OBJECTIVE: To investigate a new noninvasive diagnostic model for nonalcoholic fatty liver disease (NAFLD) based on features of tongue images. METHODS: Healthy controls and volunteers confirmed to have NAFLD by liver ultrasound were recruited from China-Japan Friendship Hospital between September 2018 and May 2019, then the anthropometric indexes and sampled tongue images were measured. The tongue images were labeled by features, based on a brief protocol, without knowing any other clinical data, after a series of corrections and data cleaning. The algorithm was trained on images using labels and several anthropometric indexes for inputs, utilizing machine learning technology. Finally, a logistic regression algorithm and a decision tree model were constructed as 2 diagnostic models for NAFLD. RESULTS: A total of 720 subjects were enrolled in this study, including 432 patients with NAFLD and 288 healthy volunteers. Of them, 482 were randomly allocated into the training set and 238 into the validation set. The diagnostic model based on logistic regression exhibited excellent performance: in validation set, it achieved an accuracy of 86.98%, sensitivity of 91.43%, and specificity of 80.61%; with an area under the curve (AUC) of 0.93 [95% confidence interval (CI) 0.68-0.98]. The decision tree model achieved an accuracy of 81.09%, sensitivity of 91.43%, and specificity of 66.33%; with an AUC of 0.89 (95% CI 0.66-0.92) in validation set. CONCLUSIONS The features of tongue images were associated with NAFLD. Both the 2 diagnostic models, which would be convenient, noninvasive, lightweight, rapid, and inexpensive technical references for early screening, can accurately distinguish NAFLD and are worth further study.
Humans ; Non-alcoholic Fatty Liver Disease/diagnostic imaging* ; Ultrasonography ; Anthropometry ; Algorithms ; China

Humans ; Artificial Intelligence ; Algorithms ; Brain ; Head

OBJECTIVE: To propose a semi-supervised material quantitative intelligent imaging algorithm based on prior information perception learning (SLMD-Net) to improve the quality and precision of spectral CT imaging. METHODS: The algorithm includes a supervised and a self- supervised submodule. In the supervised submodule, the mapping relationship between low and high signal-to-noise ratio (SNR) data was constructed through mean square error loss function learning based on a small labeled dataset. In the self- supervised sub-module, an image recovery model was utilized to construct the loss function incorporating the prior information from a large unlabeled low SNR basic material image dataset, and the total variation (TV) model was used to to characterize the prior information of the images. The two submodules were combined to form the SLMD-Net method, and pre-clinical simulation data were used to validate the feasibility and effectiveness of the algorithm. RESULTS: Compared with the traditional model-driven quantitative imaging methods (FBP-DI, PWLS-PCG, and E3DTV), data-driven supervised-learning-based quantitative imaging methods (SUMD-Net and BFCNN), a material quantitative imaging method based on unsupervised learning (UNTV-Net) and semi-supervised learning-based cycle consistent generative adversarial network (Semi-CycleGAN), the proposed SLMD-Net method had better performance in both visual and quantitative assessments. For quantitative imaging of water and bone materials, the SLMD-Net method had the highest PSNR index (31.82 and 29.06), the highest FSIM index (0.95 and 0.90), and the lowest RMSE index (0.03 and 0.02), respectively) and achieved significantly higher image quality scores than the other 7 material decomposition methods (P < 0.05). The material quantitative imaging performance of SLMD-Net was close to that of the supervised network SUMD-Net trained with labeled data with a doubled size. CONCLUSIONS A small labeled dataset and a large unlabeled low SNR material image dataset can be fully used to suppress noise amplification and artifacts in basic material decomposition in spectral CT and reduce the dependence on labeled data-driven network, which considers more realistic scenario in clinics.
Tomography, X-Ray Computed/methods* ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Signal-To-Noise Ratio ; Perception

OBJECTIVE: To propose a non-contrast CT-based algorithm for automated and accurate detection of pancreatic lesions at a low cost. METHODS: With Faster RCNN as the benchmark model, an advanced Faster RCNN (aFaster RCNN) model for pancreatic lesions detection based on plain CT was constructed. The model uses the residual connection network Resnet50 as the feature extraction module to extract the deep image features of pancreatic lesions. According to the morphology of pancreatic lesions, 9 anchor frame sizes were redesigned to construct the RPN module. A new Bounding Box regression loss function was proposed to constrain the training process of RPN module regression subnetwork by comprehensively considering the constraints of the lesion shape and anatomical structure. Finally, a detection frame was generated using the detector in the second stage. The data from a total of 728 cases of pancreatic diseases from 4 clinical centers in China were used for training (518 cases, 71.15%) and testing (210 cases, 28.85%) of the model. The performance of aFaster RCNN was verified through ablation experiments and comparison experiments with 3 classical target detection models SSD, YOLO and CenterNet. RESULTS: The aFaster RCNN model for pancreatic lesion detection achieved recall rates of 73.64% at the image level and 92.38% at the patient level, with an average precision of 45.29% and 53.80% at the image and patient levels, respectively, which were higher than those of the 3 models for comparison. CONCLUSION The proposed method can effectively extract the imaging features of pancreatic lesions from non-contrast CT images to detect the pancreatic lesions.
Humans ; Pancreas/diagnostic imaging* ; Algorithms ; China ; Pancreatic Neoplasms/diagnostic imaging* ; Tomography, X-Ray Computed

OBJECTIVE: To investigate the consistency and diagnostic performance of magnetic resonance imaging (MRI) for detecting microvascular invasion (MVI) of hepatocellular carcinoma (HCC) and the validity of deep learning attention mechanisms and clinical features for MVI grade prediction. METHODS: This retrospective study was conducted among 158 patients with HCC treated in Shunde Hospital Affiliated to Southern Medical University between January, 2017 and February, 2020. The imaging data and clinical data of the patients were collected to establish single sequence deep learning models and fusion models based on the EfficientNetB0 and attention modules. The imaging data included conventional MRI sequences (T₁WI, T₂WI, and DWI), enhanced MRI sequences (AP, PP, EP, and HBP) and synthesized MRI sequences (T1mapping-pre and T1mapping-20 min), and the high-risk areas of MVI were visualized using deep learning visualization techniques. RESULTS: The fusion model based on T1mapping-20min sequence and clinical features outperformed other fusion models with an accuracy of 0.8376, a sensitivity of 0.8378, a specificity of 0.8702, and an AUC of 0.8501 for detecting MVI. The deep fusion models were also capable of displaying the high-risk areas of MVI. CONCLUSION The fusion models based on multiple MRI sequences can effectively detect MVI in patients with HCC, demonstrating the validity of deep learning algorithm that combines attention mechanism and clinical features for MVI grade prediction.
Humans ; Carcinoma, Hepatocellular ; Retrospective Studies ; Liver Neoplasms ; Magnetic Resonance Imaging ; Algorithms

OBJECTIVE: To propose an deep learning-based algorithm for automatic prediction of dose distribution in radiotherapy planning for head and neck cancer. METHODS: We propose a novel beam dose decomposition learning (BDDL) method designed on a cascade network. The delivery matter of beam through the planning target volume (PTV) was fitted with the pre-defined beam angles, which served as an input to the convolution neural network (CNN). The output of the network was decomposed into multiple sub-fractions of dose distribution along the beam directions to carry out a complex task by performing multiple simpler sub-tasks, thus allowing the model more focused on extracting the local features. The subfractions of dose distribution map were merged into a distribution map using the proposed multi-voting mechanism. We also introduced dose distribution features of the regions-of-interest (ROIs) and boundary map as the loss function during the training phase to serve as constraining factors of the network when extracting features of the ROIs and areas of dose boundary. Public datasets of radiotherapy planning for head and neck cancer were used for obtaining the accuracy of dose distribution of the BDDL method and for implementing the ablation study of the proposed method. RESULTS: The BDDL method achieved a Dose score of 2.166 and a DVH score of 1.178 (P < 0.05), demonstrating its superior prediction accuracy to that of current state-ofthe-art (SOTA) methods. Compared with the C3D method, which was in the first place in OpenKBP-2020 Challenge, the BDDL method improved the Dose score and DVH score by 26.3% and 30%, respectively. The results of the ablation study also demonstrated the effectiveness of each key component of the BDDL method. CONCLUSION The BDDL method utilizes the prior knowledge of the delivery matter of beam and dose distribution in the ROIs to establish a dose prediction model. Compared with the existing methods, the proposed method is interpretable and reliable and can be potentially applied in clinical radiotherapy.
Humans ; Deep Learning ; Head and Neck Neoplasms/radiotherapy* ; Algorithms ; Neural Networks, Computer

OBJECTIVE: To propose a framework that combines sinogram interpolation with unsupervised image-to-image translation (UNIT) network to correct metal artifacts in CT images. METHODS: The initially corrected CT image and the prior image without artifacts, which were considered as different elements in two different domains, were input into the image transformation network to obtain the corrected image. Verification experiments were carried out to assess the effectiveness of the proposed method using the simulation data, and PSNR and SSIM were calculated for quantitative evaluation of the performance of the method. RESULTS: The experiment using the simulation data showed that the proposed method achieved better results for improving image quality as compared with other methods, and the corrected images preserved more details and structures. Compared with ADN algorithm, the proposed algorithm improved the PSNR and SSIM by 2.4449 and 0.0023 when the metal was small, by 5.9942 and 8.8388 for images with large metals, and by 8.8388 and 0.0130 when both small and large metals were present, respectively. CONCLUSION The proposed method for metal artifact correction can effectively remove metal artifacts, improve image quality, and preserve more details and structures on CT images.
Artifacts ; Algorithms ; Computer Simulation ; Tomography, X-Ray Computed

OBJECTIVE: To propose a diffusion tensor field estimation network based on 3D U-Net and diffusion tensor imaging (DTI) model constraint (3D DTI-Unet) to accurately estimate DTI quantification parameters from a small number of diffusion-weighted (DW) images with a low signal-to-noise ratio. METHODS: The input of 3D DTI-Unet was noisy diffusion magnetic resonance imaging (dMRI) data containing one non-DW image and 6 DW images with different diffusion coding directions. The noise-reduced non-DW image and accurate diffusion tensor field were predicted through 3D U-Net. The dMRI data were reconstructed using the DTI model and compared with the true value of dMRI data to optimize the network and ensure the consistency of the dMRI data with the physical model of the diffusion tensor field. We compared 3D DTI-Unet with two DW image denoising algorithms (MP-PCA and GL-HOSVD) to verify the effect of the proposed method. RESULTS: The proposed method was better than MP-PCA and GL-HOSVD in terms of quantitative results and visual evaluation of DW images, diffusion tensor field and DTI quantification parameters. CONCLUSION The proposed method can obtain accurate DTI quantification parameters from one non-DW image and 6 DW images to reduce image acquisition time and improve the reliability of quantitative diagnosis.
Diffusion Tensor Imaging ; Reproducibility of Results ; Diffusion Magnetic Resonance Imaging ; Algorithms ; Signal-To-Noise Ratio

OBJECTIVE: To propose a sensitivity test method for geometric correction position deviation of cone-beam CT systems. METHODS: We proposed the definition of center deviation and its derivation. We analyzed the influence of the variation of the three-dimensional spatial center of the steel ball point, the projection center and the size of the steel ball point on the deviation of geometric parameters and the reconstructed image results by calculating the geometric correction parameters based on the Noo analytical method using the FDK reconstruction algorithm for image reconstruction. RESULTS: The radius of the steel ball point was within 3 mm. The deviation of the center of the calibration parameter was within the order of magnitude and negligible. A 10% Gaussian perturbation of a single pixel in the 3D spatial coordinates of the steel ball point produced a deviation of about 3 pixel sizes, while the same Gaussian perturbation of the 2D projection coordinates of the steel ball point produced a deviation of about 2 pixel sizes. CONCLUSION The geometric correction is more sensitive to the deviation generated by the three-dimensional spatial coordinates of the steel ball point with limited sensitivity to the deviation generated by the two-dimensional projection coordinates of the steel ball point. The deviation sensitivity of a small diameter steel ball point can be ignored.
Algorithms ; Calibration ; Cone-Beam Computed Tomography ; Steel

With the advent of artificial intelligence (AI), machines are increasingly being used to complete complicated tasks, yielding remarkable results. Machine learning (ML) is the most relevant subset of AI in medicine, which will soon become an integral part of our everyday practice. Therefore, physicians should acquaint themselves with ML and AI, and their role as an enabler rather than a competitor. Herein, we introduce basic concepts and terms used in AI and ML, and aim to demystify commonly used AI/ML algorithms such as learning methods including neural networks/deep learning, decision tree and application domain in computer vision and natural language processing through specific examples. We discuss how machines are already being used to augment the physician's decision-making process, and postulate the potential impact of ML on medical practice and medical research based on its current capabilities and known limitations. Moreover, we discuss the feasibility of full machine autonomy in medicine.
Humans ; Artificial Intelligence ; Machine Learning ; Algorithms ; Neural Networks, Computer ; Medicine