MR Imaging in the 21st Century: Technical Innovation over the First Two Decades

MRI deep learning models for assisted diagnosis of knee pathologies: a systematic review

OBJECTIVES

Despite showing encouraging outcomes, the precision of deep learning (DL) models using different convolutional neural networks (CNNs) for diagnosis remains under investigation. This systematic review aims to summarise the status of DL MRI models developed for assisting the diagnosis of a variety of knee abnormalities.

MATERIALS AND METHODS

Five databases were systematically searched, employing predefined terms such as 'Knee AND 3D AND MRI AND DL'. Selected inclusion criteria were used to screen publications by title, abstract, and full text. The synthesis of results was performed by two independent reviewers.

RESULTS

Fifty-four articles were included. The studies focused on anterior cruciate ligament injuries (n = 19, 36%), osteoarthritis (n = 9, 17%), meniscal injuries (n = 13, 24%), abnormal knee appearance (n = 11, 20%), and other (n = 2, 4%). The DL models in this review primarily used the following CNNs: ResNet (n = 11, 21%), VGG (n = 6, 11%), DenseNet (n = 4, 8%), and DarkNet (n = 3, 6%). DL models showed high-performance metrics compared to ground truth. DL models for the detection of a specific injury outperformed those by up to 4.5% for general abnormality detection.

CONCLUSION

Despite the varied study designs used among the reviewed articles, DL models showed promising outcomes in the assisted detection of selected knee pathologies by MRI. This review underscores the importance of validating these models with larger MRI datasets to close the existing gap between current DL model performance and clinical requirements.

KEY POINTS

Question What is the status of DL model availability for knee pathology detection in MRI and their clinical potential? Findings Pathology-specific DL models reported higher accuracy compared to DL models for the detection of general abnormalities of the knee. DL model performance was mainly influenced by the quantity and diversity of data available for model training. Clinical relevance These findings should encourage future developments to improve patient care, support personalised diagnosis and treatment, optimise costs, and advance artificial intelligence-based medical imaging practices.

Neuroimaging as a Tool for Advancing Pediatric Psychopharmacology

Neuroimaging, specifically magnetic resonance imaging (MRI), magnetic resonance spectroscopy (MRS), and positron emission tomography (PET), plays an important role in improving the therapeutic landscape of pediatric neuropsychopharmacology by detecting target engagement, pathway modulation, and disease-related changes in the brain. This review provides a comprehensive update on the application of neuroimaging to detect neural effects of psychotropic medication in pediatrics. Additionally, we discuss opportunities and challenges for expanding the use of neuroimaging to advance pediatric neuropsychopharmacology. PubMed and Embase were searched for studies published between 2012 and 2024 reporting neural effects of attention deficit hyperactivity disorder (ADHD) medications (e.g., methylphenidate, amphetamine, atomoxetine, guanfacine), selective serotonin reuptake inhibitors (e.g., fluoxetine, escitalopram, sertraline), serotonin/norepinephrine reuptake inhibitors (e.g., duloxetine, venlafaxine), second-generation antipsychotics (e.g., aripiprazole, olanzapine, risperidone, quetiapine, ziprasidone), and others (e.g., lithium, carbamazepine, lamotrigine, ketamine, naltrexone) used to treat pediatric psychiatric conditions. Of the studies identified (N = 57 in 3314 pediatric participants), most (86%, total participants n = 3045) used MRI to detect functional pathway modulation or anatomical changes. Fewer studies (14%, total participants n = 269) used MRS to understand neurochemical modulation. No studies used PET. Studies that included healthy controls detected normalization of disease-altered pathways following treatment. Studies that focused on affected youth detected neuromodulation following single-dose and ongoing treatment. Neuroimaging is positioned to serve as a biomarker capable of demonstrating acute brain modulation, predicting clinical response, and monitoring disease, yet biomarker validation requires further work. Neuroimaging is also well suited to fill the notable knowledge gap of long-term neuromodulatory effects of psychotropic medications in the context of ongoing brain development in children and adolescents. Future studies can leverage advancements in neuroimaging technology, acquisition, and analysis to fill these gaps and accelerate the discovery of novel therapeutics, leading to more effective prescribing and ensuring faster recovery.

Synthesis, Characterization, Magnetic Properties, and Applications of Carbon Dots as Diamagnetic Chemical Exchange Saturation Transfer Magnetic Resonance Imaging Contrast Agents: A Review

Carbon dots (CDs) are metal-free carbon-based nanoparticles. They possess excellent photoluminescent properties, various physical properties, good chemical stability, high water solubility, high biocompatibility, and tunable surface functionalities, suitable for biomedical applications. Their properties are subject to synthetic conditions such as pH, reaction time, temperature, precursor, and solvent. Until now, a large number of articles on the synthesis and biomedical applications of CDs using their photoluminescent properties have been reported. However, their research on magnetic properties and especially, diamagnetic chemical exchange saturation transfer (diaCEST) in magnetic resonance imaging (MRI) is very poor. The diaCEST MRI contrast agents are based on exchangeable protons of materials with bulk water protons and thus, different from conventional MRI contrast agents, which are based on enhancements of proton spin relaxations of bulk water and tissue. In this review, various syntheses, characterizations, magnetic properties, and potential applications of CDs as diaCEST MRI contrast agents are reviewed. Finally, future perspectives of CDs as the next-generation diaCEST MRI contrast agents are discussed.

Is Bigger Better? Exploring the Compensatory Versus Pathological Nature of Amygdala Hypertrophy

Original Article Citation Zubal R, Velicky Buecheler M, Sone D, Postma T, De Tisi J, Caciagli L, Winston GP, Sidhu MK, Long L, Xiao B, Mcevoy AW, Miserocchi A, Vos SB, Baumann CR, Duncan JS, Koepp MJ, Galovic M. Brain Hypertrophy in Patients With Mesial Temporal Lobe Epilepsy With Hippocampal Sclerosis and Its Clinical Correlates. Neurology. 2025 Jan 28;104(2):e210182. doi: 10.1212/WNL.0000000000210182. Epub 2024 Dec 23. PMID: 39715478; PMCID: PMC11666274. Background and Objectives: Mesial temporal lobe epilepsy (mTLE) is generally associated with focal brain atrophy, but little knowledge exists on possible disease-related hypertrophy of brain structures. We hypothesized that repeated seizures or adaptive plasticity may lead to focal brain hypertrophy and aimed to investigate associated clinical correlates. Methods: In this cohort study, we included patients with mTLE undergoing detailed epilepsy evaluations and matched healthy volunteers (HVs) from 2 tertiary centers (discovery and validation cohorts). We assessed areas of brain hypertrophy and their clinical correlates using whole-brain voxel-based or surface-based morphometry (VBM, SBM), subcortical volumetry, and shape analysis of T1-weighted MRI data by fitting linear models. We evaluated the functional implications of the findings on memory encoding using fMRI. Results: We included 135 patients with mTLE with neuropathology-confirmed hippocampal sclerosis (77 left, 58 right; 82 women; mean age 37 ± 11 years) and 47 HVs (29 women, mean age 36 ± 11 years) in the discovery cohort. VBM detected increased gray matter volume of the contralateral amygdala in patients with both left (t  = 8.7, p  < .001) and right (t  = 7.9, p  < .001) mTLE. We confirmed the larger volume of the contralateral amygdala using volumetry (left mTLE 1.74 ± 0.16 mL vs HVs 1.64 ± 0.11, p  < .001; right mTLE 1.79 ± 0.18 mL vs HVs 1.70 ± 0.11, p  = .002) and shape analysis (left mTLE p  ≤ .005; right mTLE p  = .006). We validated the hypertrophy of the contralateral amygdala in the validation cohort (mTLE, n  = 18, 1.91 ± 0.20 mL; HVs, n  = 18, 1.75 ± 0.13; p  = .009). In left mTLE, contralateral amygdala hypertrophy was associated with poorer verbal memory and, in right mTLE, with more frequent focal-to-bilateral tonic-clonic seizures. A larger volume of the contralateral amygdala correlated with increased functional activation of the right parietal memory encoding network in a subgroup (44/135 patients with mTLE, 26/47 HVs) receiving fMRI. Discussion: Unilateral mTLE due to hippocampal sclerosis is associated with hypertrophy of the contra-lateral amygdala. This may represent plasticity to compensate for verbal memory deficits or may be the consequence of seizure spread to the contralateral hemisphere.

"Estrogens and human brain networks: A systematic review of structural and functional neuroimaging studies"

Estrogen fluctuations during the menstrual cycle, puberty, postpartum, or in the menopausal transition are associated with cognitive, affective, and behavioral effects. Additionally, estrogens are essential in hormonal contraception, menopausal hormone therapy, or gender-affirming hormone therapy. This systematic review summarizes findings on the role of estrogens for structure, function, and connectivity of human brain networks. We searched PubMed, Web of Science, and ScienceDirect for neuroimaging articles assessing estrogens published since 2008. We included 54 studies (N = 2,494 participants) on endogenous estrogen, and 28 studies (N = 1,740 participants) on exogenous estrogen conditions. Estrogen-related changes were reported for emotion, reward, memory, and resting-state networks, and in regional white and gray matter, with a particular neural plasticity in the hippocampus and amygdala. By examining study designs, imaging measures, and analysis methods, this review highlights the role of neuroimaging in advancing neuroendocrine and neurocognitive research, particularly promoting brain health for women and individuals with ovaries.

Synthesis of MR fingerprinting information from magnitude-only MR imaging data using a parallelized, multi network U-Net convolutional neural network

Background

MR fingerprinting (MRF) is a novel method for quantitative assessment of in vivo MR relaxometry that has shown high precision and accuracy. However, the method requires data acquisition using customized, complex acquisition strategies and dedicated post processing methods thereby limiting its widespread application.

Objective

To develop a deep learning (DL) network for synthesizing MRF signals from conventional magnitude-only MR imaging data and to compare the results to the actual MRF signal acquired.

Methods

A U-Net DL network was developed to synthesize MRF signals from magnitude-only 3D T 1-weighted brain MRI data acquired from 37 volunteers aged between 21 and 62 years of age. Network performance was evaluated by comparison of the relaxometry data (T 1, T 2) generated from dictionary matching of the deep learning synthesized and actual MRF data from 47 segmented anatomic regions. Clustered bootstrapping involving 10,000 bootstraps followed by calculation of the concordance correlation coefficient were performed for both T 1 and T 2 MRF data pairs. 95% confidence limits and the mean difference between true and DL relaxometry values were also calculated.

Results

The concordance correlation coefficient (and 95% confidence limits) for T 1 and T 2 MRF data pairs over the 47 anatomic segments were 0.8793 (0.8136-0.9383) and 0.9078 (0.8981-0.9145) respectively. The mean difference (and 95% confidence limits) were 48.23 (23.0-77.3) s and 2.02 (-1.4 to 4.8) s.

Conclusion

It is possible to synthesize MRF signals from MRI data using a DL network, thereby creating the potential for performing quantitative relaxometry assessment without the need for a dedicated MRF pulse sequence.

Role of Artificial Intelligence in MRI-Based Rectal Cancer Staging: A Systematic Review

Several studies explored the application of artificial intelligence (AI) in magnetic resonance imaging (MRI)-based rectal cancer (RC) staging, but a comprehensive evaluation remains lacking. This systematic review aims to review the performance of AI models in MRI-based RC staging. PubMed and Embase were searched from the inception of the database till October 2024 without any language and year restrictions. The prospective or retrospective studies evaluating AI models (including machine learning (ML) and deep learning (DL)) for diagnostic performance in MRI-based RC staging compared with any comparator were included in this review. The performance metrics were considered as outcomes. Two independent reviewers were involved in the study selection and data extraction to limit bias; any disagreements were resolved through mutual consensus or discussion with a third reviewer. A total of 716 records were identified from the databases. Out of these, 14 studies (1.95%) were finally included in this review. These studies were published between 2019 and 2024. Various MRI technologies were adapted by the studies and multiple AI models were developed. DL was the most common. The MRI images including T1-weighted images (14.28%), T2-weighted images (85.71%), diffusion-weighted images (42.85%), or the combination of these from different landscapes and systems were used to develop the AI models. The models were built using various techniques, mainly DL such as conventional neural network (28.57%), DL reconstruction (14.28%), Weakly supervISed model DevelOpment fraMework (7.12%), deep neural network (7.12%), Faster region-based CNN (7.12%), ResNet, DL-based clinical-radiomics nomogram (7.12%), LASSO (7.12%), and random forest classifier (7.12%). All the models that used single-type images or combined imaging modalities showed a better performance than manual assessment in terms of higher accuracy, sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and area under the curve with a score of >0.75. This is considered to be a good performance. The current study indicates that MRI-based AI models for RC staging show great promise with a high performance.

Decoding Schizophrenia: How AI-Enhanced fMRI Unlocks New Pathways for Precision Psychiatry

Schizophrenia, a highly complex psychiatric disorder, presents significant challenges in diagnosis and treatment due to its multifaceted neurobiological underpinnings. Recent advancements in functional magnetic resonance imaging (fMRI) and artificial intelligence (AI) have revolutionized the understanding and management of this condition. This manuscript explores how the integration of these technologies has unveiled key insights into schizophrenia's structural and functional neural anomalies. fMRI research highlights disruptions in crucial brain regions like the prefrontal cortex and hippocampus, alongside impaired connectivity within networks such as the default mode network (DMN). These alterations correlate with the cognitive deficits and emotional dysregulation characteristic of schizophrenia. AI techniques, including machine learning (ML) and deep learning (DL), have enhanced the detection and analysis of these complex patterns, surpassing traditional methods in precision. Algorithms such as support vector machines (SVMs) and Vision Transformers (ViTs) have proven particularly effective in identifying biomarkers and aiding early diagnosis. Despite these advancements, challenges such as variability in methodologies and the disorder's heterogeneity persist, necessitating large-scale, collaborative studies for clinical translation. Moreover, ethical considerations surrounding data integrity, algorithmic transparency, and patient individuality must guide AI's integration into psychiatry. Looking ahead, AI-augmented fMRI holds promise for tailoring personalized interventions, addressing unique neural dysfunctions, and improving therapeutic outcomes for individuals with schizophrenia. This convergence of neuroimaging and computational innovation heralds a transformative era in precision psychiatry.

Etodolac utility in osteoarthritis: drug delivery challenges, topical nanotherapeutic strategies and potential synergies

Osteoarthritis (OSA) is a prevalent joint disorder characterized by losing articular cartilage, primarily affecting the hip, knee and spine joints. The impact of OSA offers a major challenge to health systems globally. Therapeutic approaches encompass surgical interventions, non-pharmacological therapies (exercise, rehabilitation, behavioral interventions) and pharmacological treatments. Inflammatory processes within OSA joints are regulated by pro-inflammatory and anti-inflammatory cytokines. Etodolac, a COX-2-selective inhibitor, is the gold standard for OSA management and uniquely does not inhibit gastric prostaglandins. This comprehensive review offers insights into OSA's pathophysiology, genetic factors and biological determinants influencing disease progression. Emphasis is placed on the pivotal role of etodolac in OSA management, supported by both preclinical and clinical evidences in topical drug delivery. Notably, in-silico docking studies suggested potential synergies between etodolac and baicalein, considering ADAMTS-4, COX-2, MMP-3 and MMP-13 as essential therapeutic targets. Integration of artificial neural network (ANN) techniques with nanotechnology approaches emerges as a promising strategy for optimizing and personalizing topical etodolac delivery. Furthermore, the synergistic potential of etodolac and baicalein warrants in-depth exploration. Hence, by embracing cutting-edge technologies like ANN and nanomedicine, the optimization of topical etodolac delivery could guide a new era of OSA treatment.

Technology-enabled patient care in medical radiation sciences: the two sides of the coin

This is an exciting time to be working in healthcare and medical radiation sciences. This article discusses the potential benefits and risks of new technological interventions for patient benefit and outlines the need for co-production, governance and education to ensure these are used for advancing patients' well-being.

Cavernous Malformations of the Central Nervous System: A Comprehensive Review of Pathophysiology, Diagnosis, and Management

Cavernous malformations (CMs) of the central nervous system (CNS) are vascular anomalies characterized by clusters of dilated, thin-walled blood vessels prone to leakage and hemorrhage. These malformations can occur throughout the CNS, including the brain and spinal cord, and present with a wide range of clinical manifestations, from asymptomatic cases to severe neurological deficits. Advances in neuroimaging, particularly magnetic resonance imaging (MRI), have greatly improved the diagnosis and understanding of CMs, enabling more precise differentiation from other vascular lesions. The management of CMs has evolved alongside advancements in surgical and radiosurgical techniques, offering various therapeutic options depending on the lesion's characteristics and patient symptoms. While conservative management is often appropriate for asymptomatic or minimally symptomatic lesions, surgical resection or stereotactic radiosurgery may be indicated in cases with recurrent hemorrhage or significant neurological impairment. This comprehensive review explores the pathophysiology, clinical presentation, diagnosis, and management of CMs, highlighting current evidence-based practices and emerging therapeutic approaches. The review also addresses the genetic and molecular underpinnings of CMs, particularly in hereditary cases, and discusses potential future directions in research and treatment. By synthesizing the latest knowledge in the field, this review aims to enhance clinical decision-making and promote further investigation into the optimal management of CMs in the CNS.

Recent advances in mitochondria-targeting theranostic agents

For its vital role in maintaining cellular activity and survival, mitochondrion is highly involved in various diseases, and several strategies to target mitochondria have been developed for specific imaging and treatment. Among these approaches, theranostic may realize both diagnosis and therapy with one integrated material, benefiting the simplification of treatment process and candidate drug evaluation. A variety of mitochondria-targeting theranostic agents have been designed based on the differential structure and composition of mitochondria, which enable more precise localization within cellular mitochondria at disease sites, facilitating the unveiling of pathological information while concurrently performing therapeutic interventions. Here, progress of mitochondria-targeting theranostic materials reported in recent years along with background information on mitochondria-targeting and therapy have been briefly summarized, determining to deliver updated status and design ideas in this field to readers.

A Comprehensive Review on the Role of MRI in the Assessment of Supratentorial Neoplasms: Comparative Insights Into Adult and Pediatric Cases

Magnetic resonance imaging (MRI) is a critical diagnostic tool in assessing supratentorial neoplasms, offering unparalleled detail and specificity in brain imaging. Supratentorial neoplasms in the cerebral hemispheres, basal ganglia, thalamus, and other structures above the tentorium cerebelli present significant diagnostic and therapeutic challenges. These challenges vary notably between adult and pediatric populations due to differences in tumor types, biological behavior, and patient management strategies. This comprehensive review explores the role of MRI in diagnosing, planning treatment, monitoring response, and detecting recurrence in supratentorial neoplasms, providing comparative insights into adult and pediatric cases. The review begins with an overview of the epidemiology and pathophysiology of these tumors in different age groups, followed by a detailed examination of standard and advanced MRI techniques, including diffusion-weighted imaging (DWI), perfusion-weighted imaging (PWI), and magnetic resonance spectroscopy (MRS). We discuss the specific imaging characteristics of various neoplasms and the importance of tailored approaches to optimize diagnostic accuracy and therapeutic efficacy. The review also addresses the technical and interpretative challenges unique to pediatric imaging and the implications for long-term patient outcomes. By highlighting the comparative utility of MRI in adult and pediatric cases, this review aims to enhance the understanding of its pivotal role in managing supratentorial neoplasms. It underscores the necessity of age-specific diagnostic and therapeutic strategies. Emerging MRI technologies and future research directions are also discussed, emphasizing the potential for advancements in personalized imaging approaches and improved patient care across all age groups.

Diagnostic Modalities in Heart Failure: A Narrative Review

Heart failure (HF) can present acutely or progress over time. It can lead to morbidity and mortality affecting 6.5 million Americans over the age of 20. The HF type is described according to the ejection fraction classification, defined as the percentage of blood volume that exits the left ventricle after myocardial contraction, undergoing ejection into the circulation, also called stroke volume, and is proportional to the ejection fraction. Cardiac catheterization is an invasive procedure to evaluate coronary artery disease leading to HF. Several biomarkers are being studied that could lead to early detection of HF and better symptom management. Testing for various biomarkers in the patient's blood is instrumental in confirming the diagnosis and elucidating the etiology of HF. There are various biomarkers elevated in response to increased myocardial stress and volume overload, including B-type natriuretic peptide (BNP) and its N-terminal prohormone BNP. We explored online libraries such as PubMed, Google Scholar, and Cochrane to find relevant articles. Our narrative review aims to extensively shed light on diagnostic modalities and novel techniques for diagnosing HF.

Virtual Reality Head-Mounted Display (HMD) and Preoperative Patient-Specific Simulation: Impact on Decision-Making in Pediatric Urology: Preliminary Data

AIM OF THE STUDY

To assess how virtual reality (VR) patient-specific simulations can support decision-making processes and improve care in pediatric urology, ultimately improving patient outcomes.

PATIENTS AND METHODS

Children diagnosed with urological conditions necessitating complex procedures were retrospectively reviewed and enrolled in the study. Patient-specific VR simulations were developed with medical imaging specialists and VR technology experts. Routine CT images were utilized to create a VR environment using advanced software platforms. The accuracy and fidelity of the VR simulations was validated through a multi-step process. This involved comparing the virtual anatomical models to the original medical imaging data and conducting feedback sessions with pediatric urology experts to assess VR simulations' realism and clinical relevance.

RESULTS

A total of six pediatric patients were reviewed. The median age of the participants was 5.5 years (IQR: 3.5-8.5 years), with an equal distribution of males and females across both groups. A minimally invasive laparoscopic approach was performed for adrenal lesions (n = 3), Wilms' tumor (n = 1), bilateral nephroblastomatosis (n = 1), and abdominal trauma in complex vascular and renal malformation (ptotic and hypoplastic kidney) (n = 1). Key benefits included enhanced visualization of the segmental arteries and the deep vascularization of the kidney and adrenal glands in all cases. The high depth perception and precision in the orientation of the arteries and veins to the parenchyma changed the intraoperative decision-making process in five patients. Preoperative VR patient-specific simulation did not offer accuracy in studying the pelvic and calyceal anatomy.

CONCLUSIONS

VR patient-specific simulations represent an empowering tool in pediatric urology. By leveraging the immersive capabilities of VR technology, preoperative planning and intraoperative navigation can greatly impact surgical decision-making. As we continue to advance in medical simulation, VR holds promise in educational programs to include even surgical treatment of more complex urogenital malformations.

Randomized controlled trials of non-pharmacological interventions for healthy seniors: Effects on cognitive decline, brain plasticity and activities of daily living-A 23-year scoping review

Little is known about the simultaneous effects of non-pharmacological interventions (NPI) on healthy older adults' behavior and brain plasticity, as measured by psychometric instruments and magnetic resonance imaging (MRI). The purpose of this scoping review was to compile an extensive list of randomized controlled trials published from January 1, 2000, to August 31, 2023, of NPI for mitigating and countervailing age-related physical and cognitive decline and associated cerebral degeneration in healthy elderly populations with a mean age of 55 and over. After inventorying the NPI that met our criteria, we divided them into six classes: single-domain cognitive, multi-domain cognitive, physical aerobic, physical non-aerobic, combined cognitive and physical aerobic, and combined cognitive and physical non-aerobic. The ultimate purpose of these NPI was to enhance individual autonomy and well-being by bolstering functional capacity that might transfer to activities of daily living. The insights from this study can be a starting point for new research and inform social, public health, and economic policies. The PRISMA extension for scoping reviews (PRISMA-ScR) checklist served as the framework for this scoping review, which includes 70 studies. Results indicate that medium- and long-term interventions combining non-aerobic physical exercise and multi-domain cognitive interventions best stimulate neuroplasticity and protect against age-related decline and that outcomes may transfer to activities of daily living.

Application of PET/MRI in Gynecologic Malignancies

The diagnosis, treatment, and management of gynecologic malignancies benefit from both positron emission tomography/computed tomography (PET/CT) and MRI. PET/CT provides important information on the local extent of disease as well as diffuse metastatic involvement. MRI offers soft tissue delineation and loco-regional disease involvement. The combination of these two technologies is key in diagnosis, treatment planning, and evaluating treatment response in gynecological malignancies. This review aims to assess the performance of PET/MRI in gynecologic cancer patients and outlines the technical challenges and clinical advantages of PET/MR systems when specifically applied to gynecologic malignancies.

Cutting Edge Developments in Spine Surgery at the University of Missouri

The treatment of spinal pathologies has evolved significantly from the times of Hippocrates and Galen to the current era. This evolution has led to the development of cutting-edge technologies to improve surgical techniques and patient outcomes. The University of Missouri Health System is a high-volume, tertiary care academic medical center that serves a large catchment area in central Missouri and beyond. The Department of Neurosurgery has sought to integrate the best available technologies to serve their spine patients. These technological advancements include intra-operative image guidance, robotic spine surgery, minimally invasive techniques, motion preservation surgery, and interdisciplinary care of metastatic disease to the spine. These advances have resulted in safer surgeries with enhanced outcomes at the University of Missouri. This integration of innovation demonstrates our tireless commitment to ensuring excellence in the comprehensive care of a diverse range of patients with complex spinal pathologies.

The Coproduction of Health Framework: Seeking Instructive Management Models and Theories

At the beginning of the 21st century, multiple and diverse social entities, including the public (consumers), private and nonprofit healthcare institutions, government (public health) and other industry sectors, began to recognize the limitations of the current fragmented healthcare system paradigm. Primary stakeholders, including employers, insurance companies, and healthcare professional organizations, also voiced dissatisfaction with unacceptable health outcomes and rising costs. Grand challenges and wicked problems threatened the viability of the health sector. American health systems responded with innovations and advances in healthcare delivery frameworks that encouraged shifts from intra- and inter-sector arrangements to multi-sector, lasting relationships that emphasized patient centrality along with long-term commitments to sustainability and accountability. This pathway, leading to a population health approach, also generated the need for transformative business models. The coproduction of health framework, with its emphasis on cross-sector alignments, nontraditional partner relationships, sustainable missions, and accountability capable of yielding return on investments, has emerged as a unique strategy for facing disruptive threats and challenges from nonhealth sector corporations. This chapter presents a coproduction of health framework, goals and criteria, examples of boundary spanning network alliance models, and operational (integrator, convener, aggregator) strategies. A comparison of important organizational science theories, including institutional theory, network/network analysis theory, and resource dependency theory, provides suggestions for future research directions necessary to validate the utility of the coproduction of health framework as a precursor for paradigm change.

A Quantitative Multiparametric MRI Analysis Platform for Estimation of Robust Imaging Biomarkers in Clinical Oncology

There is a need to develop user-friendly imaging tools estimating robust quantitative biomarkers (QIBs) from multiparametric (mp)MRI for clinical applications in oncology. Quantitative metrics derived from (mp)MRI can monitor and predict early responses to treatment, often prior to anatomical changes. We have developed a vendor-agnostic, flexible, and user-friendly MATLAB-based toolkit, MRI-Quantitative Analysis and Multiparametric Evaluation Routines ("MRI-QAMPER", current release v3.0), for the estimation of quantitative metrics from dynamic contrast-enhanced (DCE) and multi-b value diffusion-weighted (DW) MR and MR relaxometry. MRI-QAMPER's functionality includes generating numerical parametric maps from these methods reflecting tumor permeability, cellularity, and tissue morphology. MRI-QAMPER routines were validated using digital reference objects (DROs) for DCE and DW MRI, serving as initial approval stages in the National Cancer Institute Quantitative Imaging Network (NCI/QIN) software benchmark. MRI-QAMPER has participated in DCE and DW MRI Collaborative Challenge Projects (CCPs), which are key technical stages in the NCI/QIN benchmark. In a DCE CCP, QAMPER presented the best repeatability coefficient (RC = 0.56) across test-retest brain metastasis data, out of ten participating DCE software packages. In a DW CCP, QAMPER ranked among the top five (out of fourteen) tools with the highest area under the curve (AUC) for prostate cancer detection. This platform can seamlessly process mpMRI data from brain, head and neck, thyroid, prostate, pancreas, and bladder cancer. MRI-QAMPER prospectively analyzes dose de-escalation trial data for oropharyngeal cancer, which has earned it advanced NCI/QIN approval for expanded usage and applications in wider clinical trials.

Multiparametric MRI: From Simultaneous Rapid Acquisition Methods and Analysis Techniques Using Scoring, Machine Learning, Radiomics, and Deep Learning to the Generation of Novel Metrics

ABSTRACT

With the recent advancements in rapid imaging methods, higher numbers of contrasts and quantitative parameters can be acquired in less and less time. Some acquisition models simultaneously obtain multiparametric images and quantitative maps to reduce scan times and avoid potential issues associated with the registration of different images. Multiparametric magnetic resonance imaging (MRI) has the potential to provide complementary information on a target lesion and thus overcome the limitations of individual techniques. In this review, we introduce methods to acquire multiparametric MRI data in a clinically feasible scan time with a particular focus on simultaneous acquisition techniques, and we discuss how multiparametric MRI data can be analyzed as a whole rather than each parameter separately. Such data analysis approaches include clinical scoring systems, machine learning, radiomics, and deep learning. Other techniques combine multiple images to create new quantitative maps associated with meaningful aspects of human biology. They include the magnetic resonance g-ratio, the inner to the outer diameter of a nerve fiber, and the aerobic glycolytic index, which captures the metabolic status of tumor tissues.

Recent Developments in PET and SPECT Radiotracers as Radiopharmaceuticals for Hypoxia Tumors

Hypoxia, a deficiency in the levels of oxygen, is a common feature of most solid tumors and induces many characteristics of cancer. Hypoxia is associated with metastases and strong resistance to radio- and chemotherapy, and can decrease the accuracy of cancer prognosis. Non-invasive imaging methods such as positron emission tomography (PET) and single-photon emission computed tomography (SPECT) using hypoxia-targeting radiopharmaceuticals have been used for the detection and therapy of tumor hypoxia. Nitroimidazoles are bioreducible moieties that can be selectively reduced under hypoxic conditions covalently bind to intracellular macromolecules, and are trapped within hypoxic cells and tissues. Recently, there has been a strong motivation to develop PET and SPECT radiotracers as radiopharmaceuticals containing nitroimidazole moieties for the visualization and treatment of hypoxic tumors. In this review, we summarize the development of some novel PET and SPECT radiotracers as radiopharmaceuticals containing nitroimidazoles, as well as their physicochemical properties, in vitro cellular uptake values, in vivo biodistribution, and PET/SPECT imaging results.

Predicting Histopathological Grading of Adult Gliomas Based On Preoperative Conventional Multimodal MRI Radiomics: A Machine Learning Model

PURPOSE

The accurate preoperative histopathological grade diagnosis of adult gliomas is of great significance for the formulation of a surgical plan and the implementation of a subsequent treatment. The aim of this study is to establish a predictive model for classifying adult gliomas into grades 2-4 based on preoperative conventional multimodal MRI radiomics.

PATIENTS AND METHODS

Patients with pathologically confirmed gliomas at Huashan Hospital, Fudan University, between February 2017 and July 2019 were retrospectively analyzed. Two regions of interest (ROIs), called the maximum anomaly region (ROI1) and the tumor region (ROI2), were delineated on the patients' preoperative MRIs utilizing the tool ITK-SNAP, and Pyradiomics 3.0 was applied to execute feature extraction. Feature selection was performed utilizing a least absolute shrinkage and selection operator (LASSO) filter. Six classifiers, including Gaussian naive Bayes (GNB), random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM) with a linear kernel, adaptive boosting (AB), and multilayer perceptron (MLP) were used to establish predictive models, and the predictive performance of the six classifiers was evaluated through five-fold cross-validation. The performance of the predictive models was evaluated using the AUC and other metrics. After that, the model with the best predictive performance was tested using the external data from The Cancer Imaging Archive (TCIA).

RESULTS

According to the inclusion and exclusion criteria, 240 patients with gliomas were identified for inclusion in the study, including 106 grade 2, 68 grade 3, and 66 grade 4 gliomas. A total of 150 features was selected, and the MLP classifier had the best predictive performance among the six classifiers based on T2-FLAIR (mean AUC of 0.80 ± 0.07). The SVM classifier had the best predictive performance among the six classifiers based on DWI (mean AUC of 0.84 ± 0.05); the SVM classifier had the best predictive performance among the six classifiers based on CE-T1WI (mean AUC of 0.85 ± 0.06). Among the six classifiers, based on ROI1, the MLP classifier had the best prediction performance (mean AUC of 0.78 ± 0.07); among the six classifiers, based on ROI2, the SVM classifier had the best prediction performance (mean AUC of 0.82 ± 0.07). Among the six classifiers, based on the multimodal MRI of all the ROIs, the SVM classifier had the best prediction performance (average AUC of 0.85 ± 0.04). The SVM classifier, based on the multimodal MRI of all the ROIs, achieved an AUC of 0.81 using the external data from TCIA.

CONCLUSIONS

The prediction model, based on preoperative conventional multimodal MRI radiomics, established in this study can conveniently, accurately, and noninvasively classify adult gliomas into grades 2-4, providing certain assistance for the precise diagnosis and treatment of patients and optimizing their clinical management.

Clinical applications of artificial intelligence in liver imaging

This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.