Related references
Note: Only part of the references are listed.
Article
Computer Science, Hardware & Architecture
Jiaji Wang et al.
Summary: The eyes are crucial for human observation and perception, but visual impairment causes inconveniences in the lives of visually impaired individuals. Therefore, it is important to focus on their needs. Researchers are working to help visually impaired people live normal lives, using deep learning technology for the diagnosis of eye diseases and the development of visual aids. This paper summarizes recent research in these areas and provides an overview of how artificial intelligence can assist the visually impaired in the future.
Article
Computer Science, Information Systems
Mingjie Li et al.
Summary: Medical reports have significant clinical value, but generating them accurately is challenging. To address this challenge, we propose an Auxiliary Signal-Guided Knowledge Encoder-Decoder (ASGK) that combines auxiliary signals and the Transformer architecture. Our approach achieves a significant improvement in medical report generation and outperforms previous approaches in medical terminology classification and paragraph generation metrics.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2023)
Review
Computer Science, Artificial Intelligence
Chenxi Huang et al.
Summary: Oral diseases have significant impact on human health, but they are often unnoticed in early stages. Deep learning, as a promising field in artificial intelligence, has achieved remarkable success in various domains, particularly in dentistry. This paper aims to provide an overview of recent research on deep learning applications in dentistry, with a focus on dental imaging. Deep learning algorithms excel in difficult tasks such as image segmentation and recognition, enabling accurate identification of oral conditions and abnormalities. Integration of deep learning with other oral health data offers a holistic understanding of the relationship between oral and systemic health. However, there are still many challenges that need to be addressed.
Article
Engineering, Biomedical
Siyuan He et al.
Summary: Recently, significant progress has been made in artificial neural network (ANN)-based aid diagnosis methods for magnetic resonance (MR) images. However, designing an aid diagnosis method for spinal MR images with detailed information output is still challenging due to the computational consumption. In this study, we propose a lightweight ANN-based aid diagnosis report generation method for lumbar MR images, which can provide intuitive diagnostic reports with less computational consumption. The experimental results demonstrate the potential of our method to aid diagnosis for radiologists in scenarios with limited computing power, achieving 89% accuracy of abnormal disc detection and 0.687 of BLEU-1 score.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Biomedical
Palak Handa et al.
Summary: The rapid advancement of AI in medical image analysis has shown various applications, but its real-time use is still hindered by factors like lack of clinical trials, diverse datasets, model generalization, interpretability, and biases. The introduction of ChatGPT has created both opportunities and challenges in this field. This editorial explores the role of ChatGPT in medical image analysis through an analysis of its responses to questions related to the field.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Biomedical
Xiaowei Liu et al.
Summary: This paper proposes a U-shaped medical image segmentation model that combines large kernel convolutions with Transformers, achieving efficient refinement of features by introducing multi-scale kernel convolutional attention mechanisms into the skip connections of the encoder. The model outperforms state-of-the-art methods on multi-modal medical image datasets, particularly on small-scale medical datasets.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Biomedical
Vasundhara S. Rathod et al.
Summary: This research focuses on predicting texts and suggesting letters for communication through eye blinking, specifically targeting individuals with locked-in syndrome and motor neuron disorders. By utilizing signal processing, feature extraction techniques, and optimized classifiers, the study achieves efficient text prediction and letter suggestion.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Interdisciplinary Applications
Zhanyu Wang et al.
Summary: This paper proposes a pure transformer-based framework for automated radiographic report generation in the medical field. It addresses the challenges of visual similarity among medical images and the importance of disease-related words. By improving visual-textual alignment, multi-label classification, and word importance weighting, the framework achieves promising performance in generating accurate reports.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Robin Rombach et al.
Summary: By applying diffusion models (DMs) in the latent space of powerful pretrained autoencoders, this paper achieves high-quality image generation on limited computational resources. The introduction of cross-attention layers further enhances the flexibility and performance of the generator.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Article
Biology
Tawsifur Rahman et al.
Summary: Computer-aided diagnosis for fast and reliable detection of COVID-19 using a large X-ray dataset, various image enhancement techniques, and deep learning models has shown promising results in this study.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
A. Emre Kavur et al.
Summary: Abdominal organ segmentation has long been a comprehensive research field, with recent developments in deep learning introducing new state-of-the-art segmentation systems. However, the effects of DL model properties and parameters on performance are still difficult to interpret, and multi-tasking DL models often perform worse compared to organ-specific ones.
MEDICAL IMAGE ANALYSIS
(2021)
Review
Radiology, Nuclear Medicine & Medical Imaging
Maria Francesca Spadea et al.
Summary: This study systematically reviewed deep learning-based methods for generating synthetic computed tomography images, categorizing them into three groups based on their clinical applications. Key characteristics of DL methods were extracted and compared among network architectures and metrics, with a detailed review of each category provided.
Proceedings Paper
Computer Science, Artificial Intelligence
Yuanen Zhou et al.
Summary: Current state-of-the-art image captioning models suffer from heavy latency due to autoregressive decoders, while non-autoregressive models aim to accelerate speed but often sacrifice generation quality. The SATIC model strikes a better balance between speed and quality by combining autoregressive property in global and parallel word generation in local, showing good performance on the MSCOCO image captioning benchmark.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhanyu Wang et al.
Summary: The proposed self-boosting framework in this paper enhances radiographic report generation by cooperating the main task of report generation with an auxiliary task of image-text matching, where the two tasks influence each other cooperatively and iteratively to improve the overall performance significantly, demonstrating superior results over state-of-the-art methods in image captioning and medical report generation.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Article
Biology
Tulin Ozturk et al.
COMPUTERS IN BIOLOGY AND MEDICINE
(2020)
Article
Computer Science, Information Systems
Muhammad E. H. Chowdhury et al.
Article
Computer Science, Information Systems
Dina Demner-Fushman et al.
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION
(2016)
Review
Radiology, Nuclear Medicine & Medical Imaging
Stacy K. Goergen et al.
JOURNAL OF MEDICAL IMAGING AND RADIATION ONCOLOGY
(2013)
