Placental segmentation is critical for the quantitative analysis of prenatal imaging applications. However, segmenting the placenta using magnetic resonance imaging (MRI) and ultrasound is challenging because of variations in fetal position, dynamic placental development, and image quality. Most segmentation methods define regions of interest with different shapes and intensities, encompassing the entire placenta or specific structures. Recently, deep learning has emerged as a key approach that offer high segmentation performance across diverse datasets. This review focuses on the recent advances in deep learning techniques for placental segmentation in medical imaging, specifically MRI and ultrasound modalities, and cover studies from 2019 to 2024. This review synthesizes recent research, expand knowledge in this innovative area, and highlight the potential of deep learning approaches to significantly enhance prenatal diagnostics. These findings emphasize the importance of selecting appropriate imaging modalities and model architectures tailored to specific clinical scenarios. In addition, integrating both MRI and ultrasound can enhance segmentation performance by leveraging complementary information. This review also discusses the challenges associated with the high costs and limited availability of advanced imaging technologies. It provides insights into the current state of placental segmentation techniques and their implications for improving maternal and fetal health outcomes, underscoring the transformative impact of deep learning on prenatal diagnostics.

Accurate identification of bone marrow invasion (BMI) is critical for determining the prognosis of and treatment strategies for lymphoma. Although bone marrow biopsy (BMB) is the current gold standard, its invasive nature and sampling errors highlight the necessity for noninvasive alternatives. We aimed to develop and validate an interpretable machine learning model that integrates clinical data, ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) parameters, radiomic features, and deep learning features to predict BMI in lymphoma patients. We included 159 newly diagnosed lymphoma patients (118 from Center I and 41 from Center II), excluding those with prior treatments, incomplete data, or under 18 years of age. Data from Center I were randomly allocated to training (n = 94) and internal test (n = 24) sets; Center II served as an external validation set (n = 41). Clinical parameters, PET/CT features, radiomic characteristics, and deep learning features were comprehensively analyzed and integrated into machine learning models. Model interpretability was elucidated via Shapley Additive exPlanations (SHAPs). Additionally, a comparative diagnostic study evaluated reader performance with and without model assistance. BMI was confirmed in 70 (44%) patients. The key clinical predictors included B symptoms and platelet count. Among the tested models, the ExtraTrees classifier achieved the best performance. For external validation, the combined model (clinical + PET/CT + radiomics + deep learning) achieved an area under the receiver operating characteristic curve (AUC) of 0.886, outperforming models that use only clinical (AUC 0.798), radiomic (AUC 0.708), or deep learning features (AUC 0.662). SHAP analysis revealed that PET radiomic features (especially PET_lbp_3D_m1_glcm_DependenceEntropy), platelet count, and B symptoms were significant predictors of BMI. Model assistance significantly enhanced junior reader performance (AUC improved from 0.663 to 0.818, p = 0.03) and improved senior reader accuracy, although not significantly (AUC 0.768 to 0.867, p = 0.10). Our interpretable machine learning model, which integrates clinical, imaging, radiomic, and deep learning features, demonstrated robust BMI prediction performance and notably enhanced physician diagnostic accuracy. These findings underscore the clinical potential of interpretable AI to complement medical expertise and potentially reduce the reliance on invasive BMB for lymphoma staging.

To assess the prevalence of motion artifacts and the factors associated with them in a cohort of suspected stroke patients, and to determine their impact on diagnostic accuracy for both AI and radiologists. This retrospective cross-sectional study included brain MRI scans of consecutive adult suspected stroke patients from a non-comprehensive Danish stroke center between January and April 2020. An expert neuroradiologist identified acute ischemic, hemorrhagic, and space-occupying lesions as references. Two blinded radiology residents rated MRI image quality and motion artifacts. The diagnostic accuracy of a CE-marked deep learning tool was compared to that of radiology reports. Multivariate analysis examined associations between patient characteristics and motion artifacts. 775 patients (68 years ± 16, 420 female) were included. Acute ischemic, hemorrhagic, and space-occupying lesions were found in 216 (27.9%), 12 (1.5%), and 20 (2.6%). Motion artifacts were present in 57 (7.4%). Increasing age (OR per decade, 1.60; 95% CI: 1.26, 2.09; p < 0.001) and limb motor symptoms (OR, 2.36; 95% CI: 1.32, 4.20; p = 0.003) were independently associated with motion artifacts in multivariate analysis. Motion artifacts significantly reduced the accuracy of detecting hemorrhage. This reduction was greater for the AI tool (from 88 to 67%; p < 0.001) than for radiology reports (from 100 to 93%; p < 0.001). Ischemic and space-occupying lesion detection was not significantly affected. Motion artifacts are common in suspected stroke patients, particularly in the elderly and patients with motor symptoms, reducing accuracy for hemorrhage detection by both AI and radiologists. Question Motion artifacts reduce the quality of MRI scans, but it is unclear which factors are associated with them and how they impact diagnostic accuracy. Findings Motion artifacts occurred in 7% of suspected stroke MRI scans, associated with higher patient age and motor symptoms, lowering hemorrhage detection by AI and radiologists. Clinical relevance Motion artifacts in stroke brain MRIs significantly reduce the diagnostic accuracy of human and AI detection of intracranial hemorrhages. Elderly patients and those with motor symptoms may benefit from a greater focus on motion artifact prevention and reduction.

Epicardial Adipose Tissue (EAT) is a recognized risk factor for cardiovascular diseases and plays a pivotal role in the pathophysiology of Atrial Fibrillation (AF). Accurate automatic segmentation of the EAT around the Left Atrium (LA) from Magnetic Resonance Imaging (MRI) data remains challenging. While Convolutional Neural Networks excel at multi-scale feature extraction using stacked convolutions, they struggle to capture long-range self-similarity and hierarchical relationships, which are essential in medical image segmentation. In this study, we present and validate PoinUNet, a deep learning model that integrates a Poincaré embedding layer into a 3D UNet to enhance LA wall and fat segmentation from Dixon MRI data. By using hyperbolic space learning, PoinUNet captures complex LA and EAT relationships and addresses class imbalance and fat geometry challenges using a new loss function. Sixty-six participants, including forty-eight AF patients, were scanned at 1.5T. The first network identified fat regions, while the second utilized Poincaré embeddings and convolutional layers for precise segmentation, enhanced by fat fraction maps. PoinUNet achieved a Dice Similarity Coefficient of 0.87 and a Hausdorff distance of 9.42 on the test set. This performance surpasses state-of-the-art methods, providing accurate quantification of the LA wall and LA EAT.

Tractography algorithms leverage diffusion MRI to reconstruct the fibrous architecture of the brain's white matter. Among machine learning approaches, reinforcement learning (RL) has emerged as a promising framework for tractography, outperforming traditional methods in several key aspects. TractOracle-RL, a recent RL-based approach, reduces false positives by incorporating anatomical priors into the training process via a reward-based mechanism. In this paper, we investigate four extensions of the original TractOracle-RL framework by integrating recent advances in RL, and we evaluate their performance across five diverse diffusion MRI datasets. Results demonstrate that combining an oracle with the RL framework consistently leads to robust and reliable tractography, regardless of the specific method or dataset used. We also introduce a novel RL training scheme called Iterative Reward Training (IRT), inspired by the Reinforcement Learning from Human Feedback (RLHF) paradigm. Instead of relying on human input, IRT leverages bundle filtering methods to iteratively refine the oracle's guidance throughout training. Experimental results show that RL methods trained with oracle feedback significantly outperform widely used tractography techniques in terms of accuracy and anatomical validity.

Currently, the application of convolutional neural networks (CNNs) in artificial intelligence (AI) for medical imaging diagnosis has emerged as a highly promising tool. In particular, AI-assisted diagnosis holds significant potential for orthopedic and emergency department physicians by improving diagnostic efficiency and enhancing the overall patient experience. This systematic review and meta-analysis has the objective of assessing the application of AI in diagnosing facial fractures and evaluating its diagnostic performance. This study adhered to the guidelines of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and PRISMA-Diagnostic Test Accuracy (PRISMA-DTA). A comprehensive literature search was conducted in the PubMed, Cochrane Library, and Web of Science databases to identify original articles published up to December 2024. The risk of bias and applicability of the included studies were assessed using the QUADAS-2 tool. The results were analyzed using a Summary Receiver Operating Characteristic (SROC) curve. A total of 16 studies were included in the analysis, with contingency tables extracted from 11 of them. The pooled sensitivity was 0.889 (95% CI: 0.844-0.922), and the pooled specificity was 0.888 (95% CI: 0.834-0.926). The area under the Summary Receiver Operating Characteristic (SROC) curve was 0.911. In the subgroup analysis of nasal and mandibular fractures, the pooled sensitivity for nasal fractures was 0.851 (95% CI: 0.806-0.887), and the pooled specificity was 0.883 (95% CI: 0.862-0.902). For mandibular fractures, the pooled sensitivity was 0.905 (95% CI: 0.836-0.947), and the pooled specificity was 0.895 (95% CI: 0.824-0.940). AI can be developed as an auxiliary tool to assist clinicians in diagnosing facial fractures. The results demonstrate high overall sensitivity and specificity, along with a robust performance reflected by the high area under the SROC curve. This study has been prospectively registered on Prospero, ID:CRD42024618650, Creat Date:10 Dec 2024. https://www.crd.york.ac.uk/PROSPERO/view/CRD42024618650 .

Enhance mammography quality to increase cancer detection by implementing continuous AI-driven feedback mechanisms, ensuring reliable, consistent, and high-quality screening by the 'Perfect', 'Good', 'Moderate', and 'Inadequate' (PGMI) criteria. To assess the impact of the AI software 'b-box^TM' on mammography quality, we conducted a comparative analysis of PGMI scores. We evaluated scores 50 days before (A) and after the software's implementation in 2021 (B), along with assessments made in the first week of August 2022 (C1) and 2023 (C2), comparing them to evaluations conducted by two readers. Except for postsurgical patients, we included all diagnostic and screening mammograms from one tertiary hospital. A total of 4577 mammograms from 1220 women (mean age: 59, range: 21-94, standard deviation: 11.18) were included. 1728 images were obtained before (A) and 2330 images after the 2021 software implementation (B), along with 269 images in 2022 (C1) and 250 images in 2023 (C2). The results indicated a significant improvement in diagnostic image quality (p < 0.01). The percentage of 'Perfect' examinations rose from 22.34% to 32.27%, while 'Inadequate' images decreased from 13.31% to 5.41% in 2021, continuing the positive trend with 4.46% and 3.20% 'inadequate' images in 2022 and 2023, respectively (p < 0.01). Using a reliable software platform to perform AI-driven quality evaluation in real-time has the potential to make lasting improvements in image quality, support radiographers' professional growth, and elevate institutional quality standards and documentation simultaneously. Question How can AI-powered quality assessment reduce inadequate mammographic quality, which is known to impact sensitivity and increase the risk of interval cancers? Findings AI implementation decreased 'inadequate' mammograms from 13.31% to 3.20% and substantially improved parenchyma visualization, with consistent subgroup trends. Clinical relevance By reducing 'inadequate' mammograms and enhancing imaging quality, AI-driven tools improve diagnostic reliability and support better outcomes in breast cancer screening.

Phase-sensitive inversion recovery late gadolinium enhancement (LGE) improves tissue contrast, however it is challenging to combine with a free-breathing acquisition. Deep-learning (DL) algorithms have growing applications in cardiac magnetic resonance imaging (CMR) to improve image quality. We compared a novel combination of a free-breathing single-shot phase-sensitive LGE with respiratory triggering (FB-PS) sequence with DL noise reduction reconstruction algorithm to a conventional segmented phase-sensitive LGE acquired during breath holding (BH-PS). 61 adult subjects (29 male, age 51 ± 15) underwent clinical CMR (1.5 T) with the FB-PS sequence and the conventional BH-PS sequence. DL noise reduction was incorporated into the image reconstruction pipeline. Qualitative metrics included image quality, artifact severity, diagnostic confidence. Quantitative metrics included septal-blood border sharpness, LGE sharpness, blood-myocardium apparent contrast-to-noise ratio (CNR), LGE-myocardium CNR, LGE apparent signal-to-noise ratio (SNR), and LGE burden. The sequences were compared via paired t-tests. 27 subjects had positive LGE. Average time to acquire a slice for FB-PS was 4-12 s versus ~32-38 s for BH-PS (including breath instructions and break time in between breath hold). FB-PS with medium DL noise reduction had better image quality (FB-PS 3.0 ± 0.7 vs. BH-PS 1.5 ± 0.6, p < 0.0001), less artifact (4.8 ± 0.5 vs. 3.4 ± 1.1, p < 0.0001), and higher diagnostic confidence (4.0 ± 0.6 vs. 2.6 ± 0.8, p < 0.0001). Septum sharpness in FB-PS with DL reconstruction versus BH-PS was not significantly different. There was no significant difference in LGE sharpness or LGE burden. FB-PS had superior blood-myocardium CNR (17.2 ± 6.9 vs. 16.4 ± 6.0, p = 0.040), LGE-myocardium CNR (12.1 ± 7.2 vs. 10.4 ± 6.6, p = 0.054), and LGE SNR (59.8 ± 26.8 vs. 31.2 ± 24.1, p < 0.001); these metrics further improved with DL noise reduction. A FB-PS sequence shortens scan time by over 5-fold and reduces motion artifact. Combined with a DL noise reduction algorithm, FB-PS provides better or similar image quality compared to BH-PS. This is a promising solution for patients who cannot hold their breath.

Radiology reports can change during workflows, especially when residents draft preliminary versions that attending physicians finalize. We explored how large language models (LLMs) and embedding techniques can categorize these changes into textual, semantic, or clinically actionable types. We evaluated 400 adult CT reports drafted by residents against finalized versions by attending physicians. Changes were rated on a five-point scale from no changes to critical ones. We examined open-source LLMs alongside traditional metrics like normalized word differences, Levenshtein and Jaccard similarity, and text embedding similarity. Model performance was assessed using quadratic weighted Cohen's kappa (κ), (balanced) accuracy, F₁, precision, and recall. Inter-rater reliability among evaluators was excellent (κ = 0.990). Of the reports analyzed, 1.3 % contained critical changes. The tested methods showed significant performance differences (P < 0.001). The Qwen3-235B-A22B model using a zero-shot prompt, most closely aligned with human assessments of changes in clinical reports, achieving a κ of 0.822 (SD 0.031). The best conventional metric, word difference, had a κ of 0.732 (SD 0.048), the difference between the two showed statistical significance in unadjusted post-hoc tests (P = 0.038) but lost significance after adjusting for multiple testing (P = 0.064). Embedding models underperformed compared to LLMs and classical methods, showing statistical significance in most cases. Large language models like Qwen3-235B-A22B demonstrated moderate to strong alignment with expert evaluations of the clinical significance of changes in radiology reports. LLMs outperformed embedding methods and traditional string and word approaches, achieving statistical significance in most instances. This demonstrates their potential as tools to support peer review.

Despite continued advances in oncology, cancer remains a leading cause of global mortality, highlighting the need for diagnostic and prognostic tools that are both accurate and interpretable. Unimodal approaches often fail to capture the biological and clinical complexity of tumors. In this study, we present a suite of task-specific AI models that leverage CT imaging, multi-omics profiles, and structured clinical data to address distinct challenges in segmentation, classification, and prognosis. We developed three independent models across large public datasets. Task 1 applied a 3D U-Net to segment pancreatic tumors from CT scans, achieving a Dice Similarity Coefficient (DSC) of 0.7062. Task 2 employed a hierarchical ensemble of omics-based classifiers to distinguish tumor from normal tissue and classify six major cancer types with 98.67% accuracy. Task 3 benchmarked classical machine learning models on clinical data for prognosis prediction across three cancers (LIHC, KIRC, STAD), achieving strong performance (e.g., C-index of 0.820 in KIRC, AUC of 0.978 in LIHC). Across all tasks, explainable AI methods such as SHAP and attention-based visualization enabled transparent interpretation of model outputs. These results demonstrate the value of tailored, modality-aware models and underscore the clinical potential of applying such tailored AI systems for precision oncology. Technical FoundationsO_LISegmentation (Task 1): A custom 3D U-Net was trained using the Task07_Pancreas dataset from the Medical Segmentation Decathlon (MSD). CT images were preprocessed with MONAI-based pipelines, resampled to (64, 96, 96) voxels, and intensity-windowed to HU ranges of -100 to 240. C_LIO_LIClassification (Task 2): Multi-omics data from TCGA--including gene expression, methylation, miRNA, CNV, and mutation profiles--were log-transformed and normalized. Five modality-specific LightGBM classifiers generated meta-features for a late-fusion ensemble. Stratified 5-fold cross-validation was used for evaluation. C_LIO_LIPrognosis (Task 3): Clinical variables from TCGA were curated and imputed (median/mode), with high-missing-rate columns removed. Survival models (e.g., Cox-PH, Random Forest, XGBoost) were trained with early stopping. No omics or imaging data were used in this task. C_LIO_LIInterpretability: SHAP values were computed for all tree-based models, and attention-based overlays were used in imaging tasks to visualize salient regions. C_LI