Deep learning-based detection of anthropometric landmarks in 3D infants head models

Torres, Helena R.; Oliveira, Bruno; Veloso, Fernando; Ruediger, Mario; Burkhardt, Wolfram; Moreira, António H. J.; Dias, Nuno; Morais, Pedro; Fonseca, Jaime C.; Vilaça, João L.

doi:10.1117/12.2512196

Cited by 8 publications

(3 citation statements)

References 15 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, preprocessing is a necessary process which includes facial cropping, histogram equalization and fiducial points marking over eyes, nose and lips. Second, the handcrafted feature is extracted from the facial image, including Anthropometric Models [5], Active Appearance Models (AAM) [6], Local Binary Pattern (LBP) [7], Aging pattern Subspace (AGES) [8]. Third, the dimension of the extracted feature is reduced by PCA or KPCA [9] to remove the noise.…”

Section: Introductionmentioning

confidence: 99%

Age Estimation via Selecting Discriminated Features and Preserving Geometry

2020

KSII TIIS

View full text Add to dashboard Cite

Human apparent age estimation has become a popular research topic and attracted great attention in recent years due to its wide applications, such as personal security and law enforcement. To achieve the goal of age estimation, a large number of methods have been pro-posed, where the models derived through the cumulative attribute coding achieve promised performance by preserving the neighbor-similarity of ages. However, these methods afore-mentioned ignore the geometric structure of extracted facial features. Indeed, the geometric structure of data greatly affects the accuracy of prediction. To this end, we propose an age estimation algorithm through joint feature selection and manifold learning paradigms, so-called Feature-selected and Geometry-preserved Least Square Regression (FGLSR). Based on this, our proposed method, compared with the others, not only preserves the geometry structures within facial representations, but also selects the discriminative features. Moreover, a deep learning extension based FGLSR is proposed later, namely Feature selected and Geometry preserved Neural Network (FGNN). Finally, related experiments are conducted on Morph2 and FG-Net datasets for FGLSR and on Morph2 datasets for FGNN. Experimental results testify our method achieve the best performances.

show abstract

Section: Introductionmentioning

confidence: 99%

Age Estimation via Selecting Discriminated Features and Preserving Geometry

2020

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…evaluate the craniofacial anatomy in the scanned 3D models, manual identification of anatomic landmarks is performed, followed by the calculation of established measurements. However, the manual identification of the landmarks is a timeconsuming task that it is also highly prone to observer variability [4], [5]. Thus, automated solutions to detect the landmarks can be useful tools to clinical practice.…”

mentioning

confidence: 99%

“…Recently, with the improvement of computing capabilities, deep neural networks have been widely used for medical and computer vision tasks, such as landmark localization [4], [6]- [8]. In fact, deep learning (DL) showed superior performance over the conventional machine learning strategies or registration-based approaches [9].…”

mentioning

confidence: 99%

3D Facial Landmark Localization for cephalometric analysis

Torres

Morais

Fritze

et al. 2022

2022 44th Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

Self Cite

View full text Add to dashboard Cite

Cephalometric analysis is an important and routine task in the medical field to assess craniofacial development and to diagnose cranial deformities and midline facial abnormalities. The advance of 3D digital techniques potentiated the development of 3D cephalometry, which includes the localization of cephalometric landmarks in the 3D models. However, manual labeling is still applied, being a tedious and time-consuming task, highly prone to intra/inter-observer variability. In this paper, a framework to automatically locate cephalometric landmarks in 3D facial models is presented. The landmark detector is divided into two stages: (i) creation of 2D maps representative of the 3D model; and (ii) landmarks' detection through a regression convolutional neural network (CNN). In the first step, the 3D facial model is transformed to 2D maps retrieved from 3D shape descriptors. In the second stage, a CNN is used to estimate a probability map for each landmark using the 2D representations as input. The detection method was evaluated in three different datasets of 3D facial models, namely the Texas 3DFR, the BU3DFE, and the Bosphorus databases. An average distance error of 2.3, 3.0, and 3.2 mm were obtained for the landmarks evaluated on each dataset. The obtained results demonstrated the accuracy of the method in different 3D facial datasets with a performance competitive to the state-of-the-art methods, allowing to prove its versability to different 3D models.Clinical Relevance-Overall, the performance of the landmark detector demonstrated its potential to be used for 3D cephalometric analysis. I. INTRODUCTIONCephalometric analysis refers to the assessment of the craniofacial structure to evaluate its growth and development and to diagnose cranial deformities, midline facial abnormalities, and orthodontic problems [1]. Traditionally, 2D radiographs are used for cephalometric analysis, but Computed Tomography (CT) and Magnetic Resonance (MR) imaging systems have been enabling 3D cephalometry [2]. More recently, some works proposed to use 3D digital models (e.g. laser scans) to perform the cephalometric analysis [3]. To

show abstract

Infant head and brain segmentation from magnetic resonance images using fusion-based deep learning strategies

Torres,

Oliveira,

Morais

et al. 2024

Multimedia Systems

View full text Add to dashboard Cite

Magnetic resonance (MR) imaging is widely used for assessing infant head and brain development and for diagnosing pathologies. The main goal of this work is the development of a segmentation framework to create patient-specific head and brain anatomical models from MR images for clinical evaluation. The proposed strategy consists of a fusion-based Deep Learning (DL) approach that combines the information of different image sequences within the MR acquisition protocol, including the axial T1w, sagittal T1w, and coronal T1w after contrast. These image sequences are used as input for different fusion encoder–decoder network architectures based on the well-established U-Net framework. Specifically, three different fusion strategies are proposed and evaluated, namely early, intermediate, and late fusion. In the early fusion approach, the images are integrated at the beginning of the encoder–decoder architecture. In the intermediate fusion strategy, each image sequence is processed by an independent encoder, and the resulting feature maps are then jointly processed by a single decoder. In the late fusion method, each image is individually processed by an encoder–decoder, and the resulting feature maps are then combined to generate the final segmentations. A clinical in-house dataset consisting of 19 MR scans was used and divided into training, validation, and testing sets, with 3 MR scans defined as a fixed validation set. For the remaining 16 MR scans, a cross-validation approach was adopted to assess the performance of the methods. The training and testing processes were carried out with a split ratio of 75% for the training set and 25% for the testing set. The results show that the early and intermediate fusion methodologies presented the better performance (Dice coefficient of 97.6 ± 1.5% and 97.3 ± 1.8% for the head and Dice of 94.5 ± 1.7% and 94.8 ± 1.8% for the brain, respectively), whereas the late fusion method generated slightly worst results (Dice of 95.5 ± 4.4% and 93.8 ± 3.1% for the head and brain, respectively). Nevertheless, the volumetric analysis showed that no statistically significant differences were found between the volumes of the models generated by all the segmentation strategies and the ground truths. Overall, the proposed frameworks demonstrate accurate segmentation results and prove to be feasible for anatomical model analysis in clinical practice.

show abstract

Deep learning-based detection of anthropometric landmarks in 3D infants head models

Cited by 8 publications

References 15 publications

Age Estimation via Selecting Discriminated Features and Preserving Geometry

Age Estimation via Selecting Discriminated Features and Preserving Geometry

3D Facial Landmark Localization for cephalometric analysis

Infant head and brain segmentation from magnetic resonance images using fusion-based deep learning strategies

Contact Info

Product

Resources

About