Abstract
The detection of anatomical landmarks in bioimages is a necessary but tedious step for geometric morphometrics studies in many research domains. We propose variants of a multi-resolution tree-based approach to speed-up the detection of landmarks in bioimages. We extensively evaluate our method variants on three different datasets (cephalometric, zebrafish, and drosophila images). We identify the key method parameters (notably the multi-resolution) and report results with respect to human ground truths and existing methods. Our method achieves recognition performances competitive with current existing approaches while being generic and fast. The algorithms are integrated in the open-source Cytomine software and we provide parameter configuration guidelines so that they can be easily exploited by end-users. Finally, datasets are readily available through a Cytomine server to foster future research.
Highlights
Geometric morphometrics has become the dominant set of methods used to quantify size and shape of biological objects[1]
Several successful landmark detection algorithms have been proposed in this domain that are based on pixel classification or regression using machine learning techniques followed by global landmark structure refinement[13,14,15]
Because these approaches have been proposed in the literature to tackle specific applications, such as face analysis or cephalometry, none of them was systematically evaluated on a broader range of biomedical applications
Summary
Geometric morphometrics has become the dominant set of methods used to quantify size and shape of biological objects[1]. Several successful landmark detection algorithms have been proposed in this domain that are based on pixel classification or regression using machine learning techniques followed by global landmark structure refinement[13,14,15] Because these approaches have been proposed in the literature to tackle specific applications, such as face analysis or cephalometry, none of them was systematically evaluated on a broader range of biomedical applications. We study variants of a generic method for landmark detection that makes no specific assumption about the types of images to analyze and landmarks to detect It is based on the extraction of multi-resolution features and the use of generic tree-based ensemble machine learning methods, namely (Extremely) Randomized Forests[16,17]. These comparisons show that our approach yields competitive results in terms of accuracy, with lighter models and lower prediction times. We provide an open-source implementation of these algorithms through the Cytomine platform[23] that further implements proofreading tools to combine automatic detection and manual refinements. As an important side contribution, we provide an easy access to the datasets used in this study with the hope that the landmark detection problem will gain more interest in bioimage informatics and machine learning research
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
