-
International Journal of Ophthalmology 2021To assist with retinal vein occlusion (RVO) screening, artificial intelligence (AI) methods based on deep learning (DL) have been developed to alleviate the pressure...
AIM
To assist with retinal vein occlusion (RVO) screening, artificial intelligence (AI) methods based on deep learning (DL) have been developed to alleviate the pressure experienced by ophthalmologists and discover and treat RVO as early as possible.
METHODS
A total of 8600 color fundus photographs (CFPs) were included for training, validation, and testing of disease recognition models and lesion segmentation models. Four disease recognition and four lesion segmentation models were established and compared. Finally, one disease recognition model and one lesion segmentation model were selected as superior. Additionally, 224 CFPs from 130 patients were included as an external test set to determine the abilities of the two selected models.
RESULTS
Using the Inception-v3 model for disease identification, the mean sensitivity, specificity, and F1 for the three disease types and normal CFPs were 0.93, 0.99, and 0.95, respectively, and the mean area under the curve (AUC) was 0.99. Using the DeepLab-v3 model for lesion segmentation, the mean sensitivity, specificity, and F1 for four lesion types (abnormally dilated and tortuous blood vessels, cotton-wool spots, flame-shaped hemorrhages, and hard exudates) were 0.74, 0.97, and 0.83, respectively.
CONCLUSION
DL models show good performance when recognizing RVO and identifying lesions using CFPs. Because of the increasing number of RVO patients and increasing demand for trained ophthalmologists, DL models will be helpful for diagnosing RVO early in life and reducing vision impairment.
PubMed: 34926205
DOI: 10.18240/ijo.2021.12.13 -
Journal of the American College of... Sep 2019Concepts of atherogenesis have evolved considerably with time. Early animal experiments showed that a cholesterol-rich diet could induce fatty lesion formation in... (Review)
Review
Concepts of atherogenesis have evolved considerably with time. Early animal experiments showed that a cholesterol-rich diet could induce fatty lesion formation in arteries. The elucidation of lipoprotein metabolism ultimately led to demonstrating the clinical benefits of lipid lowering. The view of atheromata as bland accumulations of smooth muscle cells that elaborated an extracellular matrix that could entrap lipids then expanded to embrace inflammation as providing pathways that could link risk factors to atherogenesis. The characterization of leukocyte adhesion molecules and their control by proinflammatory cytokines, the ability of chemokines to recruit leukocytes, and the identification of inflammatory cell subtypes in lesions spurred the unraveling of innate and adaptive immune pathways that contribute to atherosclerosis and its thrombotic complications. Such pathophysiologic insights have led to the identification of biomarkers that can define categories of risk and direct therapies and to the development of new treatments.
Topics: Atherosclerosis; Humans; Inflammation; Lipid Metabolism; Thrombosis
PubMed: 31537270
DOI: 10.1016/j.jacc.2019.07.061 -
Frontiers in Medicine 2023The management of acne requires the consideration of its severity; however, a universally adopted evaluation system for clinical practice is lacking. Artificial...
BACKGROUND
The management of acne requires the consideration of its severity; however, a universally adopted evaluation system for clinical practice is lacking. Artificial intelligence (AI) evaluation systems hold the promise of enhancing the efficiency and reproducibility of assessments. Artificial intelligence (AI) evaluation systems offer the potential to enhance the efficiency and reproducibility of assessments in this domain. While the identification of skin lesions represents a crucial component of acne evaluation, existing AI systems often overlook lesion identification or fail to integrate it with severity assessment. This study aimed to develop an AI-powered acne grading system and compare its performance with physician image-based scoring.
METHODS
A total of 1,501 acne patients were included in the study, and standardized pictures were obtained using the VISIA system. The initial evaluation involved 40 stratified sampled frontal photos assessed by seven dermatologists. Subsequently, the three doctors with the highest inter-rater agreement annotated the remaining 1,461 images, which served as the dataset for the development of the AI system. The dataset was randomly divided into two groups: 276 images were allocated for training the acne lesion identification platform, and 1,185 images were used to assess the severity of acne.
RESULTS
The average precision of our model for skin lesion identification was 0.507 and the average recall was 0.775. The AI severity grading system achieved good agreement with the true label (linear weighted kappa = 0.652). After integrating the lesion identification results into the severity assessment with fixed weights and learnable weights, the kappa rose to 0.737 and 0.696, respectively, and the entire evaluation on a Linux workstation with a Tesla K40m GPU took less than 0.1s per picture.
CONCLUSION
This study developed a system that detects various types of acne lesions and correlates them well with acne severity grading, and the good accuracy and efficiency make this approach potentially an effective clinical decision support tool.
PubMed: 37869155
DOI: 10.3389/fmed.2023.1255704 -
World Journal of Gastroenterology Sep 2020There are few reports on major gastrointestinal (GI) bleeding among patients receiving an antithrombotic.
BACKGROUND
There are few reports on major gastrointestinal (GI) bleeding among patients receiving an antithrombotic.
AIM
To describe clinical characteristics, bleeding locations, management and in-hospital mortality related to these events.
METHODS
Over a three-year period, we prospectively identified 1080 consecutive adult patients admitted in two tertiary care hospitals between January 1, 2013 and December 31, 2015 for major GI bleeding while receiving an antithrombotic. The bleeding events were medically validated. Clinical characteristics, causative lesions, management and fatalities were described. The distribution of antithrombotics prescribed was compared across the bleeding lesions identified.
RESULTS
Of 576 patients had symptoms of upper GI bleeding and 504 symptoms of lower GI bleeding. No cause was identified for 383 (35.5%) patients. Gastro-duodenal ulcer was the first causative lesion in the upper tract (209 out of 408) and colonic diverticulum the first causative lesion in the lower tract (120 out of 289). There was a larger proportion of direct oral anticoagulant use among patients with lower GI than among those with upper GI lesion locations ( = 0.03). There was an independent association between gastro-duodenal ulcer and antithrombotic use ( = 0.03), taking account of confounders and proton pump inhibitor co-prescription. Pair wise comparisons pointed to a difference between vitamin K antagonist, direct oral anticoagulants, and antiplatelet agents in monotherapy dual antiplatelet agents.
CONCLUSION
We showed a higher rate of bleeding lesion identification and suggested a different pattern of antithrombotic exposure between upper and lower GI lesion locations and between gastro-duodenal ulcer and other identified upper GI causes of bleeding. Management was similar across antithrombotics and in-hospital mortality was low (5.95%).
Topics: Adult; Anticoagulants; Fibrinolytic Agents; Gastrointestinal Hemorrhage; Humans; Peptic Ulcer; Platelet Aggregation Inhibitors
PubMed: 33024397
DOI: 10.3748/wjg.v26.i36.5463 -
MSystems Aug 2021Bovine digital dermatitis (DD) is a skin disorder that is a significant cause of infectious lameness in cattle around the world. However, very little is known about the...
Bovine digital dermatitis (DD) is a skin disorder that is a significant cause of infectious lameness in cattle around the world. However, very little is known about the etiopathogenesis of the disease and the microbiota associated with DD in beef cattle. In this study, we provide a comprehensive characterization of DD and healthy skin microbiota of feedlot beef cattle. We also developed and validated a novel multiplex quantitative PCR (qPCR) assay to quantify the distribution of DD-associated bacterial species across DD lesion stages. We determined the DD-associated microbiota with deep amplicon sequencing of the V3-V4 hypervariable region of the 16S rRNA gene, followed by the application of novel and existing qPCR assays to quantify species distributions of Treponema, , , and across lesion stages. Deep amplicon sequencing revealed that Treponema, , , and were associated with DD lesions. Culturing of DD biopsy specimens identified Porphyromonas levii, Bacteroides pyogenes, and two spp. within DD lesions. Using species-specific qPCR on DD lesion DNA, we identified P. levii in 100% of active lesion stages. Early-stage lesions were particularly associated with Treponema medium, T. phagedenis, and . This study suggests a core DD microbial group consisting of species of Treponema, , , and , which may be closely tied with the etiopathogenesis of DD. Further characterizations of these species and spp. are necessary to understand the microbial factors involved in DD pathogenesis, which will help elucidate DD etiology and facilitate more targeted and effective mitigation and treatment strategies. Previous work, primarily in dairy cattle, has identified various taxa associated with digital dermatitis (DD) lesions. However, there is a significant gap in our knowledge of DD microbiology in beef cattle. In addition, characterization of bacteria at the species level in DD lesions is limited. In this study, we provide a framework for the accurate and reproducible quantification of major DD-associated bacterial species from DNA samples. Our findings support DD as a polymicrobial infection, and we identified a variety of bacterial species spanning multiple genera that are consistently associated with DD lesions. The DD-associated microbiota identified in this study may be capable of inducing the formation and progression of DD lesions and thus should be primary targets in future DD pathogenesis studies.
PubMed: 34313462
DOI: 10.1128/mSystems.00708-21 -
Advances in Clinical and Experimental... Oct 2021The assessment of functional severity of moderate coronary stenoses is challenging. Coronary angiography remains the standard technique for diagnosis, although, due to... (Review)
Review
The assessment of functional severity of moderate coronary stenoses is challenging. Coronary angiography remains the standard technique for diagnosis, although, due to its limitations, it is frequently insufficient to detect relevant myocardial ischemia. Fractional flow reserve (FFR) is defined as the ratio between the mean hyperemic coronary artery pressure distal to the lesion and mean pressure in the aorta. The FFR measurement is currently supported by guidelines to evaluate the hemodynamic significance of lesions. Proper identification of patients that have the potential to benefit from revascularization is crucial. Based on already published literature, we focus on the long-term follow-up of patients with FFR-driven treatment. We also provide a review of specific clinical cases such as borderline FFR values, comorbidities or lesions in anatomical risk locations, in which interpretation can be challenging during the physiological assessment. The aim of this paper is to provide an overview of the evidence of FFR implementation in daily clinical practice and determine issues that raise doubts.
Topics: Coronary Angiography; Coronary Artery Disease; Coronary Stenosis; Fractional Flow Reserve, Myocardial; Hemodynamics; Humans; Severity of Illness Index
PubMed: 34510843
DOI: 10.17219/acem/138862 -
Journal of Lower Genital Tract Disease Jul 2022The aim of the study was to evaluate clinicopathologic features of cases demonstrating an acanthotic tissue reaction not clearly consistent with psoriasis, lichen...
OBJECTIVE
The aim of the study was to evaluate clinicopathologic features of cases demonstrating an acanthotic tissue reaction not clearly consistent with psoriasis, lichen simplex chronicus, mycosis, or condyloma.
MATERIALS AND METHODS
This is a retrospective pathologic case series of biopsies reported as "benign acanthotic lesion" and "acanthotic tissue reaction" that lacked a clear diagnosis on expert review. Cases with nuclear atypia were excluded. Clinical and histopathologic data were collected, immunohistochemistry for p16 and p53 were obtained, and molecular testing for 28 common anogenital human papillomavirus (HPV) genotypes was undertaken.
RESULTS
There were 17 cases with a median age of 47 years. Unilaterality and medial location were clinical reasons for diagnostic difficulty. Histopathologic uncertainty often related to lack of papillary dermal fibrosis to support lichen simplex chronicus or psoriasiform lesions without parakeratosis, subcorneal pustules, and/or mycotic elements. Firm pathologic diagnoses were not possible, but 3 groups emerged: favoring chronic dermatitis, favoring psoriasis, and unusual morphologies. p16 results were negative or nonblock positive while p53 was normal or basal overexpressed. Human papillomavirus testing was negative in 12, low positive for HPV 16 in 1, unassessable in 3, and not requested in 1.
CONCLUSIONS
There is a group of acanthotic tissue reactions that cannot be classified with standard histopathologic assessment. Further clinicopathologic research into unilateral acanthotic lesions may provide insight into separation of psoriasis and mycosis when organisms are absent. Once nuclear atypia is excluded, immunohistochemistry for p16 and p53 and HPV molecular testing do not assist in diagnostic identification.
Topics: Alphapapillomavirus; Female; Humans; Middle Aged; Neurodermatitis; Papillomaviridae; Papillomavirus Infections; Psoriasis; Retrospective Studies; Tumor Suppressor Protein p53; Vulvar Neoplasms
PubMed: 35543596
DOI: 10.1097/LGT.0000000000000681 -
Scientific Reports Mar 2023Identification of potential therapeutic targets and biomarkers indicative of burden of early atherosclerosis that occur prior to advancement to life-threatening unstable...
Identification of potential therapeutic targets and biomarkers indicative of burden of early atherosclerosis that occur prior to advancement to life-threatening unstable plaques is the key to eradication of CAD prevalence and incidences. We challenged 16 baboons with a high cholesterol, high fat diet for 2 years and evaluated early-stage atherosclerotic lesions (fatty streaks, FS, and fibrous plaques, FP) in formalin-fixed common iliac arteries (CIA). We used small RNA sequencing to identify expressed miRNAs in CIA and in baseline blood samples of the same animals. We found 412 expressed miRNAs in CIA and 356 in blood samples. Eight miRNAs (miR-7975, -486-5p, -451a, -191-5p, -148a-3p, -17-5p, -378c, and -144-3p) were differentially expressed between paired fatty streak lesion and no-lesion sites of the tissue, and 27 miRNAs (e.g., miR-92a-3p, -5001, -342-3p, miR-28-3p, -21-5p, -221-3p, 146a-5p, and -16-5p) in fibrous plaques. The expression of 14 blood miRNAs significantly correlated with extent of lesions and the number of plaques. We identified coordinately regulated miRNA-gene networks in which miR-17-5p and miR-146a-5p are central hubs and miR-5001 and miR-7975 are potentially novel miRNAs associated with early atherosclerosis. In summary, we have identified miRNAs expressed in lesions and in blood that correlate with lesion burden and are potential therapeutic targets and biomarkers. These findings are a first step in elucidating miRNA regulated molecular mechanisms that underlie early atherosclerosis in a baboon model, enabling translation of our findings to humans.
Topics: Animals; Humans; Atherosclerosis; Aorta, Abdominal; Biomarkers; Diet, High-Fat; MicroRNAs; Papio; Plaque, Amyloid
PubMed: 36859458
DOI: 10.1038/s41598-023-29074-1 -
Indian Journal of Ophthalmology Oct 2021In this article we focus on a systematic approach to assess common orbital lesions on magnetic resonance imaging (MRI). The identification of the probable compartment or... (Review)
Review
In this article we focus on a systematic approach to assess common orbital lesions on magnetic resonance imaging (MRI). The identification of the probable compartment or structure of origin helps narrow the differential diagnosis of a lesion. Analyzing the morphology, appearance, and signal intensity on various sequences, the pattern, and degree of contrast enhancement are key to characterize lesions on MRI. Imaging features suggesting cellularity and vascularity can also be determined to help plan for biopsy or surgery of these lesions. MRI can also distinguish active from chronic disease in certain pathologies and aids in selecting appropriate medical management. MRI may thus serve as a diagnostic tool and help in guiding therapeutic strategies and posttreatment follow-up.
Topics: Contrast Media; Diagnosis, Differential; Humans; Magnetic Resonance Imaging; Orbit; Orbital Neoplasms
PubMed: 34571598
DOI: 10.4103/ijo.IJO_904_21 -
Journal of Arrhythmia Feb 2021Radiofrequency catheter ablation has become an established treatment for ventricular tachycardia. The exponential increase in procedures has provided further insights... (Review)
Review
Radiofrequency catheter ablation has become an established treatment for ventricular tachycardia. The exponential increase in procedures has provided further insights into mechanisms causing arrhythmias and identification of ablation targets with the development of new mapping strategies. Since the definition of criteria to identify myocardial dense scar, borderzone and normal myocardium, and the description of isolated late potentials, local abnormal ventricular activity and decrementing evoked potential mapping, substrate-guided ablation has progressively become the method of choice to guide procedures. Accordingly, a wide range of ablation strategies have been developed from scar homogenization to scar dechanneling or core isolation using increasingly complex and precise tools such as multipolar or omnipolar mapping catheters. Despite these advances long-term success rates for VT ablation have remained static and lower in nonischemic than ischemic heart disease because of the more patchy distribution of myocardial scar. Ablation aims to deliver an irreversible loss of cellular excitability by myocardial heating to a temperatures exceeding 50°C. Many indicators of ablation efficacy have been developed such as contact force, impedance drop, force-time integral and ablation index, mostly validated in atrial fibrillation ablation. In ventricular procedures there is limited data and ablation lesion parameters have been scarcely investigated. Since VT arrhythmia recurrence can be related to inadequate RF lesion formation, it seems reasonable to establish robust markers of ablation efficacy.
PubMed: 33664896
DOI: 10.1002/joa3.12489