Automatic and robust segmentation of the left ventricle (LV) in magnetic resonance images (MRI) has remained challenging for many decades. With the great success of deep learning in object detection and classification, the research focus of LV segmentation has changed to convolutional neural network (CNN) in recent years. However, LV segmentation is a pixel-level classification problem and its categories are intractable compared to object detection and classification. Although lots of CNN based methods have been proposed for LV segmentation, no robust and reproducible results are achieved yet. In this paper, we try to reproduce the CNN based LV segmentation methods with their disclosed codes and trained CNN models. Not surprisingly, the reproduced results are significantly worse than their claimed accuracies. We also proposed a fully automated LV segmentation method based on slope difference distribution (SDD) threshold selection to compare with the reproduced CNN methods. The proposed method achieved 95.44% DICE score on the test set of automated cardiac diagnosis challenge (ACDC) while the two compared CNN methods achieved 90.28% and 87.13% DICE scores. Our achieved accuracy is also higher than the best accuracy reported in the published literatures. The MATLAB codes of our proposed method are freely available on line.
To separate the overlapped cells, a bottleneck detection approach is proposed in this paper. The cell image is segmented by slope difference distribution (SDD) threshold selection. For each segmented binary clump, its one-dimensional boundary is computed as the distance distribution between its centroid and each point on the two-dimensional boundary. The bottleneck points of the one-dimensional boundary is detected by SDD and then transformed back into two-dimensional bottleneck points. Two largest concave parts of the binary clump are used to select the valid bottleneck points. Two bottleneck points from different concave parts with the minimum Euclidean distance is connected to separate the binary clump with minimum-cut. The binary clumps are separated iteratively until the number of computed concave parts is smaller than two. We use four types of open-accessible cell datasets to verify the effectiveness of the proposed approach and experimental results showed that the proposed approach is significantly more robust than state of the art methods.