Background
The usefulness of computer‐assisted detection (CAD) for detecting cerebral aneurysms has been reported; therefore, the improved performance of CAD will help to detect cerebral aneurysms.
...Purpose
To develop a CAD system for intracranial aneurysms on unenhanced magnetic resonance angiography (MRA) images based on a deep convolutional neural network (CNN) and a maximum intensity projection (MIP) algorithm, and to demonstrate the usefulness of the system by training and evaluating it using a large dataset.
Study Type
Retrospective study.
Subjects
There were 450 cases with intracranial aneurysms. The diagnoses of brain aneurysms were made on the basis of MRA, which was performed as part of a brain screening program.
Field Strength/Sequence
Noncontrast‐enhanced 3D time‐of‐flight (TOF) MRA on 3T MR scanners.
Assessment
In our CAD, we used a CNN classifier that predicts whether each voxel is inside or outside aneurysms by inputting MIP images generated from a volume of interest (VOI) around the voxel. The CNN was trained in advance using manually inputted labels. We evaluated our method using 450 cases with intracranial aneurysms, 300 of which were used for training, 50 for parameter tuning, and 100 for the final evaluation.
Statistical Tests
Free‐response receiver operating characteristic (FROC) analysis.
Results
Our CAD system detected 94.2% (98/104) of aneurysms with 2.9 false positives per case (FPs/case). At a sensitivity of 70%, the number of FPs/case was 0.26.
Data Conclusion
We showed that the combination of a CNN and an MIP algorithm is useful for the detection of intracranial aneurysms.
Level of Evidence: 4
Technical Efficacy: Stage 1
J. Magn. Reson. Imaging 2018;47:948–953.
Despite their importance in determining the dosing regimen of drugs in the clinic, only a few studies have investigated methods for predicting blood-to-plasma concentration ratios (Rb). This study ...established an Rb prediction model incorporating typical human pharmacokinetics (PK) parameters. Experimental Rb values were compiled for 289 compounds, offering reliable predictions by expanding the applicability domain. Notably, it is the largest list of Rb values reported so far. Subsequently, human PK parameters calculated from plasma drug concentrations, including the volume of distribution (Vd), clearance, mean residence time, and plasma protein binding rate, as well as 2702 kinds of molecular descriptors, were used to construct quantitative structure–PK relationship models for Rb. Among the evaluated PK parameters, logVd correlated best with Rb (correlation coefficient of 0.47). Thus, in addition to molecular descriptors selected by XGBoost, logVd was employed to construct the prediction models. Among the analyzed algorithms, artificial neural networks gave the best results. Following optimization using six molecular descriptors and logVd, the model exhibited a correlation coefficient of 0.64 and a root-mean-square error of 0.205, which were superior to those previously reported for other Rb prediction methods. Since Vd values and chemical structures are known for most medications, the Rb prediction model described herein is expected to be valuable in clinical settings.
Graphical abstract
Background:Since endovascular aneurysm repair has become predominant, the issue of training young vascular surgeons in open abdominal aortic aneurysm (AAA) surgery has received significant attention. ...Through learning curve analysis, we aimed to determine the number of cases needed for young surgeons to achieve satisfactory open surgical skills.Methods and Results:A total of 562 consecutive patients who underwent open repair either by an attending surgeon (group A) or 6 young vascular surgeons (group Y) were included and assessed with regards to the preparation, clamp, and total operation times. Although some of the patients’ characteristics were different, the surgical procedures were comparable between the 2 groups. There was a clear trend towards a decrease in each 10 successive cases in group Y. The operation times in group A were constant at 72±30 (preparation), 48±10 (clamp), and 231±59 min (total), which were achieved by young vascular surgeons in 10, 30, and 10 cases, respectively. In the cumulative sum analysis, 25–27 cases were necessary for young vascular surgeons to enhance their surgical skills. The complication rate in group Y was no higher than that in group A.Conclusions:Young vascular surgeons can safely learn open AAA repair without increasing operation time or complications. Approximately 30 cases would be necessary to gain satisfactory surgical skills.
The purposes of this study are to propose an unsupervised anomaly detection method based on a deep neural network (DNN) model, which requires only normal images for training, and to evaluate its ...performance with a large chest radiograph dataset. We used the auto-encoding generative adversarial network (α-GAN) framework, which is a combination of a GAN and a variational autoencoder, as a DNN model. A total of 29,684 frontal chest radiographs from the Radiological Society of North America Pneumonia Detection Challenge dataset were used for this study (16,880 male and 12,804 female patients; average age, 47.0 years). All these images were labeled as “Normal,” “No Opacity/Not Normal,” or “Opacity” by board-certified radiologists. About 70% (6,853/9,790) of the Normal images were randomly sampled as the training dataset, and the rest were randomly split into the validation and test datasets in a ratio of 1:2 (7,610 and 15,221). Our anomaly detection system could correctly visualize various lesions including a lung mass, cardiomegaly, pleural effusion, bilateral hilar lymphadenopathy, and even dextrocardia. Our system detected the abnormal images with an area under the receiver operating characteristic curve (AUROC) of 0.752. The AUROCs for the abnormal labels Opacity and No Opacity/Not Normal were 0.838 and 0.704, respectively. Our DNN-based unsupervised anomaly detection method could successfully detect various diseases or anomalies in chest radiographs by training with only the normal images.
Purpose
To develop an anomaly detection system in PET/CT with the tracer
18
F-fluorodeoxyglucose (FDG) that requires only normal PET/CT images for training and can detect abnormal FDG uptake at any ...location in the chest region.
Materials and methods
We trained our model based on a Bayesian deep learning framework using 1878 PET/CT scans with no abnormal findings. Our model learns the distribution of standard uptake values in these normal training images and detects out-of-normal uptake regions. We evaluated this model using 34 scans showing focal abnormal FDG uptake in the chest region. This evaluation dataset includes 28 pulmonary and 17 extrapulmonary abnormal FDG uptake foci. We performed per-voxel and per-slice receiver operating characteristic (ROC) analyses and per-lesion free-response receiver operating characteristic analysis.
Results
Our model showed an area under the ROC curve of 0.992 on discriminating abnormal voxels and 0.852 on abnormal slices. Our model detected 41 of 45 (91.1%) of the abnormal FDG uptake foci with 12.8 false positives per scan (FPs/scan), which include 26 of 28 pulmonary and 15 of 17 extrapulmonary abnormalities. The sensitivity at 3.0 FPs/scan was 82.2% (37/45).
Conclusion
Our model trained only with normal PET/CT images successfully detected both pulmonary and extrapulmonary abnormal FDG uptake in the chest region.
Purpose
The performance of computer-aided detection (CAD) software depends on the quality and quantity of the dataset used for machine learning. If the data characteristics in development and ...practical use are different, the performance of CAD software degrades. In this study, we investigated changes in detection performance due to differences in training data for cerebral aneurysm detection software in head magnetic resonance angiography images.
Materials and methods
We utilized three types of CAD software for cerebral aneurysm detection in MRA images, which were based on 3D local intensity structure analysis, graph-based features, and convolutional neural network. For each type of CAD software, we compared three types of training pattern, which were two types of training using single-site data and one type of training using multisite data. We also carried out internal and external evaluations.
Results
In training using single-site data, the performance of CAD software largely and unpredictably fluctuated when the training dataset was changed. Training using multisite data did not show the lowest performance among the three training patterns for any CAD software and dataset.
Conclusion
The training of cerebral aneurysm detection software using data collected from multiple sites is desirable to ensure the stable performance of the software.
This study was aimed to predict drug-induced liver injury caused by reactive metabolites. Reactive metabolites covalently bind to proteins and could result in severe outcomes in patients. However, ...the relation between the extent of covalent binding and clinical hepatotoxicity is still unclear. From a perspective of body burden (human in vivo exposure to reactive metabolites), we developed a risk assessment method in which reactive metabolite burden (RM burden), an index that could reflect the body burden associated with reactive metabolite exposure, is calculated using the extent of covalent binding, clinical dose, and human in vivo clearance. The relationship between RM burden and hepatotoxicity in humans was then investigated. The results indicated that this RM burden assessment exhibited good predictability for sensitivity and specificity, and drugs with over 10 mg/day RM burden have high-risk for hepatotoxicity. Furthermore, a quantitative trapping assay using radiolabeled trapping agents (35Scysteine and 14CKCN) was also developed, to detect reactive metabolite formation in the early drug discovery stage. RM burden calculated using this assay showed as good predictability as RM burden calculated using conventional time- and cost-consuming covalent binding assays. These results indicated that the combination of RM burden and our trapping assay would be a good risk assessment method for reactive metabolites from the drug discovery stage.
A more accurate lung nodule detection algorithm is needed. We developed a modified three-dimensional (3D) U-net deep-learning model for the automated detection of lung nodules on chest CT images. The ...purpose of this study was to evaluate the accuracy of the developed modified 3D U-net deep-learning model.
In this Health Insurance Portability and Accountability Act-compliant, Institutional Review Board-approved retrospective study, the 3D U-net based deep-learning model was trained using the Lung Image Database Consortium and Image Database Resource Initiative dataset. For internal model validation, we used 89 chest CT scans that were not used for model training. For external model validation, we used 450 chest CT scans taken at an urban university hospital in Japan. Each case included at least one nodule of >5 mm identified by an experienced radiologist. We evaluated model accuracy using the competition performance metric (CPM) (average sensitivity at 1/8, 1/4, 1/2, 1, 2, 4, and 8 false-positives per scan). The 95% confidence interval (CI) was computed by bootstrapping 1000 times.
In the internal validation, the CPM was 94.7% (95% CI: 89.1%–98.6%). In the external validation, the CPM was 83.3% (95% CI: 79.4%–86.1%).
The modified 3D U-net deep-learning model showed high performance in both internal and external validation.
This study examines 4β-Hydroxycholesterol (4β-HC), which is considered to be a potential marker for the CYP3A4 induction of new chemical entities (NCEs) in drug development. To ensure the use of ...4β-HC as a practical biomarker, it is necessary to accurately measure 4β-HC and demonstrate that CYP3A4 induction can be appropriately assessed, even for weak inducers. In clinical trials of NCEs, plasma is often collected with various anticoagulants, in some cases, the plasma is acidified, then stored for an extended period. In this study, we examined the effects of these manipulations on the measurement of 4β-HC, and based on the results, we optimized the plasma collection and storage protocols. We also found that a cholesterol oxidation product is formed when plasma is stored, and by monitoring the compound, we were able to identify when plasma was stored inappropriately. After evaluating the above, clinical drug-drug interaction (DDI) studies were conducted using two NCEs (novel retinoid-related orphan receptor γ antagonists). The weak CYP3A4 induction by the NCEs (which were determined based on a slight decline in the systemic exposure of a probe substrate (midazolam)), was detected by the significant increase in 4β-HC levels (more specifically, 4β-HC/total cholesterol ratios). Our new approach, based on monitoring a cholesterol oxidation product to identify plasma that is stored inappropriately, allowed for the accurate measurement of 4β-HC, and thus, it enabled the evaluation of weak CYP3A4 inducers in clinical studies without using a probe substrate.