[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Machine Learning in Aerodynamic Shape Optimization

Diabetic retinopathy (DR) is a common complication of long-term diabetes, affecting the human eye and potentially leading to permanent blindness. The early detection of DR is crucial for effective treatment, as symptoms often manifest in later stages. The manual grading of retinal images is time-consuming, prone to errors, and lacks patient-friendliness. In this study, we propose two deep learning (DL) architectures, a hybrid network combining VGG16 and XGBoost Classifier, and the DenseNet 121 network, for DR detection and classification. To evaluate the two DL models, we preprocessed a collection of retinal images obtained from the APTOS 2019 Blindness Detection Kaggle Dataset. This dataset exhibits an imbalanced image class distribution, which we addressed through appropriate balancing techniques. The performance of the considered models was assessed in terms of accuracy. The results showed that the hybrid network achieved an accuracy of 79.50%, while the DenseNet 121 model achieved an accuracy of 97.30%. Furthermore, a comparative analysis with existing methods utilizing the same dataset revealed the superior performance of the DenseNet 121 network. The findings of this study demonstrate the potential of DL architectures for the early detection and classification of DR. The superior performance of the DenseNet 121 model highlights its effectiveness in this domain. The implementation of such automated methods can significantly improve the efficiency and accuracy of DR diagnosis, benefiting both healthcare providers and patients.

/pdf/using-deep-learning-architectures-for-detection-and-3qsv3san.pdf

Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy

With the advent of the Deep learning era, an unprecedented change has come in the field of medical image analysis via CAD (Computer-Aided Diagnosis) [1]–[13] system. With feature extraction capability, Deep learning effectively performs the classification task and thus enhances the prediction of Medical images. CNN models like Dense net 121, Resnet-50, Alex net, Mobile Net, and Inceptionv3 have been used to identify lung disease, but no model was able to predict the particular class of illness with 100% accuracy. In this paper, we apply the voting method, which combines three models Dense net 121, Mobile Net, NasNet, and predictions are made on the basis of the majority of optimistic predictions. Our approach was found to improve the prediction of a particular class of lung disease like Bacterial Pneumonia, Covid, and Lung Opacity. Normal lungs are predicted with 100% accuracy with our approach.

Application of Voting Based Approach on Deep Learning Algorithm for Lung Disease Classification

Given the inherent risks in medical decision-making, medical professionals carefully evaluate a patient's symptoms before arriving at a plausible diagnosis. For AI to be widely accepted and useful technology, it must replicate human judgment and interpretation abilities. XAI attempts to describe the data underlying the black-box approach of deep learning (DL), machine learning (ML), and natural language processing (NLP) that explain how judgments are made. This chapter provides a survey of the most recent XAI methods employed in medical imaging and related fields, categorizes and lists the types of XAI, and highlights the methods used to make medical imaging topics more interpretable. Additionally, it focuses on the challenging XAI issues in medical applications and guides the development of better deep-learning system explanations by applying XAI principles in the analysis of medical pictures and text. 

Explainable AI in Healthcare Application

Importance. With the booming growth of artificial intelligence (AI), especially the recent advancements of deep learning, utilizing advanced deep learning-based methods for medical image analysis has become an active research area both in medical industry and academia. This paper reviewed the recent progress of deep learning research in medical image analysis and clinical applications. It also discussed the existing problems in the field and provided possible solutions and future directions. Highlights. This paper reviewed the advancement of convolutional neural network-based techniques in clinical applications. More specifically, state-of-the-art clinical applications include four major human body systems: the nervous system, the cardiovascular system, the digestive system, and the skeletal system. Overall, according to the best available evidence, deep learning models performed well in medical image analysis, but what cannot be ignored are the algorithms derived from small-scale medical datasets impeding the clinical applicability. Future direction could include federated learning, benchmark dataset collection, and utilizing domain subject knowledge as priors. Conclusion. Recent advanced deep learning technologies have achieved great success in medical image analysis with high accuracy, efficiency, stability, and scalability. Technological advancements that can alleviate the high demands on high-quality large-scale datasets could be one of the future developments in this area.

/pdf/advances-in-deep-learning-based-medical-image-analysis-g69aodktwj.pdf

Advances in Deep Learning-Based Medical Image Analysis

Hepatic epithelioid angiomyolipoma (HEAML) is a rare tumour of mesenchymal tissue with a malignant tendency. Occurring most frequently in women, the relative incidence in men and women, according to incomplete statistics, is approximately 1:5. In rare cases, disease occurrence and development is hidden. Lesions are generally discovered as chance findings by patients; abdominal pain is the first symptom, and imaging has no specificity in diagnosing the disease. Therefore, great difficulties exist in the diagnosis and treatment of HEAML. Here, the case of a 51-year-old female patient with a history of hepatitis B, and abdominal pain over 8 months as the initial symptom, is described. The patient was found to have multiple intrahepatic angiomyolipoma. Due to the small and scattered foci, complete resection was impossible, and because of her history of hepatitis B, conservative treatment was undertaken, with the patient undergoing regular follow-up. When hepatic cell carcinoma could not be excluded, the patient was treated with transcatheter arterial chemoembolization. No tumour neogenesis or metastasis was detected at the 1-year follow-up.

Hepatic epithelioid angiomyolipoma is scattered and unsuitable for surgery: a case report

In the last few decades, microRNAs (miRNAs) are possible to effectively control and treat cancer. However, the function of miR-613 in renal cell carcinoma (RCC) is not very clear up to now. Here, the direction of this research was to investigate the influence of miR-613 for the proliferation, invasion and migration of RCC, and the underlying molecular mechanism. First, the mRNA and protein expression levels of miR-613 were determined in RCC tissues and cancer cells (786-O and ACHN). Using bioinformatics and literature review, anexelekto (AXL), as the target of miR-613 in renal cell carcinoma, was screened. Phenotype experiment and mechanism experiment illustrated the targeting relationship between miR-613 and AXL in cancer cells. Furthermore, a rescue assay with AXL overexpression was performed to make a profound study whether miR-613 disturbs RCC proliferation, invasion, and migration through direct regulation of AXL. Finally, through experiment in vivo, we observe the influence of miR-613 overexpression for tumor. These results were as follows. The present findings proved, in RCC, that the production of miR-613 was at a low level. Except for this point, this current research confirmed, in RCC cells, that the upregulation of miR-613 can control proliferation, metastasis, and invasion by reducing AXL levels and controlling the phosphoinositide 3-kinase (PI3K)/AKT signaling pathway.

miR-613 suppresses renal cell carcinoma proliferation, invasion and migration by regulating the AXL/AKT pathway

BAW: learning from class imbalance and noisy labels with batch adaptation weighted loss

Momentum contrast [16] (MoCo) for unsupervised visual representation learning has a close performance to supervised learning, but it sometimes possesses excess parameters. Extracting a subnetwork from an over-parameterized unsupervised network without sacrificing performance is of particular interest to accelerate inference speed. Typical pruning methods are not applicable for MoCo, because in the fine-tune stage after pruning, the slow update of the momentum encoder will undermine the pretrained encoder. In this paper, we propose a Momentum Contrastive Pruning (MCP) method, which prunes the momentum encoder instead to obtain a momentum subnet. It maintains an un-pruned momentum encoder as a smooth transition scheme to alleviate the representation gap between the encoder and momentum subnet. To fulfill the sparsity requirements of the encoder, alternating direction method of multipliers [40] (ADMM) is adopted. Experiments prove that our MCP method can obtain a momentum subnet that has almost equal performance as the over-parameterized MoCo when transferred to downstream tasks, meanwhile has much less parameters and float operations per second (FLOPs).

Momentum Contrastive Pruning

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Siyuan Pan

Author Tools

Chat about Author