Deep learning offers transformative potential in medical imaging, yet its clinical adoption is frequently hampered by challenges such as data scarcity, distribution shifts, and the need for robust task generalization. Prompt-based methodologies have emerged as a pivotal strategy to guide deep learning models, providing flexible, domain-specific adaptations that significantly enhance model performance and adaptability without extensive retraining. This systematic review critically examines the burgeoning landscape of prompt engineering in medical imaging. We dissect diverse prompt modalities, including textual instructions, visual prompts, and learnable embeddings, and analyze their integration for core tasks such as image generation, segmentation, and classification. Our synthesis reveals how these mechanisms improve task-specific outcomes by enhancing accuracy, robustness, and data efficiency and reducing reliance on manual feature engineering while fostering greater model interpretability by making the model's guidance explicit. Despite substantial advancements, we identify persistent challenges, particularly in prompt design optimization, data heterogeneity, and ensuring scalability for clinical deployment. Finally, this review outlines promising future trajectories, including advanced multimodal prompting and robust clinical integration, underscoring the critical role of prompt-driven AI in accelerating the revolution of diagnostics and personalized treatment planning in medicine.

Accurate preoperative differentiation of benign and malignant thyroid nodules is critical for optimal patient management. However, conventional imaging modalities present inherent diagnostic limitations. To develop a non-contrast computed tomography-based machine learning model integrating radiomics and clinical features for preoperative thyroid nodule classification. This multicenter retrospective study enrolled 272 patients with thyroid nodules (376 thyroid lobes) from center A (May 2021-April 2024), using histopathological findings as the reference standard. The dataset was stratified into a training cohort (264 lobes) and an internal validation cohort (112 lobes). Additional prospective temporal (97 lobes, May-August 2024, center A) and external multicenter (81 lobes, center B) test cohorts were incorporated to enhance generalizability. Thyroid lobes were segmented along the isthmus midline, with segmentation reliability confirmed by an intraclass correlation coefficient (≥ 0.80). Radiomics feature extraction was performed using Pearson correlation analysis followed by least absolute shrinkage and selection operator regression with 10-fold cross-validation. Seven machine learning algorithms were systematically evaluated, with model performance quantified through the area under the receiver operating characteristic curve (AUC), Brier score, decision curve analysis, and DeLong test for comparison with radiologists interpretations. Model interpretability was elucidated using SHapley Additive exPlanations (SHAP). The extreme gradient boosting model demonstrated robust diagnostic performance across all datasets, achieving AUCs of 0.899 [95% confidence interval (CI): 0.845-0.932] in the training cohort, 0.803 (95%CI: 0.715-0.890) in internal validation, 0.855 (95%CI: 0.775-0.935) in temporal testing, and 0.802 (95%CI: 0.664-0.939) in external testing. These results were significantly superior to radiologists assessments (AUCs: 0.596, 0.529, 0.558, and 0.538, respectively; <i>P</i> < 0.001 by DeLong test). SHAP analysis identified radiomic score, age, tumor size stratification, calcification status, and cystic components as key predictive features. The model exhibited excellent calibration (Brier scores: 0.125-0.144) and provided significant clinical net benefit at decision thresholds exceeding 20%, as evidenced by decision curve analysis. The non-contrast computed tomography-based radiomics-clinical fusion model enables robust preoperative thyroid nodule classification, with SHAP-driven interpretability enhancing its clinical applicability for personalized decision-making.

IntroductionPoint-of-care ultrasonography (POCUS) enables clinicians to obtain critical diagnostic information at the bedside especially in resource limited settings. This information may include 2D cardiac quantitative data, although measuring the data manually can be time-consuming and subject to user experience. Artificial intelligence (AI) can potentially automate this quantification. This study assessed the interpretation of key cardiac measurements on POCUS images by an AI-enabled device (AISAP Cardio V1.0). MethodsThis retrospective diagnostic accuracy study included 200 POCUS cases from four hospitals (two in Israel and two in the United States). Each case was independently interpreted by three cardiologists and the device for seven measurements (left ventricular (LV) ejection fraction, inferior vena cava (IVC) maximal diameter, left atrial (LA) area, right atrial (RA) area, LV end diastolic diameter, right ventricular (RV) fractional area change and aortic root diameter). The endpoints were the root mean square error (RMSE) of the device compared to the average cardiologist measurement (LV ejection fraction and IVC maximal diameter were primary endpoints; the other measurements were secondary endpoints). Predefined passing criteria were based on the upper bounds of the RMSE 95% confidence intervals (CIs). The inter-cardiologist RMSE was also calculated for reference. ResultsThe device achieved the passing criteria for six of the seven measurements. While not achieving the passing criterion for RV fractional area change, it still achieved a better RMSE than the inter-cardiologist RMSE. The RMSE was 6.20% (95% CI: 5.57 to 6.83; inter-cardiologist RMSE of 8.23%) for LV ejection fraction, 0.25cm (95% CI: 0.20 to 0.29; 0.36cm) for IVC maximal diameter, 2.39cm2 (95% CI: 1.96 to 2.82; 4.39cm2) for LA area, 2.11cm2 (95% CI: 1.75 to 2.47; 3.49cm2) for RA area, 5.06mm (95% CI: 4.58 to 5.55; 4.67mm) for LV end diastolic diameter, 10.17% (95% CI: 9.01 to 11.33; 14.12%) for RV fractional area change and 0.19cm (95% CI: 0.16 to 0.21; 0.24cm) for aortic root diameter. DiscussionThe device accurately calculated these cardiac measurements especially when benchmarked against inter-cardiologist variability. Its use could assist clinicians who utilize POCUS and better enable their clinical decision-making.

BackgroundInadequate pharmacologic stress may limit the diagnostic and prognostic accuracy of myocardial perfusion imaging (MPI). The splenic ratio (SR), a measure of stress adequacy, has emerged as a potential imaging biomarker. ObjectivesTo evaluate the prognostic value of artificial intelligence (AI)-derived SR in a large multicenter 82Rb-PET cohort undergoing regadenoson stress testing. MethodsWe retrospectively analyzed 10,913 patients from three sites in the REFINE PET registry with clinically indicated MPI and linked clinical outcomes. SR was calculated using fully automated algorithms as the ratio of splenic uptake at stress versus rest. Patients were stratified by SR into high ([&ge;]90th percentile) and low (<90th percentile) groups. The primary outcome was major adverse cardiovascular events (MACE). Survival analysis was conducted using Kaplan-Meier and Cox proportional hazards models adjusted for clinical and imaging covariates, including myocardial flow reserve (MFR [&ge;]2 vs. <2). ResultsThe cohort had a median age of 68 years, with 57% male patients. Common risk factors included hypertension (84%), dyslipidemia (76%), diabetes (33%), and prior coronary artery disease (31%). Median follow-up was 4.6 years. Patients with high SR (n=1,091) had an increased risk of MACE (HR 1.18, 95% CI 1.06-1.31, p=0.002). Among patients with preserved MFR ([&ge;]2; n=7,310), high SR remained independently associated with MACE (HR 1.44, 95% CI 1.24-1.67, p<0.0001). ConclusionsElevated AI-derived SR was independently associated with adverse cardiovascular outcomes, including among patients with preserved MFR. These findings support SR as a novel, automated imaging biomarker for risk stratification in 82Rb PET MPI. Condensed AbstractAI-derived splenic ratio (SR), a marker of pharmacologic stress adequacy, was independently associated with increased cardiovascular risk in a large 82Rb PET cohort, even among patients with preserved myocardial flow reserve (MFR). High SR identified individuals with elevated MACE risk despite normal perfusion and flow findings, suggesting unrecognized physiologic vulnerability. Incorporating automated SR into PET MPI interpretation may enhance risk stratification and identify patients who could benefit from intensified preventive care, particularly when traditional imaging markers appear reassuring. These findings support SR as a clinically meaningful, easily integrated biomarker in stress PET imaging.

BackgroundPrecise delineation of non-contrast-enhancing tumor (nCET) in glioblastoma (GB) is critical for maximal safe resection, yet routine imaging cannot reliably separate infiltrative tumor from vasogenic edema. The aim of this study was to develop and validate an automated method to identify nCET and assess its prognostic value. MethodsPre-operative T2-weighted and FLAIR MRI from 940 patients with newly diagnosed GB in four multicenter cohorts were analyzed. A deep-learning model segmented enhancing tumor, edema and necrosis; a non-local spatially varying finite mixture model then isolated edema subregions containing nCET. The ratio of nCET to total edema volume--the Diffuse Infiltration Index (DII)--was calculated. Associations between DII and overall survival (OS) were examined with Kaplan-Meier curves and multivariable Cox regression. ResultsThe algorithm distinguished nCET from vasogenic edema in 97.5 % of patients, showing a mean signal-intensity gap > 5 %. Higher DII is able to stratify patients with shorter OS. In the NCT03439332 cohort, DII above the optimal threshold doubled the hazard of death (hazard ratio 2.09, 95 % confidence interval 1.34-3.25; p = 0.0012) and reduced median survival by 122 days. Significant, though smaller, effects were confirmed in GLIOCAT & BraTS (hazard ratio 1.31; p = 0.022), OUS (hazard ratio 1.28; p = 0.007) and in pooled analysis (hazard ratio 1.28; p = 0.0003). DII remained an independent predictor after adjustment for age, extent of resection and MGMT methylation. ConclusionsWe present a reproducible, server-hosted tool for automated nCET delineation and DII biomarker extraction that enables robust, independent prognostic stratification. It promises to guide supramaximal surgical planning and personalized neuro-oncology research and care. Key Points- KP1: Robust automated MRI tool segments non-contrast-enhancing (nCET) glioblastoma. - KP2: Introduced and validated the Diffuse Infiltration Index with prognostic value. - KP3: nCET mapping enables RANO supramaximal resection for personalized surgery. Importance of the StudyThis study underscores the clinical importance of accurately delineating non-contrast-enhancing tumor (nCET) regions in glioblastoma (GB) using standard MRI. Despite their lack of contrast enhancement, nCET areas often harbor infiltrative tumor cells critical for disease progression and recurrence. By integrating deep learning segmentation with a non-local finite mixture model, we developed a reproducible, automated methodology for nCET delineation and introduced the Diffuse Infiltration Index (DII), a novel imaging biomarker. Higher DII values were independently associated with reduced overall survival across large, heterogeneous cohorts. These findings highlight the prognostic relevance of imaging-defined infiltration patterns and support the use of nCET segmentation in clinical decision-making. Importantly, this methodology aligns with and operationalizes recent RANO criteria on supramaximal resection, offering a practical, image-based tool to improve surgical planning. In doing so, our work advances efforts toward more personalized neuro-oncological care, potentially improving outcomes while minimizing functional compromise.

The role of imaging in diagnosis of pulmonary hypertension is multifaceted, spanning from estimation of pulmonary arterial pressures, understanding pulmonary artery-right ventricular interaction, and identification of the cause. The purpose of this review is to provide a comprehensive overview of multimodality imaging in evaluation of pulmonary hypertension as well as the novel applications of imaging techniques that have improved our detection and understanding of pulmonary hypertension. There are diverse imaging modalities available for comprehensive assessment of pulmonary hypertension that are expanding with new tracers (e.g., hyperpolarized xenon gas, 129Xe) and imaging techniques (C-arm cone-bean computed tomography). Artificial intelligence applications may improve efficiency and accuracy of screening for pulmonary hypertension as well as further characterize pulmonary vasculopathies using computed tomography of the chest. In the face of increasing imaging options, a "value-based imaging" approach should be adopted to reduce unnecessary burden on the patient and the healthcare system without compromising the accuracy and completeness of diagnostic assessment. Future studies are needed to optimize use of multimodality imaging and artificial intelligence in comprehensive evaluation of patients with pulmonary hypertension.

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.

ObjectiveTo develop and validate machine learning (ML) models for objective and comprehensive quantification of sagittal craniosynostosis (SCS) severity, enhancing clinical assessment, management, and research.DesignA cross-sectional study that combined the analysis of computed tomography (CT) scans and expert ratings.SettingThe study was conducted at a children's hospital and a major computer imaging institution. Our survey collected expert ratings from participating surgeons.ParticipantsThe study included 195 patients with nonsyndromic SCS, 221 patients with nonsyndromic metopic craniosynostosis (CS), and 178 age-matched controls. Fifty-four craniofacial surgeons participated in rating 20 patients head CT scans.InterventionsComputed tomography scans for cranial morphology assessment and a radiographic diagnosis of nonsyndromic SCS.Main OutcomesAccuracy of the proposed Sagittal Severity Score (SSS) in predicting expert ratings compared to cephalic index (CI). Secondary outcomes compared Likert ratings with SCS status, the predictive power of skull-based versus skin-based landmarks, and assessments of an unsupervised ML model, the Cranial Morphology Deviation (CMD), as an alternative without ratings.ResultsThe SSS achieved significantly higher accuracy in predicting expert responses than CI (<i>P</i> < .05). Likert ratings outperformed SCS status in supervising ML models to quantify within-group variations. Skin-based landmarks demonstrated equivalent predictive power as skull landmarks (<i>P</i> < .05, threshold 0.02). The CMD demonstrated a strong correlation with the SSS (Pearson coefficient: 0.92, Spearman coefficient: 0.90, <i>P</i> < .01).ConclusionsThe SSS and CMD can provide accurate, consistent, and comprehensive quantification of SCS severity. Implementing these data-driven ML models can significantly advance CS care through standardized assessments, enhanced precision, and informed surgical planning.

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.

Automated detection and segmentation of surgical devices, such as catheters or wires, in X-ray fluoroscopic images have the potential to enhance image guidance in minimally invasive heart surgeries. In this paper, we present a convolutional neural network model that integrates a resnet architecture with multiple prediction heads to achieve real-time, accurate localization of electrodes on catheters and catheter segmentation in an end-to-end deep learning framework. We also propose a multi-task learning strategy in which our model is trained to perform both accurate electrode detection and catheter segmentation simultaneously. A key challenge with this approach is achieving optimal performance for both tasks. To address this, we introduce a novel multi-level dynamic resource prioritization method. This method dynamically adjusts sample and task weights during training to effectively prioritize more challenging tasks, where task difficulty is inversely proportional to performance and evolves throughout the training process. The proposed method has been validated on both public and private datasets for single-task catheter segmentation and multi-task catheter segmentation and detection. The performance of our method is also compared with existing state-of-the-art methods, demonstrating significant improvements, with a mean <math xmlns="http://www.w3.org/1998/Math/MathML"><mi>J</mi></math> of 64.37/63.97 and with average precision over all IoU thresholds of 84.15/83.13, respectively, for detection and segmentation multi-task on the validation and test sets of the catheter detection and segmentation dataset. Our approach achieves a good balance between accuracy and efficiency, making it well-suited for real-time surgical guidance applications.