In this work, we explored a computational framework for task-based adaptive SPECT imaging based on a robotic platform. The framework has two key components. First, we utilized the modified uniform Cramér–Rao bound (MUCRB) to approximate the imaging variance attainable with a given system configuration characterized by the imaging time distribution (ITD) over a discretized system configuration space. Second, we developed a computational approach to enable direct optimization of the ITD (and the associated system configuration) to achieve a minimum imaging variance. To enable efficient system optimization, a convex surrogate of the MUCRB-based variance metric was derived, and a non-uniform object-space pixelation (NUOP) strategy was introduced to reduce computational load, while preserving resolution within regions of interest (ROIs). This framework was evaluated using simulation studies with a 12-camera-head robotic SPECT system. We used several phantoms and a series of performance measures to demonstrate the effectiveness of the adaptive imaging strategy. For the brain phantom, the adapted ITD reduced RMSE from 859.0 to 734.3. For the hot-rod phantom, RMSE was reduced from 1411.9/1316.5 to 1191.2/1138.0 across the two ROIs, while CRC increased from 0.092/0.351 to 0.181/0.604. For the cold-rod phantom, RMSE was reduced from 720.0/691.1 to 603.5/587.4 across the two ROIs relative to whole-view ITD, while CRC increased from 0.069/0.150 to 0.373/0.499. These results demonstrated that the proposed framework enables efficient, task-specific optimization of acquisition strategies and significantly improved ROI image quality.
Few-shot medical image segmentation (FSMIS) aims to segment unseen anatomical structures using only a few annotated examples, alleviating the heavy annotation burden in clinical practice. Most existing FSMIS methods adopt prototype-based learning but suffer from two limitations. First, equal treatment of foreground pixels ignores their heterogeneous reliability and weakens prototype discriminability. Second, query mask prediction uses simple prototype-query similarity matching, which can induce spurious high similarity and mistakenly match background regions to the foreground prototype, producing false positives. In this work, we propose CORE, a confidence-aware prototype learning framework designed to suppress spurious similarity for FSMIS to address these issues. CORE constructs foreground prototypes from regions with different confidence levels, which prevents excessive averaging and preserves intra-class diversity under extremely limited supervision. Furthermore, an adaptive veto guided query prototype interaction module suppresses unreliable prototype-query matching under spurious inter-class similarity. Extensive experiments demonstrate that CORE achieves the best average performance across four few-shot medical segmentation datasets, with pronounced gains on CHAOS-MRI, Synapse-CT, and CMR, and consistent gains on Prostate-MRI. Our code is available at https://gitlab.com/xuchuanzhen/core.
Photon Counting CT (PCCT) employs photon counting detectors (PCDs) which possess the unique ability to partition different energy ranges of the incoming photons. This fundamental function allows PCCT to differentiate materials in objects by fully utilizing the spectrum information through material decomposition. However, due to the differences in materials, fabrication and bonding, the spectrum response between each PCD pixel exhibits slight variation, leading to significant ring artifacts in direct reconstruction images. Furthermore, inaccurate material decomposition also induces ring artifacts in virtual monoenergetic image (VMI), which pose obstacles to clinical diagnosis. To address these issues and current bottle-necks of corresponding research area, we introduce a self-adaptive dual-domain fine-tuning strategy for ring artifact reduction. Specifically, we employ linear optimization on the projection-domain sinogram guided by edge-preserving image-domain constraints. This strategy efficiently detects and removes the ring artifacts on the reconstructed images while maintaining edge information. Visual and quantitative analyses on a clinical prototype system demonstrate the effectiveness of our ring artifact reduction method.
Medical image segmentation plays a pivotal role in computer-aided diagnosis. However, the scarcity of annotated data severely hinders the deployment of deep learning models. Few-shot learning (FSL) is designed to achieve rapid adaptation to unseen classes using limited labeled samples, among which prototype-based methods have emerged as a dominant paradigm. Nevertheless, existing approaches often rely on single or coarse multi-prototype representations, failing to capture complex morphological variations and local details in medical images. Furthermore, boundary feature contamination arising from convolutional receptive fields severely degrades segmentation accuracy. To address these challenges, this paper proposes an Auxiliary Supervision-guided Edge Prototype Purification Network (EPPNet) for few-shot medical image segmentation. Specifically, the network introduces a novel Prototype Purification Module (PPM). By evaluating the semantic consistency between edge and main prototypes, the PPM selectively integrates high-confidence edge prototypes via a learnable adaptive threshold, aiming to substantially alleviate boundary feature contamination. Simultaneously, an Adaptive Prototype Generation (APG) module and an Adaptive Weight Decoding (AWD) mechanism are designed to dynamically extract semantic-aware prototypes for foreground, background, and edge regions, while assigning optimal fusion weights. Furthermore, a parallel U-Net auxiliary branch is constructed to enhance the generalization capability and spatial context modeling of the feature encoder through fully supervised dense pixel prediction. Extensive experiments on three public datasets (CHAOS-MRI, Synapse-CT, and CMRSeg) demonstrate that the proposed method outperforms existing state-of-the-art techniques across multiple organ segmentation tasks. Detailed analyses and validation further confirm significant improvements in prototype representation and boundary information utilization.
Chromium-compensated Gallium Arsenide (GaAs:Cr) has emerged as a promising sensor material for photon counting detectors (PCDs) due to its excellent resistivity and charge carrier mobility. However, due to the limitations of the Cr compensation process, the GaAs:Cr wafer thickness is less than 1 mm, which distorts its X-ray absorption efficiency and limits its application in clinical computed tomography (CT). This study proposes a GaAs detector with an edge-on structure for clinical photon counting CT (PCCT) applications. To evaluate the performance of the detector, we modeled the spectral response and analyzed material decomposition (MD) noise using a full-chain detector model. In imaging domain study, digital phantoms, such as low contrast phantom, Gammex phantom, and XCAT digital phantoms, were virtually scanned to assess the image uniformity, CT number accuracy, material decomposition, and virtual mono-energetic imaging (VMI) performance, with the detector system modeled to reflect actual PCCT prototypes. The results indicate that the GaAs:Cr detector exhibits excellent mono-energetic spectrum response and low material decomposition (MD) noise. Additionally, the GaAs:Cr detector provides lower noise, higher contrast-to-noise ratio (CNR) in VMI results, and more precise concentration measurements in quantitative analysis, compared to existing PCDs. These findings highlight the feasibility of developing GaAs:Cr detectors for clinical CT applications, offering potential advantages over existing PCDs.
