Landmark annotation through feature combinations: a comparative study on cephalometric images with in-depth analysis of model’s explainability
Dentomaxillofacial Radiology · 08.02.2024 · 53 (2) · 115-126
DOI: 10.1093/dmfr/twad011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 13.12.2023. Verfasst von Rashmi S und 3 weiteren Autor:innen. Beteiligte Einrichtung: Dept. of Computer Science and Engineering, Sri Jayachamarajendra College of Engineering, JSS Science and Technology University, Mysuru, 570006, India. Hauptthemen laut MEDLINE: Cephalometry, Anatomic Landmarks. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 38 Literaturangaben.
Abstract (Originalsprache)
Objectives
The objectives of this study are to explore and evaluate the automation of anatomical landmark localization in cephalometric images using machine learning techniques, with a focus on feature extraction and combinations, contextual analysis, and model interpretability through Shapley Additive exPlanations (SHAP) values.
Methods
We conducted extensive experimentation on a private dataset of 300 lateral cephalograms to thoroughly study the annotation results obtained using pixel feature descriptors including raw pixel, gradient magnitude, gradient direction, and histogram-oriented gradient (HOG) values. The study includes evaluation and comparison of these feature descriptions calculated at different contexts namely local, pyramid, and global. The feature descriptor obtained using individual combinations is used to discern between landmark and nonlandmark pixels using classification method. Additionally, this study addresses the opacity of LGBM ensemble tree models across landmarks, introducing SHAP values to enhance interpretability.
Results
The performance of feature combinations was assessed using metrics like mean radial error, standard deviation, success detection rate (SDR) (2 mm), and test time. Remarkably, among all the combinations explored, both the HOG and gradient direction operations demonstrated significant performance across all context combinations. At the contextual level, the global texture outperformed the others, although it came with the trade-off of increased test time. The HOG in the local context emerged as the top performer with an SDR of 75.84% compared to others.
Conclusions
The presented analysis enhances the understanding of the significance of different features and their combinations in the realm of landmark annotation but also paves the way for further exploration of landmark-specific feature combination methods, facilitated by explainability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Dept. of Computer Science and Engineering, Sri Jayachamarajendra College of Engineering, JSS Science and Technology University, Mysuru, 570006, India.
- Dept. of Pediatric & Preventive Dentistry, JSS Dental College & Hospital, JSS Academy of Higher Education & Research, Mysuru, 570015, India.
ORCID-Profile: Rashmi S, Srinath S, Prashanth S Murthy, Seema Deshmukh
Zitieren
APA
S, R., S, S., S Murthy, P., & Deshmukh, S. (2024). Landmark annotation through feature combinations: a comparative study on cephalometric images with in-depth analysis of model’s explainability. Dentomaxillofacial Radiology, 53(2), 115-126. https://doi.org/10.1093/dmfr/twad011
Vancouver
S R, S S, S Murthy P, Deshmukh S. Landmark annotation through feature combinations: a comparative study on cephalometric images with in-depth analysis of model’s explainability. Dentomaxillofacial Radiology. 2024;53(2):115-126. doi:10.1093/dmfr/twad011
BibTeX
@article{S2024,
author = {S, Rashmi and S, Srinath and S Murthy, Prashanth and Deshmukh, Seema},
title = {Landmark annotation through feature combinations: a comparative study on cephalometric images with in-depth analysis of model’s explainability},
journal = {Dentomaxillofacial Radiology},
year = {2024},
volume = {53},
number = {2},
pages = {115--126},
doi = {10.1093/dmfr/twad011}
}
EUVIMED