Differential Requirements for eIF4E Dose in Normal Development and Cancer.

eIF4E, the major cap-binding protein, has long been considered limiting for translating the mammalian genome. However, the eIF4E dose requirement at an organismal level remains unexplored. By generating an Eif4e haploinsufficient mouse, we found that a 50% reduction in eIF4E expression, while compatible with normal development and global protein synthesis, significantly impeded cellular transformation. Genome-wide translational profiling uncovered a translational program induced by oncogenic transformation and revealed a critical role for the dose of eIF4E, specifically in translating a network of mRNAs enriched for a unique 5' UTR signature. In particular, we demonstrate that the dose of eIF4E is essential for translating mRNAs that regulate reactive oxygen species, fueling transformation and cancer cell survival in vivo. Our findings indicate eIF4E is maintained at levels in excess for normal development that are hijacked by cancer cells to drive a translational program supporting tumorigenesis.

Reconfiguring the Electronic Structure of Heteroatom Doped Carbon Supported Bimetallic Oxide@Metal Sulfide Core-Shell Heterostructure via In Situ Nb Incorporation toward Extrinsic Pseudocapacitor.

High-energy-density battery-type materials have sparked considerable interest as supercapacitors electrode; however, their sluggish charge kinetics limits utilization of redox-active sites, resulting in poor electrochemical performance. Here, the unique core-shell architecture of metal organic framework derived N-S codoped carbon@Cox Sy micropetals decorated with Nb-incorporated cobalt molybdate nanosheets (Nb-CMO4 @Cx Sy NC) is demonstrated. Coordination bonding across interfaces and π-π stacking interactions between CMO4 @Cx Sy and N and, S-C can prevent volume expansion during cycling. Density functional theory analysis reveals that the excellent interlayer and the interparticle conductivity imparted by Nb doping in heteroatoms synergistically alter the electronic states and offer more accessible species, leading to increased electrical conductivity with lower band gaps. Consequently, the optimized electrode has a high specific capacity of 276.3 mAh g-1 at 1 A g-1 and retains 98.7% of its capacity after 10 000 charge-discharge cycles. A flexible quasi-solid-state SC with a layer-by-layer deposited reduced graphene oxide /Ti3 C2 TX anode achieves a specific energy of 75.5 Wh kg-1 (volumetric energy of 1.58 mWh cm-3 ) at a specific power of 1.875 kWh kg-1 with 96.2% capacity retention over 10 000 charge-discharge cycles.

Tool-Wear-Estimation System in Milling Using Multi-View CNN Based on Reflected Infrared Images.

A novel method for tool wear estimation in milling using infrared (IR) laser vision and a deep-learning algorithm is proposed and demonstrated. The measurement device employs an IR line laser to irradiate the tool focal point at angles of -7.5°, 0.0°, and +7.5° to the vertical plane, and three cameras are placed at 45° intervals around the tool to collect the reflected IR light at different locations. For the processing materials and methods, a dry processing method was applied to a 100 mm × 100 mm × 40 mm SDK-11 workpiece through end milling and downward cutting using a TH308 insert. This device uses the diffused light reflected off the surface of a rotating tool roughened by flank wear, and a polarization filter is considered. As the measured tool wear images exhibit a low dynamic range of exposure, high dynamic range (HDR) images are obtained using an exposure fusion method. Finally, tool wear is estimated from the images using a multi-view convolutional neural network. As shown in the results of the estimated tool wear, a mean absolute error (MAE) of prediction error calculated was to be 9.5~35.21 µm. The proposed method can improve machining efficiency by reducing the downtime for tool wear measurement and by increasing tool life utilization.

Temporal Estimation of Non-Rigid Dynamic Human Point Cloud Sequence Using 3D Skeleton-Based Deformation for Compression.

This paper proposes an algorithm for transmitting and reconstructing the estimated point cloud by temporally estimating a dynamic point cloud sequence. When a non-rigid 3D point cloud sequence (PCS) is input, the sequence is divided into groups of point cloud frames (PCFs), and a key PCF is selected. The 3D skeleton is predicted through 3D pose estimation, and the motion of the skeleton is estimated by analyzing the joints and bones of the 3D skeleton. For the deformation of the non-rigid human PC, the 3D PC model is transformed into a mesh model, and the key PCF is rigged using the 3D skeleton. After deforming the key PCF into the target PCF utilizing the motion vector of the estimated skeleton, the residual PC between the motion compensation PCF and the target PCF is generated. If there is a key PCF, the motion vector of the target PCF, and a residual PC, the target PCF can be reconstructed. Just as compression is performed using pixel correlation between frames in a 2D video, this paper compresses 3D PCFs by estimating the non-rigid 3D motion of a 3D object in a 3D PC. The proposed algorithm can be regarded as an extension of the 2D motion estimation of a rigid local region in a 2D plane to the 3D motion estimation of a non-rigid object (human) in 3D space. Experimental results show that the proposed method can successfully compress 3D PC sequences. If it is used together with a PC compression technique such as MPEG PCC (point cloud compression) in the future, a system with high compression efficiency may be configured.

Dosimetry in radionuclide therapy: the clinical role of measuring radiation dose.

Radionuclide therapy is a rapidly expanding oncological treatment method. Overwhelmingly, the application of radionuclide therapy in clinical practice relies on fixed or empirical dosing strategies. In principle, the application of dosimetry promises to improve patient outcomes by tailoring administered radionuclide therapy activities to each patient's unique tumour burden and tumour uptake. However, robust prospective data are scarce due to few prospective randomised clinical trials investigating the use of dosimetry in radionuclide therapy. In this Review, we describe the role of dosimetry as it has been applied historically and in modern clinical practice and its potential future applications. We further emphasise areas of future growth and a potential pathway to optimised personalised activity modulation of radionuclide therapy.

[18F]-(2S,4R)4-Fluoroglutamine PET Imaging of Glutamine Metabolism in Murine Models of Hepatocellular Carcinoma (HCC).

Purpose: Quantitative in vivo [18F]-(2S,4R)4-fluoroglutamine ([18F]4-FGln or more simply [18F]FGln) metabolic kinetic parameters are compared with activity levels of glutamine metabolism in different types of hepatocellular carcinoma (HCC). Methods: For this study, we used two transgenic mouse models of HCC induced by protooncogenes, MYC, and MET. Biochemical data have shown that tumors induced by MYC have increased levels of glutamine metabolism compared to those induced by MET. One-hour dynamic [18F]FGln PET data were acquired and reconstructed for fasted MYC mice (n = 11 tumors from 7 animals), fasted MET mice (n = 8 tumors from 6 animals), fasted FVBN controls (n = 8 normal liver regions from 6 animals), nonfasted MYC mice (n = 16 tumors from 6 animals), and nonfasted FVBN controls (n = 8 normal liver regions from 3 animals). The influx rate constants (K 1) using the one-tissue compartment model were derived for each tumor with the left ventricular blood pool input function. Results: Influx rate constants were significantly higher for MYC tumors (K 1 = 0.374 ± 0.133) than for MET tumors (K 1 = 0.141 ± 0.058) under fasting conditions (P = 0.0002). Rate constants were also significantly lower for MET tumors (K 1 = 0.141 ± 0.135) than normal livers (K 1 = 0.332 ± 0.179) under fasting conditions (P = 0.0123). Fasting conditions tested for MYC tumors and normal livers did not result in any significant difference with P values > 0.005. Conclusion: Higher influx rate constants corresponded to elevated levels of glutamine metabolism as determined by biochemical assays. The data showed that there is a distinctive difference in glutamine metabolism between MYC and MET tumors. Our study has demonstrated the potential of [18F]FGln PET imaging as a tool to assess glutamine metabolism in HCC tumors in vivo with a caution that it may not be able to clearly distinguish HCC tumors from normal liver tissue.

Biodistribution of a Mitochondrial Metabolic Tracer, [18F]F-AraG, in Healthy Volunteers.

Purpose: [18F]F-AraG is a radiolabeled nucleoside analog that shows relative specificity for activated T cells. The aim of this study was to investigate the biodistribution of [18F]F-AraG in healthy volunteers and assess the preliminary safety and radiation dosimetry. Methods: Six healthy subjects (three female and three male) between the ages of 24 and 60 participated in the study. Each subject received a bolus venous injection of [18F]F-AraG (dose range: 244.2-329.3 MBq) prior to four consecutive PET/MR whole-body scans. Blood samples were collected at regular intervals and vital signs monitored before and after tracer administration. Regions of interest were delineated for multiple organs, and the area under the time-activity curves was calculated for each organ and used to derive time-integrated activity coefficient (TIAC). TIACs were input for absorbed dose and effective dose calculations using OLINDA. Results: PET/MR examination was well tolerated, and no adverse effects to the administration of [18F]F-AraG were noted by the study participants. The biodistribution was generally reflective of the expression and activity profiles of the enzymes involved in [18F]F-AraG's cellular accumulation, mitochondrial kinase dGK, and SAMHD1. The highest uptake was observed in the kidneys and liver, while the brain, lung, bone marrow, and muscle showed low tracer uptake. The estimated effective dose for [18F]F-AraG was 0.0162 mSv/MBq (0.0167 mSv/MBq for females and 0.0157 mSv/MBq for males). Conclusion: Biodistribution of [18F]F-AraG in healthy volunteers was consistent with its association with mitochondrial metabolism. PET/MR [18F]F-AraG imaging was well tolerated, with a radiation dosimetry profile similar to other commonly used [18F]-labeled tracers. [18F]F-AraG's connection with mitochondrial biogenesis and favorable biodistribution characteristics make it an attractive tracer with a variety of potential applications.

Imaging joint infections using D-methyl-11C-methionine PET/MRI: initial experience in humans.

PURPOSE: Non-invasive imaging is a key clinical tool for detection and treatment monitoring of infections. Existing clinical imaging techniques are frequently unable to distinguish infection from tumors or sterile inflammation. This challenge is well-illustrated by prosthetic joint infections that often complicate joint replacements. D-methyl-11C-methionine (D-11C-Met) is a new bacteria-specific PET radiotracer, based on an amino acid D-enantiomer, that is rapidly incorporated into the bacterial cell wall. In this manuscript, we describe the biodistribution, radiation dosimetry, and initial human experience using D-11C-Met in patients with suspected prosthetic joint infections. METHODS: 614.5 ± 100.2 MBq of D-11C-Met was synthesized using an automated in-loop radiosynthesis method and administered to six healthy volunteers and five patients with suspected prosthetic joint infection, who were studied by PET/MRI. Time-activity curves were used to calculate residence times for each source organ. Absorbed doses to each organ and body effective doses were calculated using OLINDA/EXM 1.1 with both ICRP 60 and ICRP 103 tissue weighting factors. SUVmax and SUVpeak were calculated for volumes of interest (VOIs) in joints with suspected infection, the unaffected contralateral joint, blood pool, and soft tissue background. A two-tissue compartment model was used for kinetic modeling. RESULTS: D-11C-Met was well tolerated in all subjects. The tracer showed clearance from both urinary (rapid) and hepatobiliary (slow) pathways as well as low effective doses. Moreover, minimal background was observed in both organs with resident micro-flora and target organs, such as the spine and musculoskeletal system. Additionally, D-11C-Met showed increased focal uptake in areas of suspected infection, demonstrated by a significantly higher SUVmax and SUVpeak calculated from VOIs of joints with suspected infections compared to the contralateral joints, blood pool, and background (P < 0.01). Furthermore, higher distribution volume and binding potential were observed in suspected infections compared to the unaffected joints. CONCLUSION: D-11C-Met has a favorable radiation profile, minimal background uptake, and fast urinary extraction. Furthermore, D-11C-Met showed increased uptake in areas of suspected infection, making this a promising approach. Validation in larger clinical trials with a rigorous gold standard is still required.

Functional Adaptation of LPS-affected Dentoalveolar Fibrous Joints in Rats.

INTRODUCTION: The functional interplay between cementum of the root and alveolar bone of the socket is tuned by a uniquely positioned 70-80 µm wide fibrous and lubricious ligament in a dentoalveolar joint (DAJ). In this study, structural and biomechanical properties of the DAJ, periodontal ligament space (PDL-space also known as the joint space), alveolar bone of the socket, and cementum of the tooth root that govern the biomechanics of a lipopolysaccharide (LPS)-affected DAJ were mapped both in space and time. METHODS: The hemi-maxillae from 20 rats (4 control at 6 weeks of age, 4 control and 4 LPS-affected at 12 weeks of age, 4 control and 4 LPS-affected at 16 weeks of age) were investigated using a hybrid technique; micro-X-ray computed tomography (5 µm resolution) in combination with biomechanical testing in situ. Temporal variations in bone and cementum volume fractions were evaluated. Trends in mineral apposition rates (MAR) in additional six Sprague Dawley rats (3 controls, 3 LPS-affected) were revealed by transforming spatial fluorochrome signals to functional growth rates (linearity factor - RW) of bone, dentin, and cementum using a fast Fourier transform on fluorochrome signals from 100-µm hemi-maxillae sections. RESULTS: An overall change in LPS-affected DAJ biomechanics (a 2.5-4.5X increase in tooth displacement and 2X tooth rotation at 6 weeks, no increase in displacement and a 7X increase in rotation at 12 weeks; 27% increase in bone effective strain at 6 weeks and 11% at 12 weeks relative to control) was associated with structural changes in the coronal regions of the DAJ (15% increase in PDL-space from 0 to 6 weeks but only 5% from 6 to 12 weeks compared to control). A significant increase (p < 0.05) in PDL-space between ligated and age-matched control was observed. The bone fraction of ligated at 12 weeks was significantly lower than its age-matched control, and no significant differences (p > 0.05) between groups were observed at 6 weeks. Cementum in the apical regions grew faster but nonlinearly (11% and 20% increase in cementum fraction (CF) at 6 and 12 weeks) compared to control. Alveolar bone revealed site-specific nonlinear growth with an overall increase in MAR (108.5 µm/week to 126.7 µm/week after LPS treatment) compared to dentin (28.3 µm/week in control vs. 26.1 µm/week in LPS-affected) and cementum (126.5 µm/week in control vs. 119.9 µm/week in LPS-affected). A significant increase in CF (p < 0.05) in ligated specimens was observed at 6 weeks of age. CONCLUSIONS: Anatomy-specific responses of cementum and bone to the mechano-chemo stimuli, and their collective temporal contribution to observed changes in PDL-space were perpetuated by altered tooth movement. Data highlight the "resilience" of DAJ function through the predominance of nonlinear growth response of cementum, changes in PDL-space, and bone architecture. Despite the significant differences in bone and cementum architectures, data provided insights into the reactionary effects of cementum as a built-in compensatory mechanism to reestablish functional competence of the DAJ. The spatial shifts in architectures of alveolar bone and cementum, and consequently ligament space, highlight adaptations farther away from the site of insult, which also is another novel insight from this study. These adaptations when correlated within the context of joint function (biomechanics) illustrate that they are indeed necessary to sustain DAJ function albeit being pathological.

Phase-only hologram video compression using a deep neural network for up-scaling and restoration.

This paper proposes a coding method for compressing a phase-only hologram video (PoHV), which can be directly displayed in a commercial phase-only spatial light modulator. Recently, there has been active research to use a standard codec as an anchor to develop a new video coding for 3D data such as MPEG point cloud compression. The main merit of this approach is that if a new video codec is developed, the performance of relative coding methods can be increased simultaneously. Furthermore, compatibility is increased by the capability to use various anchor codecs, and the developing time is decreased. This paper uses a currently used video codec as an anchor codec and develops a coding method including progressive scaling and a deep neural network to overcome low temporal correlation between frames of a PoHV. Since it is difficult to temporally predict a correlation between frames of a PoHV, this paper adopts a scaling function and a neural network in the encoding and decoding process, not adding complexity to an anchor itself to predict temporal correlation. The proposed coding method shows an enhanced coding gain of an average of 22%, compared with an anchor in all coding conditions. When observing numerical and optical reconstructions, the result images by the proposed show clearer objects and less juddering than the result by the anchor.

Clinical language search algorithm from free-text: facilitating appropriate imaging.

BACKGROUND: The comprehensiveness and maintenance of the American College of Radiology (ACR) Appropriateness Criteria (AC) makes it a unique resource for evidence-based clinical imaging decision support, but it is underutilized by clinicians. To facilitate the use of imaging recommendations, we develop a natural language processing (NLP) search algorithm that automatically matches clinical indications that physicians write into imaging orders to appropriate AC imaging recommendations. METHODS: We apply a hybrid model of semantic similarity from a sent2vec model trained on 223 million scientific sentences, combined with term frequency inverse document frequency features. AC documents are ranked based on their embeddings' cosine distance to query. For model testing, we compiled a dataset of simulated simple and complex indications for each AC document (n = 410) and another with clinical indications from randomly sampled radiology reports (n = 100). We compare our algorithm to a custom google search engine. RESULTS: On the simulated indications, our algorithm ranked ground truth documents as top 3 for 98% of simple queries and 85% of complex queries. Similarly, on the randomly sampled radiology report dataset, the algorithm ranked 86% of indications with a single match as top 3. Vague and distracting phrases present in the free-text indications were main sources of errors. Our algorithm provides more relevant results than a custom Google search engine, especially for complex queries. CONCLUSIONS: We have developed and evaluated an NLP algorithm that matches clinical indications to appropriate AC guidelines. This approach can be integrated into imaging ordering systems for automated access to guidelines.

3D Static Point Cloud Registration by Estimating Temporal Human Pose at Multiview.

This paper proposes a new technique for performing 3D static-point cloud registration after calibrating a multi-view RGB-D camera using a 3D (dimensional) joint set. Consistent feature points are required to calibrate a multi-view camera, and accurate feature points are necessary to obtain high-accuracy calibration results. In general, a special tool, such as a chessboard, is used to calibrate a multi-view camera. However, this paper uses joints on a human skeleton as feature points for calibrating a multi-view camera to perform calibration efficiently without special tools. We propose an RGB-D-based calibration algorithm that uses the joint coordinates of the 3D joint set obtained through pose estimation as feature points. Since human body information captured by the multi-view camera may be incomplete, a joint set predicted based on image information obtained through this may be incomplete. After efficiently integrating a plurality of incomplete joint sets into one joint set, multi-view cameras can be calibrated by using the combined joint set to obtain extrinsic matrices. To increase the accuracy of calibration, multiple joint sets are used for optimization through temporal iteration. We prove through experiments that it is possible to calibrate a multi-view camera using a large number of incomplete joint sets.

Dynamic Reconstruction and Mesh Compression of 4D Volumetric Model Using Correspondence-Based Deformation for Streaming Service.

A sequence of 3D models generated using volumetric capture has the advantage of retaining the characteristics of dynamic objects and scenes. However, in volumetric data, since 3D mesh and texture are synthesized for every frame, the mesh of every frame has a different shape, and the brightness and color quality of the texture is various. This paper proposes an algorithm to consistently create a mesh of 4D volumetric data using dynamic reconstruction. The proposed algorithm comprises remeshing, correspondence searching, and target frame reconstruction by key frame deformation. We make non-rigid deformation possible by applying the surface deformation method of the key frame. Finally, we propose a method of compressing the target frame using the target frame reconstructed using the key frame with error rates of up to 98.88% and at least 20.39% compared to previous studies. The experimental results show the proposed method's effectiveness by measuring the geometric error between the deformed key frame and the target frame. Further, by calculating the residual between two frames, the ratio of data transmitted is measured to show a compression performance of 18.48%.

Robust Estimation and Optimized Transmission of 3D Feature Points for Computer Vision on Mobile Communication Network.

Due to the amount of transmitted data and the security of personal or private information in wireless communication, there are cases where the information for a multimedia service should be directly transferred from the user's device to the cloud server without the captured original images. This paper proposes a new method to generate 3D (dimensional) keypoints based on a user's mobile device with a commercial RGB camera in a distributed computing environment such as a cloud server. The images are captured with a moving camera and 2D keypoints are extracted from them. After executing feature extraction between continuous frames, disparities are calculated between frames using the relationships between matched keypoints. The physical distance of the baseline is estimated by using the motion information of the camera, and the actual distance is calculated by using the calculated disparity and the estimated baseline. Finally, 3D keypoints are generated by adding the extracted 2D keypoints to the calculated distance. A keypoint-based scene change method is proposed as well. Due to the existing similarity between continuous frames captured from a camera, not all 3D keypoints are transferred and stored, only the new ones. Compared with the ground truth of the TUM dataset, the average error of the estimated 3D keypoints was measured as 5.98 mm, which shows that the proposed method has relatively good performance considering that it uses a commercial RGB camera on a mobile device. Furthermore, the transferred 3D keypoints were decreased to about 73.6%.

Incorporating Radiomics into Machine Learning Models to Predict Outcomes of Neuroblastoma.

Neuroblastoma is one of the most common pediatric cancers. This study used machine learning (ML) to predict the mortality and a few other investigated intermediate outcomes of neuroblastoma patients non-invasively from CT images. Performances of multiple ML algorithms over retrospective CT images of 65 neuroblastoma patients are analyzed. An artificial neural network (ANN) is used on tumor radiomic features extracted from 3D CT images. A pre-trained 2D convolutional neural network (CNN) is used on slices of the same images. ML models are trained for various pathologically investigated outcomes of these patients. A subspecialty-trained pediatric radiologist independently reviewed the manually segmented primary tumors. Pyradiomics library is used to extract 105 radiomic features. Six ML algorithms are compared to predict the following outcomes: mortality, presence or absence of metastases, neuroblastoma differentiation, mitosis-karyorrhexis index (MKI), presence or absence of MYCN gene amplification, and presence of image-defined risk factors (IDRF). The prediction ranges over multiple experiments are measured using the area under the receiver operating characteristic (ROC-AUC) for comparison. Our results show that the radiomics-based ANN method slightly outperforms the other algorithms in predicting all outcomes except classification of the grade of neuroblastic differentiation, for which the elastic regression model performed the best. Contributions of the article are twofold: (1) noninvasive models for the prognosis from CT images of neuroblastoma, and (2) comparison of relevant ML models on this medical imaging problem.

Domain specific word embeddings for natural language processing in radiology.

BACKGROUND: There has been increasing interest in machine learning based natural language processing (NLP) methods in radiology; however, models have often used word embeddings trained on general web corpora due to lack of a radiology-specific corpus. PURPOSE: We examined the potential of Radiopaedia to serve as a general radiology corpus to produce radiology specific word embeddings that could be used to enhance performance on a NLP task on radiological text. MATERIALS AND METHODS: Embeddings of dimension 50, 100, 200, and 300 were trained on articles collected from Radiopaedia using a GloVe algorithm and evaluated on analogy completion. A shallow neural network using input from either our trained embeddings or pre-trained Wikipedia 2014 + Gigaword 5 (WG) embeddings was used to label the Radiopaedia articles. Labeling performance was evaluated based on exact match accuracy and Hamming loss. The McNemar's test with continuity and the Benjamini-Hochberg correction and a 5×2 cross validation paired two-tailed t-test were used to assess statistical significance. RESULTS: For accuracy in the analogy task, 50-dimensional (50-D) Radiopaedia embeddings outperformed WG embeddings on tumor origin analogies (p < 0.05) and organ adjectives (p < 0.01) whereas WG embeddings tended to outperform on inflammation location and bone vs. muscle analogies (p < 0.01). The two embeddings had comparable performance on other subcategories. In the labeling task, the Radiopaedia-based model outperformed the WG based model at 50, 100, 200, and 300-D for exact match accuracy (p < 0.001, p < 0.001, p < 0.01, and p < 0.05, respectively) and Hamming loss (p < 0.001, p < 0.001, p < 0.01, and p < 0.05, respectively). CONCLUSION: We have developed a set of word embeddings from Radiopaedia and shown that they can preserve relevant medical semantics and augment performance on a radiology NLP task. Our results suggest that the cultivation of a radiology-specific corpus can benefit radiology NLP models in the future.

Deep-learning-based hologram generation using a generative model.

We propose a new learning and inferring model that generates digital holograms using deep neural networks (DNNs). This DNN uses a generative adversarial network, trained to infer a complex two-dimensional fringe pattern from a single object point. The intensity and fringe patterns inferred for each object point were multiplied, and all the fringe patterns were accumulated to generate a perfect hologram. This method can achieve generality by recording holograms for two spaces (16 Space and 32 Space). The reconstruction results of both spaces proved to be almost the same as numerical computer-generated holograms by showing the performance at 44.56 and 35.11 dB, respectively. Through displaying the generated hologram in the optical equipment, we proved that the holograms generated by the proposed DNN can be optically reconstructed.

High precision localization of pulmonary nodules on chest CT utilizing axial slice number labels.

BACKGROUND: Reidentification of prior nodules for temporal comparison is an important but time-consuming step in lung cancer screening. We develop and evaluate an automated nodule detector that utilizes the axial-slice number of nodules found in radiology reports to generate high precision nodule predictions. METHODS: 888 CTs from Lung Nodule Analysis were used to train a 2-dimensional (2D) object detection neural network. A pipeline of 2D object detection, 3D unsupervised clustering, false positive reduction, and axial-slice numbers were used to generate nodule candidates. 47 CTs from the National Lung Cancer Screening Trial (NLST) were used for model evaluation. RESULTS: Our nodule detector achieved a precision of 0.962 at a recall of 0.573 on the NLST test set for any nodule. When adjusting for unintended nodule predictions, we achieved a precision of 0.931 at a recall 0.561, which corresponds to 0.06 false positives per CT. Error analysis revealed better detection of nodules with soft tissue attenuation compared to ground glass and undeterminable attenuation. Nodule margins, size, location, and patient demographics did not differ between correct and incorrect predictions. CONCLUSIONS: Utilization of axial-slice numbers from radiology reports allowed for development of a lung nodule detector with a low false positive rate compared to prior feature-engineering and machine learning approaches. This high precision nodule detector can reduce time spent on reidentification of prior nodules during lung cancer screening and can rapidly develop new institutional datasets to explore novel applications of computer vision in lung cancer imaging.

Development and web deployment of an automated neuroradiology MRI protocoling tool with natural language processing.

BACKGROUND: A systematic approach to MRI protocol assignment is essential for the efficient delivery of safe patient care. Advances in natural language processing (NLP) allow for the development of accurate automated protocol assignment. We aim to develop, evaluate, and deploy an NLP model that automates protocol assignment, given the clinician indication text. METHODS: We collected 7139 spine MRI protocols (routine or contrast) and 990 head MRI protocols (routine brain, contrast brain, or other) from a single institution. Protocols were split into training (n = 4997 for spine MRI; n = 839 for head MRI), validation (n = 1071 for spine MRI, fivefold cross-validation used for head MRI), and test (n = 1071 for spine MRI; n = 151 for head MRI) sets. fastText and XGBoost were used to develop 2 NLP models to classify spine and head MRI protocols, respectively. A Flask-based web app was developed to be deployed via Heroku. RESULTS: The spine MRI model had an accuracy of 83.38% and a receiver operator characteristic area under the curve (ROC-AUC) of 0.8873. The head MRI model had an accuracy of 85.43% with a routine brain protocol ROC-AUC of 0.9463 and contrast brain protocol ROC-AUC of 0.9284. Cancer, infectious, and inflammatory related keywords were associated with contrast administration. Structural anatomic abnormalities and stroke/altered mental status were indicative of routine spine and brain MRI, respectively. Error analysis revealed increasing the sample size may improve performance for head MRI protocols. A web version of the model is provided for demonstration and deployment. CONCLUSION: We developed and web-deployed two NLP models that accurately predict spine and head MRI protocol assignment, which could improve radiology workflow efficiency.

Digital Hologram Watermarking Based on Multiple Deep Neural Networks Training Reconstruction and Attack.

This paper proposes a method to embed and extract a watermark on a digital hologram using a deep neural network. The entire algorithm for watermarking digital holograms consists of three sub-networks. For the robustness of watermarking, an attack simulation is inserted inside the deep neural network. By including attack simulation and holographic reconstruction in the network, the deep neural network for watermarking can simultaneously train invisibility and robustness. We propose a network training method using hologram and reconstruction. After training the proposed network, we analyze the robustness of each attack and perform re-training according to this result to propose a method to improve the robustness. We quantitatively evaluate the results of robustness against various attacks and show the reliability of the proposed technique.