CEPHA29: Automatic Cephalometric Landmark Detection Challenge 2023

Khalid, Muhammad Anwaar; Zulfiqar, Kanwal; Bashir, Ulfat; Shaheen, Areeba; Iqbal, Rida; Rizwan, Zarnab; Rizwan, Ghina; Fraz, Muhammad Moazam

doi:10.48550/arxiv.2212.04808

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the previous studies all use different datasets, their prediction accuracy could not be compared with the other published methods. Unified datasets of 3D images and landmark coordinate values should be published, as they were for the 2D challenges [23,24,34]. Generally, in studies using data with low variance, the prediction error is small; meanwhile, in studies that use highly dispersed data, the prediction error is large.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Three-Dimensional Craniofacial Landmark Detection in Series of CT Slices Using Multi-Phased Regression Networks

et al. 2023

View full text Add to dashboard Cite

Geometrical assessments of human skulls have been conducted based on anatomical landmarks. If developed, the automatic detection of these landmarks will yield both medical and anthropological benefits. In this study, an automated system with multi-phased deep learning networks was developed to predict the three-dimensional coordinate values of craniofacial landmarks. Computed tomography images of the craniofacial area were obtained from a publicly available database. They were digitally reconstructed into three-dimensional objects. Sixteen anatomical landmarks were plotted on each of the objects, and their coordinate values were recorded. Three-phased regression deep learning networks were trained using ninety training datasets. For the evaluation, 30 testing datasets were employed. The 3D error for the first phase, which tested 30 data, was 11.60 px on average (1 px = 500/512 mm). For the second phase, it was significantly improved to 4.66 px. For the third phase, it was further significantly reduced to 2.88. This was comparable to the gaps between the landmarks, as plotted by two experienced practitioners. Our proposed method of multi-phased prediction, which conducts coarse detection first and narrows down the detection area, may be a possible solution to prediction problems, taking into account the physical limitations of memory and computation.

show abstract

Section: Discussionmentioning

confidence: 99%

“…A systematic review of the use of artificial intelligence in cephalometric landmark identification was recently conducted [33]. A new challenge with larger datasets is currently underway [34].…”

Section: Introductionmentioning

confidence: 99%

Three-Dimensional Craniofacial Landmark Detection in Series of CT Slices Using Multi-Phased Regression Networks

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Acknowledging the importance of automatic landmark detection, The ISBI, which stands for the International Symposium on Biomedical Imaging, has led the organization of a number of challenges related to the matter, namely in 2014 [13], in 2015 [14], and is set to continue its impact in the year of 2023 [15].…”

Section: Related Workmentioning

confidence: 99%

Cephalometric Landmarks Identification Through an Object Detection-based Deep Learning Model

Tafala,

Ben-Bouazza,

Edder

et al. 2024

IJACSA

View full text Add to dashboard Cite

In the field of orthodontics, the accurate identification of cephalometric landmarks in dental radiography plays a crucial role in ensuring precise diagnoses and efficient treatment planning. Previous studies have demonstrated the impressive capabilities of advanced deep learning models in this particular domain. However, due to the ever-changing technological landscape, it is imperative to consistently investigate and explore emerging algorithms to further improve efficiency in this field. The present study centers around the assessment of the effectiveness of YOLOv8, the most recent version of the 'You Only Look Once (YOLO)' algorithm series, with a particular emphasis on its autonomous capability to accurately identify cephalometric landmarks. In this study, a thorough examination was conducted to evaluate the YOLOv8 algorithm efficiency in detecting cephalometric landmarks. The assessments encompassed various aspects such as precision, adaptability in challenging conditions, and a comparative analysis with alternative algorithms. The predefined proximities of 2mm, 2.5mm, and 3mm were utilized for the comparisons. By focusing on its potential as a noteworthy breakthrough, the investigation seeks to ascertain whether the recent enhancements indeed bring about a significant stride in the precise identification of cephalometric landmarks.

show abstract

CEPHA29: Automatic Cephalometric Landmark Detection Challenge 2023

Cited by 2 publications

References 0 publications

Three-Dimensional Craniofacial Landmark Detection in Series of CT Slices Using Multi-Phased Regression Networks

Three-Dimensional Craniofacial Landmark Detection in Series of CT Slices Using Multi-Phased Regression Networks

Cephalometric Landmarks Identification Through an Object Detection-based Deep Learning Model

Contact Info

Product

Resources

About