To develop a deep learning model based on Residual Networks (ResNet) for the automated and accurate identification of contrast phases in abdominal CT images. A dataset of 1175 abdominal contrast-enhanced CT scans was retrospectively collected for the model development, and another independent dataset of 215 scans from five hospitals was collected for external testing. Each contrast phase was independently annotated by two radiologists. A ResNet-based model was developed to automatically classify phases into the early arterial phase (EAP) or late arterial phase (LAP), portal venous phase (PVP), and delayed phase (DP). Strategy A identified EAP or LAP, PVP, and DP in one step. Strategy B used a two-step approach: first classifying images as arterial phase (AP), PVP, and DP, then further classifying AP images into EAP or LAP. Model performance and strategy comparison were evaluated. In the internal test set, the overall accuracy of the two-step strategy was 98.3% (283/288; p < 0.001), significantly higher than that of the one-step strategy (91.7%, 264/288; p < 0.001). In the external test set, the two-step model achieved an overall accuracy of 99.1% (639/645), with sensitivities of 95.1% (EAP), 99.4% (LAP), 99.5% (PVP), and 99.5% (DP). The proposed two-step ResNet-based model provides highly accurate and robust identification of contrast phases in abdominal CT images, outperforming the conventional one-step strategy. Automated and accurate identification of contrast phases in abdominal CT images provides a robust tool for improving image quality control and establishes a strong foundation for AI-driven applications, particularly those leveraging contrast-enhanced abdominal imaging data. Accurate identification of contrast phases is crucial in abdominal CT imaging. The two-step ResNet-based model achieved superior accuracy across internal and external datasets. Automated phase classification strengthens imaging quality control and supports precision AI applications.

Patients with recurrent complaints after total knee arthroplasty may suffer from aseptic implant loosening. Current imaging modalities do not quantify looseness of knee arthroplasty components. A recently developed and validated workflow quantifies the tibial component displacement relative to the bone from CT scans acquired under valgus and varus load. The 3D analysis approach includes segmentation and registration of the tibial component and bone. In the current approach, the semi-automatic segmentation requires user interaction, adding complexity to the analysis. The research question is whether the segmentation step can be fully automated while keeping outcomes indifferent. In this study, different deep-learning (DL) models for fully automatic segmentation are proposed and evaluated. For this, we employ three different datasets for model development (20 cadaveric CT pairs and 10 cadaveric CT scans) and evaluation (72 patient CT pairs). Based on the performance on the development dataset, the final model was selected, and its predictions replaced the semi-automatic segmentation in the current approach. Implant displacement was quantified by the rotation about the screw-axis, maximum total point motion, and mean target registration error. The displacement parameters of the proposed approach showed a statistically significant difference between fixed and loose samples in a cadaver dataset, as well as between asymptomatic and loose samples in a patient dataset, similar to the outcomes of the current approach. The methodological error calculated on a reproducibility dataset showed values that were not statistically significant different between the two approaches. The results of the proposed and current approaches showed excellent reliability for one and three operators on two datasets. The conclusion is that a full automation in knee implant displacement assessment is feasible by utilizing a DL-based segmentation model while maintaining the capability of distinguishing between fixed and loose implants.

Identifying amyloid-beta (Aβ)-positive patients is essential for Alzheimer's disease (AD) clinical trials and disease-modifying treatments but currently requires PET or cerebrospinal fluid sampling. Previous MRI-based deep learning models, using only T1-weighted (T1w) images, have shown moderate performance. Multi-contrast MRI and PET-based quantitative Aβ deposition were retrospectively obtained from three public datasets: ADNI, OASIS3, and A4. Aβ positivity was defined using each dataset's recommended centiloid threshold. Two EfficientNet models were trained to predict amyloid positivity: one using only T1w images and another incorporating both T1w and T2-FLAIR. Model performance was assessed using an internal held-out test set, evaluating AUC, accuracy, sensitivity, and specificity. External validation was conducted using an independent cohort from Stanford Alzheimer's Disease Research Center. DeLong's and McNemar's tests were used to compare AUC and accuracy, respectively. A total of 4,056 exams (mean [SD] age: 71.6 [6.3] years; 55% female; 55% amyloid-positive) were used for network development, and 149 exams were used for external testing (mean [SD] age: 72.1 [9.6] years; 58% female; 56% amyloid-positive). The multi-contrast model outperformed the single-modality model in the internal held-out test set (AUC: 0.67, 95% CI: 0.65-0.70, <i>P</i> < 0.001; accuracy: 0.63, 95% CI: 0.62-0.65, <i>P</i> < 0.001) compared to the T1w-only model (AUC: 0.61; accuracy: 0.59). Among cognitive subgroups, the highest performance (AUC: 0.71) was observed in mild cognitive impairment. The multi-contrast model also demonstrated consistent performance in the external test set (AUC: 0.65, 95% CI: 0.60-0.71, <i>P</i> = 0.014; accuracy: 0.62, 95% CI: 0.58- 0.65, <i>P</i> < 0.001). The use of multi-contrast MRI, specifically incorporating T2-FLAIR in addition to T1w images, significantly improved the predictive accuracy of PET-determined amyloid status from MRI scans using a deep learning approach. Aβ＝ amyloid-beta; AD＝ Alzheimer's disease; AUC＝ area under the receiver operating characteristic curve; CN＝ cognitively normal; MCI＝ mild cognitive impairment; T1w = T1-wegithed; T2-FLAIR = T2-weighted fluid attenuated inversion recovery; FBP＝¹⁸F-florbetapir; FBB＝¹⁸F-florbetaben; SUVR＝ standard uptake value ratio.

Automatic detection and classification of Cardiovascular disease (CVD) from Computed Tomography (CT) images play an important part in facilitating better-informed clinical decisions. However, most of the recent deep learning based methods either directly work on raw CT data or utilize it in pair with anatomical cardiac structure segmentation by training an end-to-end classifier. As such, these approaches become much more difficult to interpret from a clinical perspective. To address this challenge, in this work, we break down the CVD classification pipeline into three components: (i) image segmentation, (ii) image registration, and (iii) downstream CVD classification. Specifically, we utilize the Atlas-ISTN framework and recent segmentation foundational models to generate anatomical structure segmentation and a normative healthy atlas. These are further utilized to extract clinically interpretable radiomic features as well as deformation field based geometric features (through atlas registration) for CVD classification. Our experiments on the publicly available ASOCA dataset show that utilizing these features leads to better CVD classification accuracy (87.50\%) when compared against classification model trained directly on raw CT images (67.50\%). Our code is publicly available: https://github.com/biomedia-mira/grc-net

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.

To develop a high-performance machine learning model for predicting and interpreting features of pulmonary diseases. This retrospective study analyzed clinical and imaging data from patients with non-small cell lung cancer (NSCLC), granulomatous inflammation, and benign tumors, collected across multiple centers from January 2015 to October 2023. Data from two hospitals in Anhui Province were split into a development set (n = 1696) and a test set (n = 424) in an 8:2 ratio, with an external validation set (n = 909) from Zhejiang Province. Features with p < 0.05 from univariate analyses were selected using the Boruta algorithm for input into Random Forest (RF) and XGBoost models. Model efficacy was assessed using receiver operating characteristic (ROC) analysis. A total of 3030 patients were included: 2269 with NSCLC, 529 with granulomatous inflammation, and 232 with benign tumors. The Obuchowski indices for RF and XGBoost in the test set were 0.7193 (95% CI: 0.6567-0.7812) and 0.8282 (95% CI: 0.7883-0.8650), respectively. In the external validation set, indices were 0.7932 (95% CI: 0.7572-0.8250) for RF and 0.8074 (95% CI: 0.7740-0.8387) for XGBoost. XGBoost achieved better accuracy in both the test (0.81) and external validation (0.79) sets. Calibration Curve and Decision Curve Analysis (DCA) showed XGBoost offered higher net clinical benefit. The XGBoost model outperforms RF in the three-class classification of lung diseases. XGBoost surpasses Random Forest in accurately classifying NSCLC, granulomatous inflammation, and benign tumors, offering superior clinical utility via multicenter data. Lung cancer classification model has broad clinical applicability. XGBoost outperforms random forests using CT imaging data. XGBoost model can be deployed on a website for clinicians.

Low-dose computed tomography (LDCT) denoising plays an important role in medical imaging for reducing the radiation dose to patients. Recently, various data-driven and diffusion-based deep learning (DL) methods have been developed and shown promising results in LDCT denoising. However, challenges remain in ensuring generalizability to different datasets and mitigating uncertainty from stochastic sampling. In this paper, we introduce a novel dose-aware diffusion model that effectively reduces CT image noise while maintaining structural fidelity and being generalizable to different dose levels.&#xD;Approach: Our approach employs a physics-based forward process with continuous timesteps, enabling flexible representation of diverse noise levels. We incorporate a computationally efficient noise calibration module in our diffusion framework that resolves misalignment between intermediate results and their corresponding timesteps. Furthermore, we present a simple yet effective method for estimating appropriate timesteps for unseen LDCT images, allowing generalization to an unknown, arbitrary dose levels.&#xD;Main Results: Both qualitative and quantitative evaluation results on Mayo Clinic datasets show that the proposed method outperforms existing denoising methods in preserving the noise texture and restoring anatomical structures. The proposed method also shows consistent results on different dose levels and an unseen dataset.&#xD;Significance: We propose a novel dose-aware diffusion model for LDCT denoising, aiming to address the generalization and uncertainty issues of existing diffusion-based DL methods. Our experimental results demonstrate the effectiveness of the proposed method across different dose levels. We expect that our approach can provide a clinically practical solution for LDCT denoising with its high structural fidelity and computational efficiency.

To evaluate the depiction capability of fine lung nodules and airways using high-resolution settings on ultra-high-resolution energy-integrating detector CT (UHR-CT), incorporating large matrix sizes, thin-slice thickness, and iterative reconstruction (IR)/deep-learning reconstruction (DLR), using cadaveric human lungs and corresponding histological images. Images of 20 lungs were acquired using conventional CT (CCT), UHR-CT, and photon-counting detector CT (PCD-CT). CCT images were reconstructed with a 512 matrix and IR (CCT-512-IR). UHR-CT images were reconstructed with four settings by varying the matrix size and the reconstruction method: UHR-512-IR, UHR-1024-IR, UHR-2048-IR, and UHR-1024-DLR. Two imaging settings of PCD-CT were used: PCD-512-IR and PCD-1024-IR. CT images were visually evaluated and compared with histology. Overall, 6769 nodules (median: 1321 µm) and 92 airways (median: 851 µm) were evaluated. For nodules, UHR-2048-IR outperformed CCT-512-IR, UHR-512-IR, and UHR-1024-IR (p < 0.001). UHR-1024-DLR showed no significant difference from UHR-2048-IR in the overall nodule score after Bonferroni correction (uncorrected p = 0.043); however, for nodules > 1000 μm, UHR-2048-IR demonstrated significantly better scores than UHR-1024-DLR (p = 0.003). For airways, UHR-1024-IR and UHR-512-IR showed significant differences (p < 0.001), with no notable differences among UHR-1024-IR, UHR-2048-IR, and UHR-1024-DLR. UHR-2048-IR detected nodules and airways with median diameters of 604 µm and 699 µm, respectively. No significant difference was observed between UHR-512-IR and PCD-512-IR (p > 0.1). PCD-1024-IR outperformed UHR-CTs for nodules > 1000 μm (p ≤ 0.001), while UHR-1024-DLR outperformed PCD-1024-IR for airways > 1000 μm (p = 0.005). UHR-2048-IR demonstrated the highest scores among the evaluated EID-CT images. UHR-CT showed potential for detecting submillimeter nodules and airways. With the 512 matrix, UHR-CT demonstrated performance comparable to PCD-CT. Question There are scarce data evaluating the depiction capabilities of ultra-high-resolution energy-integrating detector CT (UHR-CT) for fine structures, nor any comparisons with photon-counting detector CT (PCD-CT). Findings UHR-CT depicted nodules and airways with median diameters of 604 µm and 699 µm, showing no significant difference from PCD-CT with the 512 matrix. Clinical relevance High-resolution imaging is crucial for lung diagnosis. UHR-CT has the potential to contribute to pulmonary nodule diagnosis and airway disease evaluation by detecting fine opacities and airways.

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.

The C-arm biplane imaging system, designed for cerebral angiography, detects pathologies like aneurysms using dual rotating detectors for high-precision, real-time vascular imaging. However, accuracy can be affected by source-detector trajectory deviations caused by gravitational artifacts and mechanical instabilities. This study addresses calibration challenges and suggests leveraging interventional devices with radio-opaque markers to optimize C-arm geometry. We propose an online calibration method using image-specific features derived from interventional devices like guidewires and catheters (In the remainder of this paper, the term"catheter" will refer to both catheter and guidewire). The process begins with gantry-recorded data, refined through iterative nonlinear optimization. A machine learning approach detects and segments elongated devices by identifying candidates via thresholding on a weighted sum of curvature, derivative, and high-frequency indicators. An ensemble classifier segments these regions, followed by post-processing to remove false positives, integrating vessel maps, manual correction and identification markers. An interpolation step filling gaps along the catheter. Among the optimized ensemble classifiers, the one trained on the first frames achieved the best performance, with a specificity of 99.43% and precision of 86.41%. The calibration method was evaluated on three clinical datasets and four phantom angiogram pairs, reducing the mean backprojection error from 4.11 ± 2.61 to 0.15 ± 0.01 mm. Additionally, 3D accuracy analysis showed an average root mean square error of 3.47% relative to the true marker distance. This study explores using interventional tools with radio-opaque markers for C-arm self-calibration. The proposed method significantly reduces 2D backprojection error and 3D RMSE, enabling accurate 3D vascular reconstruction.