Review
Computer Science, Artificial Intelligence
Xintong Li, Chen Li, Md Mamunur Rahaman, Hongzan Sun, Xiaoqi Li, Jian Wu, Yudong Yao, Marcin Grzegorzek
Summary: This paper reviews the machine learning methods for Whole-slide Image (WSI) analysis, including the development status of WSI and computer-aided diagnosis (CAD) methods, publicly available WSI datasets and evaluation metrics, and the latest development of machine learning techniques in WSI segmentation, classification, and detection. The application prospects of these methods in the field are also discussed.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Remote Sensing
Wen Zhang, Baoxin Hu
Summary: This study developed a method based on convolutional neural networks for forest road identification and extraction, successfully extracting roads in forested areas from high spatial resolution multispectral imagery.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2021)
Article
Computer Science, Artificial Intelligence
Xiaoqing Li, Jiansheng Yang, Jinwen Ma
Summary: With the advancement of Internet technology and digital devices, Content-Based Image Retrieval (CBIR) has rapidly developed and been widely applied. This paper surveyed the fast developments and applications of CBIR theories and algorithms from 2009 to 2019, focusing on technological advancements in image representation and database search, as well as practical applications in various fields.
Article
Computer Science, Software Engineering
K. Karthik, S. Sowmya Kamath
Summary: A deep neural network-based approach is proposed for efficient medical image retrieval, achieving a low error score and significant improvement compared to other works, highlighting its suitability for real-world applications.
Article
Computer Science, Information Systems
Yashwant Kurmi, Vijayshri Chaurasia
Summary: This paper presents a content-based image retrieval algorithm for histopathology image segmentation for identification and extraction of nuclei, which confirms the superiority of the proposed method in qualitative and quantitative analysis through performance investigation on six hematoxylins and eosin (H&E) stained histopathology images datasets.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Review
Chemistry, Analytical
Joanna Czajkowska, Martyna Borak
Summary: Computer-aided diagnosis systems have been widely used in clinical practice, providing assistance to clinicians in daily diagnostic tasks. The rapid development of image processing techniques, especially in high-frequency ultrasound analysis, has opened up new possibilities in dermatology, allergology, cosmetology, and aesthetic medicine. This paper presents a comprehensive overview of high-frequency ultrasound image processing techniques and discusses the bridge between diagnostic needs and existing solutions, as well as their limitations and future directions.
Article
Computer Science, Artificial Intelligence
Zhuoqun Liu, Fan Guo, Heng Liu, Xiaoyue Xiao, Jin Tang
Summary: In this paper, a new approach to visual geo-localization for natural environments is proposed by creating a panoramic skyline database using digital elevation model (DEM) data in virtual space. The combination of the skyline database and real-world image data enables visual geo-localization as a cross-modal image retrieval problem. The paper introduces the LineNet semantic segmentation model for skyline extractions, which has proven to be robust in complex natural environments. Additionally, a compound index is designed to reduce storage space and improve retrieval efficiency, resulting in the proposed method outperforming most state-of-the-art methods.
IET IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Jifeng Guo, Zhiqi Pang, Miaoyuan Bai, Yanbang Xiao, Jian Zhang
Summary: The core idea of active learning is to achieve higher model performance at a reduced annotation cost. This paper introduces an independency-enhancing adversarial active learning method, which differs from previous approaches by emphasizing sample independence. The informativeness of a group of samples is believed to be related to sample independence rather than the simple sum of individual sample informativeness. To ensure sample independence, an independent sample selection module based on hierarchical clustering is designed. An adversarial approach is also utilized to learn the feature representation and label the state of the sample based on predicted loss value. Sample selection is performed based on sample uncertainty, diversity, and independence. Experimental results on four datasets demonstrate the effectiveness and superiority of this independency-enhancing adversarial active learning approach.
IET IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Zechao Hu, Adrian G. Bors
Summary: Content-based image retrieval (CBIR) aims to provide similar images to a given query. Feature extraction is crucial in CBIR for retrieval performance. This paper introduces a query-sensitive co-attention mechanism for large-scale CBIR tasks, which employs clustering of selected local features to reduce computation cost. Experimental results show that the proposed co-attention maps achieve the best retrieval results in challenging situations. (c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Article
Chemistry, Multidisciplinary
Haojun Qin, Lei Zhang, Quan Guo
Summary: This study developed a computer-aided diagnostic system based on deep learning to classify benign and malignant tumors in breast ultrasound images from paper reports. The proposed method achieved an accuracy of 89.31%, recall rate of 88.65%, specificity of 89.57%, F1 score of 89.42%, and AUC of 94.53% when the input images contained noise. This approach is more suitable for practical applications and can assist patients in obtaining prompt and accurate classification results of ultrasound reports.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Theory & Methods
Zhiyong Liu, Chuan Yang, Jun Huang, Shaopeng Liu, Yumin Zhuo, Xu Lu
Summary: The study proposes a deep learning model for the computer-aided diagnosis of prostate cancer using ultrasound images. Through improved algorithms and network structures, the method can accurately detect prostate images and segment prostate information at the pixel-level simultaneously.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Nepoleon Keisham, Arambam Neelima
Summary: Recently, CBIR system faces challenges due to the growth of multimedia contents on the internet. This study proposes a Deep Search and Rescue (SAR) Algorithm-based CBIR system, which effectively retrieves relevant images through pre-processing, feature extraction, fusion, clustering, and classification steps.
Article
Computer Science, Information Systems
Xiuli Chai, Yinjing Wang, Zhihua Gan, Xiuhui Chen, Yushu Zhang
Summary: This article investigates the issue of content-based encrypted image retrieval in the cloud, and proposes a Thumbnail Preserving Encryption (TPE) method based on genetic algorithm, which obfuscates and diffuses pixels to achieve encrypted privacy protection while preserving thumbnail availability. Additionally, a color histogram-based retrieval algorithm is introduced, and the Bhattacharyya distance is utilized to improve retrieval accuracy.
INFORMATION SCIENCES
(2022)
Article
Engineering, Multidisciplinary
Dong H. Kang, Young-Jin Cha
Summary: In this paper, a novel semantic transformer representation network (STRNet) is developed for crack segmentation with fast processing speed and high performance. The network is trained and tested in complex scenes, achieving high precision, recall, F1 score, and mIoU. Comparing with other advanced networks, STRNet shows the best performance in evaluation metrics with the fastest processing speed.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2022)
Article
Physiology
Haoyang Li, Juexiao Zhou, Yi Zhou, Qiang Chen, Yangyang She, Feng Gao, Ying Xu, Jieyu Chen, Xin Gao
Summary: Periodontitis is a prevalent global disease, requiring an automatic diagnostic tool to prevent tooth loss. Therefore, a interpretable method called Deetal-Perio is proposed to predict the severity of periodontitis, which performs well and helps doctors understand its working mechanism.
FRONTIERS IN PHYSIOLOGY
(2021)