A validated active contour method driven by parabolic arc model for detection and segmentation of mitochondria

Abstract

Recent studies reveal that mitochondria take substantial responsibility in cellular functions that are closely related to aging diseases caused by degeneration of neurons. These studies emphasize that the membrane and crista morphology of a mitochondrion should receive attention in order to investigate the link between mitochondrial function and its physical structure. Electron microscope tomography (EMT) allows analysis of the inner structures of mitochondria by providing highly detailed visual data from large volumes. Computerized segmentation of mitochondria with minimum manual effort is essential to accelerate the study of mitochondrial structure/function relationships. In this work, we improved and extended our previous attempts to detect and segment mitochondria from transmission electron microcopy (TEM) images. A parabolic arc model was utilized to extract membrane structures. Then, curve energy based active contours were employed to obtain roughly outlined candidate mitochondrial regions. Finally, a validation process was applied to obtain the final segmentation data. 3D extension of the algorithm is also presented in this paper. Our method achieved an average F-score performance of 0.84. Average Dice Similarity Coefficient and boundary error were measured as 0.87 and 14 nm respectively.

Automatic Mitochondria Segmentation for EM Data Using a 3D Supervised Convolutional Network

“…Because the shape of mitochondria is sometimes irregular, manual annotations near mitochondria borders are not always accurate, which might influence the precision of the evaluation. Motivated by Li et al ( 2017b ); Tasel et al ( 2016 ), we defined that a predicted mitochondria is considered a TP only if the voxel-wise overlap between the prediction and corresponding ground truth reaches at least 70%. For the sake of completeness, we also conducted several experiments by considering different voxel-wise overlapping thresholds for TP on both datasets.…”

“…Since mitochondrial structures vary in living cells and the corresponding shapes range from punctuate structures to tubular networks with sizes between 0.5 and 10 μm, optical microscopy, with limited resolution, cannot provide sufficient resolution to reveal these fine structures (Tasel et al, 2016 ). Fortunately, several new scanning electron microscopy (SEM) imaging methods have emerged, and their high-resolution capability has provided new in-depth insights into mitochondrial structures and functions (Mannella et al, 1997 ).…”

“…Lucchi et al put forward an automated mitochondria segmentation method, which utilized an approximate subgradient descent algorithm to minimize the margin-sensitive hinge loss in the structured support vector machine (SSVM) frameworks (Lucchi et al, 2013 ). For anisotropic image stacks, Tasel et al first utilized a parabolic arc model to extract membrane structures and then employed the curve energy based on an active contour to obtain the roughly outlined candidate mitochondrial regions (Tasel et al, 2016 ). Finally, they achieved mitochondria segmentation by means of a validation process in serial section transmission electron microscopy (ssTEM) image stacks (Harris et al, 2006 ).…”

3D Orientation Field Transform

“…The efficacy of combining the above mentioned six transform components through the function in eqn (16), i.e., Alg. 1 with function f defined in eqn (17), is shown in (b) of Fig. 7 and Fig.…”

“…Prevailing existing autosegmentation approaches include: 1) general noise-reduction techniques, most common of which are different variations of wavelet transform [4]- [9], nonlinear anisotropic diffusion or bilateral filtering [4], [5], [10], [11]; 2) direct segmentation techniques such as thresholding [4], [12]- [14], morphological operations [4], region-based approaches utilising watershed transform [4], [5], [15], and energy-based approaches in the manner of active contour [4], [5], [16], [17]. Moreover, there lately have also been attempts at using machine-learning algorithms to improve the segmentation quality, e.g.…”