OBJECTIVES: We present a new low-dose CT reconstruction method using sub-pixel and anisotropic diffusion. METHODS: The sub-pixel intensity values and their second-order differences were obtained using linear interpolation techniques, and the new gradient information was then embedded into an anisotropic diffusion process, which was introduced into a penalty-weighted least squares model to reduce the noise in low-dose CT projection data. The high-quality CT image was finally reconstructed using the classical filtered back-projection (FBP) algorithm from the estimated data. RESULTS: In the Shepp-Logan phantom experiments, the structural similarity (SSIM) index of the CT image reconstructed by the proposed algorithm, as compared with FBP, PWLS-Gibbs and PWLS-TV algorithms, was increased by 28.13%, 5.49%, and 0.91%, the feature similarity (FSIM) index was increased by 21.08%, 1.78%, and 1.36%, and the root mean square error (RMSE) was reduced by 69.59%, 18.96%, and 3.90%, respectively. In the digital XCAT phantom experiments, the SSIM index of the CT image reconstructed by the proposed algorithm, as compared with FBP, PWLS-Gibbs and PWLS-TV algorithms, was increased by 14.24%, 1.43% and 7.89%, the FSIM index was increased by 9.61%, 1.78% and 5.66%, and the RMSE was reduced by 26.88%, 9.41% and 18.39%, respectively. In clinical experiments, the SSIM index of the image reconstructed using the proposed algorithm was increased by 19.24%, 15.63% and 3.68%, the FSIM index was increased by 4.30%, 2.92% and 0.43%, and the RMSE was reduced by 44.60%, 36.84% and 15.22% in comparison with FBP, PWLS-Gibbs and PWLS-TV algorithms, respectively. CONCLUSIONS The proposed method can effectively reduce the noises and artifacts while maintaining the structural details in low-dose CT images.
Tomography, X-Ray Computed/methods* ; Algorithms ; Phantoms, Imaging ; Anisotropy ; Image Processing, Computer-Assisted/methods* ; Humans ; Radiation Dosage

OBJECTIVES: We propose a novel deep learning segmentation algorithm (DSRF) based on multi-scale supervision and residual feedback strategy for precise segmentation of the optic chiasm and optic nerves in CT images of nasopharyngeal carcinoma (NPC) patients. METHODS: We collected 212 NPC CT images and their ground truth labels from SegRap2023, StructSeg2019 and HaN-Seg2023 datasets. Based on a hybrid pooling strategy, we designed a decoder (HPS) to reduce small organ feature loss during pooling in convolutional neural networks. This decoder uses adaptive and average pooling to refine high-level semantic features, which are integrated with primary semantic features to enable network learning of finer feature details. We employed multi-scale deep supervision layers to learn rich multi-scale and multi-level semantic features under deep supervision, thereby enhancing boundary identification of the optic chiasm and optic nerves. A residual feedback module that enables multiple iterations of the network was designed for contrast enhancement of the optic chiasm and optic nerves in CT images by utilizing information from fuzzy boundaries and easily confused regions to iteratively refine segmentation results under supervision. The entire segmentation framework was optimized with the loss from each iteration to enhance segmentation accuracy and boundary clarity. Ablation experiments and comparative experiments were conducted to evaluate the effectiveness of each component and the performance of the proposed model. RESULTS: The DSRF algorithm could effectively enhance feature representation of small organs to achieve accurate segmentation of the optic chiasm and optic nerves with an average DSC of 0.837 and an ASSD of 0.351. Ablation experiments further verified the contributions of each component in the DSRF method. CONCLUSIONS The proposed deep learning segmentation algorithm can effectively enhance feature representation to achieve accurate segmentation of the optic chiasm and optic nerves in CT images of NPC.
Humans ; Tomography, X-Ray Computed/methods* ; Optic Chiasm/diagnostic imaging* ; Optic Nerve/diagnostic imaging* ; Algorithms ; Nasopharyngeal Carcinoma ; Deep Learning ; Nasopharyngeal Neoplasms/diagnostic imaging* ; Neural Networks, Computer ; Image Processing, Computer-Assisted/methods*

OBJECTIVES: We propose a low-dose CT image restoration method based on central guidance and alternating optimization (FedGP). METHODS: The FedGP framework revolutionizes the traditional federated learning model by adopting a structure without a fixed central server, where each institution alternatively serves as the central server. This method uses an institution-modulated CT image restoration network as the core of client-side local training. Through a federated learning approach of central guidance and alternating optimization, the central server leverages local labeled data to guide client-side network training to enhance the generalization capability of the CT imaging model across multiple institutions. RESULTS: In the low-dose and sparse-view CT image restoration tasks, the FedGP method showed significant advantages in both visual and quantitative evaluation and achieved the highest PSNR (40.25 and 38.84), the highest SSIM (0.95 and 0.92), and the lowest RMSE (2.39 and 2.56). Ablation study of FedGP demonstrated that compared with FedGP(w/o GP) without central guidance, the FedGP method better adapted to data heterogeneity across institutions, thus ensuring robustness and generalization capability of the model in different imaging conditions. CONCLUSIONS FedGP provides a more flexible FL framework to solve the problem of CT imaging heterogeneity and well adapts to multi-institutional data characteristics to improve generalization ability of the model under diverse imaging geometric configurations.
Tomography, X-Ray Computed/methods* ; Humans ; Radiation Dosage ; Image Processing, Computer-Assisted/methods* ; Algorithms

OBJECTIVES: To establish a three-dimensional (3D) visualization-based classification of the left hepatic portal vein (LHPV) and left hepatic vein (LHV) systems using 3D reconstruction technology to facilitate precise segmental/subsegmental resection of left liver lesions. METHODS: Thin-slice contrast-enhanced CT datasets from 244 patients were reconstructed using MI-3DV Works software. The spatial anatomy (origins, branching patterns, and spatial relationships) of the LHPV and LHV branches was analyzed to determine their 3D classifications and segmental liver divisions for guiding surgical planning for anatomical left liver resections. RESULTS: The 3D models of the third- and fourth-order branches of the LHPV and LHV were successfully reconstructed for all the 244 patients. Two types of the LHPV system were identified, where the LHPV either had independent origins [242 cases (99.1%)] or had right anterior portal branches arising from the LHPV trunk [2 cases (0.9%)]. 3D classifications identified two types of the Segment II of the LHPV (based on branch number), 3 types of the Segment III (by spatial distribution of the branches), compact vs dispersed types of the left lateral lobe (determined by Segment II/III branches proximity), 3 types of the Segment IV (by branch number and origin), and 3 types the fourth hilar vessels (transverse branches of the left portal vein) for their supplied segments. The LHV system had two drainage types into the inferior vena cava, and the umbilical fissure veins were classified into 3 types by drainage patterns and distance to the venous roots. These classifications combined with liver segmentations allowed individualized surgical planning for segment-specific resections. CONCLUSIONS The 3D classification of the LHPV and LHV provides valuable clinical guidance for precise anatomical resections of left liver lesions using liver segments or subsegments as anatomical units to enhance surgical accuracy and improve the outcomes of hepatobiliary surgery.
Humans ; Hepatectomy/methods* ; Imaging, Three-Dimensional ; Hepatic Veins/anatomy & histology* ; Portal Vein/anatomy & histology* ; Liver/surgery* ; Liver Neoplasms/blood supply* ; Tomography, X-Ray Computed ; Female

OBJECTIVES: To construct a bone tumor classification model based on feature decoupling and fusion for processing modality loss and fusing multimodal information to improve classification accuracy. METHODS: A decoupling completion module was designed to extract local and global bone tumor image features from available modalities. These features were then decomposed into shared and modality-specific features, which were used to complete the missing modality features, thereby reducing completion bias caused by modality differences. To address the challenge of modality differences that hinder multimodal information fusion, a cross-attention-based fusion module was introduced to enhance the model's ability to learn cross-modal information and fully integrate specific features, thereby improving the accuracy of bone tumor classification. RESULTS: The experiment was conducted using a bone tumor dataset collected from the Third Affiliated Hospital of Southern Medical University for training and testing. Among the 7 available modality combinations, the proposed method achieved an average AUC, accuracy, and specificity of 0.766, 0.621, and 0.793, respectively, which represent improvements of 2.6%, 3.5%, and 1.7% over existing methods for handling missing modalities. The best performance was observed when all the modalities were available, resulting in an AUC of 0.837, which still reached 0.826 even with MRI alone. CONCLUSIONS The proposed method can effectively handle missing modalities and successfully integrate multimodal information, and show robust performance in bone tumor classification under various complex missing modality scenarios.
Humans ; Bone Neoplasms/diagnosis* ; Multimodal Imaging/methods* ; Magnetic Resonance Imaging ; Tomography, X-Ray Computed ; Image Processing, Computer-Assisted/methods* ; Algorithms

BACKGROUND: There is little literature describing the artificial intelligence (AI)-aided diagnosis of severe pneumonia (SP) subphenotypes and the association of the subphenotypes with the ventilatory treatment efficacy. The aim of our study is to illustrate whether clinical and biological heterogeneity, such as ventilation and gas-exchange, exists among patients with SP using chest computed tomography (CT)-based AI-aided latent class analysis (LCA). METHODS: This retrospective study included 413 patients hospitalized at Xinhua Hospital diagnosed with SP from June 1, 2015 to May 30, 2020. AI quantification results of chest CT and their combination with additional clinical variables were used to develop LCA models in an SP population. The optimal subphenotypes were determined though evaluating statistical indicators of all the LCA models, and clinical implications of them such as guiding ventilation strategies were further explored by statistical methods. RESULTS: The two-class LCA model based on AI quantification results of chest CT can describe the biological characteristics of the SP population well and hence yielded the two clinical subphenotypes. Patients with subphenotype-1 had milder infections ( P <0.001) than patients with subphenotype-2 and had lower 30-day ( P <0.001) and 90-day ( P <0.001) mortality, and lower in-hospital ( P = 0.001) and 2-year ( P <0.001) mortality. Patients with subphenotype-1 showed a better match between the percentage of non-infected lung volume (used to quantify ventilation) and oxygen saturation (used to reflect gas exchange), compared with patients with subphenotype-2. There were significant differences in the matching degree of lung ventilation and gas exchange between the two subphenotypes ( P <0.001). Compared with patients with subphenotype-2, those with subphenotype-1 showed a relatively better match between CT-based AI metrics of the non-infected region and oxygenation, and their clinical outcomes were effectively improved after receiving invasive ventilation treatment. CONCLUSIONS A two-class LCA model based on AI quantification results of chest CT in the SP population particularly revealed clinical heterogeneity of lung function. Identifying the degree of match between ventilation and gas-exchange may help guide decisions about assisted ventilation.
Humans ; Tomography, X-Ray Computed/methods* ; Male ; Female ; Retrospective Studies ; Middle Aged ; Artificial Intelligence ; Aged ; Pneumonia/diagnosis* ; Latent Class Analysis ; Adult

Artificial intelligence (AI), particularly deep learning, has demonstrated remarkable performance in medical imaging across a variety of modalities, including X-ray, computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, positron emission tomography (PET), and pathological imaging. However, most existing state-of-the-art AI techniques are task-specific and focus on a limited range of imaging modalities. Compared to these task-specific models, emerging foundation models represent a significant milestone in AI development. These models can learn generalized representations of medical images and apply them to downstream tasks through zero-shot or few-shot fine-tuning. Foundation models have the potential to address the comprehensive and multifactorial challenges encountered in clinical practice. This article reviews the clinical applications of both task-specific and foundation models, highlighting their differences, complementarities, and clinical relevance. We also examine their future research directions and potential challenges. Unlike the replacement relationship seen between deep learning and traditional machine learning, task-specific and foundation models are complementary, despite inherent differences. While foundation models primarily focus on segmentation and classification, task-specific models are integrated into nearly all medical image analyses. However, with further advancements, foundation models could be applied to other clinical scenarios. In conclusion, all indications suggest that task-specific and foundation models, especially the latter, have the potential to drive breakthroughs in medical imaging, from image processing to clinical workflows.
Humans ; Artificial Intelligence ; Deep Learning ; Diagnostic Imaging/methods* ; Magnetic Resonance Imaging ; Tomography, X-Ray Computed ; Positron-Emission Tomography

Among numerous medical imaging modalities, diffusion weighted imaging (DWI) is extremely sensitive to acute ischemic stroke lesions, especially small infarcts. However, magnetic resonance imaging is time-consuming and expensive, and it is also prone to interference from metal implants. Therefore, the aim of this study is to design a medical image synthesis method based on generative adversarial network, Stroke-p2pHD, for synthesizing DWI images from computed tomography (CT). Stroke-p2pHD consisted of a generator that effectively fused local image features and global context information (Global_to_Local) and a multi-scale discriminator (M ²Dis). Specifically, in the Global_to_Local generator, a fully convolutional Transformer (FCT) and a local attention module (LAM) were integrated to achieve the synthesis of detailed information such as textures and lesions in DWI images. In the M ²Dis discriminator, a multi-scale convolutional network was adopted to perform the discrimination function of the input images. Meanwhile, an optimization balance with the Global_to_Local generator was ensured and the consistency of features in each layer of the M ²Dis discriminator was constrained. In this study, the public Acute Ischemic Stroke Dataset (AISD) and the acute cerebral infarction dataset from Yantaishan Hospital were used to verify the performance of the Stroke-p2pHD model in synthesizing DWI based on CT. Compared with other methods, the Stroke-p2pHD model showed excellent quantitative results (mean-square error = 0.008, peak signal-to-noise ratio = 23.766, structural similarity = 0.743). At the same time, relevant experimental analyses such as computational efficiency verify that the Stroke-p2pHD model has great potential for clinical applications.
Humans ; Tomography, X-Ray Computed/methods* ; Diffusion Magnetic Resonance Imaging/methods* ; Cerebral Infarction/diagnostic imaging* ; Stroke/diagnostic imaging* ; Neural Networks, Computer ; Image Processing, Computer-Assisted/methods* ; Algorithms

In this study, we propose an automatic contour outlining method to measure the spatial resolution of homemade automatic tube current modulation (ATCM) phantom by outlining the edge contour of the phantom image, selecting the region of interest (ROI), and measuring the spatial resolution characteristics of computer tomography (CT) phantom image. Specifically, the method obtains a binarized image of the phantom outlined by an automated fast region convolutional neural network (AFRCNN) model, measures the edge spread function (ESF) of the CT phantom with different tube currents and layer thicknesses, and differentiates the ESF to obtain the line spread function (LSF). Finally, the values passing through the zeros are normalized by the Fourier transform to obtain the CT spatial resolution index (RI) for the automatic measurement of the modulation transfer function (MTF). In this study, this algorithm is compared with the algorithm that uses polymethylmethacrylate (PMMA) to measure the MTF of the phantom edges to verify the feasibility of this method, and the results show that the AFRCNN model not only improves the efficiency and accuracy of the phantom contour outlining, but also is able to obtain a more accurate spatial resolution value through automated segmentation. In summary, the algorithm proposed in this study is accurate in spatial resolution measurement of phantom images and has the potential to be widely used in real clinical CT images.
Phantoms, Imaging ; Tomography, X-Ray Computed/instrumentation* ; Algorithms ; Neural Networks, Computer ; Image Processing, Computer-Assisted/methods* ; Humans ; Polymethyl Methacrylate

Alveolar bone reconstruction simulation is an effective means for quantifying orthodontics, but currently, it is not possible to directly obtain human alveolar bone material models for simulation. This study introduces a prediction method for the equivalent shear modulus of three-dimensional random porous materials, integrating the first-order Ogden hyperelastic model to construct a computed tomography (CT) based porous hyperelastic Ogden model (CT-PHO) for human alveolar bone. Model parameters are derived by combining results from micro-CT, nanoindentation experiments, and uniaxial compression tests. Compared to previous predictive models, the CT-PHO model shows a lower root mean square error (RMSE) under all bone density conditions. Simulation results using the CT-PHO model parameters in uniaxial compression experiments demonstrate more accurate prediction of the mechanical behavior of alveolar bone under compression. Further prediction and validation with different individual human alveolar bone samples yield accurate results, confirming the generality of the CT-PHO model. The study suggests that the CT-PHO model proposed in this paper can estimate the material properties of human alveolar bone and may eventually be used for bone reconstruction simulations to guide clinical treatment.
Humans ; Tomography, X-Ray Computed/methods* ; Porosity ; Alveolar Process/physiology* ; Bone Density ; Computer Simulation ; Elasticity ; X-Ray Microtomography ; Stress, Mechanical ; Finite Element Analysis ; Models, Biological