Consistent nuclear expression of thyroid transcription factor 1 in subependymal giant cell astrocytomas suggests lineage-restricted histogenesis.

Thyroid transcription factor 1 (TTF-1) is encoded by the NKX2-1 homeobox gene. Besides specifying thyroid and pulmonary organogenesis, it is also temporarily expressed during embryonic development of the ventral forebrain. We recently observed widespread immunoreactivity for TTF-1 in a case of subependymal giant cell astrocytoma (SEGA, WHO grade I) – a defining lesion of the tuberous sclerosis complex (TSC). This prompted us to investigate additional SEGAs in this regard. We found tumor cells in all 7 specimens analyzed to be TTF-1 positive. In contrast, we did not find TTF-1 immunoreactivity in a cortical tuber or two renal angiomyolipomas resected from TSC patients. We propose our finding of consistent TTF-1 expression in SEGAs to indicate lineage-committed derivation of these tumors from a regionally specified cell of origin. The medial ganglionic eminence, ventral septal region, and preoptic area of the developing brain may represent candidates for the origin of SEGAs. Such lineagerestricted histogenesis may also explain the stereotypic distribution of SEGAs along the caudate nucleus in the lateral ventricles.

Optimal Confidence Bands for Shape-Restricted Curves

Let Y be a stochastic process on [0,1] satisfying dY(t)=n 1/2 f(t)dt+dW(t) , where n≥1 is a given scale parameter (`sample size'), W is standard Brownian motion and f is an unknown function. Utilizing suitable multiscale tests, we construct confidence bands for f with guaranteed given coverage probability, assuming that f is isotonic or convex. These confidence bands are computationally feasible and shown to be asymptotically sharp optimal in an appropriate sense.

Fast Prediction of Femoral Biomechanics Using Supervised Machine Learning and Statistical Shape Modeling

Finite element (FE) analysis is an important computational tool in biomechanics. However, its adoption into clinical practice has been hampered by its computational complexity and required high technical competences for clinicians. In this paper we propose a supervised learning approach to predict the outcome of the FE analysis. We demonstrate our approach on clinical CT and X-ray femur images for FE predictions ( FEP), with features extracted, respectively, from a statistical shape model and from 2D-based morphometric and density information. Using leave-one-out experiments and sensitivity analysis, comprising a database of 89 clinical cases, our method is capable of predicting the distribution of stress values for a walking loading condition with an average correlation coefficient of 0.984 and 0.976, for CT and X-ray images, respectively. These findings suggest that supervised learning approaches have the potential to leverage the clinical integration of mechanical simulations for the treatment of musculoskeletal conditions.

Discourse-level Annotation over Europarl for Machine Translation: Connectives and Pronouns

This paper describes methods and results for the annotation of two discourse-level phenomena, connectives and pronouns, over a multilingual parallel corpus. Excerpts from Europarl in English and French have been annotated with disambiguation information for connectives and pronouns, for about 3600 tokens. This data is then used in several ways: for cross-linguistic studies, for training automatic disambiguation software, and ultimately for training and testing discourse-aware statistical machine translation systems. The paper presents the annotation procedures and their results in detail, and overviews the first systems trained on the annotated resources and their use for machine translation.

Shallow Dialogue Processing Using Machine Learning Algorithms (or not)

This paper presents a shallow dialogue analysis model, aimed at human-human dialogues in the context of staff or business meetings. Four components of the model are defined, and several machine learning techniques are used to extract features from dialogue transcripts: maximum entropy classifiers for dialogue acts, latent semantic analysis for topic segmentation, or decision tree classifiers for discourse markers. A rule-based approach is proposed for solving cross-modal references to meeting documents. The methods are trained and evaluated thanks to a common data set and annotation format. The integration of the components into an automated shallow dialogue parser opens the way to multimodal meeting processing and retrieval applications.