Universal autofocus for quantitative volumetric microscopy of whole mouse brains.

Unbiased quantitative analysis of macroscopic biological samples demands fast imaging systems capable of maintaining high resolution across large volumes. Here we introduce RAPID (rapid autofocusing via pupil-split image phase detection), a real-time autofocus method applicable in every widefield-based microscope. RAPID-enabled light-sheet microscopy reliably reconstructs intact, cleared mouse brains with subcellular resolution, and allowed us to characterize the three-dimensional (3D) spatial clustering of somatostatin-positive neurons in the whole encephalon, including densely labeled areas. Furthermore, it enabled 3D morphological analysis of microglia across the entire brain. Beyond light-sheet microscopy, we demonstrate that RAPID maintains high image quality in various settings, from in vivo fluorescence imaging to 3D tracking of fast-moving organisms. RAPID thus provides a flexible autofocus solution that is suitable for traditional automated microscopy tasks as well as for quantitative analysis of large biological specimens.

Betahistine dihydrochloride in the treatment of peripheral vestibular vertigo.

The present study compares the efficacy and safety of betahistine dihydrochloride to that of a placebo in recurrent vertigo resulting from Meniere's disease (MD) or in paroxysmal positional vertigo (PPV) of probable vascular origin. The design was double-blind, multicentre and parallel-group randomised. Eleven Italian centres enrolled 144 patients: 75 of the patients were treated with betahistine (41 MD/34 PPV) and 69 with placebos (40 MD/29 PPV). The betahistine dosage was 16 mg twice per day for 3 months. Compared to the placebo, betahistine had a significant effect on the frequency, intensity and duration of vertigo attacks. Associated symptoms and the quality of life also were significantly improved by betahistine. Both the physician's judgement and the patient's opinion on the efficacy and acceptability of the treatment were in agreement as to the superiority of betahistine. The effective and safe profile of betahistine in the treatment of vertigo due to peripheral vestibular disorders was confirmed.

Failures in snoring and OSAS surgery.

Significant reduction of snoring noise and valid prevention of neurological and/or cardiovascular complications of OSAS are the basic goals of all modern snoring and OSAS surgical procedures. Any kind of operation, single or multiple, included into a one-step or multistep programs, is said to fail if snoring is not reduced to a significant extent for the patient or if clinical and/or instrumental data after the operation show that Upper Airways Resistance Syndrome (UARS) or OSAS continues to be probably dangerous for the patient to some extent. The real figure of failures in different situations of sleep-disordered syndromes surgery is discussed, along with the possible explanations. A group of patients operated on for snoring and OSAS in our clinic is analyzed retrospectively from the subjective point of view and by means of sleep studies to get a precise quantitative and qualitative idea of the failed cases. The final goal would be to understand how it is possible to reduce to a minimal level the number of true failures.

Exploiting the past and the future in protein secondary structure prediction.

MOTIVATION: Predicting the secondary structure of a protein (alpha-helix, beta-sheet, coil) is an important step towards elucidating its three-dimensional structure, as well as its function. Presently, the best predictors are based on machine learning approaches, in particular neural network architectures with a fixed, and relatively short, input window of amino acids, centered at the prediction site. Although a fixed small window avoids overfitting problems, it does not permit capturing variable long-rang information. RESULTS: We introduce a family of novel architectures which can learn to make predictions based on variable ranges of dependencies. These architectures extend recurrent neural networks, introducing non-causal bidirectional dynamics to capture both upstream and downstream information. The prediction algorithm is completed by the use of mixtures of estimators that leverage evolutionary information, expressed in terms of multiple alignments, both at the input and output levels. While our system currently achieves an overall performance close to 76% correct prediction--at least comparable to the best existing systems--the main emphasis here is on the development of new algorithmic ideas. AVAILABILITY: The executable program for predicting protein secondary structure is available from the authors free of charge. CONTACT: pfbaldi@ics.uci.edu, gpollast@ics.uci.edu, brunak@cbs.dtu.dk, paolo@dsi.unifi.it.

A general framework for adaptive processing of data structures.

A structured organization of information is typically required by symbolic processing. On the other hand, most connectionist models assume that data are organized according to relatively poor structures, like arrays or sequences. The framework described in this paper is an attempt to unify adaptive models like artificial neural nets and belief nets for the problem of processing structured information. In particular, relations between data variables are expressed by directed acyclic graphs, where both numerical and categorical values coexist. The general framework proposed in this paper can be regarded as an extension of both recurrent neural networks and hidden Markov models to the case of acyclic graphs. In particular we study the supervised learning problem as the problem of learning transductions from an input structured space to an output structured space, where transductions are assumed to admit a recursive hidden statespace representation. We introduce a graphical formalism for representing this class of adaptive transductions by means of recursive networks, i.e., cyclic graphs where nodes are labeled by variables and edges are labeled by generalized delay elements. This representation makes it possible to incorporate the symbolic and subsymbolic nature of data. Structures are processed by unfolding the recursive network into an acyclic graph called encoding network. In so doing, inference and learning algorithms can be easily inherited from the corresponding algorithms for artificial neural networks or probabilistic graphical model.

Input-output HMMs for sequence processing.

We consider problems of sequence processing and propose a solution based on a discrete-state model in order to represent past context. We introduce a recurrent connectionist architecture having a modular structure that associates a subnetwork to each state. The model has a statistical interpretation we call input-output hidden Markov model (IOHMM). It can be trained by the estimation-maximization (EM) or generalized EM (GEM) algorithms, considering state trajectories as missing data, which decouples temporal credit assignment and actual parameter estimation. The model presents similarities to hidden Markov models (HMMs), but allows us to map input sequences to output sequences, using the same processing style as recurrent neural networks. IOHMMs are trained using a more discriminant learning paradigm than HMMs, while potentially taking advantage of the EM algorithm. We demonstrate that IOHMMs are well suited for solving grammatical inference problems on a benchmark problem. Experimental results are presented for the seven Tomita grammars, showing that these adaptive models can attain excellent generalization.

Computational capabilities of local-feedback recurrent networks acting as finite-state machines.

In this paper we explore the expressive power of recurrent networks with local feedback connections for symbolic data streams. We rely on the analysis of the maximal set of strings that can be shattered by the concept class associated to these networks (i.e. strings that can be arbitrarily classified as positive or negative), and find that their expressive power is inherently limited, since there are sets of strings that cannot be shattered, regardless of the number of hidden units. Although the analysis holds for networks with hard threshold units, we claim that the incremental computational capabilities gained when using sigmoidal units are severely paid in terms of robustness of the corresponding representation.

Learning in multilayered networks used as autoassociators.

Gradient descent learning algorithms may get stuck in local minima, thus making the learning suboptimal. In this paper, we focus attention on multilayered networks used as autoassociators and show some relationships with classical linear autoassociators. In addition, by using the theoretical framework of our previous research, we derive a condition which is met at the end of the learning process and show that this condition has a very intriguing geometrical meaning in the pattern space.

Learning without local minima in radial basis function networks.

Learning from examples plays a central role in artificial neural networks. The success of many learning schemes is not guaranteed, however, since algorithms like backpropagation may get stuck in local minima, thus providing suboptimal solutions. For feedforward networks, optimal learning can be achieved provided that certain conditions on the network and the learning environment are met. This principle is investigated for the case of networks using radial basis functions (RBF). It is assumed that the patterns of the learning environment are separable by hyperspheres. In that case, we prove that the attached cost function is local minima free with respect to all the weights. This provides us with some theoretical foundations for a massive application of RBF in pattern recognition.

Learning long-term dependencies with gradient descent is difficult.

Recurrent neural networks can be used to map input sequences to output sequences, such as for recognition, production or prediction problems. However, practical difficulties have been reported in training recurrent neural networks to perform tasks in which the temporal contingencies present in the input/output sequences span long intervals. We show why gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases. These results expose a trade-off between efficient learning by gradient descent and latching on information for long periods. Based on an understanding of this problem, alternatives to standard gradient descent are considered.