Questo è quello che abbiamo trovato per te
Medical imaging is a critical diagnostic modality with diverse applications. Many countries are already using AI-assisted chest x-rays (CXR) for tuberculosis (TB) screening. Point-of-care ultrasound (POCUS) is becoming increasingly accessible, and modeling suggests that its implementation with AI-guided interpretation could prevent infant deaths.1
Stroke, Ahead of Print.
Introduction
Microwave imaging presents several potential advantages including its non-ionising and harmless nature. This open, multicentric, interventional, prospective, non-randomised trial aims to validate MammoWave’s artificial intelligence (AI)-based classification algorithm, leveraging microwave imaging, to achieve a sensitivity exceeding 75% and a specificity exceeding 90% in breast screening.
Methods and analysis
10 000 volunteers undergoing regular mammographic breast cancer screening will be recruited across 9 European centres and invited to participate in the clinical study, involving MammoWave testing on both breasts. MammoWave results will be checked against the reference standard, to be intended as the output of conventional breast examination path (with histological confirmation of cancer cases) with 2 years follow-up. Anonymised clinical and MammoWave’s results, including microwave images, associated features and a label provided by the AI-based classification algorithm, will be collected and stored in a dedicated electronic case report form. The prospective study will involve a comparative analysis between the output of the conventional breast examination path (control intervention) and the labels provided by MammoWave’s AI system (experimental intervention). These labels will categorise breasts into two groups: breast With Suspicious Finding, indicating the presence of a suspicious lesion or No Suspicious Finding, indicating the absence of a lesion or the presence of a low-suspicion lesion. This trial aims to provide evidence regarding the novel MammoWave’s AI system for detecting breast cancer in asymptomatic populations during screening.
Ethics and dissemination
This study was approved by the Research Ethics Committee of the Liguria Region (CET), Italy (CET-Liguria: 524/2023—DB id 13399), the Research Ethics Committee of Complejo Hospitalario de Toledo (CEIC), Spain (CEIC-1094), the National Ethics Committee for Clinical Research (CEIC), Portugal (CEIC-2311KC814), the Bioethical Committee of Pomeranian Medical University in Szczecin, Poland (KB-006/23/2024) and the Zurich Cantonal Ethics Commission, Switzerland (BASEC 2023-D0101). The findings of this study will be disseminated through academic and scientific conferences as well as peer-reviewed journals.
Trial registration number
NCT06291896.
This Special Communication discusses the merits and feasibility of imaging biomarkers in psychiatry, balancing scientific and practical considerations.
Introduction
Localised renal masses are an increasing burden on healthcare due to the rising number of cases. However, conventional imaging cannot reliably distinguish between benign and malignant renal masses, and renal mass biopsies are unable to characterise the entirety of the tumour due to sampling error, which may lead to delayed treatment or overtreatment. There is an unmet clinical need to develop novel imaging techniques to characterise renal masses more accurately. Renal tumours demonstrate characteristic metabolic reprogramming, and novel MRI methods have the potential to detect these metabolic perturbations, which may therefore aid accurate characterisation. Here, we present our study protocol for the investigation of the differential biology of benign and malignant renal masses using advanced MRI techniques (IBM-Renal).
Methods and analysis
IBM-Renal is a multiarm, single-centre, non-randomised, feasibility study with the aim to provide preliminary evidence for the potential role of the novel MRI techniques to phenotype localised renal lesions. 30 patients with localised renal masses will be recruited to three imaging arms, with 10 patients in each: (1) hyperpolarised [1-13C]-pyruvate MRI, (2) deuterium metabolic imaging (DMI) and (3) sodium MRI. The diagnosis will be made on samples acquired at biopsy or at surgery. The primary objective is the technical development of the novel MRI techniques, with the ultimate aim to understand whether these can identify differences between benign and malignant tumours, while the secondary objectives aim to assess how complementary the techniques are, and if they provide additional information. The exploratory objective is to link imaging findings with clinical data and molecular analyses for the biological validation of the novel MRI techniques.
Ethics and dissemination
This study was ethically approved (UK REC HRA: 22/EE/0136; current protocol version 2.1 dated 11 August 2022). The plans for dissemination include presentations at conferences, publications in scientific journals, a doctoral thesis and patient and public involvement.
Trial registration number
NCT06016075.
Stroke, Ahead of Print. BACKGROUND:In acute stroke, diffusion-weighted imaging (DWI) is used to assess the ischemic core. Dynamic-susceptibility contrast perfusion magnetic resonance imaging allows an estimation of the oxygen extraction fraction (OEF), but the outcome of DWI lesions with increased OEF postrecanalization is unclear. This study investigated the impact of OEF on the fate of DWI lesions in patients achieving recanalization after thrombectomy.METHODS:This was a retrospective analysis of the HIBISCUS-STROKE cohort (Cohort of Patients to Identify Biological and Imaging Markers of Cardiovascular Outcomes in Stroke; NCT: 03149705), a single-center observational study that prospectively enrolled patients who underwent magnetic resonance imaging triage for thrombectomy and a day-6 T2-fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging. Automated postprocessing of admission dynamic-susceptibility contrast perfusion magnetic resonance imaging generated OEF maps. At visual analysis, the OEF status within DWI lesions was assessed in comparison to the contralateral side and correlated with volume changes (difference of ischemic lesion between admission DWI and registered day-6 T2-FLAIR). At voxel-based analysis, recovered DWI regions (lesions present on the admission DWI but absent on the registered day-6 T2-FLAIR) and nonrecovered regions were segmented to extract semiquantitative OEF values.RESULTS:Of the participants enrolled from 2016 to 2022, 134 of 321 (41.7%) were included (median age, 71.0 years; 58.2% male; median baseline National Institutes of Health Scale score, 15.0). At visual analysis, 46 of 134 (34.3%) patients had increased OEF within DWI lesions. These patients were more likely to show a reduction in ischemic lesion volumes compared with those without increased OEF (median change, −4.0 versus 4.8 mL;P
Our results suggested that such an imaging-driven, biotype-guided approaches hold promise for facilitating personalized treatment of ADHD and exploring possible boundaries through innovative deep learning algorithms to improve medication treatment effectiveness.
Stroke, Ahead of Print.
Circulation, Volume 150, Issue 14, Page 1087-1089, October 1, 2024.
Circulation, Ahead of Print. BACKGROUND:Early detection of acute brain injury (ABI) at the bedside is critical in improving survival for patients with extracorporeal membrane oxygenation (ECMO) support. We aimed to examine the safety of ultra–low-field (ULF; 0.064-T) portable magnetic resonance imaging (pMRI) in patients undergoing ECMO and to investigate the ABI frequency and types with ULF-pMRI.METHODS:This was a multicenter prospective observational study (SAFE MRI ECMO study [Assessing the Safety and Feasibility of Bedside Portable Low-Field Brain Magnetic Resonance Imaging in Patients on ECMO]; NCT05469139) from 2 tertiary centers (Johns Hopkins, Baltimore, MD and University of Texas–Houston) with specially trained intensive care units. Primary outcomes were safety of ULF-pMRI during ECMO support, defined as completion of ULF-pMRI without significant adverse events.RESULTS:Of 53 eligible patients, 3 were not scanned because of a large head size that did not fit within the head coil. ULF-pMRI was performed in 50 patients (median age, 58 years; 52% male), with 34 patients (68%) on venoarterial ECMO and 16 patients (32%) on venovenous ECMO. Of 34 patients on venoarterial ECMO, 11 (22%) were centrally cannulated and 23 (46%) were peripherally cannulated. In venovenous ECMO, 9 (18%) had single-lumen cannulation and 7 (14%) had double-lumen cannulation.Of 50 patients, adverse events occurred in 3 patients (6%), with 2 minor adverse events (ECMO suction event; transient low ECMO flow) and one serious adverse event (intra-aortic balloon pump malfunction attributable to electrocardiographic artifacts). All images demonstrated discernible intracranial pathologies with good quality. ABI was observed in 22 patients (44%). Ischemic stroke (36%) was the most common type of ABI, followed by intracranial hemorrhage (6%) and hypoxic-ischemic brain injury (4%). Of 18 patients (36%) with both ULF-pMRI and head computed tomography within 24 hours, ABI was observed in 9 patients with a total of 10 events (8 ischemic, 2 hemorrhagic events). Of the 8 ischemic events, pMRI observed all 8, and head computed tomography observed only 4 events. For intracranial hemorrhage, pMRI observed only 1 of them, and head computed tomography observed both (2 events).CONCLUSIONS:Our study demonstrates that ULF-pMRI can be performed in patients on ECMO across different ECMO cannulation strategies in specially trained intensive care units. The incidence of ABI was high, seen in 44% of ULF-pMRI studies. ULF-pMRI imaging appears to be more sensitive to ABI, particularly ischemic stroke, compared with head computed tomography.
Objectives
To identify the barriers and facilitators to the successful implementation of imaging-based diagnostic artificial intelligence (AI)-assisted decision-making software in China, using the updated Consolidated Framework for Implementation Research (CFIR) as a theoretical basis to develop strategies that promote effective implementation.
Design
This qualitative study involved semistructured interviews with key stakeholders from both clinical settings and industry. Interview guide development, coding, analysis and reporting of findings were thoroughly informed by the updated CFIR.
Setting
Four healthcare institutions in Beijing and Shanghai and two vendors of AI-assisted decision-making software for lung nodules detection and diabetic retinopathy screening were selected based on purposive sampling.
Participants
A total of 23 healthcare practitioners, 6 hospital informatics specialists, 4 hospital administrators and 7 vendors of the selected AI-assisted decision-making software were included in the study.
Results
Within the 5 CFIR domains, 10 constructs were identified as barriers, 8 as facilitators and 3 as both barriers and facilitators. Major barriers included unsatisfactory clinical performance (Innovation); lack of collaborative network between primary and tertiary hospitals, lack of information security measures and certification (outer setting); suboptimal data quality, misalignment between software functions and goals of healthcare institutions (inner setting); unmet clinical needs (individuals). Key facilitators were strong empirical evidence of effectiveness, improved clinical efficiency (innovation); national guidelines related to AI, deployment of AI software in peer hospitals (outer setting); integration of AI software into existing hospital systems (inner setting) and involvement of clinicians (implementation process).
Conclusions
The study findings contributed to the ongoing exploration of AI integration in healthcare from the perspective of China, emphasising the need for a comprehensive approach considering both innovation-specific factors and the broader organisational and contextual dynamics. As China and other developing countries continue to advance in adopting AI technologies, the derived insights could further inform healthcare practitioners, industry stakeholders and policy-makers, guiding policies and practices that promote the successful implementation of imaging-based diagnostic AI-assisted decision-making software in healthcare for optimal patient care.
Message Barrier healing represents a novel therapeutic target in ulcerative colitis (UC), although its assessment remains challenging and lacks standardisation. This exploratory study evaluates the ability of ultra-high magnification endocytoscopy to guide tissue sampling and drive automated quantification of tight junction (TJ) proteins to assess intestinal barrier integrity and predict major adverse outcomes (MAOs). 34 UC patients in clinical remission prospectively underwent assessment with endocytoscopy and machine learning-enabled intestinal barrier protein evaluation. The combination of endocytoscopy with Claudin-2 expression showed promise in accurately predicting MAOs over 12 months. This integrative approach holds promise in identifying deep healing and enhancing treat-to-target strategy in UC. Detail Barrier healing is attracting fresh attention as a therapeutic target in UC.1 2 However, its evaluation is subjective and not standardised. It has generally depended on probe permeability with considerable variability, thus highlighting an unmet need for novel…
Stroke, Ahead of Print. While imaging has traditionally played a fundamental role in the selection of patients undergoing endovascular thrombectomy, recent thrombectomy trials involving patients with large ischemic strokes demonstrated a consistent benefit of endovascular thrombectomy across all imaging strata, suggesting that reperfusion benefit may exist independent of current imaging constructs. Although these findings attest to the uniformly beneficial effects of reperfusion, they also shed doubt on the accuracy and utility of our imaging modalities in defining reversible versus irreversible ischemia and challenge the premise of imaging-based selection. We aimed to review the histopathologic studies and clinical trials that have shaped our understanding of current imaging constructs aiming to outline the existing imaging-neuropathological gap that may be far wider than previously perceived.
Stroke, Ahead of Print. BACKGROUND:Perfusion abnormalities in the infarct and salvaged penumbra have been proposed as a potential reason for poor clinical outcome (modified Rankin Scale score >2) despite complete angiographic reperfusion (Thrombolysis in Cerebral Infarction [TICI3]). In this study, we aimed to identify different microvascular perfusion patterns and their association with clinical outcomes among TICI3 patients.METHODS:University Hospital Bern’s stroke registry of all patients between February 2015 and December 2021. Macrovascular reperfusion was graded using the TICI scale. Microvascular reperfusion status was evaluated within the infarct area on cerebral blood volume and cerebral blood flow perfusion maps obtained 24-hour postintervention. Primary outcome was functional independence (90-day modified Rankin Scale score 0–2) evaluated with the logistic regression analysis adjusted for age, sex, and 24-hour infarct volume from follow-up imaging.RESULTS:Based on microvascular perfusion findings, the entire cohort (N=248) was stratified into one of the 4 clusters: (1) normoperfusion (no perfusion abnormalities; n=143/248); (2) hyperperfusion (hyperperfusion on both cerebral blood volume and cerebral blood flow; n=54/248); (3) hypoperfusion (hypoperfusion on both cerebral blood volume and cerebral blood flow; n=14/248); and (4) mixed (discrepant findings, eg, cerebral blood volume hypoperfusion and cerebral blood flow hyperperfusion; n=37/248). Compared with the normoperfusion cluster, patients in the hypoperfusion cluster were less likely to achieve functional independence (adjusted odds ratio, 0.3 [95% CI, 0.1–0.9]), while patients in the hyperperfusion cluster tended to have better outcomes (adjusted odds ratio, 3.3 [95% CI, 1.3–8.8]).CONCLUSIONS:In around half of TICI3 patients, perfusion abnormalities on the microvascular level can be observed. Microvascular hypoperfusion, despite complete macrovascular reperfusion, is rare but may explain the poor clinical course among some TICI3 patients, while a detrimental effect of hyperperfusion after reperfusion could not be confirmed.
Inflammation is a critical component of most acute and chronic liver diseases. The liver is a unique immunological organ with a dense vascular network, leading to intense crosstalk between tissue-resident immune cells, passenger leucocytes and parenchymal cells. During acute and chronic liver diseases, the multifaceted immune response is involved in disease promoting and repair mechanisms, while upholding core liver immune functions. In recent years, single-cell technologies have unravelled a previously unknown heterogeneity of immune cells, reshaping the complexity of the hepatic immune response. However, inflammation is a dynamic biological process, encompassing various immune cells, orchestrated in temporal and spatial dimensions, and driven by multiorgan signals. Intravital microscopy (IVM) has emerged as a powerful tool to investigate immunity by visualising the dynamic interplay between different immune cells and their surroundings within a near-natural environment. In this review, we summarise the experimental considerations to perform IVM and highlight recent technological developments. Furthermore, we outline the unique contributions of IVM to our understanding of liver immunity. Through the lens of liver disease, we discuss novel immune-mediated disease mechanisms uncovered by imaging-based studies.
Stroke, Ahead of Print.
