Accurate preoperative diagnosis of parotid gland tumors (PGTs) is crucial for surgical planning since malignant tumors require more extensive excision. Though fine-needle aspiration biopsy is the diagnostic gold standard, its sensitivity in detecting malignancies is limited. While Deep learning (DL) models based on magnetic resonance imaging (MRI) are common in medicine, they are less studied for parotid gland tumors. This study used a 2.5D imaging approach (Incorporating Inter-Slice Information) to train a DL model to differentiate between benign and malignant PGTs. This retrospective study included 122 parotid tumor patients, using MRI and clinical features to build predictive models. In the traditional model, univariate analysis identified statistically significant features, which were then used in multivariate logistic regression to determine independent predictors. The model was built using four-fold cross-validation. The deep learning model was trained using 2D and 2.5D imaging approaches, with a transformer-based architecture employed for transfer learning. The model's performance was evaluated using the area under the receiver operating characteristic curve (AUC) and confusion matrix metrics. In the traditional model, boundary and peritumoral invasion were identified as independent predictors for PGTs, and the model was constructed based on these features. The model achieved an AUC of 0.79 but demonstrated low sensitivity (0.54). In contrast, the DL model based on 2.5D T2 fat-suppressed images showed superior performance, with an AUC of 0.86 and a sensitivity of 0.78. The 2.5D imaging technique, when integrated with a transformer-based transfer learning model, demonstrates significant efficacy in differentiating between PGTs.

The accurate assessment of computed tomography (CT) image quality is crucial for ensuring diagnostic reliability while minimizing radiation dose. Radiologists' evaluations are time-consuming and labor-intensive. Existing automated approaches often require large CT datasets with predefined image quality assessment (IQA) scores, which often do not align well with clinical evaluations. We aim to develop a reference-free, automated method for CT IQA that closely reflects radiologists' evaluations, reducing the dependency on large annotated datasets. We propose Task-Focused Knowledge Transfer (TFKT), a deep learning-based IQA method leveraging knowledge transfer from task-similar natural image datasets. TFKT incorporates a hybrid convolutional neural network-transformer model, enabling accurate quality predictions by learning from natural image distortions with human-annotated mean opinion scores. The model is pre-trained on natural image datasets and fine-tuned on low-dose computed tomography perceptual image quality assessment data to ensure task-specific adaptability. Extensive evaluations demonstrate that the proposed TFKT method effectively predicts IQA scores aligned with radiologists' assessments on in-domain datasets and generalizes well to out-of-domain clinical pediatric CT exams. The model achieves robust performance without requiring high-dose reference images. Our model is capable of assessing the quality of <math xmlns="http://www.w3.org/1998/Math/MathML"><mrow><mo>∼</mo> <mn>30</mn></mrow> </math> CT image slices in a second. The proposed TFKT approach provides a scalable, accurate, and reference-free solution for CT IQA. The model bridges the gap between traditional and deep learning-based IQA, offering clinically relevant and computationally efficient assessments applicable to real-world clinical settings.

In domain continual medical image segmentation, distillation-based methods mitigate catastrophic forgetting by continuously reviewing old knowledge. However, these approaches often exhibit biases towards both new and old knowledge simultaneously due to confounding factors, which can undermine segmentation performance. To address these biases, we propose the Causality-Adjusted Data Augmentation (CauAug) framework, introducing a novel causal intervention strategy called the Texture-Domain Adjustment Hybrid-Scheme (TDAHS) alongside two causality-targeted data augmentation approaches: the Cross Kernel Network (CKNet) and the Fourier Transformer Generator (FTGen). (1) TDAHS establishes a domain-continual causal model that accounts for two types of knowledge biases by identifying irrelevant local textures (L) and domain-specific features (D) as confounders. It introduces a hybrid causal intervention that combines traditional confounder elimination with a proposed replacement approach to better adapt to domain shifts, thereby promoting causal segmentation. (2) CKNet eliminates confounder L to reduce biases in new knowledge absorption. It decreases reliance on local textures in input images, forcing the model to focus on relevant anatomical structures and thus improving generalization. (3) FTGen causally intervenes on confounder D by selectively replacing it to alleviate biases that impact old knowledge retention. It restores domain-specific features in images, aiding in the comprehensive distillation of old knowledge. Our experiments show that CauAug significantly mitigates catastrophic forgetting and surpasses existing methods in various medical image segmentation tasks. The implementation code is publicly available at: https://github.com/PerceptionComputingLab/CauAug_DCMIS.

Early detection of glaucoma represents a vital factor in securing vision while the disease retains its position as one of the central causes of blindness worldwide. The current glaucoma screening strategies with expert interpretation depend on complex and time-consuming procedures which slow down both diagnosis processes and intervention timing. This research adopts a complex automated glaucoma diagnostic system that combines optimized segmentation solutions together with classification platforms. The proposed segmentation approach implements an enhanced version of U-Net++ using dynamic parameter control provided by GWO to segment optic disc and cup regions in retinal fundus images. Through the implementation of GWO the algorithm uses wolf-pack hunting strategies to adjust parameters dynamically which enables it to locate diverse textural patterns inside images. The system uses a CapsNet capsule network for classification because it maintains visual spatial organization to detect glaucoma-related patterns precisely. The developed system secures an evaluation accuracy of 95.1% in segmentation and classification tasks better than typical approaches. The automated system eliminates and enhances clinical diagnostic speed as well as diagnostic precision. The tool stands out because of its supreme detection accuracy and reliability thus making it an essential clinical early-stage glaucoma diagnostic system and a scalable healthcare deployment solution. To develop an advanced automated glaucoma diagnostic system by integrating an optimized U-Net++ segmentation model with a Capsule Network (CapsNet) classifier, enhanced through Grey Wolf Optimization Algorithm (GWOA), for precise segmentation of optic disc and cup regions and accurate glaucoma classification from retinal fundus images. This study proposes a two-phase computer-assisted diagnosis (CAD) framework. In the segmentation phase, an enhanced U-Net++ model, optimized by GWOA, is employed to accurately delineate the optic disc and cup regions in fundus images. The optimization dynamically tunes hyperparameters based on grey wolf hunting behavior for improved segmentation precision. In the classification phase, a CapsNet architecture is used to maintain spatial hierarchies and effectively classify images as glaucomatous or normal based on segmented outputs. The performance of the proposed model was validated using the ORIGA retinal fundus image dataset, and evaluated against conventional approaches. The proposed GWOA-UNet++ and CapsNet framework achieved a segmentation and classification accuracy of 95.1%, outperforming existing benchmark models such as MTA-CS, ResFPN-Net, DAGCN, MRSNet and AGCT. The model demonstrated robustness against image irregularities, including variations in optic disc size and fundus image quality, and showed superior performance across accuracy, sensitivity, specificity, precision, and F1-score metrics. The developed automated glaucoma detection system exhibits enhanced diagnostic accuracy, efficiency, and reliability, offering significant potential for early-stage glaucoma detection and clinical decision support. Future work will involve large-scale multi-ethnic dataset validation, integration with clinical workflows, and deployment as a mobile or cloud-based screening tool.

In this work, we introduce a benchtop, turn-table photon-counting (PC) micro-CT scanner and highlight its application for dynamic small animal perfusion imaging.&#xD;Approach: Built on recently published hardware, the system now features a CdTe-based photon-counting detector (PCD). We validated its static spectral PC micro-CT imaging using conventional phantoms and assessed dynamic performance with a custom flow-configurable dual-compartment perfusion phantom. The phantom was scanned under varied flow conditions during injections of a low molecular weight iodinated contrast agent. In vivo mouse studies with identical injection settings demonstrated potential applications. A pretrained denoising CNN processed large multi-energy, temporal datasets (20 timepoints × 4 energies × 3 spatial dimensions), reconstructed via weighted filtered back projection. A separate CNN, trained on simulated data, performed gamma variate-based 2D perfusion mapping, evaluated qualitatively in phantom and in vivo tests.&#xD;Main Results: Full five-dimensional reconstructions were denoised using a CNN in ~3% of the time of iterative reconstruction, reducing noise in water at the highest energy threshold from 1206 HU to 86 HU. Decomposed iodine maps, which improved contrast to noise ratio from 16.4 (in the lowest energy CT images) to 29.4 (in the iodine maps), were used for perfusion analysis. The perfusion CNN outperformed pixelwise gamma variate fitting by ~33%, with a test set error of 0.04 vs. 0.06 in blood flow index (BFI) maps, and quantified linear BFI changes in the phantom with a coefficient of determination of 0.98.&#xD;Significance: This work underscores the PC micro-CT scanner's utility for high-throughput small animal perfusion imaging, leveraging spectral PC micro-CT and iodine decomposition. It provides a versatile platform for preclinical vascular research and advanced, time-resolved studies of disease models and therapeutic interventions.

The increasing integration of Artificial Intelligence (AI) into health and biomedical systems necessitates robust frameworks for transparency, accountability, and ethical compliance. Existing frameworks often rely on human-readable, manual documentation which limits scalability, comparability, and machine interpretability across projects and platforms. They also fail to provide a unique, verifiable identity for AI models to ensure their provenance and authenticity across systems and use cases, limiting reproducibility and stakeholder trust. This paper introduces the concept of the AI Model Passport, a structured and standardized documentation framework that acts as a digital identity and verification tool for AI models. It captures essential metadata to uniquely identify, verify, trace and monitor AI models across their lifecycle - from data acquisition and preprocessing to model design, development and deployment. In addition, an implementation of this framework is presented through AIPassport, an MLOps tool developed within the ProCAncer-I EU project for medical imaging applications. AIPassport automates metadata collection, ensures proper versioning, decouples results from source scripts, and integrates with various development environments. Its effectiveness is showcased through a lesion segmentation use case using data from the ProCAncer-I dataset, illustrating how the AI Model Passport enhances transparency, reproducibility, and regulatory readiness while reducing manual effort. This approach aims to set a new standard for fostering trust and accountability in AI-driven healthcare solutions, aspiring to serve as the basis for developing transparent and regulation compliant AI systems across domains.

Reasoning is a hallmark of human intelligence, enabling adaptive decision-making in complex and unfamiliar scenarios. In contrast, machine intelligence remains bound to training data, lacking the ability to dynamically refine solutions at inference time. While some recent advances have explored reasoning in machines, these efforts are largely limited to verbal domains such as mathematical problem-solving, where explicit rules govern step-by-step reasoning. Other critical real-world tasks - including visual perception, spatial reasoning, and radiological diagnosis - require non-verbal reasoning, which remains an open challenge. Here we present a novel learning paradigm that enables machine reasoning in vision by allowing performance improvement with increasing thinking time (inference-time compute), even under conditions where labelled data is very limited. Inspired by dual-process theories of human cognition in psychology, our approach integrates a fast-thinking System I module for familiar tasks, with a slow-thinking System II module that iteratively refines solutions using self-play reinforcement learning. This paradigm mimics human reasoning by proposing, competing over, and refining solutions in data-scarce scenarios. We demonstrate superior performance through extended thinking time, compared not only to large-scale supervised learning but also foundation models and even human experts, in real-world vision tasks. These tasks include computer-vision benchmarks and cancer localisation on medical images across five organs, showcasing transformative potential for non-verbal machine reasoning.

The generalization of deep learning-based low-dose computed tomography (CT) reconstruction models to doses unseen in the training data is important and remains challenging. Previous efforts heavily rely on paired data to improve the generalization performance and robustness through collecting either diverse CT data for re-training or a few test data for fine-tuning. Recently, diffusion models have shown promising and generalizable performance in low-dose CT (LDCT) reconstruction, however, they may produce unrealistic structures due to the CT image noise deviating from Gaussian distribution and imprecise prior information from the guidance of noisy LDCT images. In this paper, we propose a noise-inspired diffusion model for generalizable LDCT reconstruction, termed NEED, which tailors diffusion models for noise characteristics of each domain. First, we propose a novel shifted Poisson diffusion model to denoise projection data, which aligns the diffusion process with the noise model in pre-log LDCT projections. Second, we devise a doubly guided diffusion model to refine reconstructed images, which leverages LDCT images and initial reconstructions to more accurately locate prior information and enhance reconstruction fidelity. By cascading these two diffusion models for dual-domain reconstruction, our NEED requires only normal-dose data for training and can be effectively extended to various unseen dose levels during testing via a time step matching strategy. Extensive qualitative, quantitative, and segmentation-based evaluations on two datasets demonstrate that our NEED consistently outperforms state-of-the-art methods in reconstruction and generalization performance. Source code is made available at https://github.com/qgao21/NEED.

Magnetic resonance imaging (MRI) is a crucial tool for visualizing orbital structures and detecting eye pathologies. However, manual segmentation of orbital anatomy is challenging due to the complexity and variability of the structures. Recent advancements in deep learning (DL), particularly convolutional neural networks (CNNs), offer promising solutions for automated segmentation in medical imaging. This study aimed to train and evaluate a U-Net-based model for the automated segmentation of key orbital structures. This retrospective study included 117 patients with various orbital pathologies who underwent orbital MRI. Manual segmentation was performed on four anatomical structures: the ocular bulb, ocular tumors, retinal detachment, and the optic nerve. Following the UNet autoconfiguration by nnUNet, we conducted a five-fold cross-validation and evaluated the model's performances using Dice Similarity Coefficient (DSC) and Relative Absolute Volume Difference (RAVD) as metrics. nnU-Net achieved high segmentation performance for the ocular bulb (mean DSC: 0.931) and the optic nerve (mean DSC: 0.820). Segmentation of ocular tumors (mean DSC: 0.788) and retinal detachment (mean DSC: 0.550) showed greater variability, with performance declining in more challenging cases. Despite these challenges, the model achieved high detection rates, with ROC AUCs of 0.90 for ocular tumors and 0.78 for retinal detachment. This study demonstrates nnU-Net's capability for accurate segmentation of orbital structures, particularly the ocular bulb and optic nerve. However, challenges remain in the segmentation of tumors and retinal detachment due to variability and artifacts. Future improvements in deep learning models and broader, more diverse datasets may enhance segmentation performance, ultimately aiding in the diagnosis and treatment of orbital pathologies.

Ultrasound Coherent Plane Wave Compounding (CPWC) enhances image contrast by combining echoes from multiple steered transmissions. While increasing the number of angles generally improves image quality, it drastically reduces the frame rate and can introduce blurring artifacts in fast-moving targets. Moreover, compounded images remain susceptible to noise, particularly when acquired with a limited number of transmissions. We propose a zero-shot denoising framework tailored for low-angle CPWC acquisitions, which enhances contrast without relying on a separate training dataset. The method divides the available transmission angles into two disjoint subsets, each used to form compound images that include higher noise levels. The new compounded images are then used to train a deep model via a self-supervised residual learning scheme, enabling it to suppress incoherent noise while preserving anatomical structures. Because angle-dependent artifacts vary between the subsets while the underlying tissue response is similar, this physics-informed pairing allows the network to learn to disentangle the inconsistent artifacts from the consistent tissue signal. Unlike supervised methods, our model requires no domain-specific fine-tuning or paired data, making it adaptable across anatomical regions and acquisition setups. The entire pipeline supports efficient training with low computational cost due to the use of a lightweight architecture, which comprises only two convolutional layers. Evaluations on simulation, phantom, and in vivo data demonstrate superior contrast enhancement and structure preservation compared to both classical and deep learning-based denoising methods.