Medverse: A Universal Model for Full-Resolution 3D Medical Image Segmentation, Transformation and Enhancement

his thesis describes the development and evaluation of deep learning approaches for analyzing three-dimensional medical images, with a particular focus on thoracic CT scans. The work emphasizes practical clinical applications while advancing reproducible research practices in medical image analysis, particularly through public datasets, standardized evaluation frameworks, and openly available implementation code. It introduces a method that can estimate global measurements while simultaneously determining regional contributions, demonstrated through applications in COVID-19 severity assessment and pulmonary function testing. The research presents a systematic evaluation of algorithm components for automatic COVID-19 grading from CT. It describes a medical image analysis challenge structure aimed at producing reusable methods that can be trained on private datasets and shows the viability of this challenge structure through a challenge for classifying severe COVID-19 from CT scans. To promote development of more generalizable solutions, a comprehensive database for 3D medical image classification is introduced, featuring standardized data formats and evaluation methods across multiple imaging modalities and anatomical regions.

To explore the nature and extent of peer-reviewed literature related to the use of diagnostic imaging by nurse practitioners (NPs) to inform future practice and research. Nurse practitioners undertake advanced assessment, diagnosis, and management of patients, including requesting and interpretation of diagnostic imaging. It is unclear what evidence exists related to the quality use of radiological investigations by NPs in recent years. A scoping review based on the steps suggested by the Joanna Briggs Institute. A structured review of the databases Medline, CINAHL and Embase was undertaken using the keywords and MESH terms 'nurse practitioner', 'medical imaging', 'diagnostic imaging', 'scan' and 'radiography'. Only English language articles were included, and no date limit was applied. Database review was completed on 30 May 2021. Eight themes were identified-country and clinical context, requesting diagnostic imaging, performing diagnostic imaging, image-guided interventions, interpreting diagnostic imaging, training education and knowledge, impact on resource usage and comparison with medical practitioners. There were more studies across a greater breadth of clinical specialties and imaging modalities in the United States than in other countries. Nurse practitioner practice is frequently benchmarked against that of medical colleagues. There is a paucity of studies focusing on educational preparation and the lack of relevant university curricula for NPs around diagnostic imaging. There are significant gaps in the evidence outside of the United States across several of the identified themes. Further studies are needed to explore NP access to and use of diagnostic imaging and to understand the barriers and facilitators to this. Studies from four countries were included in this review. The evidence suggests that, where studied, nurse practitioners (NPs) can safely and appropriately request and interpret plain x-rays in the emergency and minor injuries setting. Further research is needed to evaluate the educational needs of NPs in relation to diagnostic imaging and their use of advanced imaging techniques, particularly outside of the United States. No patient or public contribution.

The fields of medical imaging and medical imaging instrumentation are increasingly important. The state-of-the-art continues to advance at a very rapid pace. In fact, various medical imaging modalities are under development at the National Synchrotron Light Source (such as MECT and Transvenous Angiography.) It is important to understand how these techniques compare with today`s more conventional imaging modalities. The purpose of this report is to provide some basic information about the various medical imaging technologies currently in use and their potential developments as a basis for this comparison. This report is by no means an in-depth study of the physics and instrumentation of the various imaging modalities; instead, it is an attempt to provide an explanation of the physical bases of these techniques and their principal clinical and research capabilities.

Over the past decade, Deep Learning (DL) techniques have demonstrated remarkable advancements across various domains, driving their widespread adoption. Particularly in medical image analysis, DL received greater attention for tasks like image segmentation, object detection, and classification. This paper provides an overview of DL-based object recognition in medical images, exploring recent methods and emphasizing different imaging techniques and anatomical applications. Utilizing a meticulous quantitative and qualitative analysis following PRISMA guidelines, we examined publications based on citation rates to explore into the utilization of DL-based object detectors across imaging modalities and anatomical domains. Our findings reveal a consistent rise in the utilization of DL-based object detection models, indicating unexploited potential in medical image analysis. Predominantly within Medicine and Computer Science domains, research in this area is most active in the US, China, and Japan. Notably, DL-based object detection methods have gotten significant interest across diverse medical imaging modalities and anatomical domains. These methods have been applied to a range of techniques including CR scans, pathology images, and endoscopic imaging, showcasing their adaptability. Moreover, diverse anatomical applications, particularly in digital pathology and microscopy, have been explored. The analysis underscores the presence of varied datasets, often with significant discrepancies in size, with a notable percentage being labeled as private or internal, and with prospective studies in this field remaining scarce. Our review of existing trends in DL-based object detection in medical images offers insights for future research directions. The continuous evolution of DL algorithms highlighted in the literature underscores the dynamic nature of this field, emphasizing the need for ongoing research and fitted optimization for specific applications.

This book places an emphasis on the basic principles and recent advances in medical imaging technologies. After an introduction, the rest of the text can be categorized into three main parts. Part 1 provides a comprehensive tutorial on the fundamentals of medical imaging modalities and image processing methodologies. Part 2 highlights the cutting-edge imaging modalities for radiography and the recent developments of information technology in biomedicine. Part 3 provides some case studies and applications in radiation therapy and computer-aided diagnosis along with a perspective on future trends in medical and molecular imaging. The book is well organized and well presented. A concise summary before each chapter highlights the most important points of the text. This book can be used as a textbook for graduate courses and as an excellent reference for radiologists, neurologists, biomedical engineers, and researchers who are interested in imaging processing and modeling.

Medical imaging is becoming indispensable for patients' healthcare. Machine learning plays an essential role in the medical imaging field, including computer-aided diagnosis, image segmentation, image registration, image fusion, image-guided therapy, image annotation, and image database retrieval. With advances in medical imaging, new imaging modalities and methodologies such as cone-beam/multislice CT, 3D ultrasound imaging, tomosynthesis, diffusion-weighted magnetic resonance imaging (MRI), positron-emission tomography (PET)/CT, electrical impedance tomography, and diffuse optical tomography, new machine-learning algorithms/applications are demanded in the medical imaging field. Because of large variations and complexityit is generally difficult to derive analytic solutions or simple equations to represent objects such as lesions and anatomy in medical images. Therefore, tasks in medical imaging require “learning from examples” for accurate representation of data and prior knowledge. Because of its essential needs, machine learning in medical imaging is one of the most promising, growing fields. The main aim of this special issue is to help advance the scientific research within the broad field of machine learning in medical imaging. The special issue was planned in conjunction with the International Workshop on Machine Learning in Medical Imaging (MLMI 2010) [1], which was the first workshop on this topic, held at the 13th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2010) in September, 2010, in Beijing, China. This special issue is one in a series of special issues of journals on this topic [2]; it focuses on major trends and challenges in this area, and it presents work aimed at identifying new cutting-edge techniques and their use in medical imaging. The quality level of the submissions for this special issue was very high. A total of 17 papers were submitted to this issue in response to the call for papers. Based on a rigorous review process, 10 papers (59%) were accepted for publication in the special issue. The special issue starts by a review of studies on a class of machine-learning techniques, called pixel/voxel-based machine learning, in medical imaging by K. Suzuki. A series of medical imaging applications of machine-learning techniques are presented. A large variety of applications are well represented here, including organ modeling by D. Wang et al. and X. Qiao and Y.-W. Chen, brain function estimation by V. Michel et al., image reconstruction by H. Shouno et al., lesion classification by P. Wighton et al., modality classification by X.-H. Han and Y.-W. Chen, lesion segmentation by M. Zortea et al., organ segmentation by S. Alzubi et al., and visualization of molecular signals by F. Mattoli et al. Also, the issue covers various biomedical imaging modalities, including MRI by D. Wang et al., CT by X. Qiao and Y.-W. Chen and H. Shouno et al., functional MRI by V. Michel et al., dermoscopy by P. Wighton et al. and M. Zortea et al., scintigraphy by X.-H. Han and Y.-W. Chen, ultrasound imaging by X.-H. Han and Y.-W. Chen, radiography by X.-H. Han and Y.-W. Chen, MR angiography by S. Alzubi et al., and microscopy by F. Mattoli et al. as well as a variety of organs, including the kidneys by D. Wang et al., liver by X. Qiao and Y.-W. Chen, brain by V. Michel et al. and F. Mattoli et al., chest by S. Alzubi et al., skin by P. Wighton et al. and M. Zortea et al., and heart by F. Mattoli et al. Various machine-learning techniques were developed/used to solve the respective problems, including structured dictionary learning by D. Wang et al., generalized N-dimensional principal component analysis by X. Qiao et al., multiclass sparse Bayesian regression by V. Michel et al., Bayesian hyperparameter inference by H. Shouno et al., supervised learning of probabilistic models based on maximum aposteriori estimation and conditional random fields by P. Wighton et al., joint kernel equal contribution in support vector classification by X.-H. Han and Y.-W. Chen, and iterative hybrid classification by M. Zortea et al. We are grateful to all authors for their excellent contributions to this special issue and to all reviewers for their reviews and constructive suggestions. We hope that this special issue will inspire further ideas for creative research, advance the field of machine learning in medical imaging, and facilitate the translation of the research from bench to bedside. Kenji Suzuki Pingkun Yan Fei Wang Dinggang Shen

Medical image saliency prediction plays a pivotal role in emulating clinician visual attention to prioritize diagnostically critical regions. Current methods remain constrained by their spatial-domain dependency and limited cross-modality generalizability, neglecting frequency-domain patterns critical for subtle pathology detection while suffering from over-specialization in specific imaging modalities. Therefore, we propose a dual-domain visual prompt network (DVPNet) that integrates cross-modality generalization with spectral pattern awareness. On the one hand, DVPNet establishes a dataset prompt branch that dynamically modulates spatial feature encoding through modality-specific priors, allowing adaptive interpretation of heterogeneous medical imaging domains. On the other hand, a spatial-frequency hybrid prompt module employs learnable wavelet filters to decompose images into multi-scale spectral components, preserving low-frequency anatomical context while enhancing discriminative high-frequency biomarkers that are typically obscured in previous pixel-level analysis. By seamlessly integrating these complementary representations, DVPNet optimally synthesizes spatial and spectral evidence, enabling robust generalization across diverse medical imaging modalities while sustaining computational efficiency. Extensive experimental results on two distinct datasets demonstrate that the proposed method outperforms state-of-the-art approaches, showing superior saliency prediction performance and enhanced generalizability across medical contexts.

The medical imaging community has embraced Machine Learning (ML) as evidenced by the rapid increase in the number of ML models being developed, but validating and deploying these models in the clinic remains a challenge. The engineering involved in integrating and assessing the efficacy of ML models within the clinical workflow is complex. This paper presents a general-purpose, end-to-end, clinically integrated ML model deployment and validation system implemented at UCSF. Engineering and usability challenges and results from 3 use cases are presented. A generalized validation system based on free, open-source software (OSS) was implemented, connecting clinical imaging modalities, the Picture Archiving and Communication System (PACS), and an ML inference server. ML pipelines were implemented in NVIDIA’s Clara Deploy framework with results and clinician feedback stored in a customized XNAT instance, separate from the clinical record but linked from within PACS. Prospective clinical validation studies of 3 ML models were conducted, with data routed from multiple clinical imaging modalities and PACS. Completed validation studies provided expert clinical feedback on model performance and usability, plus system reliability and performance metrics. Clinical validation of ML models entails assessing model performance, impact on clinical infrastructure, robustness, and usability. Study results must be easily accessible to participating clinicians but remain outside the clinical record. Building a system that generalizes and scales across multiple ML models takes the concerted effort of software engineers, clinicians, data scientists, and system administrators, and benefits from the use of modular OSS. The present work provides a template for institutions looking to translate and clinically validate ML models in the clinic, together with required resources and expected challenges.

Context and Policy Issues The purpose of the CMII is to document current practices and developments in the supply, distribution, technical operations, and general clinical use of advanced imaging equipment across Canada. Medical imaging is a vital component of modern health care, playing a role in the diagnosis, staging, and monitoring of many diseases and conditions. As new medical imaging technologies become available and population needs change, it is important to keep track of where imaging capacity exists, how equipment is used, and the adoption of tools that may support appropriate imaging, system efficiencies, and wait-list reductions. Methods CADTH collected data on six advanced imaging modalities: CT, MRI, PET-CT, single-photon emission computed tomography (SPECT), SPECT-CT, and PET-MRI using a web-based survey and a search of the literature. The data were reviewed by validators for accuracy and validators provided additional information of provincial and regional policies and practices. Summary of Evidence Of the modalities surveyed, CT is the most widely distributed, with the highest number of units, followed by MRI. All provinces and territories have at least one CT unit; all provinces and Yukon have at least one MRI unit; and all provinces have at least one SPECT and/or SPECT-CT unit. None of the territories have SPECT or SPECT-CT. Nine provinces have PET-CT in clinical use. Two provinces, Alberta and Ontario, have PET-MRI that is used for research purposes. Regarding the total volume of exams, CT is the most-used modality (5.41 million exams per year), followed by MRI (2.33 million exams per year), SPECT and SPECT-CT combined (1.2 million exams per year), and PET-CT (125,775 exams per year). Each imaging modality, apart from SPECT, experienced growth in the last decade in Canada in the number of units and the number of units per million people. CT experienced the slowest growth rate of all imaging modalities — at a 1.4% increase in units per million people over the last decade — compared with other imaging modalities (MRI 20%; PET-CT 25%; and SPECT-CT 70%). Over the last decade, the overall volume of exams increased by 32% and 62% for CT and MRI, respectively. Similarly, the number of exams per thousand population increased by 18% and 46%, respectively. Examination data for the other modalities were not available in 2010. Conclusions and Implications for Decision or Policy-Making The CMII data provides insight into the current context of medical imaging across Canada and raise questions related to how medical imaging is monitored and regulated, and how it is optimally used. As well, the data raise questions about how funding structures are organized, what the most cost-effective practices are, and whether access is equitable, especially in rural and remote areas. Overall, the findings of this report may help decision-makers identify gaps in service; inform medical imaging-related strategic planning on a national, provincial, or territorial basis; and help anticipate future growth and need for replacement. Additionally, the data can be used to identify system efficiencies and monitor the adoption of practices and tools that may support appropriate imaging and wait-list reductions.

IntroductionTransformer-based deep learning has shown great potential in medical imaging, but its real-world applicability remains limited due to the scarcity of annotated data. This study aims to develop a practical framework for the few-shot deployment of pretrained MRI transformers across diverse brain imaging tasks.MethodsWe employ a Masked Autoencoder (MAE) pretraining strategy on a large-scale, multi-cohort brain MRI dataset comprising over 31 million 2D slices to learn transferable representations. For classification tasks, a frozen MAE encoder with a lightweight linear head (MAE-classify) is used. For segmentation, we propose MAE-FUnet, a hybrid architecture that fuses pretrained MAE embeddings with multi-scale CNN features. Extensive evaluations are conducted on multiple datasets, including NACC, ADNI, OASIS, NFBS, SynthStrip, and MRBrainS18, under controlled few-shot settings.ResultsThe proposed framework achieves state-of-the-art performance in MRI sequence classification, reaching an accuracy of 99.24% with only 6,152 trainable parameters. For segmentation tasks, MAE-FUnet consistently outperforms strong baselines, achieving superior Dice and IoU scores across skull stripping and multi-class anatomical segmentation benchmarks. The model also demonstrates enhanced robustness and stability under data-limited conditions, with lower performance variance compared to competing methods.DiscussionThese results highlight the effectiveness of pretrained MAE representations for few-shot medical imaging tasks. The proposed framework enables efficient, scalable, and adaptable deployment of transformer-based models in data-constrained clinical environments. The fusion of global transformer embeddings with local CNN features provides a generalizable design paradigm for a wide range of medical imaging applications.

In clinical imaging modalities, MRI is suitable for preoperative examination. Fluorescence imaging has been proposed to improve the detectability of cancer lesions during the operation. However, the specificity and accuracy of the two imaging modalities is limited. To improve the prognosis and survival rate of the patient suffering from hepatocellular carcinoma (HCC), it is very important to develop a specific probe to achieve early detection and precise resection of HCC. We selected HCC targeting peptide SP94 to conjugate with a NIR dye and Gd chelated DOTA to enhance the specificity of different imaging modalities. MRI and fluorescence imaging were used for preoperative examination of the cancer and detecting the tumor in the operation, respectively. MRI and fluorescence signals significantly increased when HCC occurs and the obtained probe shows high uptake in HCC but negligible uptake in the normal liver tissues. The signal-to-background ratio is higher than 2.23 (MRI) and 2.0 (fluorescence imaging) with noninvasive imaging modalities. After the intraperitoneal cavity was surgically exposed, the signal-to-background ratio is higher than 4.6. By combining the high specificity of our probe with the high sensitivity of fluorescence imaging, the microprimary malignancy and micrometastasis foci (diameter <1 mm) can be easily detected after the intraperitoneal cavity is exposed. These results indicated that our probe is conductive to the early detection and precise resection of the HCC and has the potential to improve the diagnosis and treatment of patients with HCC.

A narrative review on characterization of acute respiratory distress syndrome in COVID-19-infected lungs using artificial intelligence

Precision medicine is a revolutionary medical approach that takes into account individual variations in genes, environment, and lifestyle to tailor treatment and prevention strategies for each patient. One crucial aspect of precision medicine is medical imaging, which plays a fundamental role in the accurate assessment and diagnosis of diseases. By utilizing various imaging modalities, such as MRI, CT scan, and PET scan, doctors can obtain detailed information about a patient's condition and make informed decisions about the most effective therapeutic options. Furthermore, imaging techniques like radiomics have emerged as a promising tool in precision medicine. By extracting quantitative data from medical images, radiomics allows for objective and quantitative analysis of the biological characteristics of diseases. This information can then be correlated and integrated with genomic data to further enhance our understanding of diseases, a concept known as radiogenomics. Imaging plays a vital role in the development of precision medicine. Radiomics, based on high-throughput medical imaging, allows for the extraction of vast amounts of data from medical images to perform objective and quantitative analysis of the biological characteristics of diseases. This is crucial for tumor diagnosis, differential diagnosis, prognosis evaluation, and prediction of treatment response. Medical imaging, specifically radiomics, has greatly advanced the field of precision medicine by providing a comprehensive analysis of tumors and extracting quantitative data from medical images. This data can be correlated and integrated with genomic information to enhance our understanding of diseases and enable personalized treatment plans. In summary, medical imaging, particularly radiomics, plays a central and vital role in the development of precision medicine.

This renowned work is derived from the authors' acclaimed national review course (Physics of Medical Imaging) at the University of California-Davis for radiology residents. The text is a guide to the fundamental principles of medical imaging physics, radiation protection and radiation biology, with complex topics presented in the clear and concise manner and style for which these authors are known. Coverage includes the production, characteristics and interactions of ionizing radiation used in medical imaging and the imaging modalities in which they are used, including radiography, mammography, fluoroscopy, computed tomography and nuclear medicine. Special attention is paid to optimizing patient dose in each of these modalities. Sections of the book address topics common to all forms of diagnostic imaging, including image quality and medical informatics as well as the non-ionizing medical imaging modalities of MRI and ultrasound. The basic science important to nuclear imaging, including the nature and production of radioactivity, internal dosimetry and radiation detection and measurement, are presented clearly and concisely. Current concepts in the fields of radiation biology and radiation protection relevant to medical imaging, and a number of helpful appendices complete this comprehensive textbook. The text is enhanced by numerous full color charts, tables, images and superb illustrations that reinforce central concepts. The book is ideal for medical imaging professionals, and teachers and students in medical physics and biomedical engineering. Radiology residents will find this text especially useful in bolstering their understanding of imaging physics and related topics prior to board exams. Features: new Four-color throughout; new Companion website with fully searchable text and images; basic line drawings help to explain concepts; comprehensive coverage of diagnostic imaging modalities; and superb writing style of the author team helps make a difficult subject approachable and engaging.

Medical images have made a great impact on diagnosis, clinical studies and treatment planning. The most important part of medicalimage processing is segmentation. It is one of the hardest and most frequently required steps in Medical image processing. Many segmentation methods have been proposed for medical images. Methods for performing medical image segmentation vary widely depending on imaging modality, the specific application and type of body part tobe studied. The performance of these techniques is highly associated with the extraction of anatomic structures and separation of suspicious regions from the background and soft tissues effectively.This review paper investigates applicability of different algorithms for computer-aided segmentation of medical images. The study revealed that several algorithms have been explored in the literature for segmentation of anatomic structures from different medical images. Among them k-means, fuzzy c-means and variations of kmeans clustering techniques are extensively used for medical image segmentation.