Semi-automatic landmark point annotation for geometric morphometrics

Abstract

Background: In previous work, the authors described a software package for the digitisation of 3D landmarks for use in geometric morphometrics. In this paper, we describe extensions to this software that allow semi-automatic localisation of 3D landmarks, given a database of manually annotated training images. Multi-stage registration was applied to align image patches from the database to a query image, and the results from multiple database images were combined using an array-based voting scheme. The software automatically highlights points that have been located with low confidence, allowing manual correction.Results: Evaluation was performed on micro-CT images of rodent skulls for which two independent sets of manual landmark annotations had been performed. This allowed assessment of landmark accuracy in terms of both the distance between manual and automatic annotations, and the repeatability of manual and automatic annotation. Automatic annotation attained accuracies equivalent to those achievable through manual annotation by an expert for 87.5% of the points, with significantly higher repeatability.Conclusions: Whilst user input was required to produce the training data and in a final error correction stage, the software was capable of reducing the number of manual annotations required in a typical landmark identification process using 3D data by a factor of ten, potentially allowing much larger data sets to be annotated and thus increasing the statistical power of the results from subsequent processing e.g. Procrustes/principal component analysis. The software is freely available, under the GNU General Public Licence, from our web-site (www.tina-vision.net).

Automated Detection of 3D Landmarks for the Elimination of Non-Biological Variation in Geometric Morphometric Analyses

“…These values are similar to those obtain by Tautz et.al . [5] who assessed errors in manual annotation of consomic Mus musculus mandibles.…”

“…If application to different species or anatomical regions of interest is desired, algorithms would need to be modified or new ones would have to be developed. In contrast, the recently described semi-automated approach [5] can be applied to any 3D structure. However, this method requires the prior creation of a manually annotated training set from which landmark locations on query images are estimated.…”

“…al. [5] describe a semi-automated approach to landmark a query image that relies on the presence of a manually annotated training set. Limited user input is required to first identify four landmarks, following which, the query image is registered to the training image using a hierarchical multi-stage patch-based approach.…”

Craniofacial shape transition across the house mouse hybrid zone: implications for the genetic architecture and evolution of between-species differences

“…However, to ensure that all mice were phenotyped under the same conditions, all 249 mice used in this study were phenotyped in the following way: Landmarks were placed using the semi-automatic landmarking tool implemented in TINA tool (Bromiley et al 2014) using a reference database of ten manually landmarked mice. Landmark position was revised and manually adjusted when necessary.…”

Automatic Localisation of Vertebrae in DXA Images Using Random Forest Regression Voting

“…This provides robustness to vertebrae that are obscured or not present. The use of multiple models, and Hough voting to combine their results, provides robustness to fit failures [18]. The failure of any one RF to detect vertebrae will result in responses scattered throughout the voting array.…”