Exploring the knowledge contained in neuroimages: Statistical discriminant analysis and automatic segmentation of the most significant changes

Objective: The aim of this article is to propose an integrated framework for extracting and describing patterns of disorders from medical images using a combination of linear discriminant analysis and active contour models. Methods: A multivariate statistical methodology was first used to identify the most discriminating hyperplane separating two groups of images (from healthy controls and patients with schizophrenia) contained in the input data. After this, the present work makes explicit the differences found by the multivariate statistical method by subtracting the discriminant models of controls and patients, weighted by the pooled variance between the two groups. A variational level-set technique was used to segment clusters of these differences. We obtain a label of each anatomical change using the Talairach atlas. Results: In this work all the data was analysed simultaneously rather than assuming a priori regions of interest. As a consequence of this, by using active contour models, we were able to obtain regions of interest that were emergent from the data. The results were evaluated using, as gold standard, well-known facts about the neuroanatomical changes related to schizophrenia. Most of the items in the gold standard was covered in our result set. Conclusions: We argue that such investigation provides a suitable framework for characterising the high complexity of magnetic resonance images in schizophrenia as the results obtained indicate a high sensitivity rate with respect to the gold standard. (C) 2010 Elsevier B.V. All rights reserved.

Effect of temporal lobe structure volume on memory in elderly depressed patients

Objective: To compare the volume of the hippocampus and parahippocampal gyrus in elderly individuals with and without depressive disorders, and to determine whether the volumes of these regions correlate with scores on memory tests. Method: Clinical and demographic differences, as well as differences in regional gray matter volumes, were assessed in 48 elderly patients with depressive disorders and 31 control subjects. Brain (structural MRI) scans were processed using statistical parametric mapping and voxel-based morphometry. Cognitive tests were administered to subjects in both groups. Results: There were no between-group gray matter volume differences in the hippocampus or parahippocampal gyrus. In the elderly depressed group only, the volume of the left parahippocampal gyrus correlated with scores on the delayed naming portion of the visual verbal learning test. There were also significant direct correlations in depressed subjects between the volumes of the left hippocampus, right and left parahippocampal gyrus and immediate recall scores on verbal episodic memory tests and visual learning tests. In the control group, there were direct correlations only between overall cognitive performance (as assessed with the MMSE) and the volume of right hippocampus, and between the total score on the visual verbal learning test and the volume of the right and left parahippocampal gyrus. Conclusions: These findings highlight different patterns of relationship between cognitive performance and volumes of medial temporal structures in depressed individuals and healthy elderly subjects. The direct correlation between delayed visual verbal memory recall scores with left parahippocampal volumes specifically in elderly depressed individuals provides support to the view that depression in elderly populations may be a risk factor for dementia. (C) 2009 Elsevier Inc. All rights reserved.

A decision support system to facilitate management of patients with acute gastrointestinal bleeding

Objective: To develop a model to predict the bleeding source and identify the cohort amongst patients with acute gastrointestinal bleeding (GIB) who require urgent intervention, including endoscopy. Patients with acute GIB, an unpredictable event, are most commonly evaluated and managed by non-gastroenterologists. Rapid and consistently reliable risk stratification of patients with acute GIB for urgent endoscopy may potentially improve outcomes amongst such patients by targeting scarce health-care resources to those who need it the most. Design and methods: Using ICD-9 codes for acute GIB, 189 patients with acute GIB and all. available data variables required to develop and test models were identified from a hospital medical records database. Data on 122 patients was utilized for development of the model and on 67 patients utilized to perform comparative analysis of the models. Clinical data such as presenting signs and symptoms, demographic data, presence of co-morbidities, laboratory data and corresponding endoscopic diagnosis and outcomes were collected. Clinical data and endoscopic diagnosis collected for each patient was utilized to retrospectively ascertain optimal management for each patient. Clinical presentations and corresponding treatment was utilized as training examples. Eight mathematical models including artificial neural network (ANN), support vector machine (SVM), k-nearest neighbor, linear discriminant analysis (LDA), shrunken centroid (SC), random forest (RF), logistic regression, and boosting were trained and tested. The performance of these models was compared using standard statistical analysis and ROC curves. Results: Overall the random forest model best predicted the source, need for resuscitation, and disposition with accuracies of approximately 80% or higher (accuracy for endoscopy was greater than 75%). The area under ROC curve for RF was greater than 0.85, indicating excellent performance by the random forest model Conclusion: While most mathematical models are effective as a decision support system for evaluation and management of patients with acute GIB, in our testing, the RF model consistently demonstrated the best performance. Amongst patients presenting with acute GIB, mathematical models may facilitate the identification of the source of GIB, need for intervention and allow optimization of care and healthcare resource allocation; these however require further validation. (c) 2007 Elsevier B.V. All rights reserved.