. Creatinine and BUN values were greater before LVAD implant (1.7 and 37 mg/dl) than before transplantation (1.2 and 19 mg/dl). The creatinine values were also greater after transplantation at 30 and 60 days (2.0 and 1.6 mg/dl) than at comparable intervals after LVAD implantation (1.0 and 1.2 mg/dl), presumably as a result of the use of immunosuppressive drugs. End organ function was markedly improved while on the device, enhancing the physiologic status of the patients before transplantation.(ABSTRACT TRUNCATED AT 250 WORDS)