-
Scientific Data Jun 2024Accurate differentiation between angina with no obstructive coronary arteries (ANOCA) and mental stress-induced myocardial ischemia (MSIMI) is crucial for tailored...
Accurate differentiation between angina with no obstructive coronary arteries (ANOCA) and mental stress-induced myocardial ischemia (MSIMI) is crucial for tailored treatment strategies, yet public data scarcity hampers understanding. Given the higher incidence of both conditions in women, this study prospectively enrolled 80 female ANOCA and 39 age-matched female controls, subjecting them to three types of mental stress tasks. ECGs were continuously monitored across Rest, Stress, and Recover stages of the mental stress tasks, with PET/CT imaging during the Stress stage to evaluate myocardial perfusion. With PET/CT serving as the gold standard for MSIMI diagnosis, 35 of the 80 ANOCA patients were diagnosed as MSIMI. Using ECG variables from different stages of mental stress tasks, we developed five machine learning models to diagnose MSIMI. The results showed that ECG data from different stages provide valuable information for MSIMI classification. Additionally, the dataset encompassed demographic details, physiological, and blood sample test results of the patients. We anticipate this new dataset will significantly push further progress in ANOCA and MSIMI research.
Topics: Humans; Female; Myocardial Ischemia; Stress, Psychological; Electrocardiography; Machine Learning; Positron Emission Tomography Computed Tomography; Middle Aged; Angina Pectoris; Prospective Studies
PubMed: 38937514
DOI: 10.1038/s41597-024-03462-2 -
BMJ Case Reports Jun 2024Choroidal neovascular membrane (CNVM) in Vogt-Koyanagi-Harada disease (VKH) is a known entity, observed primarily during the chronic convalescent and chronic-recurrent...
Choroidal neovascular membrane (CNVM) in Vogt-Koyanagi-Harada disease (VKH) is a known entity, observed primarily during the chronic convalescent and chronic-recurrent phases of the disease. However, the peripapillary location of CNVM is a rare finding.We describe a case of chronic VKH with bilateral peripapillary CNVM detected using multimodal imaging and the associated differential diagnoses and treatment approach.A combination of anti-vascular endothelial growth factor injections, systemic steroids and immunosuppressants is often required to manage the aggressive course of this choroidal neovascularisation.
Topics: Humans; Uveomeningoencephalitic Syndrome; Choroidal Neovascularization; Tomography, Optical Coherence; Fluorescein Angiography; Diagnosis, Differential; Male; Female; Adult; Angiogenesis Inhibitors
PubMed: 38937264
DOI: 10.1136/bcr-2023-256973 -
BMJ Case Reports Jun 2024A man in his 70s presented with a sudden onset stabbing back pain radiating to the chest and pre-syncopal symptoms. He underwent urgent investigations, including a CT...
A man in his 70s presented with a sudden onset stabbing back pain radiating to the chest and pre-syncopal symptoms. He underwent urgent investigations, including a CT angiogram aorta which did not reveal any abnormalities within the thorax, abdomen or pelvis and no cause of symptoms was identified. After being discharged, he re-presented 2 days later with syncopal episodes, abdominal pain and a significant drop in haemoglobin levels. This time, a CT mesenteric angiogram showed two hepatic artery pseudoaneurysms and a large haemoperitoneum. Following a hepatic artery embolisation, a workup showed that the likely cause of the pseudoaneurysms was a rare first presentation of polyarteritis nodosa. This case highlights the importance of considering the possibility of an aneurysmal rupture, especially when common causes of an acute abdomen have been excluded, and not relying on previous negative investigations to exclude pathology, as the outcomes can be detrimental.
Topics: Humans; Polyarteritis Nodosa; Aneurysm, False; Male; Hepatic Artery; Aged; Embolization, Therapeutic; Aneurysm, Ruptured; Computed Tomography Angiography; Rupture, Spontaneous; Hemoperitoneum; Abdominal Pain
PubMed: 38937262
DOI: 10.1136/bcr-2023-257411 -
Asian Journal of Surgery Jun 2024
PubMed: 38937234
DOI: 10.1016/j.asjsur.2024.06.023 -
Ophthalmology. Retina Jun 2024Describe visual function and retinal features of female carriers of choroideremia (CHM), using multimodal imaging and microperimetry.
PURPOSE
Describe visual function and retinal features of female carriers of choroideremia (CHM), using multimodal imaging and microperimetry.
DESIGN
Cross-sectional cohort study PARTICIPANTS AND CONTROLS: CHM carriers seen in Australia (Melbourne or Perth) or United Kingdom (Oxford or Cambridge) between 2012 and 2023. Healthy age-matched controls seen in Melbourne, Australia, between 2022 and 2023.
METHODS
Participants had visual acuity, fundus-tracked microperimetry, optical coherence tomography (OCT), and fundus autofluorescence (FAF) imaging performed. CHM carriers were either genetically and/or clinically confirmed (i.e., obligate carriers). CHM carriers were grouped according to their retinal phenotype and compared to healthy controls. Statistical analyses were performed on StataBE (v18.0).
MAIN OUTCOME MEASURES
Best-corrected visual acuity (BCVA), low-luminance visual acuity (LLVA), average retinal sensitivity, volume of macular hill of vision (HoV), inner retinal thickness (IRT), and photoreceptor complex (PRC) thickness.
RESULTS
Eighty-six eyes of 43 CHM carriers and 60 eyes of 30 healthy controls were examined using multimodal imaging and microperimetry. Median age was 54 and 48.5 years for CHM carriers and controls, respectively (p=0.18). Most CHM carriers (86%) were genetically confirmed. CHM carriers and controls had strong inter-eye correlation between eyes for BCVA and average retinal sensitivity (p<0.001). LLVA and macular HoV tests were sensitive tests to detect changes in CHM carriers with mild phenotypes (i.e., fine and coarse). CHM carriers with geographic and/or male pattern phenotypes had reduced BCVA, LLVA, retinal sensitivity, and retinal thinning, compared to healthy controls. Retinal thickening of the inner retina was observed in the central 1 degree, despite generalised thinning of the PRC in the central 7 degrees, indicating retinal remodelling in CHM carriers, compared to controls. There were no genotype-phenotype correlations observed.
CONCLUSIONS
Female carriers of CHM with severe retinal phenotypes (i.e., geographic or male pattern) have significantly decreased visual function and retinal structural changes, when compared to age-matched controls and those carriers with milder phenotypes. LLVA and volumetric measures of the macular HoV were found to be the most sensitive functional tests to detect milder retinal disease (fine and coarse phenotypes) in CHM carriers.
PubMed: 38936773
DOI: 10.1016/j.oret.2024.06.011 -
Journal of Biomedical Informatics Jun 2024Comprehensive analysis of histopathology images and transcriptomics data enables the identification of candidate biomarkers and multimodal association patterns. Most...
OBJECTIVE
Comprehensive analysis of histopathology images and transcriptomics data enables the identification of candidate biomarkers and multimodal association patterns. Most existing multimodal data association studies are derived from extensions of the joint nonnegative matrix factorization model for identifying complex data associations, which can make full use of clinical prior information. However, the raw data were usually taken as the input without considering the underlying complex multi-subspace structure, influencing the subsequent integration analysis results.
METHODS
This study proposed a deep-self reconstructed joint nonnegative matrix factorization (DSRJNMF) model to use self-expressive properties to reconstruct the raw data to characterize the similarity structure associated with clinical labels. Then, the sparsity, orthogonality, and regularization constraints constructed from prior information are added to the DSRJNMF model to determine the sparse set of biologically relevant features across modalities.
RESULTS
The algorithm has been applied to identify the imaging genetic association of triple negative breast cancer (TNBC). Multilevel experimental results demonstrate that the proposed algorithm better estimates potential associations between pathological image features and miRNA-gene and identifies consistent multimodal imaging genetic biomarkers to guide the interpretation of TNBC.
CONCLUSION
The propose method provides a novel idea of data association analysis oriented to complex diseases.
PubMed: 38936566
DOI: 10.1016/j.jbi.2024.104684 -
The Lancet. Oncology Jul 2024Extranodal extension of tumour on histopathology is known to be a negative prognostic factor in head and neck cancer. Compelling evidence suggests that extranodal... (Review)
Review
Criteria for the diagnosis of extranodal extension detected on radiological imaging in head and neck cancer: Head and Neck Cancer International Group consensus recommendations.
Extranodal extension of tumour on histopathology is known to be a negative prognostic factor in head and neck cancer. Compelling evidence suggests that extranodal extension detected on radiological imaging is also a negative prognostic factor. Furthermore, if imaging detected extranodal extension could be identified reliably before the start of treatment, it could be used to guide treatment selection, as patients might be better managed with non-surgical approaches to avoid the toxicity and cost of trimodality therapy (surgery, chemotherapy, and radiotherapy together). There are many aspects of imaging detected extranodal extension that remain unresolved or are without consensus, such as the criteria to best diagnose them and the associated terminology. The Head and Neck Cancer International Group conducted a five-round modified Delphi process with a group of 18 international radiology experts, representing 14 national clinical research groups. We generated consensus recommendations on the terminology and diagnostic criteria for imaging detected extranodal extension to harmonise clinical practice and research. These recommendations have been endorsed by 19 national and international organisations, representing 34 countries. We propose a new classification system to aid diagnosis, which was supported by most of the participating experts over existing systems, and which will require validation in the future. Additionally, we have created an online educational resource for grading imaging detected extranodal extensions.
Topics: Humans; Head and Neck Neoplasms; Consensus; Extranodal Extension; Delphi Technique; Terminology as Topic; Prognosis
PubMed: 38936388
DOI: 10.1016/S1470-2045(24)00066-4 -
American Society of Clinical Oncology... Jun 2024The landscape of prostate cancer care has rapidly evolved. We have transitioned from the use of conventional imaging, radical surgeries, and single-agent androgen... (Review)
Review
The landscape of prostate cancer care has rapidly evolved. We have transitioned from the use of conventional imaging, radical surgeries, and single-agent androgen deprivation therapy to an era of advanced imaging, precision diagnostics, genomics, and targeted treatment options. Concurrently, the emergence of large language models (LLMs) has dramatically transformed the paradigm for artificial intelligence (AI). This convergence of advancements in prostate cancer management and AI provides a compelling rationale to comprehensively review the current state of AI applications in prostate cancer care. Here, we review the advancements in AI-driven applications across the continuum of the journey of a patient with prostate cancer from early interception to survivorship care. We subsequently discuss the role of AI in prostate cancer drug discovery, clinical trials, and clinical practice guidelines. In the localized disease setting, deep learning models demonstrated impressive performance in detecting and grading prostate cancer using imaging and pathology data. For biochemically recurrent diseases, machine learning approaches are being tested for improved risk stratification and treatment decisions. In advanced prostate cancer, deep learning can potentially improve prognostication and assist in clinical decision making. Furthermore, LLMs are poised to revolutionize information summarization and extraction, clinical trial design and operations, drug development, evidence synthesis, and clinical practice guidelines. Synergistic integration of multimodal data integration and human-AI integration are emerging as a key strategy to unlock the full potential of AI in prostate cancer care.
Topics: Humans; Male; Prostatic Neoplasms; Artificial Intelligence
PubMed: 38935882
DOI: 10.1200/EDBK_438516 -
International Journal of Surgery... Jun 2024To develop a multimodal learning application system that integrates electronic medical records (EMR) and hysteroscopic images for reproductive outcome prediction and...
Multimodal learning system integrating electronic medical records and hysteroscopic images for reproductive outcome prediction and risk stratification of endometrial injury: a multicenter diagnostic study.
OBJECTIVE
To develop a multimodal learning application system that integrates electronic medical records (EMR) and hysteroscopic images for reproductive outcome prediction and risk stratification of patients with intrauterine adhesions (IUAs) resulting from endometrial injuries.
MATERIALS AND METHODS
EMR and 5014 revisited hysteroscopic images of 753 post hysteroscopic adhesiolysis patients from the multicenter IUA database we established were randomly allocated to training, validation, and test datasets. The respective datasets were used for model development, tuning, and testing of the multimodal learning application. MobilenetV3 was employed for image feature extraction, and XGBoost for EMR and image feature ensemble learning. The performance of the application was compared against the single-modal approaches (EMR or hysteroscopic images), DeepSurv and ElasticNet models, along with the clinical scoring systems. The primary outcome was the 1-year conception prediction accuracy, and the secondary outcome was the assisted reproductive technology (ART) benefit ratio after risk stratification.
RESULTS
The multimodal learning system exhibited superior performance in predicting conception within 1-year, achieving areas under the curves of 0.967 (95% CI: 0.950-0.985), 0.936 (95% CI: 0.883-0.989), and 0.965 (95% CI: 0.935-0.994) in the training, validation, and test datasets, respectively, surpassing single-modal approaches, other models and clinical scoring systems (all P<0.05). The application of the model operated seamlessly on the hysteroscopic platform, with an average analysis time of 3.7±0.8 s per patient. By employing the application's conception probability-based risk stratification, mid-high-risk patients demonstrated a significant ART benefit (odds ratio=6, 95% CI: 1.27-27.8, P=0.02), while low-risk patients exhibited good natural conception potential, with no significant increase in conception rates from ART treatment (P=1).
CONCLUSIONS
The multimodal learning system using hysteroscopic images and EMR demonstrates promise in accurately predicting the natural conception of patients with IUAs and providing effective postoperative stratification, potentially contributing to ART triage after IUA procedures.
Topics: Humans; Female; Hysteroscopy; Adult; Electronic Health Records; Risk Assessment; Endometrium; Tissue Adhesions; Pregnancy; Uterine Diseases; Reproductive Techniques, Assisted
PubMed: 38935827
DOI: 10.1097/JS9.0000000000001241 -
Journal of Behavioral Addictions Jun 2024Changes in brain structural connections appear to be important in the pathophysiology of substance use disorders, but their role in behavioral addictions, such as...
BACKGROUND
Changes in brain structural connections appear to be important in the pathophysiology of substance use disorders, but their role in behavioral addictions, such as gambling disorder (GD), is unclear. GD also offers a model to study addiction mechanisms without pharmacological confounding factors. Here, we used multimodal MRI data to examine the integrity of white matter connections in individuals with GD. We hypothesized that the affected areas would be in the fronto-striatal-thalamic circuit.
METHODS
Twenty individuals with GD (mean age: 64 years, GD duration: 15.7 years) and 40 age- and sex-matched healthy controls (HCs) underwent detailed clinical examinations together with brain 3T MRI scans (T1, T2, FLAIR and DWI). White matter (WM) analysis involved fractional anisotropy and lesion load, while gray matter (GM) analysis included voxel- and surface-based morphometry. These measures were compared between groups, and correlations with GD-related behavioral characteristics were examined.
RESULTS
Individuals with GD showed reduced WM integrity in the left and right frontal parts of the corona radiata and corpus callosum (pFWE < 0.05). WM gambling symptom severity (SOGS score) was negatively associated to WM integrity in these areas within the left hemisphere (p < 0.05). Individuals with GD also exhibited higher WM lesion load in the left anterior corona radiata (pFWE < 0.05). GM volume in the left thalamus and GM thickness in the left orbitofrontal cortex were reduced in the GD group (pFWE < 0.05).
CONCLUSIONS
Similar to substance addictions, the fronto-striatal-thalamic circuit is also affected in GD, suggesting that this circuitry may have a crucial role in addictions, independent of pharmacological substances.
Topics: Humans; Male; Middle Aged; Gray Matter; White Matter; Gambling; Female; Magnetic Resonance Imaging; Aged; Multimodal Imaging; Frontal Lobe; Thalamus
PubMed: 38935433
DOI: 10.1556/2006.2024.00031