Fully automated deep learning model for detecting proximity of mandibular third molar root to inferior alveolar canal using panoramic radiographs.

OBJECTIVE: This study endeavored to develop a novel, fully automated deep-learning model to determine the topographic relationship between mandibular third molar (MM3) roots and the inferior alveolar canal (IAC) using panoramic radiographs (PRs). STUDY DESIGN: A total of 1570 eligible subjects with MM3s who had paired PR and cone beam computed tomography (CBCT) from January 2019 to December 2020 were retrospectively collected and randomly grouped into training (80%), validation (10%), and testing (10%) cohorts. The spatial relationship of MM3/IAC was assessed by CBCT and set as the ground truth. MM3-IACnet, a modified deep learning network based on YOLOv5 (You only look once), was trained to detect MM3/IAC proximity using PR. Its diagnostic performance was further compared with dentists, AlexNet, GoogleNet, VGG-16, ResNet-50, and YOLOv5 in another independent cohort with 100 high-risk MM3 defined as root overlapping with IAC on PR. RESULTS: The MM3-IACnet performed best in predicting the MM3/IAC proximity, as evidenced by the highest accuracy (0.885), precision (0.899), area under the curve value (0.95), and minimal time-spending compared with other models. Moreover, our MM3-IACnet outperformed other models in MM3/IAC risk prediction in high-risk cases. CONCLUSION: MM3-IACnet model can assist clinicians in MM3s risk assessment and treatment planning by detecting MM3/IAC topographic relationship using PR.

Nuclear Norm Regularized Deep Neural Network for EEG-Based Emotion Recognition.

Electroencephalography (EEG) based emotion recognition enables machines to perceive users' affective states, which has attracted increasing attention. However, most of the current emotion recognition methods neglect the structural information among different brain regions, which can lead to the incorrect learning of high-level EEG feature representation. To mitigate possible performance degradation, we propose a novel nuclear norm regularized deep neural network framework (NRDNN) that can capture the structural information among different brain regions in EEG decoding. The proposed NRDNN first utilizes deep neural networks to learn high-level feature representations of multiple brain regions, respectively. Then, a set of weights indicating the contributions of each brain region can be automatically learned using a region-attention layer. Subsequently, the weighted feature representations of multiple brain regions are stacked into a feature matrix, and the nuclear norm regularization is adopted to learn the structural information within the feature matrix. The proposed NRDNN method can learn the high-level representations of EEG signals within multiple brain regions, and the contributions of them can be automatically adjusted by assigning a set of weights. Besides, the structural information among multiple brain regions can be captured in the learning procedure. Finally, the proposed NRDNN can perform in an efficient end-to-end manner. We conducted extensive experiments on publicly available emotion EEG dataset to evaluate the effectiveness of the proposed NRDNN. Experimental results demonstrated that the proposed NRDNN can achieve state-of-the-art performance by leveraging the structural information.

Static coded aperture in robotic X-ray tomography systems.

Coded aperture X-ray computed tomography is a computational imaging technique capable of reconstructing inner structures of an object from a reduced set of X-ray projection measurements. Coded apertures are placed in front of the X-ray sources from different views and thus significantly reduce the radiation dose. This paper introduces coded aperture X-ray computed tomography for robotic X-ray systems which offer positioning flexibility. While single coded-aperture 3D tomography was recently introduced for standard trajectory CT scanning, it is shown that significant gains in imaging performance can be attained by simple modifications in the CT scanning trajectories enabled by emerging dual robotic CT systems. In particular, the subject is fixed on a plane and the CT system uniformly rotates around the r -axis which is misaligned with the coordinate axes. A single stationary coded aperture is placed on front of the robotic X-ray source above the plane and the corresponding X-ray projections are measured by a two-dimensional detector on the second arm of the robotic system. The compressive measurements with misalignment enable the reconstruction of high-resolution three-dimensional volumetric images from the low-resolution coded projections on the detector at a sub-sampling rate. An efficient algorithm is proposed to generate the rotation matrix with two basic sub-matrices and thus the forward model is formulated. The stationary coded aperture is designed based on the Pearson product-moment correlation coefficient analysis and the direct binary search algorithm is used to obtain the optimized coded aperture. Simulations using simulated datasets show significant gains in reconstruction performance compared to conventional coded aperture CT systems.

Limited-view CT Reconstruction Based on Autoencoder-like Generative Adversarial Networks with Joint Loss.

Limiting the scan views of X-ray computed tomography (CT) can make radiation dose reduced efficiently and consequently weaken the damage of ionizing radiation. However, it will degrade the reconstructed CT images. In this paper, we proposed to predict the missing projections and improve the reconstructed CT images by constructing an autoencoder-like generative adversarial network (GAN) with joint loss function. In the generator network, we train an autoencoder-like convolutional neural network (CNN) to generate the missing projections given a sinogram of the limited-view CT projections. For the discriminator network, a CNN is used to classify an input sinogram as real or synthetic one. To produce more realistic images, the joint loss function which includes not only reconstruction loss, but the adversarial loss is employed. While reconstruction loss can capture the overall structure of the missing projections, the latter can pick a particular mode from the distribution and make the results much sharper. After the missing projections have been estimated, we reconstruct the CT images from the completed projections by utilizing conventional filtered back-projection (FBP) method. The experiments prove the capability of our method to achieve a considerable improvement in limited-view CT reconstruction.

Online updating of context-aware landmark detectors for prostate localization in daily treatment CT images.

PURPOSE: In image guided radiation therapy, it is crucial to fast and accurately localize the prostate in the daily treatment images. To this end, the authors propose an online update scheme for landmark-guided prostate segmentation, which can fully exploit valuable patient-specific information contained in the previous treatment images and can achieve improved performance in landmark detection and prostate segmentation. METHODS: To localize the prostate in the daily treatment images, the authors first automatically detect six anatomical landmarks on the prostate boundary by adopting a context-aware landmark detection method. Specifically, in this method, a two-layer regression forest is trained as a detector for each target landmark. Once all the newly detected landmarks from new treatment images are reviewed or adjusted (if necessary) by clinicians, they are further included into the training pool as new patient-specific information to update all the two-layer regression forests for the next treatment day. As more and more treatment images of the current patient are acquired, the two-layer regression forests can be continually updated by incorporating the patient-specific information into the training procedure. After all target landmarks are detected, a multiatlas random sample consensus (multiatlas RANSAC) method is used to segment the entire prostate by fusing multiple previously segmented prostates of the current patient after they are aligned to the current treatment image. Subsequently, the segmented prostate of the current treatment image is again reviewed (or even adjusted if needed) by clinicians before including it as a new shape example into the prostate shape dataset for helping localize the entire prostate in the next treatment image. RESULTS: The experimental results on 330 images of 24 patients show the effectiveness of the authors' proposed online update scheme in improving the accuracies of both landmark detection and prostate segmentation. Besides, compared to the other state-of-the-art prostate segmentation methods, the authors' method achieves the best performance. CONCLUSIONS: By appropriate use of valuable patient-specific information contained in the previous treatment images, the authors' proposed online update scheme can obtain satisfactory results for both landmark detection and prostate segmentation.

Conditional entropy maximization for PET image reconstruction using adaptive mesh model.

Iterative image reconstruction algorithms have been widely used in the field of positron emission tomography (PET). However, such algorithms are sensitive to noise artifacts so that the reconstruction begins to degrade when the number of iterations is high. In this paper, we propose a new algorithm to reconstruct an image from the PET emission projection data by using the conditional entropy maximization and the adaptive mesh model. In a traditional tomography reconstruction method, the reconstructed image is directly computed in the pixel domain. Unlike this kind of methods, the proposed approach is performed by estimating the nodal values from the observed projection data in a mesh domain. In our method, the initial Delaunay triangulation mesh is generated from a set of randomly selected pixel points, and it is then modified according to the pixel intensity value of the estimated image at each iteration step in which the conditional entropy maximization is used. The advantage of using the adaptive mesh model for image reconstruction is that it provides a natural spatially adaptive smoothness mechanism. In experiments using the synthetic and clinical data, it is found that the proposed algorithm is more robust to noise compared to the common pixel-based MLEM algorithm and mesh-based MLEM with a fixed mesh structure.