Accuracy of Automatic Cephalometric Software on Landmark Identification

Anuwongnukroh, Niwat; Dechkunakorn, Surachai; Damrongsri, Suchaya; Nilwarat, Chayawat; Pudpong, Natthasit; Radomsutthisarn, Watcharapon; Kangern, Silinda

doi:10.1088/1757-899x/265/1/012028

Cited by 7 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although, registration-based methods have been reported to achieve relatively high accuracy when shape and appearance information are integrated, these algorithms perform poorly when there are variations due to different age patients (ie. pediatrics vs. adults), missing teeth, missing parts of the region of interest, and imaging artifacts [4], [10], [11]. In 2015, Gupta et al [12] developed a knowledge-based algorithm to localize 20 anatomical landmarks on the CBCT scans.…”

Section: Related Workmentioning

confidence: 99%

“…Additionally, landmarking on CT images is tedious and manual or semi-automated and prone to operator variability. Despite some recent elaborative efforts towards making a fully automated and accurate software for segmentation of bones and landmarking for deformation analysis in dental applications [3], [4], the problem remains largely unsolved for global CMF deformity analysis, especially for those who have congenital or developmental deformities for whom the diagnosis and treatment planning are most critically needed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Geodesic Learning for Segmentation and Anatomical Landmarking

Torosdagli

Liberton

Verma

et al. 2019

IEEE Trans. Med. Imaging

113

View full text Add to dashboard Cite

In this paper, we propose a novel deep learning framework for anatomy segmentation and automatic landmarking. Specifically, we focus on the challenging problem of mandible segmentation from cone-beam computed tomography (CBCT) scans and identification of 9 anatomical landmarks of the mandible on the geodesic space. The overall approach employs three inter-related steps. In step 1, we propose a deep neural network architecture with carefully designed regularization, and network hyper-parameters to perform image segmentation without the need for data augmentation and complex postprocessing refinement. In step 2, we formulate the landmark localization problem directly on the geodesic space for sparselyspaced anatomical landmarks. In step 3, we propose to use a long short-term memory (LSTM) network to identify closelyspaced landmarks, which is rather difficult to obtain using other standard detection networks. The proposed fully automated method showed superior efficacy compared to the state-of-theart mandible segmentation and landmarking approaches in craniofacial anomalies and diseased states. We used a very challenging CBCT dataset of 50 patients with a high-degree of craniomaxillofacial (CMF) variability that is realistic in clinical practice. Complementary to the quantitative analysis, the qualitative visual inspection was conducted for distinct CBCT scans from 250 patients with high anatomical variability. We have also shown feasibility of the proposed work in an independent dataset from MICCAI Head-Neck Challenge (2015) achieving the state-of-the-art performance. Lastly, we present an in-depth analysis of the proposed deep networks with respect to the choice of hyper-parameters such as pooling and activation functions.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Geodesic Learning for Segmentation and Anatomical Landmarking

Torosdagli

Liberton

Verma

et al. 2019

IEEE Trans. Med. Imaging

113

View full text Add to dashboard Cite

show abstract

“…However, manual landmarking is a tedious process and prone to interoperator variability. There are elaborative efforts towards making a fully-automated and accurate software for segmentation and anatomical landmarking [2], [3]. Despite this need, little progress has been made especially for bones with high deformations (approximately 5% of the CMF deformities) especially for congenital and developmental deformities.…”

Section: Introductionmentioning

confidence: 99%

“…Integration of the shape and the appearance increases the accuracy of the registration-based approaches. However, image registration is still an ill-posed problem, and when there are variations such as age (pediatrics vs. adults), missing teeth (very common in certain age groups), missing bone or bone parts, severe pathology (congenital or trauma), and imaging artifacts, the performance can be quite poor [3], [9], [10]. The same concerns apply to segmentation based approaches too.…”

Section: Introductionmentioning

confidence: 99%

Relational Reasoning Network (RRN) for Anatomical Landmarking

Torosdagli¹,

Anwar²,

Verma³

et al. 2019

Preprint

View full text Add to dashboard Cite

Accurately identifying anatomical landmarks is a crucial step in deformation analysis and surgical planning for craniomaxillofacial (CMF) bones. Available methods require segmentation of the object of interest for precise landmarking. Unlike those, our purpose in this study is to perform anatomical landmarking using the inherent relation of CMF bones without explicitly segmenting them. We propose a new deep network architecture, called relational reasoning network (RRN), to accurately learn the local and the global relations of the landmarks. Specifically, we are interested in learning landmarks in CMF region: mandible, maxilla, and nasal bones. The proposed RRN works in an end-to-end manner, utilizing learned relations of the landmarks based on dense-block units and without the need for segmentation. For a given a few landmarks as input, the proposed system accurately and efficiently localizes the remaining landmarks on the aforementioned bones. For a comprehensive evaluation of RRN, we used cone-beam computed tomography (CBCT) scans of 250 patients. The proposed system identifies the landmark locations very accurately even when there are severe pathologies or deformations in the bones. The proposed RRN has also revealed unique relationships among the landmarks that help us infer several reasoning about informativeness of the landmark points. RRN is invariant to order of landmarks and it allowed us to discover the optimal configurations (number and location) for landmarks to be localized within the object of interest (mandible) or nearby objects (maxilla and nasal). To the best of our knowledge, this is the first of its kind algorithm finding anatomical relations of the objects using deep learning.

show abstract

“…The image distortion may be different at different parts of the x-ray beam pathway. Thus, two or more objects may have different distortions when positioned at the locations with different distances from the image receptor 3,11 . The aim of this study is to determine a calibration factor used to eliminate the distortion from the linear cephalometric measurements.…”

Section: Introductionmentioning

confidence: 99%

Calibration Factor for Conventional Linear Cephalometric Measurements

Mohammed¹,

Jameel²,

Al-Mallah³

2018

RDENTJ

View full text Add to dashboard Cite

Aims: the aim of this study is to determine a calibration factor to eliminate the distortion in the linear cephalometric measurements. Materials and Methods; the study was performed on the 5 dry skulls, the first skull contained 12 radiopaque markers fixed at different plains, and radiographed by digital cephalometric x-ray machine. The X and Y axes of the shadow of each radiopaque marker used to estimate the calibration factor. Eight linear distances measured directly and radiographically on the conventional cephalographs of the 5 skulls to evaluate the detected calibration factor. Results; the results showed no-significant difference (p > 0.05) between the direct and calibrated radiographic measurement on the digital and conventional cephalographs. whereas significant difference was found between the conventional cephalometric linear measurements as compared with direct anatomical linear and the conventional cephalometric linear measurements with those measurements manipulated with the estimated calibration factor (p < 0.05). Conclusions; this study found that the conventional cephalometric linear measurements could be reliable as that of digital cephalometric linear measurements, if it's calibrated by the calibration factor (1.08) which is estimated by the present study.

show abstract

Accuracy of Automatic Cephalometric Software on Landmark Identification

Abstract: Abstract. This study was to assess the accuracy of an automatic cephalometric analysis software in the identification of cephalometric landmarks. Thirty randomly selected digital lateral cephalograms of patients undergoing orthodontic treatment were used in this study.

Cited by 7 publications

References 12 publications

Deep Geodesic Learning for Segmentation and Anatomical Landmarking

Deep Geodesic Learning for Segmentation and Anatomical Landmarking

Relational Reasoning Network (RRN) for Anatomical Landmarking

Calibration Factor for Conventional Linear Cephalometric Measurements

Contact Info

Product

Resources

About