☆ 4.2 Article

Automated wound segmentation and classification of seven common injuries in forensic medicine

FORENSIC SCIENCE MEDICINE AND PATHOLOGY (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D Images

Irem Ulku et al.

Summary: This article surveys the recent scientific development of deep learning-based 2D semantic segmentation methods, discusses the techniques and evaluation methods in the field, and categorizes the methods chronologically. Technical analysis of solutions to fundamental problems in the field is provided, along with a summary of each method's contribution.

APPLIED ARTIFICIAL INTELLIGENCE (2022)

Add to Collection

Article Multidisciplinary Sciences

Deep learning approach based on superpixel segmentation assisted labeling for automatic pressure ulcer diagnosis

Che Wei Chang et al.

Summary: A pressure ulcer is a skin and tissue injury that can be difficult for patients to access medical care, especially during the COVID-19 pandemic. Traditional machine learning (ML) has limitations in clinical applications due to complicated preprocessing steps, while deep learning (DL) can handle larger datasets. The authors propose a method using super-pixel assistance for labeling images and achieved satisfactory results using five popular DL models, with DeeplabV3 performing the best.

PLOS ONE (2022)

Add to Collection

Article Computer Science, Information Systems

Wound Detection by Simple Feedforward Neural Network

Domagoj Marijanovic et al.

Summary: This study focuses on chronic wound analysis and proposes a standard feedforward neural network for wound segmentation, which achieves high recall, precision, and F1 score. The developed network effectively extracts wounds from images and improves the overall segmentation performance.

ELECTRONICS (2022)

Add to Collection

Review Dermatology

Image-Based Artificial Intelligence in Wound Assessment: A Systematic Review

D. M. Anisuzzaman et al.

Summary: Accurately predicting wound healing trajectories is difficult due to the complexities involved. AI systems can help clinicians in diagnosing, assessing therapy effectiveness, and predicting healing outcomes. However, developing AI-based systems for high-quality wound care remains a critical issue.

ADVANCES IN WOUND CARE (2022)

Add to Collection

Article Computer Science, Information Systems

A Mobile App for Wound Localization Using Deep Learning

D. M. Anisuzzaman et al.

Summary: An automated wound localizer was developed using deep neural networks to detect wounds and surrounding tissues, achieving high accuracy on different datasets. The YOLOv3 model outperformed the SSD model in terms of mean Average Precision (mAP), demonstrating robustness and reliability across various datasets.

IEEE ACCESS (2022)

Add to Collection

Review Computer Science, Artificial Intelligence

Deep semantic segmentation of natural and medical images: a review

Saeid Asgari Taghanaki et al.

Summary: This review categorizes leading deep learning-based medical and non-medical image segmentation solutions into six main groups and provides a comprehensive review of each group's contributions. It analyzes the limitations of current approaches and presents potential future research directions for improving semantic image segmentation.

ARTIFICIAL INTELLIGENCE REVIEW (2021)

Add to Collection

Article Critical Care Medicine

Burn Images Segmentation Based on Burn-GAN

Fei Dai et al.

Summary: This study proposes an advanced burn image generation framework called Burn-GAN, which automatically generates annotated burn image datasets to improve segmentation accuracy. The framework utilizes various techniques to create human surface scenes, including burn wounds, and acquires annotated datasets through accurate data transformation. In experiments, the framework achieved good segmentation results, with precision at 90.75%, PA at 96.88%, and improved DC from 84.5 to 89.3%.

JOURNAL OF BURN CARE & RESEARCH (2021)

Add to Collection

Article Mathematical & Computational Biology

A Framework for Automatic Burn Image Segmentation and Burn Depth Diagnosis Using Deep Learning

Hao Liu et al.

Summary: Burn is a common traumatic disease with high morbidity and mortality. Deep learning technology can automate and standardize burn diagnosis, improving accuracy and reducing human errors.

COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE (2021)

Add to Collection

Article Medicine, Legal

Deep learning in forensic gunshot wound interpretation-a proof-of-concept study

Petteri Oura et al.

Summary: While deep learning applications are considered revolutionary in several medical specialties, their utilization in forensic applications remains limited. A proof-of-concept study demonstrated the potential of trained neural network architectures to predict shooting distance class based on photographs of gunshot wounds.

INTERNATIONAL JOURNAL OF LEGAL MEDICINE (2021)

Add to Collection

Article Chemistry, Analytical

Integrating 3D Model Representation for an Accurate Non-Invasive Assessment of Pressure Injuries with Deep Learning

Sofia Zahia et al.

SENSORS (2020)

Add to Collection

Article Multidisciplinary Sciences

Fully automatic wound segmentation with deep convolutional neural networks

Chuanbo Wang et al.

SCIENTIFIC REPORTS (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Automatic classification of skin burn colour images using texture-based feature extraction

Ugur Sevik et al.

IET IMAGE PROCESSING (2019)

Add to Collection

Article Emergency Medicine

Burn image segmentation based on Mask Regions with Convolutional Neural Network deep learning framework: more accurate and more convenient

Chong Jiao et al.

BURNS & TRAUMA (2019)

Add to Collection

Article Medicine, Legal

Comparison of forensic photo-documentation to a photogrammetric solution using the multi-camera system Botscan

Ramona Michienzi et al.

FORENSIC SCIENCE INTERNATIONAL (2018)

Add to Collection

Article Mathematical & Computational Biology

A Composite Model of Wound Segmentation Based on Traditional Methods and Deep Neural Networks

Fangzhao Li et al.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Feature Pyramid Network for Multi-Class Land Segmentation

Selim Seferbekov et al.

PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2018)

Add to Collection

Article Mathematical & Computational Biology

Segmentation of Chronic Wound Areas by Clustering Techniques Using Selected Color Space

Manoj Kumar Yadav et al.

JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS (2013)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Binary Tissue Classification on Wound Images With Neural Networks and Bayesian Classifiers

Francisco Veredas et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2010)

Add to Collection

© Peeref 2019-2024. All rights reserved.