-
Dental Clinics of North America Jan 2020Oral potentially malignant disorders (OPMDs) are precursor lesions that may undergo malignant transformation to oral cancer. These lesions most commonly present... (Review)
Review
Oral potentially malignant disorders (OPMDs) are precursor lesions that may undergo malignant transformation to oral cancer. These lesions most commonly present clinically as white patches (leukoplakia). However, they may also be red (erythroplakia), or red and white (erythroleukoplakia). There are many risk factors associated with the development of an OPMD, and with the risk of malignant transformation of the lesion. A biopsy with subsequent microscopic examination from the lesional tissue is necessary in identification of OPMD. This article reviews the clinical appearance of OPMDs, associated risk factors, diagnosis and histologic appearance, and treatment.
Topics: Erythroplasia; Humans; Leukoplakia, Oral; Mouth Diseases; Mouth Neoplasms; Precancerous Conditions
PubMed: 31735231
DOI: 10.1016/j.cden.2019.08.004 -
Current Opinion in Cardiology Nov 2020Management of patients with coronary artery disease (CAD) has been based on identification of a coronary obstruction causing ischemia and performing a revascularization... (Review)
Review
PURPOSE OF REVIEW
Management of patients with coronary artery disease (CAD) has been based on identification of a coronary obstruction causing ischemia and performing a revascularization procedure to reduce that ischemia, with the goal of thereby preventing subsequent major adverse cardiac events (MACEs) in that vascular territory. Recent investigations demonstrate that preemptive percutaneous coronary intervention (PCI) of nonculprit coronary lesions (NCLs) that may not cause ischemia in patients with ST-segment elevation myocardial infarction (STEMI) reduces MACE. In this review, we focus on preemptive PCI, discuss its mechanistic benefits and speculate on its potential value for other coronary syndromes.
RECENT FINDINGS
The COMPLETE trial in STEMI patients treated with primary PCI demonstrated that preemptive PCI of NCL obstructions, which may not cause ischemia, but often exhibit high-risk OCT plaque characteristics, reduced cardiovascular death or nonfatal myocardial infarction. Reduction in MACE from preemptive PCI of NCL was similar for lesions confirmed to cause ischemia (fractional flow reserve <0.80) and for lesions that were only visually assessed to have luminal obstruction at least 70%.The ISCHEMIA trial in patients with stable CAD and moderate/severe ischemia demonstrated that MACE risk increased progressively with more extensive atherosclerosis, but that performing PCI of ischemia-producing lesions did not reduce MACE. Adverse cardiac events likely originated in high-risk plaque areas not treated with PCI.
SUMMARY
In STEMI patients, preemptive PCI of high-risk NCL that may not cause ischemia improves long-term MACE. In stable CAD patients, MACE increases as the atherosclerotic burden increases, but PCI of the ischemia-producing lesion itself does not improve outcomes compared with optimal medical therapy. Adverse events likely originate in high-risk plaque areas that are distinct from ischemia-producing obstructions. Identification of highest-risk atherosclerotic lesions responsible for future MACE may provide an opportunity for preemptive PCI in patients with a variety of coronary syndromes.
Topics: Coronary Artery Disease; Fractional Flow Reserve, Myocardial; Humans; Percutaneous Coronary Intervention; ST Elevation Myocardial Infarction; Treatment Outcome
PubMed: 32852346
DOI: 10.1097/HCO.0000000000000789 -
Frontiers in Plant Science 2023Diseases have a great impact on the quality and yield of strawberries, an accurate and timely field disease identification method is urgently needed. However,...
Diseases have a great impact on the quality and yield of strawberries, an accurate and timely field disease identification method is urgently needed. However, identifying diseases of strawberries in field is challenging due to the complex background interference and subtle inter-class differences. A feasible method to address the challenges is to segment strawberry lesions from the background and learn fine-grained features of the lesions. Following this idea, we present a novel Class-Attention-based Lesion Proposal Convolutional Neural Network (CALP-CNN), which utilizes a class response map to locate the main lesion object and propose discriminative lesion details. Specifically, the CALP-CNN firstly locates the main lesion object from the complex background through a class object location module (COLM) and then applies a lesion part proposal module (LPPM) to propose the discriminative lesion details. With a cascade architecture, the CALP-CNN can simultaneously address the interference from the complex background and the misclassification of similar diseases. A series of experiments on a self-built dataset of field strawberry diseases is conducted to testify the effectiveness of the proposed CALP-CNN. The classification results of the CALP-CNN are 92.56%, 92.55%, 91.80% and 91.96% on the metrics of accuracy, precision, recall and F1-score, respectively. Compared with six state-of-the-art attention-based fine-grained image recognition methods, the CALP-CNN achieves 6.52% higher (on F1-score) than the sub-optimal baseline MMAL-Net, suggesting that the proposed methods are effective in identifying strawberry diseases in the field.
PubMed: 36844049
DOI: 10.3389/fpls.2023.1091600 -
NeuroImage Jul 2008In this paper, we propose a new automated procedure for lesion identification from single images based on the detection of outlier voxels. We demonstrate the utility of...
In this paper, we propose a new automated procedure for lesion identification from single images based on the detection of outlier voxels. We demonstrate the utility of this procedure using artificial and real lesions. The scheme rests on two innovations: First, we augment the generative model used for combined segmentation and normalization of images, with an empirical prior for an atypical tissue class, which can be optimised iteratively. Second, we adopt a fuzzy clustering procedure to identify outlier voxels in normalised gray and white matter segments. These two advances suppress misclassification of voxels and restrict lesion identification to gray/white matter lesions respectively. Our analyses show a high sensitivity for detecting and delineating brain lesions with different sizes, locations, and textures. Our approach has important implications for the generation of lesion overlap maps of a given population and the assessment of lesion-deficit mappings. From a clinical perspective, our method should help to compute the total volume of lesion or to trace precisely lesion boundaries that might be pertinent for surgical or diagnostic purposes.
Topics: Algorithms; Brain; Brain Diseases; Brain Edema; Cerebral Ventricles; Data Interpretation, Statistical; Fuzzy Logic; Humans; Image Processing, Computer-Assisted; Models, Statistical; ROC Curve
PubMed: 18482850
DOI: 10.1016/j.neuroimage.2008.03.028 -
Bioengineering (Basel, Switzerland) Sep 2023Accurate identification of lesions and their use across different medical institutions are the foundation and key to the clinical application of automatic diabetic...
Accurate identification of lesions and their use across different medical institutions are the foundation and key to the clinical application of automatic diabetic retinopathy (DR) detection. Existing detection or segmentation methods can achieve acceptable results in DR lesion identification, but they strongly rely on a large number of fine-grained annotations that are not easily accessible and suffer severe performance degradation in the cross-domain application. In this paper, we propose a cross-domain weakly supervised DR lesion identification method using only easily accessible coarse-grained lesion attribute labels. We first propose the novel lesion-patch multiple instance learning method (LpMIL), which leverages the lesion attribute label for patch-level supervision to complete weakly supervised lesion identification. Then, we design a semantic constraint adaptation method (LpSCA) that improves the lesion identification performance of our model in different domains with semantic constraint loss. Finally, we perform secondary annotation on the open-source dataset EyePACS, to obtain the largest fine-grained annotated dataset EyePACS-pixel, and validate the performance of our model on it. Extensive experimental results on the public dataset FGADR and our EyePACS-pixel demonstrate that compared with the existing detection and segmentation methods, the proposed method can identify lesions accurately and comprehensively, and obtain competitive results using only coarse-grained annotations.
PubMed: 37760202
DOI: 10.3390/bioengineering10091100 -
ACS Nano Sep 2023Atherosclerosis is a common pathology present in many cardiovascular diseases. Although the current therapies (including statins and inhibitors of the serine protease...
Atherosclerosis is a common pathology present in many cardiovascular diseases. Although the current therapies (including statins and inhibitors of the serine protease PCSK9) can effectively reduce low-density lipoprotein (LDL) cholesterol levels to guideline-recommended levels, major adverse cardiovascular events still occur frequently. Indeed, the subendothelial retention of lipoproteins in the artery wall triggers multiple events of inflammation in macrophages and is a major contributor to the pathological progression of atherosclerosis. It has been gradually recognized that modulating inflammation is, therefore, an attractive avenue to forestall and treat atherosclerosis and its complications. Unfortunately, challenges with specificity and efficacy in managing plaque inflammation have hindered progress in atherosclerosis treatment. Herein, we report an NP-mediated mRNA therapeutic approach to target atherosclerotic lesional macrophages, modulating inflammation in advanced atherosclerotic lesions for the treatment of atherosclerosis. We demonstrated that the targeted NPs containing mRNA colocalized with M2-like macrophages and induced IL-10 production in atherosclerotic plaques following intravenous administration to Western diet (WD)-fed mice. Additionally, the lesions showed a significantly alleviated inflammatory response, as evidenced by reduced oxidative stress and macrophage apoptosis, resulting in decreased lipid deposition, diminished necrotic areas, and increased fiber cap thickness. These results demonstrate the successful delivery of mRNA therapeutics to macrophage-enriched plaques in a preclinical model of advanced atherosclerosis, showing that this targeted NP inflammation management approach has great potential for translation into a wide range of clinical applications.
Topics: Animals; Mice; Plaque, Atherosclerotic; Proprotein Convertase 9; Interleukin-10; Atherosclerosis; Inflammation
PubMed: 37669404
DOI: 10.1021/acsnano.3c00958 -
Nature Communications Aug 2023The limited signal of long-wavelength near-infrared-II (NIR-II, 900-1880 nm) fluorophores and the strong background caused by the diffused photons make high-contrast...
The limited signal of long-wavelength near-infrared-II (NIR-II, 900-1880 nm) fluorophores and the strong background caused by the diffused photons make high-contrast fluorescence imaging in vivo with deep tissue disturbed still challenging. Here, we develop NIR-II fluorescent small molecules with aggregation-induced emission properties, high brightness, and maximal emission beyond 1200 nm by enhancing electron-donating ability and reducing the donor-acceptor (D-A) distance, to complement the scarce bright long-wavelength emissive organic dyes. The convincing single-crystal evidence of D-A-D molecular structure reveals the strong inhibition of the π-π stacking with ultralong molecular packing distance exceeding 8 Å. The delicately-designed nanofluorophores with bright fluorescent signals extending to 1900 nm match the background-suppressed imaging window, enabling the signal-to-background ratio of the tissue image to reach over 100 with the tissue thickness of ~4-6 mm. In addition, the intraluminal lesions with strong negatively stained can be identified with almost zero background. This method can provide new avenues for future long-wavelength NIR-II molecular design and biomedical imaging of deep and highly scattering tissues.
Topics: Fluorescent Dyes; Bandages; Diffusion; Electrons; Inhibition, Psychological; Ionophores
PubMed: 37596326
DOI: 10.1038/s41467-023-40728-6 -
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 -
Journal Der Deutschen Dermatologischen... Jan 2023Hidradenitis suppurativa (HS) differs widely with respect to its clinical presentation. Literature imposes different phenotypes potentially implying different treatment...
BACKGROUND AND OBJECTIVES
Hidradenitis suppurativa (HS) differs widely with respect to its clinical presentation. Literature imposes different phenotypes potentially implying different treatment modalities. The aim of this study is to develop a validated scheme that enables HS patients to identify their own lesion types.
PATIENTS AND METHODS
The developed schemes for physicians and patients were implemented in a specific software. Upon patient consent, the physician used the software to document the lesions identified. Patients subsequently logged into the patient-version of the software from the convenience of their home and selected the lesions they identified on themselves. Afterwards the correlation between professionals and patients was tested.
RESULTS
For seven lesion types, correlation coefficients were statistically significant. A large/strong correlation between patients and physicians was found for the draining fistulas (0.59) and double-ended comedones (0.50). For five other lesion types, correlation was medium/moderate, namely the inflammatory nodule (0.37), abscess (0.30), accordion like-/ bridged scar (0.45), epidermal cyst (0.33) and pilonidal sinus (0.39).
CONCLUSIONS
HS-patients demonstrate high willingness to share their experiences and data. Therefore, a self-assessment scheme, as the developed LISAI, can be a valuable tool to enrich patient surveys with the identification of lesion types, for instance as a basis for phenotyping.
Topics: Humans; Hidradenitis Suppurativa; Acne Vulgaris; Abscess; Cicatrix; Epidermal Cyst
PubMed: 36721936
DOI: 10.1111/ddg.14926 -
Physics in Medicine and Biology Dec 2021Lesions of COVID-19 can be clearly visualized using chest CT images, and hence provide valuable evidence for clinicians when making a diagnosis. However, due to the...
Lesions of COVID-19 can be clearly visualized using chest CT images, and hence provide valuable evidence for clinicians when making a diagnosis. However, due to the variety of COVID-19 lesions and the complexity of the manual delineation procedure, automatic analysis of lesions with unknown and diverse types from a CT image remains a challenging task. In this paper we propose a weakly-supervised framework for this task requiring only a series of normal and abnormal CT images without the need for annotations of the specific locations and types of lesions.A deep learning-based diagnosis branch is employed for classification of the CT image and then a lesion identification branch is leveraged to capture multiple types of lesions.Our framework is verified on publicly available datasets and CT data collected from 13 patients of the First Affiliated Hospital of Shantou University Medical College, China. The results show that the proposed framework can achieve state-of-the-art diagnosis prediction, and the extracted lesion features are capable of distinguishing between lesions showing ground glass opacity and consolidation.The proposed approach integrates COVID-19 positive diagnosis and lesion analysis into a unified framework without extra pixel-wise supervision. Further exploration also demonstrates that this framework has the potential to discover lesion types that have not been reported and can potentially be generalized to lesion detection of other chest-based diseases.
Topics: COVID-19; Humans; Lung; SARS-CoV-2; Thorax; Tomography, X-Ray Computed
PubMed: 34905733
DOI: 10.1088/1361-6560/ac4316