☆ 4.6 Article

Building Automation Pipeline for Diagnostic Classification of Sporadic Odontogenic Keratocysts and Non-Keratocysts Using Whole-Slide Images

DIAGNOSTICS (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Biomedical

Physics-Informed Deep Learning for Musculoskeletal Modeling: Predicting Muscle Forces and Joint Kinematics From Surface EMG

Jie Zhang et al.

Summary: This paper proposes a physics-informed deep learning framework for musculoskeletal modelling, where physics-based domain knowledge is brought into the data-driven model as soft constraints. Experimental results demonstrate the effectiveness and robustness of the proposed framework.

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning

Dina Elreedy et al.

Summary: Class imbalance refers to unequal class distribution, with one class being under-represented (minority class) and the other class having significantly more samples (majority class). The synthetic minority over-sampling technique (SMOTE) is a prominent method for handling imbalanced data. However, the generated SMOTE patterns may not accurately represent the original minority class distribution. This paper presents a novel theoretical analysis of SMOTE by deriving the probability distribution of the generated samples, allowing for an assessment of their representativeness.

MACHINE LEARNING (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

MS-CLAM: Mixed supervision for the classification and localization of tumors in Whole Slide Images

Paul Tourniaire et al.

Summary: Using mixed supervision, we improve the classification and localization performances of a weakly-supervised model based on attention-based deep Multiple Instance Learning. With a limited amount of patch-level labeled slides, we achieve performance close to fully-supervised models.

MEDICAL IMAGE ANALYSIS (2023)

Add to Collection

Article Medicine, General & Internal

H. pylori Related Atrophic Gastritis Detection Using Enhanced Convolution Neural Network (CNN) Learner

Yasmin Mohd Yacob et al.

Summary: Atrophic gastritis (AG) is a chronic condition caused by H. pylori infection and can lead to gastric cancer if left untreated. Early detection of AG is crucial to prevent such cases.

DIAGNOSTICS (2023)

Add to Collection

Article Pathology

Weakly Supervised Framework for Cancer Region Detection of Hepatocellular Carcinoma in Whole-Slide Pathologic Images Based on Multiscale Attention Convolutional Neural Network

Songhui Diao et al.

Summary: A weakly supervised framework based on a multiscale attention convolutional neural network (MSAN-CNN) was introduced for visual inspection of hepatocellular carcinoma cancer regions. The experimental results showed that this framework outperformed the single-scale detection method and had a very fast detection time.

AMERICAN JOURNAL OF PATHOLOGY (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep learning for bone marrow cell detection and classification on whole-slide images

Ching-Wei Wang et al.

Summary: This study developed an efficient and fully automatic hierarchical deep learning framework for bone marrow nucleated differential count (NDC) whole-slide image (WSI) analysis. The framework includes rapid localization, cell identification, and result integration steps, achieving high recall and accuracy in cell counting with superior performance compared to existing benchmark methods.

MEDICAL IMAGE ANALYSIS (2022)

Add to Collection

Article Automation & Control Systems

Multi-classification deep CNN model for diagnosing COVID-19 using iterative neighborhood component analysis and iterative ReliefF feature selection techniques with X-ray images

Narin Aslan et al.

Summary: This study aims to improve the accuracy of trained deep Convolutional Neural Networks (CNN) in automatically diagnosing COVID-19 on X-ray images by applying Iterative Neighborhood Component Analysis (INCA) and Iterative ReliefF (IRF) feature selection methods. After performing thirteen different deep CNN experiments and evaluations, the VGG16 network with INCA feature selection showed the highest predictive value. The proposed method achieved high performance criteria, enhancing the classification accuracy of COVID-19.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2022)

Add to Collection

Review Oncology

Current Trend of Artificial Intelligence Patents in Digital Pathology: A Systematic Evaluation of the Patent Landscape

Muhammad Joan Ailia et al.

Summary: The integration of digital pathology with artificial intelligence enables faster, more accurate, and thorough diagnoses, leading to more precise personalized treatment. In the past five years, there has been an increasing trend in patent filings, primarily focusing on the digitization of pathological images and AI technologies that support the vital role of pathologists.

CANCERS (2022)

Add to Collection

Review Oncology

Recent Applications of Artificial Intelligence from Histopathologic Image-Based Prediction of Microsatellite Instability in Solid Cancers: A Systematic Review

Mohammad Rizwan Alam et al.

Summary: This study assessed the current status of artificial intelligence (AI) applications for microsatellite instability (MSI) prediction based on whole slide images (WSIs), and suggested a better study design. The AI models showed promising results in predicting MSI, but the limitations included small datasets and lack of external validation. Future studies with larger datasets are needed to implement AI models in routine diagnostic practice for MSI prediction.

CANCERS (2022)

Add to Collection

Article Chemistry, Physical

A PCA-EEMD-CNN-Attention-GRU-Encoder-Decoder Accurate Prediction Model for Key Parameters of Seawater Quality in Zhanjiang Bay

Zaimi Xie et al.

Summary: An optimized water quality parameter prediction model is constructed in this study to effectively solve the problem of low accuracy in seawater water quality prediction. Experimental results show that the proposed model has high prediction accuracy and can provide a decision-making basis for water quality control and management.

MATERIALS (2022)

Add to Collection

Article Multidisciplinary Sciences

Deep learning-based breast cancer grading and survival analysis on whole-slide histopathology images

Suzanne C. Wetstein et al.

Summary: In this study, a deep learning-based model for automated grading of breast cancer on whole-slide images was developed and evaluated. The model successfully distinguished between low/intermediate and high grade tumors and showed a trend in the survival of the two predicted groups.

SCIENTIFIC REPORTS (2022)

Add to Collection

Article Dentistry, Oral Surgery & Medicine

Computer tomographic differential diagnosis of ameloblastoma and odontogenic keratocyst: classification using a convolutional neural network

Mayara Simoes Bispo et al.

Summary: This study analyzed the automatic classification performance of Google Inception v3 on tomographic images of OKCs and AMs, showing high accuracy above 90% in cross-validation using a k-fold method. However, a higher error rate was observed for the classification of AM images.

DENTOMAXILLOFACIAL RADIOLOGY (2021)

Add to Collection

Article Medicine, General & Internal

Deep Learning-Based Microscopic Diagnosis of Odontogenic Keratocysts and Non-Keratocysts in Haematoxylin and Eosin-Stained Incisional Biopsies

Roopa S. Rao et al.

Summary: The study aimed to develop a histopathology image classification automation system to identify odontogenic keratocysts. Various Deep Learning techniques were used to analyze and categorize microscopic images of different tissue structures. The proposed algorithm showed a high accuracy rate and potential for automation in diagnosing OKC and non-OKC.

DIAGNOSTICS (2021)

Add to Collection

Review Medicine, Research & Experimental

Developing image analysis pipelines of whole-slide images: Pre- and post-processing

Byron Smith et al.

Summary: Deep learning is pushing the boundaries of digital pathology by going beyond simple digitization and telemedicine, potentially becoming a disruptive technology that can reduce processing time and improve anomaly detection. However, integrating deep learning into standard laboratory workflow requires more steps than just training and testing a model.

JOURNAL OF CLINICAL AND TRANSLATIONAL SCIENCE (2021)

Add to Collection

Review Radiology, Nuclear Medicine & Medical Imaging

Whole Slide Imaging (WSI) in Pathology: Current Perspectives and Future Directions

Neeta Kumar et al.

JOURNAL OF DIGITAL IMAGING (2020)

Add to Collection

Article Dentistry, Oral Surgery & Medicine

Automatic diagnosis for cysts and tumors of both jaws on panoramic radiographs using a deep convolution neural network

Odeuk Kwon et al.

DENTOMAXILLOFACIAL RADIOLOGY (2020)

Add to Collection

Article Automation & Control Systems

Non-iterative and Fast Deep Learning: Multilayer Extreme Learning Machines

Jie Zhang et al.

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Recent advances in convolutional neural networks

Jiuxiang Gu et al.

PATTERN RECOGNITION (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

ReliefF for Multi-label Feature Selection

Newton Spolaor et al.

2013 BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS) (2013)

Add to Collection

Article Computer Science, Artificial Intelligence

Computer-aided prognosis of neuroblastoma on whole-slide images: Classification of stromal development

O. Sertel et al.

PATTERN RECOGNITION (2009)

Add to Collection

Article Dentistry, Oral Surgery & Medicine

A review of odontogenic keratocysts and the behavior of recurrences

D Chirapathomsakul et al.

ORAL SURGERY ORAL MEDICINE ORAL PATHOLOGY ORAL RADIOLOGY AND ENDODONTOLOGY (2006)

Add to Collection

© Peeref 2019-2024. All rights reserved.