Bidirectional de novo peptide sequencing using a transformer model.

In proteomics, a crucial aspect is to identify peptide sequences. De novo sequencing methods have been widely employed to identify peptide sequences, and numerous tools have been proposed over the past two decades. Recently, deep learning approaches have been introduced for de novo sequencing. Previous methods focused on encoding tandem mass spectra and predicting peptide sequences from the first amino acid onwards. However, when predicting peptides using tandem mass spectra, the peptide sequence can be predicted not only from the first amino acid but also from the last amino acid due to the coexistence of b-ion (or a- or c-ion) and y-ion (or x- or z-ion) fragments in the tandem mass spectra. Therefore, it is essential to predict peptide sequences bidirectionally. Our approach, called NovoB, utilizes a Transformer model to predict peptide sequences bidirectionally, starting with both the first and last amino acids. In comparison to Casanovo, our method achieved an improvement of the average peptide-level accuracy rate of approximately 9.8% across all species.

V2-Net: An Attention-guided Volumetric Regression Network for Tooth Landmark Localization on CT Images with Metal Artifacts.

For virtual surgical planning in orthognathic surgery, marking tooth landmarks on CT images is an important procedure. However, the manual localization procedure of tooth landmarks is time-consuming, labor-intensive, and requires expert knowledge. Also, direct and automatic tooth landmark localization on CT images is difficult because of the lower resolution and metal artifacts of dental images. The purpose of this study was to propose an attention-guided volumetric regression network (V2-Net) for accurate tooth landmark localization on CT images with metal artifacts and lower resolution. V2-Net has an attention-guided network architecture using a coarse-to-fine-attention mechanism that guided the 3D probability distribution of tooth landmark locations within anatomical structures from the coarse V-Net to the fine V-Net for more focus on tooth landmarks. In addition, we combined attention-guided learning and a 3D attention module with optimal Pseudo Huber loss to improve the localization accuracy. Our results show that the proposed method achieves state-of-the-art accuracy of 0.85 ± 0.40 mm in terms of mean radial error, outperforming previous studies. In ablation studies, we observed that the proposed attention-guided learning and a 3D attention module improved the accuracy of tooth landmark localization in CT images of lower resolution and metal artifacts. Furthermore, our method achieved 97.92% in terms of the success detection rate within the clinically accepted accuracy range of 2.0 mm.

Automatic classification of 3D positional relationship between mandibular third molar and inferior alveolar canal using a distance-aware network.

The purpose of this study was to automatically classify the three-dimensional (3D) positional relationship between an impacted mandibular third molar (M3) and the inferior alveolar canal (MC) using a distance-aware network in cone-beam CT (CBCT) images. We developed a network consisting of cascaded stages of segmentation and classification for the buccal-lingual relationship between the M3 and the MC. The M3 and the MC were simultaneously segmented using Dense121 U-Net in the segmentation stage, and their buccal-lingual relationship was automatically classified using a 3D distance-aware network with the multichannel inputs of the original CBCT image and the signed distance map (SDM) generated from the segmentation in the classification stage. The Dense121 U-Net achieved the highest average precision of 0.87, 0.96, and 0.94 in the segmentation of the M3, the MC, and both together, respectively. The 3D distance-aware classification network of the Dense121 U-Net with the input of both the CBCT image and the SDM showed the highest performance of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve, each of which had a value of 1.00. The SDM generated from the segmentation mask significantly contributed to increasing the accuracy of the classification network. The proposed distance-aware network demonstrated high accuracy in the automatic classification of the 3D positional relationship between the M3 and the MC by learning anatomical and geometrical information from the CBCT images.

False discovery rate estimation using candidate peptides for each spectrum.

BACKGROUND: False discovery rate (FDR) estimation is very important in proteomics. The target-decoy strategy (TDS), which is often used for FDR estimation, estimates the FDR under the assumption that when spectra are identified incorrectly, the probabilities of the spectra matching the target or decoy peptides are identical. However, no spectra matching target or decoy peptide probabilities are identical. We propose cTDS (target-decoy strategy with candidate peptides) for accurate estimation of the FDR using the probability that the spectrum is identified incorrectly as a target or decoy peptide. RESULTS: Most spectrum cases result in a probability of having the spectrum identified incorrectly as a target or decoy peptide of close to 0.5, but only about 1.14-4.85% of the total spectra have an exact probability of 0.5. We used an entrapment sequence method to demonstrate the accuracy of cTDS. For fixed FDR thresholds (1-10%), the false match rate (FMR) in cTDS is closer than the FMR in TDS. We compared the number of peptide-spectrum matches (PSMs) obtained with TDS and cTDS at a 1% FDR threshold with the HEK293 dataset. In the first and third replications, the number of PSMs obtained with cTDS for the reverse, pseudo-reverse, shuffle, and de Bruijn databases exceeded those obtained with TDS (about 0.001-0.132%), with the pseudo-shuffle database containing less compared to TDS (about 0.05-0.126%). In the second replication, the number of PSMs obtained with cTDS for all databases exceeds that obtained with TDS (about 0.013-0.274%). CONCLUSIONS: When spectra are actually identified incorrectly, most probabilities of the spectra matching a target or decoy peptide are not identical. Therefore, we propose cTDS, which estimates the FDR more accurately using the probability of the spectrum being identified incorrectly as a target or decoy peptide.

Canal-Net for automatic and robust 3D segmentation of mandibular canals in CBCT images using a continuity-aware contextual network.

The purpose of this study was to propose a continuity-aware contextual network (Canal-Net) for the automatic and robust 3D segmentation of the mandibular canal (MC) with high consistent accuracy throughout the entire MC volume in cone-beam CT (CBCT) images. The Canal-Net was designed based on a 3D U-Net with bidirectional convolutional long short-term memory (ConvLSTM) under a multi-task learning framework. Specifically, the Canal-Net learned the 3D anatomical context information of the MC by incorporating spatio-temporal features from ConvLSTM, and also the structural continuity of the overall MC volume under a multi-task learning framework using multi-planar projection losses complementally. The Canal-Net showed higher segmentation accuracies in 2D and 3D performance metrics (p < 0.05), and especially, a significant improvement in Dice similarity coefficient scores and mean curve distance (p < 0.05) throughout the entire MC volume compared to other popular deep learning networks. As a result, the Canal-Net achieved high consistent accuracy in 3D segmentations of the entire MC in spite of the areas of low visibility by the unclear and ambiguous cortical bone layer. Therefore, the Canal-Net demonstrated the automatic and robust 3D segmentation of the entire MC volume by improving structural continuity and boundary details of the MC in CBCT images.

A Complete Digital Workflow for Planning, Simulation, and Evaluation in Orthognathic Surgery.

The purpose of this study was to develop a complete digital workflow for planning, simulation, and evaluation for orthognathic surgery based on 3D digital natural head position reproduction, a cloud-based collaboration platform, and 3D landmark-based evaluation. We included 24 patients who underwent bimaxillary orthognathic surgery. Surgeons and engineers could share the massive image data immediately and conveniently and collaborate closely in surgical planning and simulation using a cloud-based platform. The digital surgical splint could be optimized for a specific patient before or after the physical fabrication of 3D printing splints through close collaboration. The surgical accuracy was evaluated comprehensively via the translational (linear) and rotational (angular) discrepancies between identical 3D landmarks on the simulation and postoperative computed tomography (CT) models. The means of the absolute linear discrepancy at eight tooth landmarks were 0.61 ± 0.55, 0.86 ± 0.68, and 1.00 ± 0.79 mm in left-right, advance-setback, and impaction-elongation directions, respectively, and 1.67 mm in the root mean square direction. The linear discrepancy in the left-right direction was significantly different from the other two directions as shown by analysis of variance (ANOVA, p < 0.05). The means of the absolute angular discrepancies were 1.43 ± 1.06°, 0.50 ± 0.31°, and 0.58 ± 0.41° in the pitch, roll, and yaw orientations, respectively. The angular discrepancy in the pitch orientation was significantly different from the other two orientations (ANOVA, p < 0.05). The complete digital workflow that we developed for orthognathic patients provides efficient and streamlined procedures for orthognathic surgery and shows high surgical accuracy with efficient image data sharing and close collaboration.

Comparison of false-discovery rates of various decoy databases.

BACKGROUND: The target-decoy strategy effectively estimates the false-discovery rate (FDR) by creating a decoy database with a size identical to that of the target database. Decoy databases are created by various methods, such as, the reverse, pseudo-reverse, shuffle, pseudo-shuffle, and the de Bruijn methods. FDR is sometimes over- or under-estimated depending on which decoy database is used because the ratios of redundant peptides in the target databases are different, that is, the numbers of unique (non-redundancy) peptides in the target and decoy databases differ. RESULTS: We used two protein databases (the UniProt Saccharomyces cerevisiae protein database and the UniProt human protein database) to compare the FDRs of various decoy databases. When the ratio of redundant peptides in the target database is low, the FDR is not overestimated by any decoy construction method. However, if the ratio of redundant peptides in the target database is high, the FDR is overestimated when the (pseudo) shuffle decoy database is used. Additionally, human and S. cerevisiae six frame translation databases, which are large databases, also showed outcomes similar to that from the UniProt human protein database. CONCLUSION: The FDR must be estimated using the correction factor proposed by Elias and Gygi or that by Kim et al. when (pseudo) shuffle decoy databases are used.

QCBCT-NET for direct measurement of bone mineral density from quantitative cone-beam CT: a human skull phantom study.

The purpose of this study was to directly and quantitatively measure BMD from Cone-beam CT (CBCT) images by enhancing the linearity and uniformity of the bone intensities based on a hybrid deep-learning model (QCBCT-NET) of combining the generative adversarial network (Cycle-GAN) and U-Net, and to compare the bone images enhanced by the QCBCT-NET with those by Cycle-GAN and U-Net. We used two phantoms of human skulls encased in acrylic, one for the training and validation datasets, and the other for the test dataset. We proposed the QCBCT-NET consisting of Cycle-GAN with residual blocks and a multi-channel U-Net using paired training data of quantitative CT (QCT) and CBCT images. The BMD images produced by QCBCT-NET significantly outperformed the images produced by the Cycle-GAN or the U-Net in mean absolute difference (MAD), peak signal to noise ratio (PSNR), normalized cross-correlation (NCC), structural similarity (SSIM), and linearity when compared to the original QCT image. The QCBCT-NET improved the contrast of the bone images by reflecting the original BMD distribution of the QCT image locally using the Cycle-GAN, and also spatial uniformity of the bone images by globally suppressing image artifacts and noise using the two-channel U-Net. The QCBCT-NET substantially enhanced the linearity, uniformity, and contrast as well as the anatomical and quantitative accuracy of the bone images, and demonstrated more accuracy than the Cycle-GAN and the U-Net for quantitatively measuring BMD in CBCT.

Quantitative Augmented Reality-Assisted Free-Hand Orthognathic Surgery Using Electromagnetic Tracking and Skin-Attached Dynamic Reference.

The purpose of this study was to develop a quantitative AR-assisted free-hand orthognathic surgery method using electromagnetic (EM) tracking and skin-attached dynamic reference. The authors proposed a novel, simplified, and convenient workflow for augmented reality (AR)-assisted orthognathic surgery based on optical marker-less tracking, a comfortable display, and a non-invasive, skin-attached dynamic reference frame. The 2 registrations between the physical (EM tracking) and CT image spaces and between the physical and AR camera spaces, essential processes in AR-assisted surgery, were pre-operatively performed using the registration body complex and 3D depth camera. The intraoperative model of the maxillary bone segment (MBS) was superimposed on the real patient image with the simulated goal model on a flat-panel display, and the MBS was freely handled for repositioning with respect to the skin-attached dynamic reference tool (SRT) with quantitative visualization of landmarks of interest using only EM tracking. To evaluate the accuracy of AR-assisted Le Fort I surgery, the MBS of the phantom was simulated and repositioned by 6 translational and three rotational movements. The mean absolute deviations (MADs) between the simulation and post-operative positions of MBS landmarks by the SRT were 0.20, 0.34, 0.29, and 0.55 mm in x- (left lateral, right lateral), y- (setback, advance), and z- (impaction, elongation) directions, and RMS, respectively, while those by the BRT were 0.23, 0.37, 0.30, and 0.60 mm. There were no significant differences between the translation and rotation surgeries or among surgeries in the x-, y-, and z-axes for the SRT. The MADs in the x-, y-, and z-axes exhibited no significant differences between the SRT and BRT. The developed method showed high accuracy and reliability in free-hand orthognathic surgery using EM tracking and skin-attached dynamic reference.

Development of panorama resolution phantom for comprehensive evaluation of the horizontal and vertical resolution of panoramic radiography.

Panoramic radiography is the most commonly used equipment in the dental field, but there is no comprehensive standard about how to evaluate the spatial resolution of panoramic radiography. In this study, panorama resolution phantoms were developed for evaluation of horizontal and vertical resolution reflecting unique characteristics of panoramic radiography. Four horizontal resolution phantoms of staircase shape were designed to obtain images of horizontal lead line pairs in a 52 mm width. Four vertical resolution phantoms with vertical lead line pairs placed at an oblique angle were also designed. A phantom stand was made. Three machines were evaluated twice by two oromaxillofacial radiologists. The horizontal lead line pairs were readable over the entire measured area at the values of 1.88, 2.32, and 2.58 lp/mm for all machines. A readable area of horizontal 3.19 lp/mm was observed in the lingual side. In the vertical resolution phantoms, it was possible to read a narrower range. By using the panorama resolution phantoms and phantom stand, it was possible to evaluate the resolution of a wide buccolingual width in four significant areas. By evaluating the resolution of the vertical and horizontal compartments separately, it was possible to gain a better understanding of the obtained images.

Deep Learning Hybrid Method to Automatically Diagnose Periodontal Bone Loss and Stage Periodontitis.

We developed an automatic method for staging periodontitis on dental panoramic radiographs using the deep learning hybrid method. A novel hybrid framework was proposed to automatically detect and classify the periodontal bone loss of each individual tooth. The framework is a hybrid of deep learning architecture for detection and conventional CAD processing for classification. Deep learning was used to detect the radiographic bone level (or the CEJ level) as a simple structure for the whole jaw on panoramic radiographs. Next, the percentage rate analysis of the radiographic bone loss combined the tooth long-axis with the periodontal bone and CEJ levels. Using the percentage rate, we could automatically classify the periodontal bone loss. This classification was used for periodontitis staging according to the new criteria proposed at the 2017 World Workshop on the Classification of Periodontal and Peri-Implant Diseases and Conditions. The Pearson correlation coefficient of the automatic method with the diagnoses by radiologists was 0.73 overall for the whole jaw (p < 0.01), and the intraclass correlation value 0.91 overall for the whole jaw (p < 0.01). The novel hybrid framework that combined deep learning architecture and the conventional CAD approach demonstrated high accuracy and excellent reliability in the automatic diagnosis of periodontal bone loss and staging of periodontitis.

Target-small decoy search strategy for false discovery rate estimation.

BACKGROUND: One of the most important steps in peptide identification is to estimate the false discovery rate (FDR). The most commonly used method for estimating FDR is the target-decoy search strategy (TDS). While this method is simple and effective, it is time/space-inefficient because it searches a database that is twice as large as the original protein database. This inefficiency problem becomes more evident as protein databases get bigger and bigger. We propose a target-small decoy search strategy and present a rigorous verification that it reduces the database size and search time while retaining the accuracy of target-decoy search strategy (TDS). RESULTS: We show that peptide spectrum matches (PSMs) obtained at 1% FDR in TDS overlap ~ 99% with those in our method. (Considering that 1% FDR is used, 99% overlap means our method is very accurate.) Moreover, our method is more time/space-efficient than TDS. The search time of our method is reduced to only 1/4 of that of TDS when UniProt and its 1/8 decoy database are used. CONCLUSIONS: We demonstrate that our method is almost as accurate as TDS and more time/space-efficient than TDS. Since the efficiency of our method is more evident as the database size increases, our method is expected to be useful for identifying peptides in proteogenomics databases constructed from inflated databases using genomic data.

Real-time augmented model guidance for mandibular proximal segment repositioning in orthognathic surgery, using electromagnetic tracking.

It is essential to reposition the mandibular proximal segment (MPS) as close to its original position as possible during orthognathic surgery. Conventional methods cannot pinpoint the exact position of the condyle in the fossa in real time during repositioning. In this study, based on an improved registration method and a separable electromagnetic tracking tool, we developed a real-time, augmented, model-guided method for MPS surgery to reposition the condyle into its original position more accurately. After virtual surgery planning, using a complex maxillomandibular model, the final position of the virtual MPS model was simulated via 3D rotations. The displacements resulting from the MPS simulation were applied to the MPS landmarks to indicate their final postoperative positions. We designed a new registration body with 24 fiducial points for registration, and determined the optimal point group on the registration body through a phantom study. The registration between the patient's CT image and physical spaces was performed preoperatively using the optimal points. We also developed a separable frame for installing the electromagnetic tracking tool on the patient's MPS. During MPS surgery, the electromagnetic tracking tool was repeatedly attached to, and separated from, the MPS using the separable frame. The MPS movement resulting from the surgeon's manipulation was tracked by the electromagnetic tracking system. The augmented condyle model and its landmarks were visualized continuously in real time with respect to the simulated model and landmarks. Our method also provides augmented 3D coronal and sagittal views of the fossa and condyle, to allow the surgeon to examine the 3D condyle-fossa positional relationship more accurately. The root mean square differences between the simulated and intraoperative MPS models, and between the simulated and postoperative CT models, were 1.71 ± 0.63 mm and 1.89 ± 0.22 mm respectively at three condylar landmarks. Thus, the surgeons could perform MPS repositioning conveniently and accurately based on real-time augmented model guidance on the 3D condyle positional relationship with respect to the glenoid fossa, using augmented and simulated models and landmarks.

Autonomous bone reposition around anatomical landmark for robot-assisted orthognathic surgery.

The purpose of this study was to develop a new method for enabling a robot to assist a surgeon in repositioning a bone segment to accurately transfer a preoperative virtual plan into the intraoperative phase in orthognathic surgery. We developed a robot system consisting of an arm with six degrees of freedom, a robot motion-controller, and a PC. An end-effector at the end of the robot arm transferred the movements of the robot arm to the patient's jawbone. The registration between the robot and CT image spaces was performed completely preoperatively, and the intraoperative registration could be finished using only position changes of the tracking tools at the robot end-effector and the patient's splint. The phantom's maxillomandibular complex (MMC) connected to the robot's end-effector was repositioned autonomously by the robot movements around an anatomical landmark of interest based on the tool center point (TCP) principle. The robot repositioned the MMC around the TCP of the incisor of the maxilla and the pogonion of the mandible following plans for real orthognathic patients. The accuracy of the robot's repositioning increased when an anatomical landmark for the TCP was close to the registration fiducials. In spite of this influence, we could increase the repositioning accuracy at the landmark by using the landmark itself as the TCP. With its ability to incorporate virtual planning using a CT image and autonomously execute the plan around an anatomical landmark of interest, the robot could help surgeons reposition bones more accurately and dexterously.

Virtual skeletal complex model- and landmark-guided orthognathic surgery system.

In this study, correction of the maxillofacial deformities was performed by repositioning bone segments to an appropriate location according to the preoperative planning in orthognathic surgery. The surgery was planned using the patient's virtual skeletal models fused with optically scanned three-dimensional dentition. The virtual maxillomandibular complex (MMC) model of the patient's final occlusal relationship was generated by fusion of the maxillary and mandibular models with scanned occlusion. The final position of the MMC was simulated preoperatively by planning and was used as a goal model for guidance. During surgery, the intraoperative registration was finished immediately using only software processing. For accurate repositioning, the intraoperative MMC model was visualized on the monitor with respect to the simulated MMC model, and the intraoperative positions of multiple landmarks were also visualized on the MMC surface model. The deviation errors between the intraoperative and the final positions of each landmark were visualized quantitatively. As a result, the surgeon could easily recognize the three-dimensional deviation of the intraoperative MMC state from the final goal model without manually applying a pointing tool, and could also quickly determine the amount and direction of further MMC movements needed to reach the goal position. The surgeon could also perform various osteotomies and remove bone interference conveniently, as the maxillary tracking tool could be separated from the MMC. The root mean square (RMS) difference between the preoperative planning and the intraoperative guidance was 1.16 ± 0.34 mm immediately after repositioning. After surgery, the RMS differences between the planning and the postoperative computed tomographic model were 1.31 ± 0.28 mm and 1.74 ± 0.73 mm for the maxillary and mandibular landmarks, respectively. Our method provides accurate and flexible guidance for bimaxillary orthognathic surgery based on intraoperative visualization and quantification of deviations for simulated postoperative MMC and landmarks. The guidance using simulated skeletal models and landmarks can complement and improve conventional navigational surgery for bone repositioning in the craniomaxillofacial area.