Local contrast hole filling algorithm for neura slices membrane detection — LCHF

Local Contrast Hole Filling Algorithm for Neural Slices Membrane Detection (LCHF) algorithm is non-learning, simple, easily adopted, and undependable on ground-truth; and it can recognize membrane and eliminates organelles, using a very simple algorithm that consist of short sequences of basic processing steps yet can be relatively competitive. Here, we would like to show the simple processing stages, and the effectiveness of the LCHF algorithm, with other similar neuronal datasets. The performance of the algorithm was measured in terms of Precision, Recall and F1 score. Precision (also known as positive predictive value), and Recall (also known as sensitivity). F1 score (also known as F-score or F-measure). The experiments were performed on data provided by the ISBI 2012 (IEEE International Symposium on Biomedical Imaging). LCHF generously allowed to classify pixels into membrane/non-membrane for these datasets, and took 44 seconds for 30 slices to produce the comparable best result, and recorded average F1 score of more than 71% similarity with the benchmark ground-truth image.