Optical coherence tomography (OCT) helps ophthalmologists assess macular edema, accumulation of fluids, and lesions at microscopic resolution. Quantification of retinal fluids is necessary for OCT-guided treatment management, which relies on a precise image segmentation step. As manual analysis of retinal fluids is a time-consuming, subjective, and error-prone task, there is increasing demand for fast and robust automatic solutions. In this study, a new convolutional neural architecture named RetiFluidNet is proposed for multi-class retinal fluid segmentation. The model benefits from hierarchical representation learning of textural, contextual, and edge features using a new self-adaptive dual-attention (SDA) module, multiple self-adaptive attention-based skip connections (SASC), and a novel multi-scale deep self-supervision learning (DSL) scheme. The attention mechanism in the proposed SDA module enables the model to automatically extract deformation-aware representations at different levels, and the introduced SASC paths further consider spatial-channel interdependencies for concatenation of counterpart encoder and decoder units, which improve representational capability. RetiFluidNet is also optimized using a joint loss function comprising a weighted version of dice overlap and edge-preserved connectivity-based losses, where several hierarchical stages of multi-scale local losses are integrated into the optimization process. The model is validated based on three publicly available datasets: RETOUCH, OPTIMA, and DUKE, with comparisons against several baselines. Experimental results on the datasets prove the effectiveness of the proposed model in retinal OCT fluid segmentation and reveal that the suggested method is more effective than existing state-of-the-art fluid segmentation algorithms in adapting to retinal OCT scans recorded by various image scanning instruments.

X-ray Fluorescence Computed Tomography (XFCT) is an emerging non-invasive imaging technique providing high-resolution molecular-level data. However, increased sensitivity with current benchtop X-ray sources comes at the cost of high radiation exposure. Artificial Intelligence (AI), particularly deep learning (DL), has revolutionized medical imaging by delivering high-quality images in the presence of noise. In XFCT, traditional methods rely on complex algorithms for background noise reduction, but AI holds promise in addressing high-dose concerns. We present an optimized Swin-Conv-UNet (SCUNet) model for background noise reduction in X-ray fluorescence (XRF) images at low tracer concentrations. Our method’s effectiveness is evaluated against higher-dose images, while various denoising techniques exist for X-ray and computed tomography (CT) techniques, only a few address XFCT. The DL model is trained and assessed using augmented data, focusing on background noise reduction. Image quality is measured using peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), comparing outcomes with 100% X-ray-dose images. Results demonstrate that the proposed algorithm yields high-quality images from low-dose inputs, with maximum PSNR of 39.05 and SSIM of 0.86. The model outperforms block-matching and 3D filtering (BM3D), block-matching and 4D filtering (BM4D), non-local means (NLM), denoising convolutional neural network (DnCNN), and SCUNet in both visual inspection and quantitative analysis, particularly in high-noise scenarios. This indicates the potential of AI, specifically the SCUNet model, in significantly improving XFCT imaging by mitigating the trade-off between sensitivity and radiation exposure.

X-ray Fluorescence Computed Tomography (XFCT) is an emerging non-invasive imaging technique providing molecular-level data, gaining attention for high-resolution imaging. However, increased sensitivity with benchtop X-ray sources raises radiation exposure. Artificial Intelligence (AI), particularly deep learning (DL), has revolutionized medical imaging by delivering high-quality images in the presence of noise. In XFCT, traditional methods rely on complex algorithms for noise reduction, but AI holds promise in addressing high-dose concerns. We present an optimized SCUNet model for noise reduction in low-concentration XRF images. Compared to higher-dose images, our method’s effectiveness is evaluated. While various denoising techniques exist for X-ray and CT, few address to XFCT. The DL model is trained and assessed using the augmented data, focusing on background noise reduction. Image quality is measured using PSNR and SSIM, comparing outcomes with 100% X-ray dose images. Results show the proposed algorithm achieves high-quality images from low-dose and low-contrast agents, with a maximum PSNR of 39.05 and SSIM of 0.86. The model outperforms BM3D, NLM, DnCNN, and SCUNet in both visual inspection and quantitative analysis, particularly in high-noise scenarios. This indicates the potential of AI, specifically the SCUNet model, in significantly improving XFCT imaging by mitigating the trade-off between sensitivity and radiation exposure.

Purpose: Accurate needle tracking is critical for the success of computed tomography (CT)-guided interventions, where even minor deviations may compromise procedural safety and clinical outcomes. However, existing image-guided tracking systems typically lack mechanisms to quantify and communicate the reliability of their predictions in real time, leaving clinicians to act on guidance of uncertain trustworthiness. Methods: We propose a Dynamic Uncertainty Level Assessment Framework that provides a quantitative, real-time estimate of tracking reliability by linearly linking a predicted uncertainty score to spatial tracking error. The framework consists of three different approaches: (1) a classic method based on dynamically weighted, interpretable reliability metrics; (2) a lightweight convolutional neural network (CNN) that predicts uncertainty directly from multi-view image data; and (3) a hybrid CNN that adaptively optimizes metric weights while preserving interpretability. The uncertainty level is defined on a fixed scale, with $$0\%$$ 0 % corresponding to ideal tracking (error of 0 mm) and $$100\%$$ 100 % to a tracking error of 10 mm. Results: Experimental validation on clinical and clinically realistic laboratory datasets of $$\sim $$ ∼ 30,000 frames demonstrates a strong positive correlation between uncertainty and error (Pearson $$r > 0.82$$ r > 0.82 ) and achieves a stable tracking error estimation (error difference $$<0.6$$ < 0.6 mm) with real-time performance (5 ms per frame). Conclusion: By enabling an intuitive uncertainty-to-error mapping, the proposed framework supports more informed intra-procedural decision-making, enhances operator trust in guidance data, and establishes a practical basis for integration into uncertainty-aware CT-guided intervention systems.

Holding a remote keyless entry fob near the head provides a practical opportunity to investigate configuration-dependent changes in operating range. This pilot study examined five head-contact configurations in nine adults using a factory 433.92 MHz fob and its vehicle. Complementary assessments included an anatomically shaped skull phantom and 7 T magnetic resonance imaging (MRI). Operating thresholds were determined using a staircase procedure. The submental configuration yielded positive gains in all nine participants and the largest mean and median gains: 11.11 m and 12 m, respectively. The within-subject analysis identified an overall difference among configurations in eight complete cases (Friedman ${\chi }^2\left(4\right)=23.24$; Monte Carlo $p<0.00001$ based on 200,000 permutations; Kendall’s $W=0.73$). In the phantom series, each condition with distilled water yielded a higher gain than the condition with air at the same location, although gains did not increase consistently across fill levels. These observations identify promising configurations for further investigation. MRI characterized anatomical variation to inform future studies, with no significant associations after correction for multiple comparisons. Each condition was assessed once, and placement was evaluated with fob orientation and hand/body geometry. Building on these observations, repeated measurements with independent control of these factors will help establish repeatability and clarify the electromagnetic contributions.

Background/Objectives: Establishing access is a hazardous step of laparoscopic surgery, and the widely used Veress needle offers only subjective tactile and auditory cues for peritoneal entry. Proximal vibroacoustic (VA) sensing captures needle–tissue interaction non-invasively and is known to contain a characteristic peritoneal puncture signature, which could help surgeons to precisely identify peritoneal entry. However, the VA signature has been evaluated only by retrospective, video-anchored and manual signal analysis. We investigate whether peritoneal entry can instead be detected automatically. Methods: Cavity entry is framed as a binary classification of VA signal segments, and four model families are benchmarked under a single unified protocol: a one-dimensional convolutional neural network (1D CNN), a multilayer perceptron, a bidirectional long short-term memory network (LSTM), and a support vector machine (SVM) with a radial basis function kernel. All models were trained, selected, and threshold-tuned on a synthetic abdominal phantom (996 segments) and tested once on an independent porcine cadaver dataset (154 cavity, 462 non-cavity signals) so that every test result measures generalisation across a phantom-to-porcine domain shift. Results: The 1D CNN performed the best (accuracy 0.869, AUROC 0.904, macro F1 0.833, cavity recall 0.818), closely followed by the SVM (AUROC 0.900, AUPRC 0.878). Conclusions: These results establish the feasibility of automatically detecting peritoneal entry across a phantom-to-porcine domain shift and extend the descriptive cadaveric characterisation of the puncture signature toward the automated machine learning-based detection of peritoneal entry in laparoscopic access with a Veress needle.