An SVM classifier to separate false signals from microcalcifications in digital mammograms.

In this paper we investigate the feasibility of using an SVM (support vector machine) classifier in our automatic system for the detection of clustered microcalcifications in digital mammograms. SVM is a technique for pattern recognition which relies on the statistical learning theory. It minimizes a function of two terms: the number of misclassified vectors of the training set and a term regarding the generalization classifier capability. We compare the SVM classifier with an MLP (multi-layer perceptron) in the false-positive reduction phase of our detection scheme: a detected signal is considered either microcalcification or false signal, according to the value of a set of its features. The SVM classifier gets slightly better results than the MLP one (Az value of 0.963 against 0.958) in the presence of a high number of training data; the improvement becomes much more evident (Az value of 0.952 against 0.918) in training sets of reduced size. Finally, the setting of the SVM classifier is much easier than the MLP one.

Breast cancer metastases are molecularly distinct from their primary tumors.

Metastases have been widely thought to arise from rare, selected, mutation-bearing cells in the primary tumor. Recently, however, it has been proposed that breast tumors are imprinted ab initio with metastatic ability. Thus, there is a debate over whether 'phenotypic' disease progression is really associated with 'molecular' progression. We profiled 26 matched primary breast tumors and lymph node metastases and identified 270 probesets that could discriminate between the two categories. We then used an independent cohort of breast tumors (81 samples) and unmatched distant metastases (32 samples) to validate and refine this list down to a 126-probeset list. A representative subset of these genes was subjected to analysis by in situ hybridization, on a third independent cohort (57 primary breast tumors and matched lymph node metastases). This not only confirmed the expression profile data, but also allowed us to establish the cellular origin of the signals. One-third of the analysed representative genes (4 of 11) were expressed by the epithelial component. The four epithelial genes alone were able to discriminate primary breast tumors from their metastases. Finally, engineered alterations in the expression of two of the epithelial genes (SERPINB5 and LTF) modified cell motility in vitro, in accordance with a possible causal role in metastasis. Our results show that breast cancer metastases are molecularly distinct from their primary tumors.

LGANN: a parallel system combining a local genetic algorithm and neural networks for the prediction of secondary structure of proteins.

In this work we describe a parallel system consisting of feed-forward neural networks supervised by a local genetic algorithm. The system is implemented in a transputer architecture and is used to predict the secondary structures of globular proteins. This method allows a wide search in the parameter space of the neural networks and the determination of their optimal topology for the predictive task. Different neural network topologies are selected by the genetic algorithm on the basis of minimal values of mean square errors on the testing set. When the alpha-helix, beta-strand and random coil motifs of secondary structures are discriminated, the maximal efficiency obtained is 0.62, with correlation coefficients of 0.35, 0.31 and 0.37 respectively. This level of accuracy is similar to that previously attained by means of neural networks without hidden layers and using single protein sequences as input. The results validate the neural network topologies used for the prediction of protein secondary structures and highlight the relevance of the input information in determining the limit of their performance.