To validate a deep learning foundation model for automated head computed tomography (CT) reformatting and to quantify the quality, speed, and variability of conventional manual reformats in a real-world dataset. A foundation artificial intelligence (AI) model was used to create automated reformats for 1,763 consecutive non-contrast head CT examinations. Model accuracy was first validated on a 100-exam subset by assessing landmark detection as well as rotational, centering, and zoom error against expert manual annotations. The validated model was subsequently used as a reference standard to evaluate the quality and speed of the original technician-generated reformats from the full dataset. The AI model demonstrated high concordance with expert annotations, with a mean landmark localization error of 0.6-0.9 mm. Compared to expert-defined planes, AI-generated reformats exhibited a mean rotational error of 0.7 degrees, a mean centering error of 0.3%, and a mean zoom error of 0.4%. By contrast, technician-generated reformats demonstrated a mean rotational error of 11.2 degrees, a mean centering error of 6.4%, and a mean zoom error of 6.2%. Significant variability in manual reformat quality was observed across different factors including patient age, scanner location, report findings, and individual technician operators. Manual head CT reformatting is subject to substantial variability in both quality and speed. A single-shot deep learning foundation model can generate reformats with high accuracy and consistency. The implementation of such an automated method offers the potential to improve standardization, increase workflow efficiency, and reduce operational costs in clinical practice.

Preoperative identification of high-risk locally advanced colorectal cancer (LACRC) patients is vital for optimizing treatment and minimizing toxicity. This study aims to develop and validate a combined model of CT-based images and clinical laboratory parameters to noninvasively predict postoperative early recurrence (ER) in LACRC patients. A retrospective cohort of 560 pathologically confirmed LACRC patients collected from three centers between July 2018 and March 2022 and the Gene Expression Omnibus (GEO) dataset was analyzed. We extracted radiomics and deep learning signatures (RDs) using eight machine learning techniques, integrated them with clinical-laboratory parameters to construct a preoperative combined model, and validated it in two external datasets. Its predictive performance was compared with postoperative pathological and TNM staging models. Kaplan-Meier analysis was used to evaluate preoperative risk stratification, and molecular correlations with ER were explored using GEO RNA-sequencing data. The model included five independent prognostic factors: RDs, lymphocyte-to-monocyte ratio, neutrophil-to-lymphocyte ratio, lymphocyte-Albumin, and prognostic nutritional index. It outperformed pathological and TNM models in two external datasets (AUC for test set 1:0.865 vs. 0.766, 0.665; AUC for test set 2: 0.848 vs. 0.754, 0.694). Preoperative risk stratification identified significantly better disease-free survival in low-risk vs. high-risk patients across all subgroups (p < 0.01). High enrichment scores were associated with upregulated tumor proliferation pathways (epithelial-mesenchymal transition [EMT] and inflammatory response pathways) and altered immune cell infiltration patterns in the tumor microenvironment. The preoperative model enables treatment strategy optimization and reduces unnecessary drug toxicity by noninvasively predicting ER in LACRC.

To assess whether few-shot prompting improves the performance of 2 popular large language models (LLMs) (ChatGPT o1 and DeepSeek-R1) in assigning Coronary Artery Disease Reporting and Data System (CAD-RADS™ 2.0) categories. A detailed few-shot prompt based on CAD-RADS™ 2.0 framework was developed using 20 reports from the MIMIC-IV database. Subsequently, 100 modified reports from the same database were categorized using zero-shot and few-shot prompts through the models' user interface. Model accuracy was evaluated by comparing assignments to a reference radiologist's classifications, including stenosis categories and modifiers. To assess reproducibility, 50 reports were reclassified using the same few-shot prompt. McNemar tests and Cohen kappa were used for statistical analysis. Using zero-shot prompting, accuracy was low for both models (ChatGPT: 14%, DeepSeek: 8%), with correct assignments occurring almost exclusively in CAD-RADS 0 cases. Hallucinations occurred frequently (ChatGPT: 19%, DeepSeek: 54%). Few-shot prompting significantly improved accuracy to 98% for ChatGPT and 93% for DeepSeek (both P<0.001) and eliminated hallucinations. Kappa values for agreement between model-generated and radiologist-assigned classifications were 0.979 (0.950, 1.000) (P<0.001) for ChatGPT and 0.916 (0.859, 0.973) (P<0.001) for DeepSeek, indicating almost perfect agreement for both models without a significant difference between the models (P=0.180). Reproducibility analysis yielded kappa values of 0.957 (0.900, 1.000) (P<0.001) for ChatGPT and 0.873 [0.779, 0.967] (P<0.001) for DeepSeek, indicating almost perfect and strong agreement between repeated assignments, respectively, with no significant difference between the models (P=0.125). Few-shot prompting substantially enhances LLMs' accuracy in assigning CAD-RADS™ 2.0 categories, suggesting potential for clinical application and facilitating system adoption.

Segmenting ischemic stroke lesions from Non-Contrast CT (NCCT) scans is a complex task due to the hypo-intense nature of these lesions compared to surrounding healthy brain tissue and their iso-intensity with lateral ventricles in many cases. Identifying early acute ischemic stroke lesions in NCCT remains particularly challenging. Computer-assisted detection and segmentation can serve as valuable tools to support clinicians in stroke diagnosis. This paper introduces CoAt U SegNet, a novel deep learning model designed to detect and segment acute ischemic stroke lesions from NCCT scans. Unlike conventional 3D segmentation models, this study presents an advanced 3D deep learning approach to enhance delineation accuracy. Traditional machine learning models have struggled to achieve satisfactory segmentation performance, highlighting the need for more sophisticated techniques. For model training, 50 NCCT scans were used, with 10 scans for validation and 500 scans for testing. The encoder convolution blocks incorporated dilation rates of 1, 3, and 5 to capture multi-scale features effectively. Performance evaluation on 500 unseen NCCT scans yielded a Dice similarity score of 75% and a Jaccard index of 70%, demonstrating notable improvement in segmentation accuracy. An enhanced similarity index was employed to refine lesion segmentation, which can further aid in distinguishing the penumbra from the core infarct area, contributing to improved clinical decision-making.

Pancreatic ductal adenocarcinoma (PDAC) is a leading cause of cancer-related deaths, with accurate staging being critical for treatment planning. Automated 3D segmentation models can aid in staging, but segmenting PDAC, especially in cases of locally advanced pancreatic cancer (LAPC), is challenging due to the tumor's heterogeneous appearance, irregular shapes, and extensive infiltration. This study developed and evaluated a tripartite self-supervised learning architecture for improved 3D segmentation of LAPC, addressing the challenges of heterogeneous appearance, irregular shapes, and extensive infiltration in PDAC. We implemented a tripartite architecture consisting of a teacher model, a professor model, and a student model. The teacher model, trained on manually segmented CT scans, generated initial pseudo-segmentations. The professor model refined these segmentations, which were then used to train the student model. We utilized 1115 CT scans from 903 patients for training. Three expert abdominal radiologists manually segmented 30 CT scans from 27 patients with LAPC, serving as reference standards. We evaluated the performance using DICE, Hausdorff distance (HD95), and mean surface distance (MSD). The teacher, professor, and student models achieved average DICE scores of 0.60, 0.73, and 0.75, respectively, with significant boundary accuracy improvements (teacher HD95/MSD, 25.71/5.96 mm; professor, 9.68/1.96 mm; student, 4.79/1.34 mm). Our findings demonstrate that the professor model significantly enhances segmentation accuracy for LAPC (p < 0.01). Both the professor and student models offer substantial improvements over previous work. The introduced tripartite self-supervised learning architecture shows promise for improving automated 3D segmentation of LAPC, potentially aiding in more accurate staging and treatment planning.

Accurate dose calculation on cone beam computed tomography (CBCT) images is essential for modern proton treatment planning workflows, particularly when accounting for inter-fractional anatomical changes in adaptive treatment scenarios. Traditional CBCT-based dose calculation suffers from image quality limitations, requiring complex correction workflows. This study develops and validates a deep learning approach for direct proton dose calculation from CBCT images using extended Long Short-Term Memory (xLSTM) neural networks. A retrospective dataset of 40 head-and-neck cancer patients with paired planning CT and treatment CBCT images was used to train an xLSTM-based neural network (CBCT-NN). The architecture incorporates energy token encoding and beam's-eye-view sequence modelling to capture spatial dependencies in proton dose deposition patterns. Training utilized 82,500 paired beam configurations with Monte Carlo-generated ground truth doses. Validation was performed on 5 independent patients using gamma analysis, mean percentage dose error assessment, and dose-volume histogram comparison. The CBCT-NN achieved gamma pass rates of 95.1 $\pm$ 2.7% using 2mm/2% criteria. Mean percentage dose errors were 2.6 $\pm$ 1.4% in high-dose regions ($>$90% of max dose) and 5.9 $\pm$ 1.9% globally. Dose-volume histogram analysis showed excellent preservation of target coverage metrics (Clinical Target Volume V95% difference: -0.6 $\pm$ 1.1%) and organ-at-risk constraints (parotid mean dose difference: -0.5 $\pm$ 1.5%). Computation time is under 3 minutes without sacrificing Monte Carlo-level accuracy. This study demonstrates the proof-of-principle of direct CBCT-based proton dose calculation using xLSTM neural networks. The approach eliminates traditional correction workflows while achieving comparable accuracy and computational efficiency suitable for adaptive protocols.

As medical diagnoses increasingly leverage multimodal data, machine learning models are expected to effectively fuse heterogeneous information while remaining robust to missing modalities. In this work, we propose a novel multimodal learning framework that integrates enhanced modalities dropout and contrastive learning to address real-world limitations such as modality imbalance and missingness. Our approach introduces learnable modality tokens for improving missingness-aware fusion of modalities and augments conventional unimodal contrastive objectives with fused multimodal representations. We validate our framework on large-scale clinical datasets for disease detection and prediction tasks, encompassing both visual and tabular modalities. Experimental results demonstrate that our method achieves state-of-the-art performance, particularly in challenging and practical scenarios where only a single modality is available. Furthermore, we show its adaptability through successful integration with a recent CT foundation model. Our findings highlight the effectiveness, efficiency, and generalizability of our approach for multimodal learning, offering a scalable, low-cost solution with significant potential for real-world clinical applications. The code is available at https://github.com/omron-sinicx/medical-modality-dropout.

Background: Accurate and fast dose calculation is essential for optimizing carbon ion therapy. Existing machine learning (ML) models have been developed for other radiotherapy modalities. They use patient data with uniform CT imaging properties. Purpose: This study investigates the application of several ML models for physical dose calculation in carbon ion therapy and compares their ability to generalize to CT data with varying resolutions. Among the models examined is a Diffusion Model, which is tested for the first time for the calculation of physical dose distributions. Methods: A dataset was generated using publicly available CT images of the head and neck region. Monoenergetic carbon ion beams were simulated at various initial energies using Geant4 simulation software. A U-Net architecture was developed for dose prediction based on distributions of material density in patients and of absorbed dose in water. It was trained as a Generative Adversarial Network (GAN) generator, a Diffusion Model noise estimator, and as a standalone network. Their performances were compared with two models from literature. Results: All models produced dose distributions deviating by less than 2% from that obtained by a full Monte Carlo simulation, even for a patient not seen during training. Dose calculation time on a GPU was in the range of 3 ms to 15 s. The resource-efficient U-Net appears to perform comparably to the more computationally intensive GAN and Diffusion Model. Conclusion: This study demonstrates that ML models can effectively balance accuracy and speed for physical dose calculation in carbon ion therapy. Using the computationally efficient U-Net can help conserve resources. The generalizability of the models to different CT image resolutions enables the use for different patients without extensive retraining.

This case report elucidates the application of an integrated digital workflow in which diagnosis, planning, and execution were enhanced by artificial intelligence (AI), enabling an assertive interdisciplinary esthetic-functional rehabilitation. With AI-powered software, the sequence from orthodontic treatment to the final rehabilitation achieved high predictability, addressing patient's chief complaints. A patient presented with a missing maxillary left central incisor (tooth 11) and dissatisfaction with a removable partial denture. Clinical examination revealed a gummy smile, a deviated midline, and a disproportionate mesiodistal space relative to the midline. Initial documentation included photographs, intraoral scanning, and cone-beam computed tomography of the maxilla. These data were integrated into a digital planning software to create an interdisciplinary plan. This workflow included prosthetically guided orthodontic treatment with aligners, a motivational mockup, guided implant surgery, peri-implant soft tissue management, and final prosthetic rehabilitation using a CAD/CAM approach. This digital workflow enhanced communication among the multidisciplinary team and with the patient, ensuring highly predictable esthetic and functional outcomes. Comprehensive digital workflows improve diagnostic accuracy, streamline planning with AI, and facilitate patient understanding. This approach increases patient satisfaction, supports interdisciplinary collaboration, and promotes treatment adherence.

Objective: Cone-beam computed tomography (CBCT) provides a low-dose imaging alternative to conventional CT, but suffers from noise, scatter, and artifacts that degrade image quality. Synthetic CT (sCT) aims to translate CBCT to high-quality CT-like images for improved anatomical accuracy and dosimetric precision. Although deep learning approaches have shown promise, they often face limitations in generalizability and detail preservation. Conditional diffusion models (CDMs), with their iterative refinement process, offers a novel solution. This review systematically examines the use of CDMs for CBCT-to-sCT synthesis. Methods: A systematic search was conducted in Web of Science, Scopus, and Google Scholar for studies published between 2013 and 2024. Inclusion criteria targeted works employing conditional diffusion models specifically for sCT generation. Eleven relevant studies were identified and analyzed to address three questions: (1) What conditional diffusion methods are used? (2) How do they compare to conventional deep learning in accuracy? (3) What are their clinical implications? Results: CDMs incorporating anatomical priors and spatial-frequency features demonstrated improved structural preservation and noise robustness. Energy-guided and hybrid latent models enabled enhanced dosimetric accuracy and personalized image synthesis. Across studies, CDMs consistently outperformed traditional deep learning models in noise suppression and artefact reduction, especially in challenging cases like lung imaging and dual-energy CT. Conclusion: Conditional diffusion models show strong potential for generalized, accurate sCT generation from CBCT. However, clinical adoption remains limited. Future work should focus on scalability, real-time inference, and integration with multi-modal imaging to enhance clinical relevance.