Fine structural human phantom in dentistry and instance tooth segmentation.

In this study, we present the development of a fine structural human phantom designed specifically for applications in dentistry. This research focused on assessing the viability of applying medical computer vision techniques to the task of segmenting individual teeth within a phantom. Using a virtual cone-beam computed tomography (CBCT) system, we generated over 170,000 training datasets. These datasets were produced by varying the elemental densities and tooth sizes within the human phantom, as well as varying the X-ray spectrum, noise intensity, and projection cutoff intensity in the virtual CBCT system. The deep-learning (DL) based tooth segmentation model was trained using the generated datasets. The results demonstrate an agreement with manual contouring when applied to clinical CBCT data. Specifically, the Dice similarity coefficient exceeded 0.87, indicating the robust performance of the developed segmentation model even when virtual imaging was used. The present results show the practical utility of virtual imaging techniques in dentistry and highlight the potential of medical computer vision for enhancing precision and efficiency in dental imaging processes.

Conversion map from quantitative parameter mapping to myelin water fraction: comparison with R1·R2* and myelin water fraction in white matter.

OBJECTIVE: To clarify the relationship between myelin water fraction (MWF) and R1⋅R2* and to develop a method to calculate MWF directly from parameters derived from QPM, i.e., MWF converted from QPM (MWFQPM). MATERIALS AND METHODS: Subjects were 12 healthy volunteers. On a 3 T MR scanner, dataset was acquired using spoiled gradient-echo sequence for QPM. MWF and R1⋅R2* maps were derived from the multi-gradient-echo (mGRE) dataset. Volume-of-interest (VOI) analysis using the JHU-white matter (WM) atlas was performed. All the data in the 48 WM regions measured VOI were plotted, and quadratic polynomial approximations of each region were derived from the relationship between R1·R2* and the two-pool model-MWF. The R1·R2* map was converted to MWFQPM map. MWF atlas template was generated using converted to MWF from R1·R2* per WM region. RESULTS: The mean MWF and R1·R2* values for the 48 WM regions were 11.96 ± 6.63%, and 19.94 ± 4.59 s-2, respectively. A non-linear relationship in 48 regions of the WM between MWF and R1·R2* values was observed by quadratic polynomial approximation (R2 ≥ 0.963, P < 0.0001). DISCUSSION: MWFQPM map improved image quality compared to the mGRE-MWF map. Myelin water atlas template derived from MWFQPM may be generated with combined multiple WM regions.

Pixel-by-pixel correction of beam hardening artifacts by bowtie filter in fan-beam CT.

Objective. Beam hardening (BH) artifacts in computed tomography (CT) images originate from the polychromatic nature of x-ray photons. In a CT system with a bowtie filter, residual BH artifacts remain when polynomial fits are used. These artifacts lead to worse visuals, reduced contrast, and inaccurate CT numbers. This work proposes a pixel-by-pixel correction (PPC) method to reduce the residual BH artifacts caused by a bowtie filter.Approach. The energy spectrum for each pixel at the detector after the photons pass through the bowtie filter was calculated. Then, the spectrum was filtered through a series of water slabs with different thicknesses. The polychromatic projection corresponding to the thickness of the water slab for each detector pixel could be obtained. Next, we carried out a water slab experiment with a mono energyE= 69 keV to get the monochromatic projection. The polychromatic and monochromatic projections were then fitted with a 2nd-order polynomial. The proposed method was evaluated on digital phantoms in a virtual CT system and phantoms in a real CT machine.Main results. In the case of a virtual CT system, the standard deviation of the line profile was reduced by 23.8%, 37.3%, and 14.3%, respectively, in the water phantom with different shapes. The difference of the linear attenuation coefficients (LAC) in the central and peripheral areas of an image was reduced from 0.010 to 0.003cm-1and 0.007cm-1to 0 in the biological tissue phantom and human phantom, respectively. The method was also validated using CT projection data obtained from Activion16 (Canon Medical Systems, Japan). The difference in the LAC in the central and peripheral areas can be reduced by a factor of two.Significance. The proposed PPC method can successfully remove the cupping artifacts in both virtual and authentic CT images. The scanned object's shapes and materials do not affect the technique.

Differences of white matter structure for diffusion kurtosis imaging using voxel-based morphometry and connectivity analysis.

Objectives: In a clinical study, diffusion kurtosis imaging (DKI) has been used to visualize and distinguish white matter (WM) structures' details. The purpose of our study is to evaluate and compare the diffusion tensor imaging (DTI) and DKI parameter values to obtain WM structure differences of healthy subjects. Methods: Thirteen healthy volunteers (mean age, 25.2 years) were examined in this study. On a 3-T MRI system, diffusion dataset for DKI was acquired using an echo-planner imaging sequence, and T1-weghted (T1w) images were acquired. Imaging analysis was performed using Functional MRI of the brain Software Library (FSL). First, registration analysis was performed using the T1w of each subject to MNI152. Second, DTI (eg, fractional anisotropy [FA] and each diffusivity) and DKI (eg, mean kurtosis [MK], radial kurtosis [RK], and axial kurtosis [AK]) datasets were applied to above computed spline coefficients and affine matrices. Each DTI and DKI parameter value for WM areas was compared. Finally, tract-based spatial statistics (TBSS) analysis was performed using each parameter. Results: The relationship between FA and kurtosis parameters (MK, RK, and AK) for WM areas had a strong positive correlation (FA-MK, R2 = 0.93; FA-RK, R2 = 0.89) and a strong negative correlation (FA-AK, R2 = 0.92). When comparing a TBSS connection, we found that this could be observed more clearly in MK than in RK and FA. Conclusions: WM analysis with DKI enable us to obtain more detailed information for connectivity between nerve structures. Advances in knowledge: Quantitative indices of neurological diseases were determined using segmenting WM regions using voxel-based morphometry processing of DKI images.

Determination of Alzheimer's disease based on morphology and atrophy using machine learning combined with automated segmentation.

BACKGROUND: To evaluate the degree of cerebral atrophy for Alzheimer's disease (AD), voxel-based morphometry has been performed with magnetic resonance imaging. Detailed morphological changes in a specific tissue area having the most evidence of atrophy were not considered by the machine-learning technique. PURPOSE: To develop a machine-learning system that can capture morphology features for determination of atrophy of brain tissue in early-stage AD and classification of healthy participants or patients. MATERIAL AND METHODS: Three-dimensional T1-weighted (3D-T1W) data were obtained from AD Neuroimaging Initiative (200 healthy controls and 200 patients with early-stage AD). Automated segmentation of 3D-T1W data was performed. Deep learning (DL) and support vector machine (SVM) were trained using 66-segmented volume values as input and AD diagnosis as output. DL was performed using 66 volume values or gray matter (GM) and white matter (WM) volume values. SVM learning was performed using 66 volume values and six regions with high variable importance. 3D convolutional neural network (3D-CNN) was trained using the segmented images. Accuracy and area under curve (AUC) were obtained. Variable importance was evaluated from logistic regression analysis. RESULTS: DL for GM and WM volume values, accuracy 0.6; SVM for all volume values, accuracy 0.82 and AUC 0.81; DL for all volume values, accuracy 0.82 and AUC 0.8; 3D-CNN using segmental images of the whole brain, accuracy 0.5 and AUC 0.51. SVM using volume values of six regions, accuracy 0.82; image-based 3D-CNN, highest accuracy 0.69. CONCLUSION: Our results show that atrophic features are more considerable than morphological features in the early detection of AD.

A novel CT-based radiomics model for predicting response and prognosis of chemoradiotherapy in esophageal squamous cell carcinoma.

No clinically relevant biomarker has been identified for predicting the response of esophageal squamous cell carcinoma (ESCC) to chemoradiotherapy (CRT). Herein, we established a CT-based radiomics model with artificial intelligence (AI) to predict the response and prognosis of CRT in ESCC. A total of 44 ESCC patients (stage I-IV) were enrolled in this study; training (n = 27) and validation (n = 17) cohorts. First, we extracted a total of 476 radiomics features from three-dimensional CT images of cancer lesions in training cohort, selected 110 features associated with the CRT response by ROC analysis (AUC ≥ 0.7) and identified 12 independent features, excluding correlated features by Pearson's correlation analysis (r ≥ 0.7). Based on the 12 features, we constructed 5 prediction models of different machine learning algorithms (Random Forest (RF), Ridge Regression, Naive Bayes, Support Vector Machine, and Artificial Neural Network models). Among those, the RF model showed the highest AUC in the training cohort (0.99 [95%CI 0.86-1.00]) as well as in the validation cohort (0.92 [95%CI 0.71-0.99]) to predict the CRT response. Additionally, Kaplan-Meyer analysis of the validation cohort and all the patient data showed significantly longer progression-free and overall survival in the high-prediction score group compared with the low-prediction score group in the RF model. Univariate and multivariate analyses revealed that the radiomics prediction score and lymph node metastasis were independent prognostic biomarkers for CRT of ESCC. In conclusion, we have developed a CT-based radiomics model using AI, which may have the potential to predict the CRT response as well as the prognosis for ESCC patients with non-invasiveness and cost-effectiveness.

Quantum annealing-based computed tomography using variational approach for a real-number image reconstruction.

Objective. Despite recent advancements in quantum computing, the limited number of available qubits has hindered progress in CT reconstruction. This study investigates the feasibility of utilizing quantum annealing-based computed tomography (QACT) with current quantum bit levels.Approach. The QACT algorithm aims to precisely solve quadratic unconstrained binary optimization problems. Furthermore, a novel approach is proposed to reconstruct images by approximating real numbers using the variational method. This approach allows for accurate CT image reconstruction using a small number of qubits. The study examines the impact of projection data quantity and noise on various image sizes ranging from 4 × 4 to 24 × 24 pixels. The reconstructed results are compared against conventional reconstruction algorithms, namely maximum likelihood expectation maximization (MLEM) and filtered back projection (FBP).Main result. By employing the variational approach and utilizing two qubits for each pixel of the image, accurate reconstruction was achieved with an adequate number of projections. Under conditions of abundant projections and lower noise levels, the image quality in QACT algorithm outperformed that of MLEM and FBP algorithms. However, in situations with limited projection data and in the presence of noise, the image quality in QACT was inferior to that in MLEM.Significance. This study developed the QACT reconstruction algorithm using the variational approach for real-number reconstruction. Remarkably, only 2 qubits were required for each pixel representation, demonstrating their sufficiency for accurate reconstruction.

Simplified assessment for chemical exchanged saturation transfer (CEST) imaging: local offset frequency and CEST effect.

The aim of this study is to develop a novel phantom for the evaluation of clinical CEST imaging settings, e.g., B0 and B1 field inhomogeneities, CEST contrast, and post-processing. We made a phantom composed of two slice sections: a grid section for local offset frequency evaluation and a sample section for CEST effect evaluation using different concentrations of an egg white albumin solution. On a 3 Tesla MR scanner, a phantom study was performed using CEST imaging; the mean B1 amplitudes were set at 1.2 and 1.9 µT, and CEST images with and without B0 corrections were acquired. Next, region of interest (ROI) analysis was performed for each slice. Then, CEST images with and without B0 corrections were compared at each B1 amplitude. The B0 corrected Z-spectrums at each local region in the grid section showed a shifting of the curve bottom to 0 ppm. Z-spectrum at B1 = 1.9 µT showed a broader curve shape than that at 1.2 µT. Moreover, MTRasym values at 3.5 ppm for each albumin sample at B1 = 1.9 µT were about two times higher than those at 1.2 µT. Our phantom enabled us to evaluate and optimize B0 inhomogeneity and the CEST effect at the B1 amplitude.

Virtual cone-beam computed tomography simulator with human phantom library and its application to the elemental material decomposition.

PURPOSE: The purpose of this study is to develop a virtual CBCT simulator with a head and neck (HN) human phantom library and to demonstrate the feasibility of elemental material decomposition (EMD) for quantitative CBCT imaging using this virtual simulator. METHODS: The library of 36 HN human phantoms were developed by extending the ICRP 110 adult phantoms based on human age, height, and weight statistics. To create the CBCT database for the library, a virtual CBCT simulator that simulated the direct and scattered X-ray on a flat panel detector using ray-tracing and deep-learning (DL) models was used. Gaussian distributed noise was also included on the flat panel detector, which was evaluated using a real CBCT system. The usefulness of the virtual CBCT system was demonstrated through the application of the developed DL-based EMD model for case involving virtual phantom and real patient. RESULTS: The virtual simulator could generate various virtual CBCT images based on the human phantom library, and the prediction of the EMD could be successfully performed by preparing the CBCT database from the proposed virtual system, even for a real patient. The CBCT image degradation owing to the scattered X-ray and the statistical noise affected the prediction accuracy, although these effects were minimal. Furthermore, the elemental distribution using the real CBCT image was also predictable. CONCLUSIONS: This study demonstrated the potential of using computer vision for medical data preparation and analysis, which could have important implications for improving patient outcomes, especially in adaptive radiation therapy.

X-ray energy spectrum estimation based on a virtual computed tomography system.

This paper presents a method for estimating the x-ray energy spectrum for computed tomography (CT) in the diagnostic energy range from the reconstructed CT image itself. To this end, a virtual CT system was developed, and datasets, including CT images for the Gammex phantom labeled by the corresponding energy spectra, were generated. Using these datasets, an artificial neural network (ANN) model was trained to reproduce the energy spectrum from the CT values in the Gammex inserts. In the actual application, an aluminum-based bow-tie filter was used in the virtual CT system, and an ANN model with a bow-tie filter was also developed. Both ANN models without/with a bow-tie filter can estimate the x-ray spectrum within the agreement, which is defined as one minus the absolute error, of more than 80% on average. The agreement increases as the tube voltage increases. The estimation was occasionally inaccurate when the amount of noise on the CT image was considerable. Image quality with a signal-to-noise ratio of more than 10 for the basis material of the Gammex phantom was required to predict the spectrum accurately. Based on the experimental data acquired from Activion16 (Canon Medical System, Japan), the ANN model with a bow-tie filter produced a reasonable energy spectrum by simultaneous optimization of the shape of the bow-tie filter. The present method requires a CT image for the Gammex phantom only, and no special setup, thus it is expected to be readily applied in clinical applications, such as beam hardening reduction, CT dose management, and material decomposition, all of which require exact information on the x-ray energy spectrum.

Radiomics analysis of [18F]-fluoro-2-deoxyglucose positron emission tomography for the prediction of cervical lymph node metastasis in tongue squamous cell carcinoma.

OBJECTIVES: This study aimed to create a predictive model for cervical lymph node metastasis (CLNM) in patients with tongue squamous cell carcinoma (SCC) based on radiomics features detected by [18F]-fluoro-2-deoxyglucose (18F-FDG) positron emission tomography (PET). METHODS: A total of 40 patients with tongue SCC who underwent 18F-FDG PET imaging during their first medical examination were enrolled. During the follow-up period (mean 28 months), 20 patients had CLNM, including six with late CLNM, whereas the remaining 20 patients did not have CLNM. Radiomics features were extracted from 18F-FDG PET images of all patients irrespective of metal artifact, and clinicopathological factors were obtained from the medical records. Late CLNM was defined as the CLNM that occurred after major treatment. The least absolute shrinkage and selection operator (LASSO) model was used for radiomics feature selection and sequential data fitting. The receiver operating characteristic curve analysis was used to assess the predictive performance of the 18F-FDG PET-based model and clinicopathological factors model (CFM) for CLNM. RESULTS: Six radiomics features were selected from LASSO analysis. The average values of the area under the curve (AUC), accuracy, sensitivity, and specificity of radiomics analysis for predicting CLNM from 18F-FDG PET images were 0.79, 0.68, 0.65, and 0.70, respectively. In contrast, those of the CFM were 0.54, 0.60, 0.60, and 0.60, respectively. The 18F-FDG PET-based model showed significantly higher AUC than that of the CFM. CONCLUSIONS: The 18F-FDG PET-based model has better potential for diagnosing CLNM and predicting late CLNM in patients with tongue SCC than the CFM.

Development of a more accurate Geant4 quantum molecular dynamics model for hadron therapy.

Objective. Although in heavy-ion therapy, the quantum molecular dynamics (QMD) model is one of the most fundamental physics models providing an accurate daughter-ion production yield in the final state, there are still non-negligible differences with the experimental results. The aim of this study is to improve fragment production in water phantoms by developing a more accurate QMD model in Geant4.Approach. A QMD model was developed by implementing modern Skyrme interaction parameter sets, as well as by incorporating with an ad hocα-cluster model in the initial nuclear state. Two adjusting parameters were selected that can significantly affect the fragment productions in the QMD model: the radius to discriminate a cluster to which nucleons belong after the nucleus-nucleus reaction, denoted byR, and the squared standard deviation of the Gaussian packet, denoted byL. Squared Mahalanobis's distance of fragment yields and angular distributions with 1, 2, and the higher atomic number for the produced fragments were employed as objective functions, and multi-objective optimization (MOO), which make it possible to compare quantitatively the simulated production yields with the reference experimental data, was performed.Main results. The MOO analysis showed that the QMD model with modern Skyrme parameters coupled with the proposedα-cluster model, denoted as SkM*α, can drastically improve light fragments yields in water. In addition, the proposed model reproduced the kinetic energy distribution of the fragments accurately. The optimizedLin SkM*αwas confirmed to be realistic by the charge radii analysis in the ground state formation.Significance. The proposed framework using MOO was demonstrated to be very useful in judging the superiority of the proposed nuclear model. The optimized QMD model is expected to improve the accuracy of heavy-ion therapy dosimetry.

Gradient boosting decision tree becomes more reliable than logistic regression in predicting probability for diabetes with big data.

We sought to verify the reliability of machine learning (ML) in developing diabetes prediction models by utilizing big data. To this end, we compared the reliability of gradient boosting decision tree (GBDT) and logistic regression (LR) models using data obtained from the Kokuho-database of the Osaka prefecture, Japan. To develop the models, we focused on 16 predictors from health checkup data from April 2013 to December 2014. A total of 277,651 eligible participants were studied. The prediction models were developed using a light gradient boosting machine (LightGBM), which is an effective GBDT implementation algorithm, and LR. Their reliabilities were measured based on expected calibration error (ECE), negative log-likelihood (Logloss), and reliability diagrams. Similarly, their classification accuracies were measured in the area under the curve (AUC). We further analyzed their reliabilities while changing the sample size for training. Among the 277,651 participants, 15,900 (7978 males and 7922 females) were newly diagnosed with diabetes within 3 years. LightGBM (LR) achieved an ECE of 0.0018 ± 0.00033 (0.0048 ± 0.00058), a Logloss of 0.167 ± 0.00062 (0.172 ± 0.00090), and an AUC of 0.844 ± 0.0025 (0.826 ± 0.0035). From sample size analysis, the reliability of LightGBM became higher than LR when the sample size increased more than [Formula: see text]. Thus, we confirmed that GBDT provides a more reliable model than that of LR in the development of diabetes prediction models using big data. ML could potentially produce a highly reliable diabetes prediction model, a helpful tool for improving lifestyle and preventing diabetes.

Myelin-weighted imaging derived from quantitative parameter mapping.

PURPOSE: We developed a novel method which is applicable to visualize contrast according to myelin components in the human brain using relaxation time derived from quantitative parameter mapping magnetic resonance imaging (QPM-MRI). MATERIALS AND METHODS: Using healthy volunteer data (n = 10), we verified that our method demonstrated that the myelin-weighted contrast increased proportionally by products R1 and R2*, i.e., QPM-myelin-weighted image, in which modified T1-weighted/T2-weighted (T1w/T2w) ratio mapping method was applied. We compared measurement values in white matter (WM) and gray matter (GM) regions of the T1w/T2w ratio and R1·R2* product maps of healthy volunteers. Linear regression analysis between each value. Mann Whitney U test between WM and GM signals in each myelin map. In addition, Additionally, QPM-myelin-weighted image was applied to a 32-year-old female MS patient. RESULTS: Linear regression analysis showed a highly significant correlation between conventional T1w/T2w ratios and R1·R2* products derived from QPM (R = 0.73, P < 0.0001). Moreover, there is a significant difference between WM and GM structures in each myelin images (both, P < 0.0001). Additionally, in a clinical case, MS lesions enabled observation of not only MS plaques but also heterogeneous myelin signal loss associated with demyelination more clearly than T2w image and conventional T1w/T2w ratio image. CONCLUSION: Our myelin-weighted imaging technique using QPM may be useful for myelin visualization and is expected to become independent of measurement conditions due to having quantitative characteristics of QPM itself.

Virtual computed-tomography system for deep-learning-based material decomposition.

Objective.Material decomposition (MD) evaluates the elemental composition of human tissues and organs via computed tomography (CT) and is indispensable in correlating anatomical images with functional ones. A major issue in MD is inaccurate elemental information about the real human body. To overcome this problem, we developed a virtual CT system model, by which various reconstructed images can be generated based on ICRP110 human phantoms with information about six major elements (H, C, N, O, P, and Ca).Approach.We generated CT datasets labelled with accurate elemental information using the proposed generative CT model and trained a deep learning (DL)-based model to estimate the material distribution with the ICRP110 based human phantom as well as the digital Shepp-Logan phantom. The accuracy in quad-, dual-, and single-energy CT cases was investigated. The influence of beam-hardening artefacts, noise, and spectrum variations were analysed with testing datasets including elemental density and anatomical shape variations.Main results.The results indicated that this DL approach can realise precise MD, even with single-energy CT images. Moreover, noise, beam-hardening artefacts, and spectrum variations were shown to have minimal impact on the MD.Significance.Present results suggest that the difficulty to prepare a large CT database can be solved by introducing the virtual CT system and the proposed technique can be applied to clinical radiodiagnosis and radiotherapy.

Training of deep cross-modality conversion models with a small data set, and their application in megavoltage CT to kilovoltage CT conversion.

PURPOSE: In recent years, deep learning-based image processing has emerged as a valuable tool for medical imaging owing to its high performance. However, the quality of deep learning-based methods heavily relies on the amount of training data; the high cost of acquiring a large data set is a limitation to their utilization in medical fields. Herein, based on deep learning, we developed a computed tomography (CT) modality conversion method requiring only a few unsupervised images. METHODS: The proposed method is based on cycle-consistency generative adversarial network (CycleGAN) with several extensions tailored for CT images, which aims at preserving the structure in the processed images and reducing the amount of training data. This method was applied to realize the conversion of megavoltage computed tomography (MVCT) to kilovoltage computed tomography (kVCT) images. Training was conducted using several data sets acquired from patients with head and neck cancer. The size of the data sets ranged from 16 slices (two patients) to 2745 slices (137 patients) for MVCT and 2824 slices (98 patients) for kVCT. RESULTS: The required size of the training data was found to be as small as a few hundred slices. By statistical and visual evaluations, the quality improvement and structure preservation of the MVCT images converted by the proposed model were investigated. As a clinical benefit, it was observed by medical doctors that the converted images enhanced the precision of contouring. CONCLUSIONS: We developed an MVCT to kVCT conversion model based on deep learning, which can be trained using only a few hundred unpaired images. The stability of the model against changes in data size was demonstrated. This study promotes the reliable use of deep learning in clinical medicine by partially answering commonly asked questions, such as "Is our data sufficient?" and "How much data should we acquire?"