Search

We developed machine learning methods to identify fibrolipidic and fibrocalcific A-lines in intravascular optical coherence tomography (IVOCT) images using a comprehensive set of handcrafted features. We incorporated features developed in previous studies (e.g., optical attenuation and A-line peaks). In addition, we included vascular lumen morphology and three-dimensional (3-D) digital edge and texture features. Classification methods were developed using expansive datasets (∼7000 images), consisting of both clinical in-vivo images and an ex-vivo dataset, which was validated using 3-D cryo-imaging/histology. Conditional random field was used to perform 3-D classification noise cleaning of classification results. We tested various multiclass approaches, classifiers, and feature selection schemes and found that a three-class support vector machine with minimal-redundancy-maximal-relevance feature selection gave the best performance. We found that inclusion of our morphological and 3-D features improved overall classification accuracy. On a held-out test set consisting of >1700 images, we obtained an overall accuracy of 81.58%, with the following (sensitivity/specificity) for each class: other (81.43/89.59), fibrolipidic (94.48/87.32), and fibrocalcific (74.82/95.28). The en-face views of classification results showed that automated classification easily captured the preponderance of a disease segment (e.g., a calcified segment had large regions of fibrocalcific classifications). Finally, we demonstrated proof-of-concept for streamlining A-line classification output with existing fibrolipidic and fibrocalcific boundary segmentation methods, to enable fully automated plaque quantification. The results suggest that our classification approach is a viable step toward fully automated IVOCT plaque classification and segmentation for live-time treatment planning and for offline assessment of drug and biologic therapeutics.

Background The use of cardiopulmonary bypass (CPB) may contribute to post-operative complications and organ dysfunction. Off pump coronary artery bypass grafting (OPCABG) avoids the use of CPB and hence is proposed to reduce these complications. We present the results of OPCABG in Northern Ireland over ten years. Methods Data was collected retrospectively from 1995 to 2005. Follow-up was done by telephonic questionnaire and from medical records within a closing interval of two months. Results 324 patients (224 male) underwent OPCABG with a median age of 62 years (range 35 to 79 years). There were 149 patients with CCS class III/IV angina and 48 with NYHA class III/IV. 148 patients had suffered a myocardial infarction in the past. 36 patients had a pre-operative predictive mortality score (EuroSCORE) of >5 and 48 patients had a preoperative LVEF of

Background: Studies of neuropsychological outcome following coronary artery bypass graft surgery (CABG) have traditionally dichotomised patients as "impaired" or "unimpaired". This conceals the potential heterogeneity of deficits due to different mechanisms and sites of brain injury. Objectives: To explore neuropsychological outcome following CABG and determine to what extent it conforms to prototypic cortical and/or subcortical neurobehavioral syndromes and whether different intraoperative physiologic measures are associated with different subtypes of neuropsychological outcome. Methods: Neuropsychological tests were administered to 85 patients before and after elective CABG and to 50 matched normal control subjects. Pre- to postoperative change scores were computed using standardised regression based norms. Change scores on selected memory measures were subjected to cluster analysis to identify qualitatively distinct subtypes of memory outcome. Emergent clusters were compared on non-memory measures, intraoperative physiologic measures, and demographic variables. Results: Three subtypes of memory outcome were identified: memory spared (48% of patients), retrieval deficit (35%), and encoding/storage deficit (17%). Contrary to expectation, the subgroups were indistinguishable on measures of confrontation naming and manual dexterity and on intraoperative cardiac surgical physiologic measures and demographic variables. The encoding/storage deficit subgroup exhibited executive dysfunction. Conclusions: Heterogeneous profiles of neuropsychological dysfunction were found following CABG although they did not tightly conform to prototypic cortical and subcortical neurobehavioral syndromes. This challenges the value and appropriateness of the common practice of collapsing individual test scores to arrive at a single figure to define "impairment". Whether different subtypes of neuropsychological outcome are caused by different pathophysiologic mechanisms remains unknown.