Accurate image registration is essential for downstream applications, yet current deep registration networks provide limited indications of whether and when their predictions are reliable. Existing uncertainty estimation strategies, such as Bayesian methods, ensembles, or MC dropout, require architectural changes or retraining, limiting their applicability to pretrained registration networks. Instead, we propose a test-time uncertainty estimation framework that is compatible with any pretrained networks. Our framework is grounded in the transformation equivariance property of registration, which states that the true mapping between two images should remain consistent under spatial perturbations of the input. By analyzing the variance of network predictions under such perturbations, we derive a theoretical decomposition of perturbation-based uncertainty in registration. This decomposition separates into two terms: (i) an intrinsic spread, reflecting epistemic noise, and (ii) a bias jitter, capturing how systematic error drifts under perturbations. Across four anatomical structures (brain, cardiac, abdominal, and lung) and multiple registration models (uniGradICON, SynthMorph), the uncertainty maps correlate consistently with registration errors and highlight regions requiring caution. Our framework turns any pretrained registration network into a risk-aware tool at test time, placing medical image registration one step closer to safe deployment in clinical and large-scale research settings.

SARS-CoV-2, the causative agent of COVID-19, remains a global health concern due to its high transmissibility and evolving variants. Although vaccination efforts and therapeutic advancements have mitigated disease severity, emerging mutations continue to challenge diagnostics and containment strategies. As of mid-February 2025, global test positivity has risen to 11%, marking the highest level in over 6 months, despite widespread immunization efforts. Newer variants demonstrate enhanced host cell binding, increasing both infectivity and diagnostic complexity. This study aimed to evaluate the effectiveness of deep transfer learning in delivering a rapid, accurate, and mutation-resilient COVID-19 diagnosis from medical imaging, with a focus on scalability and accessibility. An automated detection system was developed using state-of-the-art convolutional neural networks, including VGG16 (Visual Geometry Group network-16 layers), ResNet50 (residual network-50 layers), ConvNeXtTiny (convolutional next-tiny), MobileNet (mobile network), NASNetMobile (neural architecture search network-mobile version), and DenseNet121 (densely connected convolutional network-121 layers), to detect COVID-19 from chest X-ray and computed tomography (CT) images. Among all the models evaluated, DenseNet121 emerged as the best-performing architecture for COVID-19 diagnosis using X-ray and CT images. It achieved an impressive accuracy of 98%, with a precision of 96.9%, a recall of 98.9%, an F1-score of 97.9%, and an area under the curve score of 99.8%, indicating a high degree of consistency and reliability in detecting both positive and negative cases. The confusion matrix showed minimal false positives and false negatives, underscoring the model's robustness in real-world diagnostic scenarios. Given its performance, DenseNet121 is a strong candidate for deployment in clinical settings and serves as a benchmark for future improvements in artificial intelligence-assisted diagnostic tools. The study results underscore the potential of artificial intelligence-powered diagnostics in supporting early detection and global pandemic response. With careful optimization, deep learning models can address critical gaps in testing, particularly in settings constrained by limited resources or emerging variants.

The evaluation of patellofemoral joint parameters is essential for diagnosing patellar dislocation, yet manual measurements exhibit poor reproducibility and demonstrate significant variability dependent on clinician expertise. This systematic review aimed to evaluate the performance of artificial intelligence (AI) models in automatically measuring patellofemoral joint parameters. A comprehensive literature search of PubMed, Web of Science, Cochrane Library, and Embase databases was conducted from database inception through June 15, 2025. Two investigators independently performed study screening and data extraction, with methodological quality assessment based on the modified MINORS checklist. This systematic review is registered with PROSPERO. A narrative review was conducted to summarize the findings of the included studies. A total of 19 studies comprising 10,490 patients met the inclusion and exclusion criteria, with a mean age of 51.3 years and a mean female proportion of 56.8%. Among these, six studies developed AI models based on radiographic series, nine on CT imaging, and four on MRI. The results demonstrated excellent reliability, with intraclass correlation coefficients (ICCs) ranging from 0.900 to 0.940 for femoral anteversion angle, 0.910-0.920 for trochlear groove depth and 0.930-0.950 for tibial tuberosity-trochlear groove distance. Additionally, good reliability was observed for patellar height (ICCs: 0.880-0.985), sulcus angle (ICCs: 0.878-0.980), and patellar tilt angle (ICCs: 0.790-0.990). Notably, the AI system successfully detected trochlear dysplasia, achieving 88% accuracy, 79% sensitivity, 96% specificity, and an AUC of 0.88. AI-based measurement of patellofemoral joint parameters demonstrates methodological robustness and operational efficiency, showing strong agreement with expert manual measurements. To further establish clinical utility, multicenter prospective studies incorporating rigorous external validation protocols are needed. Such validation would strengthen the model's generalizability and facilitate its integration into clinical decision support systems. This systematic review was registered in PROSPERO (CRD420251075068).

Deep learning necessitates a substantial amount of data, yet obtaining sufficient medical images is difficult due to concerns about patient privacy and high collection costs. To address this issue, we propose a conditional latent diffusion model-based medical image enhancement network, referred to as the Medical Image Enhancement Network (MedIENet). To meet the rigorous standards required for image generation in the medical imaging field, a multi-attention module is incorporated in the encoder of the denoising U-Net backbone. Additionally Rotary Position Embedding (RoPE) is integrated into the self-attention module to effectively capture positional information, while cross-attention is utilised to embed integrate class information into the diffusion process. MedIENet is evaluated on three datasets: Chest CT-Scan images, Chest X-Ray Images (Pneumonia), and Tongue dataset. Compared to existing methods, MedIENet demonstrates superior performance in both fidelity and diversity of the generated images. Experimental results indicate that for downstream classification tasks using ResNet50, the Area Under the Receiver Operating Characteristic curve (AUROC) achieved with real data alone is 0.76 for the Chest CT-Scan images dataset, 0.87 for the Chest X-Ray Images (Pneumonia) dataset, and 0.78 for the Tongue Dataset. When using mixed data consisting of real data and generated data, the AUROC improves to 0.82, 0.94, and 0.82, respectively, reflecting increases of approximately 6%, 7%, and 4%. These findings indicate that the images generated by MedIENet can enhance the performance of downstream classification tasks, providing an effective solution to the scarcity of medical image training data.

Theranostics represents a transformative advancement in nuclear medicine by integrating molecular imaging and targeted radionuclide therapy within the paradigm of personalized oncology. This review elucidates the historical evolution and contemporary clinical applications of theranostics, emphasizing its pivotal role in precision cancer management. The theranostic approach involves the coupling of diagnostic and therapeutic radionuclides that target identical molecular biomarkers, enabling simultaneous visualization and treatment of malignancies such as neuroendocrine tumors (NETs), prostate cancer, and differentiated thyroid carcinoma. Key theranostic radiopharmaceutical pairs, including Gallium-68-labeled DOTA-Tyr3-octreotate (Ga-68-DOTATATE) with Lutetium-177-labeled DOTA-Tyr3-octreotate (Lu-177-DOTATATE), and Gallium-68-labeled Prostate-Specific Membrane Antigen (Ga-68-PSMA) with Lutetium-177-labeled Prostate-Specific Membrane Antigen (Lu-177-PSMA), exemplify the "see-and-treat" principle central to this modality. This article further explores critical molecular targets such as somatostatin receptor subtype 2, prostate-specific membrane antigen, human epidermal growth factor receptor 2, CD20, and C-X-C chemokine receptor type 4, along with design principles for radiopharmaceuticals that optimize target specificity while minimizing off-target toxicity. Advances in imaging platforms, including positron emission tomography/computed tomography (PET/CT), single-photon emission computed tomography/CT (SPECT/CT), and hybrid positron emission tomography/magnetic resonance imaging (PET/MRI), have been instrumental in accurate dosimetry, therapeutic response assessment, and adaptive treatment planning. Integration of artificial intelligence (AI) and radiomics holds promise for enhanced image segmentation, predictive modeling, and individualized dosimetric planning. The review also addresses regulatory, manufacturing, and economic considerations, including guidelines from the United States Food and Drug Administration (USFDA) and European Medicines Agency (EMA), Good Manufacturing Practice (GMP) standards, and reimbursement frameworks, which collectively influence global adoption of theranostics. In summary, theranostics is poised to become a cornerstone of next-generation oncology, catalyzing a paradigm shift toward biologically driven, real-time personalized cancer care that seamlessly links diagnosis and therapy.

In the evolving field of healthcare, centralized cloud-based medical image retrieval faces challenges related to security, availability, and adversarial threats. Existing deep learning-based solutions improve retrieval but remain vulnerable to adversarial attacks and quantum threats, necessitating a shift to more secure distributed cloud solutions. This article proposes SFMedIR, a secure and fault tolerant medical image retrieval framework that contains an adversarial attack-resistant federated learning for hashcode generation, utilizing a ConvNeXt-based model to improve accuracy and generalizability. The framework integrates quantum-chaos-based encryption for security, dynamic threshold-based shadow storage for fault tolerance, and a distributed cloud architecture to mitigate single points of failure. Unlike conventional methods, this approach significantly improves security and availability in cloud-based medical image retrieval systems, providing a resilient and efficient solution for healthcare applications. The framework is validated on Brain MRI and Kidney CT datasets, achieving a 60-70% improvement in retrieval accuracy for adversarial queries and an overall 90% retrieval accuracy, outperforming existing models by 5-10%. The results demonstrate superior performance in terms of both security and retrieval efficiency, making this framework a valuable contribution to the future of secure medical image management.

With increasing imaging demands, radiologists face growing workload pressures, often resulting in delays and reduced diagnostic efficiency. Recent advances in artificial intelligence (AI) have introduced tools for automated report generation, particularly in simpler imaging modalities, such as X-rays. However, limited research has assessed AI performance in complex studies such as MRI and CT scans, where report accuracy and clinical interpretation are critical. To evaluate the performance of a semi-automated AI-based reporting platform in generating radiology reports for complex imaging studies, and to compare its accuracy, efficiency, and user confidence with the traditional dictation method. This study involved 100 imaging cases, including MRI knee (n=21), MRI lumbar spine (n=30), CT head (n=23), and CT Abdomen and Pelvis (n=26). Consultant musculoskeletal radiologists reported each case using both traditional dictation and the AI platform. The radiologist first identified and entered the key positive findings, based on which the AI system generated a full draft report. Reporting time was recorded, and both methods were evaluated on accuracy, user confidence, and overall reporting experience (rated on a scale of 1-5). Statistical analysis was conducted using two-tailed t-tests and 95% confidence intervals. AI-generated reports demonstrated significantly improved performance across all parameters. The mean reporting time reduced from 6.1 to 3.43 min (p<0.0001) with AI-assisted report generation. Accuracy improved from 3.81 to 4.65 (p<0.0001), confidence ratings increased from 3.91 to 4.67 (p<0.0001), and overall reporting experience favored using the AI platform for generating radiology reports (mean 4.7 vs. 3.69, p<0.0001). Minor formatting errors and occasional anatomical misinterpretations were observed in AI-generated reports, but could be easily corrected by the radiologist during review. The AI-assisted reporting platform significantly improved efficiency and radiologist confidence without compromising accuracy. Although the tool performs well when provided with key clinical findings, it still requires expert oversight, especially in anatomically complex reporting. These findings support the use of AI as a supportive tool in radiology practice, with a focus on data integrity, consistency, and human validation.

Within the treatment process of modern stomatology, obtaining exquisite preoperative information is the key to accurate intraoperative planning with implementation and prognostic judgment. However, traditional single mode image has obvious shortcomings, such as "monotonous contents" and "unstable measurement accuracy", which could hardly meet the diversified needs of oral patients. Multimodal medical image fusion (MMIF) technique has been introduced into the studies of stomatology in the 1990s, aiming at realizing personalized patients' data analysis through multiple fusion algorithms, which combines the advantages of multimodal medical images while laying a stable foundation for new treatment technologies. Recently artificial intelligence (AI) has significantly increased the precision and efficiency of MMIF's registration: advanced algorithms and networks have confirmed the great compatibility between AI and MMIF. This article systematically reviews the development history of the multimodal image fusion technique and its current application in stomatology, while analyzing technological progresses within the domain combined with the background of AI's rapid development, in order to provide new ideas for achieving new advancements within the field of stomatology.

Anatomical understanding through deep learning is critical for automatic report generation, intra-operative navigation, and organ localization in medical imaging; however, its progress is constrained by the scarcity of expert-labeled data. A promising remedy is to leverage an annotated reference image to guide the interpretation of an unlabeled target. Although recent vision-language models (VLMs) exhibit non-trivial visual reasoning, their reference-based understanding and fine-grained localization remain limited. We introduce RAU, a framework for reference-based anatomical understanding with VLMs. We first show that a VLM learns to identify anatomical regions through relative spatial reasoning between reference and target images, trained on a moderately sized dataset. We validate this capability through visual question answering (VQA) and bounding box prediction. Next, we demonstrate that the VLM-derived spatial cues can be seamlessly integrated with the fine-grained segmentation capability of SAM2, enabling localization and pixel-level segmentation of small anatomical regions, such as vessel segments. Across two in-distribution and two out-of-distribution datasets, RAU consistently outperforms a SAM2 fine-tuning baseline using the same memory setup, yielding more accurate segmentations and more reliable localization. More importantly, its strong generalization ability makes it scalable to out-of-distribution datasets, a property crucial for medical image applications. To the best of our knowledge, RAU is the first to explore the capability of VLMs for reference-based identification, localization, and segmentation of anatomical structures in medical images. Its promising performance highlights the potential of VLM-driven approaches for anatomical understanding in automated clinical workflows.

We present a patch-based 3D nnUNet adaptation for MR to CT and CBCT to CT image translation using the multicenter SynthRAD2025 dataset, covering head and neck (HN), thorax (TH), and abdomen (AB) regions. Our approach leverages two main network configurations: a standard UNet and a residual UNet, both adapted from nnUNet for image synthesis. The Anatomical Feature-Prioritized (AFP) loss was introduced, which compares multilayer features extracted from a compact segmentation network trained on TotalSegmentator labels, enhancing reconstruction of clinically relevant structures. Input volumes were normalized per-case using zscore normalization for MRIs, and clipping plus dataset level zscore normalization for CBCT and CT. Training used 3D patches tailored to each anatomical region without additional data augmentation. Models were trained for 1000 and 1500 epochs, with AFP fine-tuning performed for 500 epochs using a combined L1+AFP objective. During inference, overlapping patches were aggregated via mean averaging with step size of 0.3, and postprocessing included reverse zscore normalization. Both network configurations were applied across all regions, allowing consistent model design while capturing local adaptations through residual learning and AFP loss. Qualitative and quantitative evaluation revealed that residual networks combined with AFP yielded sharper reconstructions and improved anatomical fidelity, particularly for bone structures in MR to CT and lesions in CBCT to CT, while L1only networks achieved slightly better intensity-based metrics. This methodology provides a stable solution for cross modality medical image synthesis, demonstrating the effectiveness of combining the automatic nnUNet pipeline with residual learning and anatomically guided feature losses.