For medical volume visualization, one of the most important tasks is to reveal clinically relevant details from the 3D scan (CT, MRI ...), e.g. the coronary arteries, without obscuring them with less significant parts. These volume datasets contain different materials which are difficult to extract and visualize with 1D transfer functions based solely on the attenuation coefficient. Multi-dimensional transfer functions allow a much more precise classification of data which makes it easier to separate different surfaces from each other. Unfortunately, setting up multi-dimensional transfer functions can become a fairly complex task, generally accomplished by trial and error. This paper explains neural networks, and then presents an efficient way to speed up visualization process by semi-automatic transfer function generation. We describe how to use neural networks to detect distinctive features shown in the 2D histogram of the volume data and how to use this information for data classification.

Circadian variation of onset of acute myocardial infarction (AMI) has been noted in many studies, but there are no data about subgroups of patients with previous coronary artery bypass grafting (CABG). Because of abnormalities in the circadian rhythm of autonomic tone after surgery, it was very interesting to analyze the circadian patterns in the onset of symptoms of AMI in various subgroups of 1784 patients with previous CABG. As in the other studies, a peak occurred in the morning hours with 26.3% of the patients, but there was a second nearly equal, but higher, peak (26.4%) in the evening hours. The subgroups with specific clinical characteristics exhibited different patterns that determined these peaks in all populations. In patients older than 70 years of age, in both sexes, in smokers, diabetics, in patients with hypertension, in those undergoing beta-blocker therapy, and in patients without previous angina, two nearly equal peaks were observed, with higher evening peaks, except in those patients with hypertension and without angina. Only one peak in the evening hours was observed in a subgroup of patients with previous congestive heart failure (CHF) and non-STEMI. The subgroup of patients with previous angina and previous AMI exhibited no discernible peaks. The distribution of time of onset within the four intervals was not uniform, and the difference was statistically significant only for patients undergoing beta-blocker therapy at time of onset (p = 0.0013), nonsmokers (p = 0.0283), and patients with non-STEMI (p = 0.0412). It is well known that patients with AMI have a dominant morning peak of circadian variation of onset. However, analyzing a different subgroup of patients with AMI after previous CABG, it was found that some subgroups had two peaks of onset, but a higher evening peak (patients older than 70 years of age, smokers, diabetics, and a group of patients who were taking beta-blocker therapy). This subgroup of patients, together with the subgroups of patients with a dominant evening peak (patients with CHF and those with non-STEMI) and with patients with no peak (patients with previous angina and previous AMI), probably appear to modify characteristic circadian variation of infarction onset, expressing a higher evening peak, respectively to the previous CABG, with adverse consequences for central nervous system functioning.