Fusion extracted features from deep learning for identification of multiple positioning errors in dental panoramic imaging.

BACKGROUND: Dental panoramic imaging plays a pivotal role in dentistry for diagnosis and treatment planning. However, correctly positioning patients can be challenging for technicians due to the complexity of the imaging equipment and variations in patient anatomy, leading to positioning errors. These errors can compromise image quality and potentially result in misdiagnoses. OBJECTIVE: This research aims to develop and validate a deep learning model capable of accurately and efficiently identifying multiple positioning errors in dental panoramic imaging. METHODS AND MATERIALS: This retrospective study used 552 panoramic images selected from a hospital Picture Archiving and Communication System (PACS). We defined six types of errors (E1-E6) namely, (1) slumped position, (2) chin tipped low, (3) open lip, (4) head turned to one side, (5) head tilted to one side, and (6) tongue against the palate. First, six Convolutional Neural Network (CNN) models were employed to extract image features, which were then fused using transfer learning. Next, a Support Vector Machine (SVM) was applied to create a classifier for multiple positioning errors, using the fused image features. Finally, the classifier performance was evaluated using 3 indices of precision, recall rate, and accuracy. RESULTS: Experimental results show that the fusion of image features with six binary SVM classifiers yielded high accuracy, recall rates, and precision. Specifically, the classifier achieved an accuracy of 0.832 for identifying multiple positioning errors. CONCLUSIONS: This study demonstrates that six SVM classifiers effectively identify multiple positioning errors in dental panoramic imaging. The fusion of extracted image features and the employment of SVM classifiers improve diagnostic precision, suggesting potential enhancements in dental imaging efficiency and diagnostic accuracy. Future research should consider larger datasets and explore real-time clinical application.

Segmentation of liver tumors with abdominal computed tomography using fully convolutional networks.

BACKGROUND: Dividing liver organs or lesions depicting on computed tomography (CT) images could be applied to help tumor staging and treatment. However, most existing image segmentation technologies use manual or semi-automatic analysis, making the analysis process costly and time-consuming. OBJECTIVE: This research aims to develop and apply a deep learning network architecture to segment liver tumors automatically after fine tuning parameters. METHODS AND MATERIALS: The medical imaging is obtained from the International Symposium on Biomedical Imaging (ISBI), which includes 3D abdominal CT scans of 131 patients diagnosed with liver tumors. From these CT scans, there are 7,190 2D CT images along with the labeled binary images. The labeled binary images are regarded as gold standard for evaluation of the segmented results by FCN (Fully Convolutional Network). The backbones of FCN are extracted from Xception, InceptionresNetv2, MobileNetv2, ResNet18, ResNet50 in this study. Meanwhile, the parameters including optimizers (SGDM and ADAM), size of epoch, and size of batch are investigated. CT images are randomly divided into training and testing sets using a ratio of 9:1. Several evaluation indices including Global Accuracy, Mean Accuracy, Mean IoU (Intersection over Union), Weighted IoU and Mean BF Score are applied to evaluate tumor segmentation results in the testing images. RESULTS: The Global Accuracy, Mean Accuracy, Mean IoU, Weighted IoU, and Mean BF Scores are 0.999, 0.969, 0.954, 0.998, 0.962 using ResNet50 in FCN with optimizer SGDM, batch size 12, and epoch 9. It is important to fine tuning the parameters in FCN model. Top 20 FNC models enable to achieve higher tumor segmentation accuracy with Mean IoU over 0.900. The occurred frequency of InceptionresNetv2, MobileNetv2, ResNet18, ResNet50, and Xception are 9, 6, 3, 5, and 2 times. Therefore, the InceptionresNetv2 has higher performance than others. CONCLUSIONS: This study develop and test an automated liver tumor segmentation model based on FCN. Study results demonstrate that many deep learning models including InceptionresNetv2, MobileNetv2, ResNet18, ResNet50, and Xception have high potential to segment liver tumors from CT images with accuracy exceeding 90%. However, it is still difficult to accurately segment tiny and small size tumors by FCN models.

Efficient Strike Artifact Reduction Based on 3D-Morphological Structure Operators from Filtered Back-Projection PET Images.

Positron emission tomography (PET) can provide functional images and identify abnormal metabolic regions of the whole-body to effectively detect tumor presence and distribution. The filtered back-projection (FBP) algorithm is one of the most common images reconstruction methods. However, it will generate strike artifacts on the reconstructed image and affect the clinical diagnosis of lesions. Past studies have shown reduction in strike artifacts and improvement in quality of images by two-dimensional morphological structure operators (2D-MSO). The morphological structure method merely processes the noise distribution of 2D space and never considers the noise distribution of 3D space. This study was designed to develop three-dimensional-morphological structure operators (3D MSO) for nuclear medicine imaging and effectively eliminating strike artifacts without reducing image quality. A parallel operation was also used to calculate the minimum background standard deviation of the images for three-dimensional morphological structure operators with the optimal response curve (3D-MSO/ORC). As a result of Jaszczak phantom and rat verification, 3D-MSO/ORC showed better denoising performance and image quality than the 2D-MSO method. Thus, 3D MSO/ORC with a 3 × 3 × 3 mask can reduce noise efficiently and provide stability in FBP images.

Classification of the Multiple Stages of Parkinson's Disease by a Deep Convolution Neural Network Based on 99mTc-TRODAT-1 SPECT Images.

Single photon emission computed tomography (SPECT) has been employed to detect Parkinson's disease (PD). However, analysis of the SPECT PD images was mostly based on the region of interest (ROI) approach. Due to limited size of the ROI, especially in the multi-stage classification of PD, this study utilizes deep learning methods to establish a multiple stages classification model of PD. In the retrospective study, the 99mTc-TRODAT-1 was used for brain SPECT imaging. A total of 202 cases were collected, and five slices were selected for analysis from each subject. The total number of images was thus 1010. According to the Hoehn and Yahr Scale standards, all the cases were divided into healthy, early, middle, late four stages, and HYS I~V six stages. Deep learning is compared with five convolutional neural networks (CNNs). The input images included grayscale and pseudo color of two types. The training and validation sets were 70% and 30%. The accuracy, recall, precision, F-score, and Kappa values were used to evaluate the models' performance. The best accuracy of the models based on grayscale and color images in four and six stages were 0.83 (AlexNet), 0.85 (VGG), 0.78 (DenseNet) and 0.78 (DenseNet).

Questionable necessity of nitroglycerin for diagnostic coronary artery examination using 320-row multi-detector computed tomography.

OBJECTIVE: This study aims to analyze and compare the diagnostic effectiveness of 320-row multi-detector computed tomography for coronary artery angiography (MDCTA) in subjects with and without sublingual vasodilator (nitroglycerin). MATERIALS AND METHODS: From September 2015 to September 2016, 70 individuals without history of major cardiovascular diseases who underwent MDCTA for health examination were retrospectively categorized into sublingual nitroglycerin (NTG) and non-NTG groups. Medical history, CT dose index (CTDI), and multi-slice CT images were compared between two groups. A diameter of coronary artery (DA, mm) was computed and analyzed. RESULTS: A total of 41 males and 29 females (mean age: 55.43±8.84 years, range: 34- 76) were reviewed. Normal and abnormal MDCTA findings were noted in 54 and 16 participants, respectively, with the detection rate of coronary artery disease being 23%. There was no significant difference in inter-observer variability of coronary CTA image quality and diagnosis between the NTG and non-NTG groups among three experienced radiologists. Although the percentage dilatation of left anterior descending branch (LAD), right coronary artery (RCA) and left circumflex branch (LCX) following in the NTG group were 12.4%, 12.8% and 25.3%, respectively (p < 0.01), there was no significant difference in image quality and diagnosis between the two groups. CONCLUSIONS: Despite the recommendation of routine nitroglycerin use for subjects undergoing computed tomography for coronary artery angiography, our results showed no significant advantage of its use in improving image quality and rate of diagnosis accuracy.

Feasible Classified Models for Parkinson Disease from 99mTc-TRODAT-1 SPECT Imaging.

The neuroimaging techniques such as dopaminergic imaging using Single Photon Emission Computed Tomography (SPECT) with 99mTc-TRODAT-1 have been employed to detect the stages of Parkinson's disease (PD). In this retrospective study, a total of 202 99mTc-TRODAT-1 SPECT imaging were collected. All of the PD patient cases were separated into mild (HYS Stage 1 to Stage 3) and severe (HYS Stage 4 and Stage 5) PD, according to the Hoehn and Yahr Scale (HYS) standard. A three-dimensional method was used to estimate six features of activity distribution and striatal activity volume in the images. These features were skewness, kurtosis, Cyhelsky's skewness coefficient, Pearson's median skewness, dopamine transporter activity volume, and dopamine transporter activity maximum. Finally, the data were modeled using logistic regression (LR) and support vector machine (SVM) for PD classification. The results showed that SVM classifier method produced a higher accuracy than LR. The sensitivity, specificity, PPV, NPV, accuracy, and AUC with SVM method were 0.82, 1.00, 0.84, 0.67, 0.83, and 0.85, respectively. Additionally, the Kappa value was shown to reach 0.68. This claimed that the SVM-based model could provide further reference for PD stage classification in medical diagnosis. In the future, more healthy cases will be expected to clarify the false positive rate in this classification model.

Diagnosed chest lesion on diffusion-weighted magnetic resonance images using apparent diffusion coefficients.

PURPOSE: A novel diagnostic method using the standard deviation (SD) value of apparent diffusion coefficient (ADC) by diffusion-weighted (DWI) magnetic resonance imaging (MRI) is applied for differential diagnosis of primary chest cancers, metastatic tumors and benign tumors. MATERIALS AND METHODS: This retrospective study enrolled 27 patients (20 males, 7 female; age, 15-85; mean age, 68) who had thoracic mass lesions in the last three years and underwent an MRI chest examination at our institution. In total, 29 mass lesions were analyzed using SD of ADC and DWI. Lesions were divided into five groups: Primary lung cancers (N = 10); esophageal cancers (N = 5); metastatic tumors (N = 8); benign tumors (N = 3); and inflammatory lesions (N = 3). Quantitative assessment of MRI parameters of mass lesions was performed. The ADC value was acquired based on the average of the entire tumor area. The error-plot, t-test and the area under receiver operating characteristic (AUC) were applied for statistical analysis. RESULTS: The SD of ADC value (mean±SD) was (4.867±1.359)×10-4 mm2/sec in primary lung cancers, and (3.598±0.350)×10-4 mm2/sec in metastatic tumors. The SD of ADC values of primary lung cancers and metastatic tumors (P <  0.05) were significantly different and the AUC was 0.800 (P <  0.05). The means of SD of ADC values was 4.532±1.406×10-4 mm2/sec and 2.973±0.364×10-4 mm2/sec for malignant tumors (including primary lung cancers, esophageal cancers) and benign tumors with respectively. The mean of SD of ADC values between malignant chest tumors and benign chest tumors was shown significant difference (P <  0.01). The values of AUC was 0.967 between malignant chest tumors and benign chest tumors (P <  0.05). The ADC values for primary lung cancers, metastatic tumors and benign tumors were not significantly difference (P >  0.05). CONCLUSIONS: The mean of SD of ADC value by DWI can be used for differential diagnosis of chest lesions.

Investigated geometrical characteristics and image density of left ventricle of multi-detector computed tomography in early coronary artery disease patients.

BACKGROUND: Coronary artery disease (CAD) remains the leading cause of death worldwide. Currently, cardiac multi-detector computed tomography (MDCT) is widely used to diagnose CAD. The purpose in this study is to identify informative and useful predictors from left ventricular (LV) in the early CAD patients using cardiac MDCT images. MATERIALS AND METHODS: Study groups comprised 42 subjects who underwent a screening health examination, including laboratory testing and cardiac angiography by 64-slice MDCT angiography. Two geometrical characteristics and one image density were defined as shape, size and stiffness on MDCT image. The t-test, logistic regression, and receiver operating characteristic curve were applied to assess and identify the significant predictors. The Kappa statistics was used to exam the agreements with physician's judgments (i.e., Golden of True, GOT). RESULTS: The proposed three characteristics of LV MDCT images are important predictors and risk factors for the early CAD patients. These predictors present over 80% of AUC and higher odds ratio. The Kappa statistics was 0.68 for the combinations of shape and stiffness into logistic regression. CONCLUSIONS: The shape, size and stiffness of the left ventricular on MDCT can be used to be the effective indicators in the early CAD patients. Besides, the combinations of shape and stiffness into logistic regression could provide substantial agreement with physician's judgments.

Scattering correction algorithm in the PET sinogram using the factorial design of experimental method: A phantom study.

Positron emission tomography (PET) had been utilized to image gene therapy, estimate tumor growth, detect neural function of the brain, and diagnose disease. However, sinogram noise always results inaccurate PET images. The factorial design of experiment (DOE), a statistical method, was applied to investigate, correct and estimate the fraction of scattering of 2D sinogram in PET. The DOE was included as factors of angle views and scatter media with two levels designed. The PET sinogram after scattering correction was then reconstructed by filtered back projection (FBP). Both Ge-68 uniform phantom and Jaszczak anthropomorphic torso phantom were applied to exam the performance of presented scattering correction algorithm. The signal-to-noise ratio (SNR), standard deviation (STD) of background, and full width at half maximum (FWHM), and uniformity test were applied to validate the performance of presented method. The proposed method provides a narrower FWHM, smaller STD of the background, higher SNR and better uniformity than those of original protocols. This method should be tested for accuracy and feasibility with three-dimensional phantoms or real animal studies and consideration effects of cross-talk between slices in future work.

Ventricular hemodynamics using cardiac computed tomography and optical flow method.

Ventricular hemodynamics plays an important role in assessing cardiac function in clinical practice. The aim of this study was to determine the ventricular hemodynamics based on contrast movement in the left ventricle (LV) between the phases in a cardiac cycle recorded using an electrocardiography (ECG) with cardiac computed tomography (CT) and optical flow method. Cardiac CT data were acquired at 120 kV and 280 mA with a 350 ms gantry rotation, which covered one cardiac cycle, on the 640-slice CT scanner with ECG for a selected patient without heart disease. Ventricular hemodynamics (mm/phase) were calculated using the optical flow method based on contrast changes with ECG phases in anterior-posterior, lateral and superior-inferior directions. Local hemodynamic information of the LV with color coating was presented. The visualization of the functional information made the hemodynamic observation easy.

Analyzed outcome for embolization of hepatic carcinoma by C-arm angiographic computed tomography.

PURPOSE: This study evaluated and monitored the outcome of angiographic embolization of hepatic carcinoma by real-time C-arm angiographic computed tomography under number of tumors, size of tumors, and patient's age.METHODS AND MARTIALS: In total, 142 patients underwent angiographic embolization of hepatic carcinoma. The control group, 71 patients, underwent conventional angiographic (CA) embolization of hepatic carcinoma. The experimental group, 71 patients, underwent C-arm angiographic computed tomography (CCT) embolization of hepatic carcinoma. The numbers of angiographic embolization, number of tumors, size of tumors, and patients ages were recorded for comparisons between groups by analysis of variance (ANOVA) with cross-interaction and the chi-square test (cross table). RESULTS: The age ranges were 20-84 and 35-84 years old for the experimental and control groups respectively. Average number of angiographic embolizations of hepatic carcinomas were 2.63 ± 1.84 and 5.32 ± 2.01 for the experimental and control groups. The number of angiographic embolizations under number of tumors, size of tumors, and patients ages between groups were significantly different (P< 0.05). The effective analyses of transcatheter arterial chemoembolization (TACE) by CCT were significant by chi-square test (P< 0.05) under ⩽ 3 cm and patients aged ⩽ 60. CONCLUSION: The main advantage by CCT for undergoing TACE under tumor size smaller than 3 cm and numbers of tumor smaller 3 times were more significantly effective than those by CA. The CCT combined with TACE had high potentially reduced numbers of undergoing TACE.

Fusion-Extracted Features by Deep Networks for Improved COVID-19 Classification with Chest X-ray Radiography.

Convolutional neural networks (CNNs) have shown promise in accurately diagnosing coronavirus disease 2019 (COVID-19) and bacterial pneumonia using chest X-ray images. However, determining the optimal feature extraction approach is challenging. This study investigates the use of fusion-extracted features by deep networks to improve the accuracy of COVID-19 and bacterial pneumonia classification with chest X-ray radiography. A Fusion CNN method was developed using five different deep learning models after transferred learning to extract image features (Fusion CNN). The combined features were used to build a support vector machine (SVM) classifier with a RBF kernel. The performance of the model was evaluated using accuracy, Kappa values, recall rate, and precision scores. The Fusion CNN model achieved an accuracy and Kappa value of 0.994 and 0.991, with precision scores for normal, COVID-19, and bacterial groups of 0.991, 0.998, and 0.994, respectively. The results indicate that the Fusion CNN models with the SVM classifier provided reliable and accurate classification performance, with Kappa values no less than 0.990. Using a Fusion CNN approach could be a possible solution to enhance accuracy further. Therefore, the study demonstrates the potential of deep learning and fusion-extracted features for accurate COVID-19 and bacterial pneumonia classification with chest X-ray radiography.

Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images.

Early detection of prostate cancer (PCa) and benign prostatic hyperplasia (BPH) is crucial for maintaining the health and well-being of aging male populations. This study aims to evaluate the performance of transfer learning with convolutional neural networks (CNNs) for efficient classification of PCa and BPH in transrectal ultrasound (TRUS) images. A retrospective experimental design was employed in this study, with 1380 TRUS images for PCa and 1530 for BPH. Seven state-of-the-art deep learning (DL) methods were employed as classifiers with transfer learning applied to popular CNN architectures. Performance indices, including sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), Kappa value, and Hindex (Youden's index), were used to assess the feasibility and efficacy of the CNN methods. The CNN methods with transfer learning demonstrated a high classification performance for TRUS images, with all accuracy, specificity, sensitivity, PPV, NPV, Kappa, and Hindex values surpassing 0.9400. The optimal accuracy, sensitivity, and specificity reached 0.9987, 0.9980, and 0.9980, respectively, as evaluated using twofold cross-validation. The investigated CNN methods with transfer learning showcased their efficiency and ability for the classification of PCa and BPH in TRUS images. Notably, the EfficientNetV2 with transfer learning displayed a high degree of effectiveness in distinguishing between PCa and BPH, making it a promising tool for future diagnostic applications.

Classification of Color Fundus Photographs Using Fusion Extracted Features and Customized CNN Models.

This study focuses on overcoming challenges in classifying eye diseases using color fundus photographs by leveraging deep learning techniques, aiming to enhance early detection and diagnosis accuracy. We utilized a dataset of 6392 color fundus photographs across eight disease categories, which was later augmented to 17,766 images. Five well-known convolutional neural networks (CNNs)-efficientnetb0, mobilenetv2, shufflenet, resnet50, and resnet101-and a custom-built CNN were integrated and trained on this dataset. Image sizes were standardized, and model performance was evaluated via accuracy, Kappa coefficient, and precision metrics. Shufflenet and efficientnetb0demonstrated strong performances, while our custom 17-layer CNN outperformed all with an accuracy of 0.930 and a Kappa coefficient of 0.920. Furthermore, we found that the fusion of image features with classical machine learning classifiers increased the performance, with Logistic Regression showcasing the best results. Our study highlights the potential of AI and deep learning models in accurately classifying eye diseases and demonstrates the efficacy of custom-built models and the fusion of deep learning and classical methods. Future work should focus on validating these methods across larger datasets and assessing their real-world applicability.

Analyzing coronary artery disease in patients with low CAC scores by 64-slice MDCT.

PURPOSE: Coronary artery calcification (CAC) scores are widely used to determine risk for Coronary Artery Disease (CAD). A CAC score does not have the diagnostic accuracy needed for CAD. This work uses a novel efficient approach to predict CAD in patients with low CAC scores. MATERIALS AND METHODS: The study group comprised 86 subjects who underwent a screening health examination, including laboratory testing, CAC scanning, and cardiac angiography by 64-slice multidetector computed tomographic angiography. Eleven physiological variables and three personal parameters were investigated in proposed model. Logistic regression was applied to assess the sensitivity, specificity, and accuracy of when using individual variables and CAC score. Meta-analysis combined physiological and personal parameters by logistic regression. RESULTS: The diagnostic sensitivity of the CAC score was 14.3% when the CAC score was ≤30. Sensitivity increased to 57.13% using the proposed model. The statistically significant variables, based on beta values and P values, were family history, LDL-c, blood pressure, HDL-c, age, triglyceride, and cholesterol. CONCLUSIONS: The CAC score has low negative predictive value for CAD. This work applied a novel prediction method that uses patient information, including physiological and society parameters. The proposed method increases the accuracy of CAC score for predicting CAD.

Quantifying liver cirrhosis by extracting significant features from MRI T2 image.

Most patients with liver cirrhosis must undergo a series of clinical examinations, including ultrasound imaging, liver biopsy, and blood tests. However, the quantification of liver cirrhosis by extracting significant features from a T2-weighted magnetic resonance image (MRI) provides useful diagnostic information in clinical tests. Sixty-two subjects were randomly selected to participate in this retrospective analysis with assigned to experimental and control groups. The T2-weighted MRI was obtained and to them dynamic adjusted gray levels. The extracted features of the image were standard deviation (SD), mean, and entropy of pixel intensity in the region of interest (ROI). The receiver operator characteristic (ROC) curve, 95% confidence intervals, and kappa statistics were used to test the significance and agreement. The analysis of area under ROC shows that SD, mean, and entropy in the ROI were significant between the experimental group and the control group. Smaller values of SD, mean, and entropy were associated with a higher probability of liver cirrhosis. The agreements between the extracted features and diagnostic results were shown significantly (P < 0.001). In this investigation, quantitative features of SD, mean, and entropy in the ROI were successfully computed by the dynamic gray level scaling of T2-weighted MRI with high accuracy.

Hemodynamic analysis of vascular stenting treatment outcome: computational fluid dynamics method vs optical flow method.

BACKGROUND AND PURPOSE: Computational fluid dynamics method (CFDM) and optical flow method (OFM) effectively provide the hemodynamic information based on the digital subtraction angiogram (DSA). However, the quantitative analysis in comparison of CFDM and OFM is still absent. The goal of this study is to apply CFDM and OFM in quantitative analysis of stenting treatment. MATERIAL AND METHOD: A left carotid stenosis patient underwent stenting of percutaneous transluminal angioplasty was analyzed as an example. CFDM and OFM for hemodynamic analysis on digital subtraction angiography before and after stenting treatment were presented. RESULTS: Improvement gains of blood flow velocities on left internal carotid artery after stenting treatment for different initial conditions on the common carotid artery were 1.91 ∼ 2.13, 1.62 ∼ 2.09, and 0.69 by CFDM with Newtonian and non-Newtonian fluids and OFM, respectively. With the CFDM analysis, the flow mapping by OFM using time resolved DSA data on the fly to estimate hemodynamic significance of a cervical carotid stenosis was explained. CONCLUSION: Quantificative blood flow estimations by CFDM and OFM to evaluate the treatment outcomes to patient with carotid stenosis are practical. Both methods are able to provide quantitative information of blood flow for stenting treatment. It is advantagious to use both methods in treatment evaluation.

Integrating ECG Monitoring and Classification via IoT and Deep Neural Networks.

Anesthesia assessment is most important during surgery. Anesthesiologists use electrocardiogram (ECG) signals to assess the patient's condition and give appropriate medications. However, it is not easy to interpret the ECG signals. Even physicians with more than 10 years of clinical experience may still misjudge. Therefore, this study uses convolutional neural networks to classify ECG image types to assist in anesthesia assessment. The research uses Internet of Things (IoT) technology to develop ECG signal measurement prototypes. At the same time, it classifies signal types through deep neural networks, divided into QRS widening, sinus rhythm, ST depression, and ST elevation. Three models, ResNet, AlexNet, and SqueezeNet, are developed with 50% of the training set and test set. Finally, the accuracy and kappa statistics of ResNet, AlexNet, and SqueezeNet in ECG waveform classification were (0.97, 0.96), (0.96, 0.95), and (0.75, 0.67), respectively. This research shows that it is feasible to measure ECG in real time through IoT and then distinguish four types through deep neural network models. In the future, more types of ECG images will be added, which can improve the real-time classification practicality of the deep model.

Effects of long-term practice and task complexity on brain activities when performing abacus-based mental calculations: a PET study.

PURPOSE: The aim of this study was to examine the neural bases for the exceptional mental calculation ability possessed by Chinese abacus experts through PET imaging. METHODS: We compared the different regional cerebral blood flow (rCBF) patterns using (15)O-water PET in 10 abacus experts and 12 non-experts while they were performing each of the following three tasks: covert reading, simple addition, and complex contiguous addition. All data collected were analyzed using SPM2 and MNI templates. RESULTS: For non-experts during the tasks of simple addition, the observed activation of brain regions were associated with coordination of language (inferior frontal network) and visuospatial processing (left parietal/frontal network). Similar activation patterns but with a larger visuospatial processing involvement were observed during complex contiguous addition tasks, suggesting the recruitment of more visuospatial memory for solving the complex problems. For abacus experts, however, the brain activation patterns showed slight differences when they were performing simple and complex addition tasks, both of which involve visuospatial processing (bilateral parietal/frontal network). These findings supported the notion that the experts were completing all the calculation process on a virtual mental abacus and relying on this same computational strategy in both simple and complex tasks, which required almost no increasing brain workload for solving the latter. CONCLUSION: In conclusion, after intensive training and practice, the neural pathways in an abacus expert have been connected more effectively for performing the number encoding and retrieval that are required in abacus tasks, resulting in exceptional mental computational ability.

Classification for liver ultrasound tomography by posterior attenuation correction with a phantom study.

The B-mode ultrasound usually contains scattering speckle noise which reduces the detailed resolution of the target and is regarded as an intrinsic noise that interferes with diagnostic precision. The aim of this study was to classify hepatic steatosis through applying attenuation correction with a phantom to reduce speckle noise in liver ultrasound tomography in patients. This retrospective study applied three randomized groups signifying different liver statuses. A total of 114 patients' effective liver ultrasound images-30 normal, 44 fatty, and 40 cancerous-were included. The proposed depth attenuation correction method was first applied to images. Three regions of interest were manually drawn on the images. Next, five feature values for the regions of interest were calculated. Finally, the hybrid method of logistic regression and support vector machine was employed to classify the ultrasound images with 10-fold cross-validation. The accuracy, kappa statistic, and mean absolute error of the proposed hybrid method were 87.5%, 0.812, and 0.119, respectively, which were higher than those of the logistic regression method-75.0%, 0.548, and 0.280-or those of the support vector machine method-75.7%, 0.637, and 0.293-respectively. Therefore, the hybrid method has been proven to be more accurate and have better performance and less error than either single method. The hybrid method provided acceptable accuracy of classification in three liver ultrasound image groups after depth attenuation correction. In the future, the deep learning approaches may be considered for the application in classifying liver ultrasound images.