Basal Slice Detection Using Long-Axis Segmentation for Cardiac Analysis (original) (raw)

Lecture Notes in Computer Science, 2016

Abstract

Estimating blood volume of the left ventricle (LV) in the end-diastolic and end-systolic phases is important in diagnosing cardio-vascular diseases. Proper estimation of the volume requires knowledge of which MRI slice contains the topmost basal region of the LV. Automatic basal slice detection has proved challenging; as a result, basal slice detection remains a manual task which is prone to inter-observer variability. This paper presents a novel method that is able to track the basal slice over the whole cardiac cycle. The method was tested on 56 healthy and pathological cases and was able to identify the basal slices similar to experts' selection for 80 % and 85 % of the cases for end-diastole and end-systole, respectively. This provides a significant improvement over the leading state-of-the-art approach that obtained 59 % and 44 % agreement with experts on the same input.

mahsa paknezhad hasn't uploaded this paper.

Let mahsa know you want this paper to be uploaded.

Ask for this paper to be uploaded.