Medical image segmentation plays a crucial role in computer-aided diagnosis and treatment planning. Unsupervised segmentation methods that can effectively leverage unlabeled data bring significant promise in clinical application. However, they remain a challenging task in maintaining anatomical structure topological consistency that often produces anatomical structure breaks, connectivity errors, or boundary discontinuities. To address these issues, we propose a novel Unsupervised Topological-Aware Diffusion Condensation Network (UTADC-Net) for medical image segmentation. Specifically, we design a diffusion condensation-based framework that achieves structural consistency in segmentation results by effectively modeling long-range dependencies between pixels and incorporating topological constraints. First, to effectively fuse local details and global semantic information, we employ a pixel-centric patch embedding module by simultaneously modeling local structural features and inter-region interactions. Second, to enhance the topological consistency of segmentation results, we introduce an adaptive topological constraint mechanism that guides the network to learn anatomically aligned structural representations through pixel-level topological relationships and corresponding loss functions. Extensive experiments conducted on three public medical image datasets demonstrate that our proposed UTADC-Net significantly outperforms existing unsupervised methods in terms of segmentation accuracy and topological structure preservation. Notably, our method demonstrates segmentation results with excellent anatomical structural consistency. These results indicate that our framework provides a novel and practical solution for unsupervised medical image segmentation.

Limited-angle cone-beam computed tomography (LA-CBCT) enables rapid imaging and reduced radiation exposure, but its severely incomplete projection data lead to ill-posed reconstructions with prominent artifacts, limiting clinical applicability. Recent advances in 3D Gaussian Splatting (3D-GS) have shown promise for efficient tomographic reconstruction, yet its performance remains highly sensitive to initialization. In this work, we present SPARK (Structurally-Informed Projection-Accelerated Reconstruction), a two-stage framework that introduces a generative, structurally informed initialization for 3D-GS. In the first stage, a geometry-conditioned network directly predicts complete 3D Gaussian parameters from a sparse subset of projections, embedding learned anatomical priors to mitigate artifact propagation. In the second stage, the generated scene is refined through physics-based 3D-GS optimization, yielding high-fidelity reconstructions consistent with measured projections. Extensive experiments on public datasets demonstrate that SPARK substantially improves both image quality and convergence speed, achieving superior PSNR/SSIM in severely limited-angle scenarios compared with analytical, iterative, and deep learning baselines. Moreover, SPARK reconstructions provide enhanced inputs for downstream post-processing networks, further boosting image fidelity. These results suggest that SPARK is a promising prior-informed 3D-GS framework for simulated LA-CBCT reconstruction under limited angular coverage, providing an effective bridge between data-driven anatomical priors and physics-based projection-domain refinement.

In current clinical practice, the localization of human acupuncture points relies extensively on the subjective experience of physicians. Therefore, despite being a crucial basic content of traditional Chinese medicine (TCM), acupuncture point localization has not been well expanded and promoted through intelligent means. Our goal is to explore an efficient and reliable solution for acupuncture point localization and recognition that addresses the shortcomings of subjectivity and standardization in this task. We focus on the weak feature body surface of the human back and propose an innovative approach that utilizes a deep learning network with a self-attention module for global extraction of image features. This methodology differs from common Convolutional Neural Networks (CNNs) which often lead to classification ambiguous in weak feature image tasks due to excessive cropping and scaling operations during feature extraction. Moreover, our self-constructed dataset of human back acupuncture points provides data support for model training. The localization task for the back acupuncture points of the subjects in the dataset strictly follows the national standard definition and is labelled by professional doctors of TCM to ensure data robustness and quality. Our preliminary experiments validate that our proposed network learns higher-quality global image features, achieving an average accuracy of less than 1cm in the localization and recognition task of 84 acupuncture points on the back of the human body.

During the process of computed tomography (CT), metallic implants often cause disruptive artifacts in the reconstructed images, impeding accurate diagnosis. Many supervised deep learning-based approaches have been proposed for metal artifact reduction (MAR). However, these methods heavily rely on training with paired simulated data, which are challenging to acquire. This limitation can lead to decreased performance when applying these methods in clinical practice. Existing unsupervised MAR methods, whether based on learning or not, typically work within a single domain, either in the image domain or the sinogram domain. In this paper, we propose an unsupervised MAR method based on the diffusion model, a generative model with a high capacity to represent data distributions. Specifically, we first train a diffusion model using CT images without metal artifacts. Subsequently, we iteratively introduce the diffusion priors in both the sinogram domain and image domain to restore the degraded portions caused by metal artifacts. Besides, we design temporally dynamic weight masks for the image-domian fusion. The dual-domain processing empowers our approach to outperform existing unsupervised MAR methods, including another MAR method based on diffusion model. The effectiveness has been qualitatively and quantitatively validated on synthetic datasets. Moreover, our method demonstrates superior visual results among both supervised and unsupervised methods on clinical datasets. Codes are available in github.com/DeepXuan/DuDoDp-MAR.

Precise classification of histopathological images is crucial to computer-aided diagnosis in clinical practice. Magnification-based learning networks have attracted considerable attention for their ability to improve performance in histopathological classification. However, the fusion of pyramids of histopathological images at different magnifications is an under-explored area. In this paper, we proposed a novel deep multi-magnification similarity learning (DSML) approach that can be useful for the interpretation of multi-magnification learning framework and easy to visualize feature representation from low-dimension (e.g., cell-level) to high-dimension (e.g., tissue-level), which has overcome the difficulty of understanding cross-magnification information propagation. It uses a similarity cross entropy loss function designation to simultaneously learn the similarity of the information among cross-magnifications. In order to verify the effectiveness of DMSL, experiments with different network backbones and different magnification combinations were designed, and its ability to interpret was also investigated through visualization. Our experiments were performed on two different histopathological datasets: a clinical nasopharyngeal carcinoma and a public breast cancer BCSS2021 dataset. The results show that our method achieved outstanding performance in classification with a higher value of area under curve, accuracy, and F-score than other comparable methods. Moreover, the reasons behind multi-magnification effectiveness were discussed.

Anatomical resection (AR) based on anatomical sub-regions is a promising method of precise surgical resection, which has been proven to improve long-term survival by reducing local recurrence. The fine-grained segmentation of an organ's surgical anatomy (FGS-OSA), i.e., segmenting an organ into multiple anatomic regions, is critical for localizing tumors in AR surgical planning. However, automatically obtaining FGS-OSA results in computer-aided methods faces the challenges of appearance ambiguities among sub-regions (i.e., inter-sub-region appearance ambiguities) caused by similar HU distributions in different sub-regions of an organ's surgical anatomy, invisible boundaries, and similarities between anatomical landmarks and other anatomical information. In this paper, we propose a novel fine-grained segmentation framework termed the "anatomic relation reasoning graph convolutional network" (ARR-GCN), which incorporates prior anatomic relations into the framework learning. In ARR-GCN, a graph is constructed based on the sub-regions to model the class and their relations. Further, to obtain discriminative initial node representations of graph space, a sub-region center module is designed. Most importantly, to explicitly learn the anatomic relations, the prior anatomic-relations among the sub-regions are encoded in the form of an adjacency matrix and embedded into the intermediate node representations to guide framework learning. The ARR-GCN was validated on two FGS-OSA tasks: i) liver segments segmentation, and ii) lung lobes segmentation. Experimental results on both tasks outperformed other state-of-the-art segmentation methods and yielded promising performances by ARR-GCN for suppressing ambiguities among sub-regions.

A novel method is proposed to obtain four-dimensional (4D) cone-beam computed tomography (CBCT) images from a routine scan in patients with upper abdominal cancer. The projections are sorted according to the location of the lung diaphragm before being reconstructed to phase-sorted data. A multiscale-discriminator generative adversarial network (MSD-GAN) is proposed to alleviate the severe streaking artifacts in the original images. The MSD-GAN is trained using simulated CBCT datasets from patient planning CT images. The enhanced images are further used to estimate the deformable vector field (DVF) among breathing phases using a deformable image registration method. The estimated DVF is then applied in the motion-compensated ordered-subset simultaneous algebraic reconstruction approach to generate 4D CBCT images. The proposed MSD-GAN is compared with U-Net on the performance of image enhancement. Results show that the proposed method significantly outperforms the total variation regularization-based iterative reconstruction approach and the method using only MSD-GAN to enhance original phase-sorted images in simulation and patient studies on 4D reconstruction quality. The MSD-GAN also shows higher accuracy than the U-Net. The proposed method enables a practical way for 4D-CBCT imaging from a single routine scan in upper abdominal cancer treatment including liver and pancreatic tumors.

In this paper, we propose a novel deep learning-based automatic delineation method of nasopharynx gross tumor volume (GTVnx) by combing computed tomography (CT) and magnetic resonance imaging (MRI) modalities. The purpose of this study is to explore whether MRI can provide additional information to improve the accuracy of delineation on CT. The proposed model can adaptively leverage the high contrast information of MRI into the automated delineation of GTVnx on CT in nasopharyngeal carcinoma (NPC) radiotherapy. In this study, the dataset collected from 192 patients with NPC was used to verify the performance of the proposed method. The average Dice Similarity Coefficient, 95% Hausdorff Distance and Average Symmetric Surface Distance of the segmentation results predicted by the proposed model are 0.7181, 9.6637mm, and 2.8014mm, respectively, which outperformed that of the single-modal and the concatenation-based multi-modal segmentation models.

Since the tumor moves with the patient's breathing movement in clinical surgery, the real-time prediction of respiratory movement is required to improve the efficacy of radiotherapy. Some RNN-based respiratory management methods have been proposed for this purpose. However, these existing RNN-based methods often suffer from the degradation of generalization performance for a long-term window (such as 600 ms) because of the structural consistency constraints. In this paper, we propose an innovative Long Short-term Transformer (LSTformer) for long-term real-time accurate respiratory prediction. Specifically, a novel Long-term Information Enhancement module (LIE) is proposed to solve the performance degradation under a long window by increasing the long-term memory of latent variables. A lightweight Transformer Encoder (LTE) is proposed to satisfy the real-time requirement via simplifying the architecture and limiting the number of layers. In addition, we propose an application-oriented data augmentation strategy to generalize our LSTformer to practical application scenarios, especially robotic radiotherapy. Extensive experiments on our augmented dataset and publicly available dataset demonstrate the state-of-the-art performance of our method on the premise of satisfying the real-time demand.

Multi-material decomposition (MMD) decomposes CT images into basis material images, and is a promising technique in clinical diagnostic CT to identify material compositions within the human body. MMD could be implemented on measurements obtained from spectral CT protocol, although spectral CT data acquisition is not readily available in most clinical environments. MMD methods using single energy CT (SECT), broadly applied in radiological departments of most hospitals, have been proposed in the literature while challenged by the inferior decomposition accuracy and the limited number of material bases due to the constrained material information in the SECT measurement. In this paper, we propose an image-domain SECT MMD method using material sparsity as an assistance under the condition that each voxel of the CT image contains at most two different elemental materials. L0norm represents the material sparsity constraint (MSC) and is integrated into the decomposition objective function with a least-square data fidelity term, total variation term, and a sum-to-one constraint of material volume fractions. An accelerated primal-dual (APD) algorithm with line-search scheme is applied to solve the problem. The pixelwise direct inversion method with the two-material assumption (TMA) is applied to estimate the initials. We validate the proposed method on phantom and patient data. Compared with the TMA method, the proposed MSC method increases the volume fraction accuracy (VFA) from 92.0% to 98.5% in the phantom study. In the patient study, the calcification area can be clearly visualized in the virtual non-contrast image generated by the proposed method, and has a similar shape to that in the ground-truth contrast-free CT image. The high decomposition image quality from the proposed method substantially facilitates the SECT-based MMD clinical applications.

SUMMARY: Nowadays, it is feasible to collect massive features for quantitative representation and precision medicine, and thus, automatic ranking to figure out the most informative and discriminative ones becomes increasingly important. To address this issue, 42 feature ranking (FR) methods are integrated to form a MATLAB toolbox (matFR). The methods apply mutual information, statistical analysis, structure clustering and other principles to estimate the relative importance of features in specific measure spaces. Specifically, these methods are summarized, and an example shows how to apply a FR method to sort mammographic breast lesion features. The toolbox is easy to use and flexible to integrate additional methods. Importantly, it provides a tool to compare, investigate and interpret the features selected for various applications. AVAILABILITY AND IMPLEMENTATION: The toolbox is freely available at http://github.com/NicoYuCN/matFR. A tutorial and an example with a dataset are provided.

Guide wire tracking in fluoroscopic images has done a significant task in assisting the physicians during radiology-aided interventions. Many groups have tried to detect the guide wire from the fluoroscopic images based on the image properties. The main challenge is that manual intervention is required during the detection. Other groups try to introduce localizers to track guide wires during intervention, which requires additional hardware equipment, and may intervene with the traditional clinical routines. Machine learning methods are also exploited. Although such methods may provide accurate tracking, they often require large amount of data and training time. In this paper, we propose a GPU-based fast and automatic approach to track guide wires in fluoroscopic sequences. We propose a multi-scale filtering and gradient vector field-based real-time tracking method for guide wire tracking from fluoroscopic images. To improve calculation efficiency and meet real-time application requirement, we propose a GPU-based acceleration scheme, and also a Bayesian filter-like motion tracking method to limit the guide wire tracking to a smaller range to improve calculation efficiency. We test our proposed method on two test data sets of fluoroscopic sequences of 102 frames and 72 frames. We achieve an average guide wire detection rate of 96.7%, a false detection rate of 0.0011% and an error distance measure of 0.83 pixels for the first sequence, and 98.8%, 0.000069% and 0.85 pixels, respectively, for the second sequence. With the proposed acceleration method, we finish calculation for the first sequence in nine seconds, thus, efficiency is enhanced by 100 times with the unaccelerated algorithm.

Freehand three-dimensional (3D) ultrasound imaging is an attractive research area because it is capable of providing large field of view and high in-plane resolution image to allow better illustration of complex anatomy structures. However, reconstructed image is corrupted with speckle noise and artifacts in the conventional reconstructed volume data. In this paper, we propose a simple but effective adaptive kernel regression method for volume reconstruction from freehand swept B-scan images. By creating a linear model for estimating the homogeneous region of the B-scan image and learning the parameters of the model with a supervised learning method, the statistical characteristic of speckle can be well recovered. With the learned linear model of speckle, we can easily estimate the homogenous region and reconstruct image with speckle reduction and edge preservation via the adaptive turning of the smoothing parameters of the kernel regression. Our algorithm lends itself to parallel processing, and yields a 288× speedup on a graphics processing unit (GPU). Experiments on the simulated data, ultrasonic abdominal phantom and in-vivo liver of human subject and comparisons with some classical and recent algorithms are used to demonstrate its improvements in both volume reconstruction accuracy and efficiency.

Segmentation of carotid intima-media (IM) borders from ultrasound sequences is challenging because of unknown image noise and varying IM border morphologies and/or dynamics. In this paper, we have developed a state-space framework to sequentially segment the carotid IM borders in each image throughout the cardiac cycle. In this framework, an ${\mathrm{H}}_{\mathrm{\infty }}$ filter is used to solve the state-space equations, and a grayscale-derivative constraint snake is used to provide accurate measurements for the ${\mathrm{H}}_{\mathrm{\infty }}$ filter. We have evaluated the performance of our approach by comparing our segmentation results to the manually traced contours of ultrasound image sequences of three synthetic models and 156 real subjects from four medical centers. The results show that our method has a small segmentation error (lumen intima, LI: 53 $\pm\, 67\;{\mathrm{\mu }}$m; media-adventitia, MA: 57 $\pm\, 63\;{\mathrm{\mu }}$m) for synthetic and real sequences of different image characteristics, and also agrees well with the manual segmentation (LI: bias = 1.44 ${\mathrm{\mu }}$m; MA: bias = $-$3.38 ${\mathrm{\mu }}$m). Our approach can robustly segment the carotid ultrasound sequences with various IM border morphologies, dynamics, and unknown image noise. These results indicate the potential of our framework to segment IM borders for clinical diagnosis.

Sparse-view computed tomography (CT) holds great promise for speeding up data acquisition and reducing radiation dose in CT scans. Recent advances in reconstruction algorithms for sparse-view CT, such as iterative reconstruction algorithms, obtained high-quality image while requiring advanced computing power. Lately, deep learning (DL) has been widely used in various applications and has obtained many remarkable outcomes. In this paper, we propose a new method for sparse-view CT reconstruction based on the DL approach. The method can be divided into two steps. First, filter backprojection (FBP) was used to reconstruct the CT image from sparsely sampled sinogram. Then, the FBP results were fed to a DL neural network, which is a DenseNet and deconvolution-based network (DD-Net). The DD-Net combines the advantages of DenseNet and deconvolution and applies shortcut connections to concatenate DenseNet and deconvolution to accelerate the training speed of the network; all of those operations can greatly increase the depth of network while enhancing the expression ability of the network. After the training, the proposed DD-Net achieved a competitive performance relative to the state-of-the-art methods in terms of streaking artifacts removal and structure preservation. Compared with the other state-of-the-art reconstruction methods, the DD-Net method can increase the structure similarity by up to 18% and reduce the root mean square error by up to 42%. These results indicate that DD-Net has great potential for sparse-view CT image reconstruction.

Malignancy of hepatocellular carcinoma (HCC) is significant to establish a therapeutic strategy preoperatively for liver cancer and is one of critical issues that influence recurrence and patient survival. Recently, quantitative texture feature of HCC in arterial phase of Contrast-enhanced MR has been shown to be promising for malignancy characterization of HCC. However, such texture feature is low-level, which is usually insufficient to capture the complicated characteristics of HCC. In this work, we propose a systematic method to automatically extract deep feature from the arterial phase of Contrast-enhanced MR using convolution neural network (CNN) in order to characterize malignancy of HCC. Specifically, we resample each 3D tumor in three orthogonal views (Axial, Coronal and Sagittal) independently to increase training sets, and train one CNN for each view to generate its corresponding deep feature. We investigate a multi-kernel feature fusion method that can fuse deep features derived from three views or fuse deep feature and texture feature in a kernel space. Our experimental results demonstrate several interesting conclusions: (1) deep feature significantly outperforms previous texture feature for malignancy characterization of HCC, (2) fusion of deep feature and texture feature yields best results for malignancy characterization of HCC.

X-ray luminescence computed tomography (XLCT), which aims to achieve molecular and functional imaging by X-rays, has recently been proposed as a new imaging modality. Combining the principles of X-ray excitation of luminescence-based probes and optical signal detection, XLCT naturally fuses functional and anatomical images and provides complementary information for a wide range of applications in biomedical research. In order to improve the data acquisition efficiency of previously developed narrow-beam XLCT, a cone beam XLCT (CB-XLCT) mode is adopted here to take advantage of the useful geometric features of cone beam excitation. Practically, a major hurdle in using cone beam X-ray for XLCT is that the inverse problem here is seriously ill-conditioned, hindering us to achieve good image quality. In this paper, we propose a novel Bayesian method to tackle the bottleneck in CB-XLCT reconstruction. The method utilizes a local regularization strategy based on Gaussian Markov random field to mitigate the ill-conditioness of CB-XLCT. An alternating optimization scheme is then used to automatically calculate all the unknown hyperparameters while an iterative coordinate descent algorithm is adopted to reconstruct the image with a voxel-based closed-form solution. Results of numerical simulations and mouse experiments show that the self-adaptive Bayesian method significantly improves the CB-XLCT image quality as compared with conventional methods.

It is very challenge to investigate the motion of the carotid artery wall in ultrasound images, because of the high nonlinear dynamics of this motion. In our study, the nonlinear dynamics of carotid artery wall motion is first approximated by our nonlinear state-space approach driven by a mathematical model of the mechanical deformation of carotid artery wall. Then, the two-dimensional motion of carotid artery wall is computed by solving the nonlinear state-space approach using the unscented Kalman filter. We have then evaluated the performance of our approach by comparing it with the manual tracing method (the correlation coefficient equals 0.9897 for the radial motion and 0.9703 for the longitudinal motion) and three other state-of-the-art methods for 73 subjects. The results indicate the reliable applicability of our approach in tracking the motion of the carotid artery wall and its potential usefulness in routine clinical diagnosis.

Identifying moving objects in a video sequence is a fundamental and critical task in video surveillance, traffic monitoring, and gesture recognition in human-machine interface. In this paper, we present a novel recursive Kernel Density Estimation based background modeling method. First, local maximum in the density functions is recursively approximated using a mean shift method. Second, components and parameters in the mixture Gaussian distributions can be selected adaptively via a proposed thresholding mechanism, and finally converge to a stable background distribution model. In the scene segmentation, foreground is firstly separated by simple background subtraction approach. And then a local texture correlation operator is introduced to fill the vacancies and remove the fractional false foreground regions so as to obtain a better video segmentation quality. Experiments conducted on synthetic and video data demonstrate the superior performance of the proposed algorithms.

The task of interactive image segmentation has attracted a significant attention in recent years. The ultimate goal is to extract an object with as few user interactions as possible. In this paper, we present SUPERCUT, a novel interactive algorithm for foreground object extraction and segmentation in images. In the algorithm, the mean shift algorithm with a boundary confidence prior is introduced to efficiently pre-segment the original image into super-pixels with precise boundary. Secondly, a Bayes decision theory is introduced to model and cluster the super-pixels so as to obtain an initial effective classification of super-pixels. To achieve a more accurate object segmentation result, a boundary refinement using Interactive rectangle box with GMM learning is adopted. Experimental results on a benchmark data set show that the proposed framework is highly effective and can accurately segment a wide variety of natural images with ease.

Extraction of thin elongated objects from natural images is an important task in many computer vision applications such as image segmentation, object detection. Extensive approaches attempt to solve this issue with region features or prior knowledge, causing local minimum or short cut path. In this paper, we propose a semi-automatic method for the extraction of thin elongated objects. Given the input image, we manually label some foreground/background pixels as training samples. We use Guassian mixture model (GMM) to model background and extract object. We compute fuzzy affinity based on G-MM and take the framework of fuzzy connectedness (FC) to obtain fuzzy connected component. To obtain better result, we use adaptive components for GMM. Qualitative and quantitative comparisons show that our method outperforms many classical algorithms in terms of accuracy.

Current image matting approaches are often implemented based upon color samples under various local assumptions. In this letter, a novel image matting algorithm is investigated by treating the alpha matting as a regression problem. Specifically, we learn spatially-varying relations between pixel features and alpha values using support vector regression. Via the learning-based approach, limitations caused by local image assumptions can be greatly relieved. In addition, the computed confidence terms in learning phase can be conveniently integrated with other matting approaches for the matting accuracy improvement. Qualitative and quantitative evaluations are implemented with a public matting benchmark. And the results are compared with some recent matting algorithms to show its advantages in both efficiency and accuracy.

Alpha matting refers to the problem of estimating the opacity mask of the foreground in an image. Many recent algorithms solve it with color samples or some local assumptions, causing artifacts when they fail to collect appropriate samples or the assumptions do not hold. In this paper, we treat alpha matting as a supervised learning problem and propose a new matting approach. Given the input image and a trimap (labeling some foreground/background pixels), we segment the unlabeled region into pieces and learn the relations between pixel features and alpha values for these pieces. We use support vector regression (SVR) in the learning process. To obtain better learning results, we design a training samples selection method and use adaptive parameters for SVR. Qualitative and quantitative evaluations on a matting benchmark show that our approach outperforms many recent algorithms in terms of accuracy.

Segmentation of video with dynamic background is an important research topic in image analysis and computer vision domains. In this paper, we present a novel recursive Bayesian learning-based method for the efficient and accurate segmentation of video with dynamic background. In the algorithm, each frame pixel is represented as the layered normal distributions which correspond to different background contents in the scene. The layers are associated with a confident term and only the layers satisfy the given confidence which will be updated via the recursive Bayesian estimation. This makes learning of background motion trajectories more accurate and efficient. To improve the segmentation quality, the coarse foreground is obtained via simple background subtraction first. Then, a local texture correlation operator is introduced to fill the vacancies and remove the fractional false foreground regions. Extensive experiments on a variety of public video datasets and comparisons with some classical and recent algorithms are used to demonstrate its improvements in both segmentation accuracy and efficiency.

Modeling background and segmenting moving objects are significant techniques for video segmentation and other video processing applications. Many different methods about background modeling and video extraction have been proposed over the recent years. In this paper, we present a novel recursive Kernel Density Estimation based video segmentation method. In the algorithm, local maximum in the density functions is approximated recursively via a mean shift method firstly. Via a proposed thresholding scheme, components and parameters in the mixture Gaussian distributions can be selected adaptively, and finally converge to a relative stable background distribution mode. In the segmentation, foreground is firstly separated by simple background subtraction method. And then, the Bayes classifier is introduced to eliminate the misclassifications points to improve the segmentation quality. Experiments on four typical video clips are used to compare with some previous methods.