Article
Public, Environmental & Occupational Health
Mengfang Li, Yuanyuan Jiang, Yanzhou Zhang, Haisheng Zhu
Summary: This article emphasizes the importance and advantages of using deep learning techniques in medical image analysis. It categorizes and evaluates various deep learning methods, finding that Python is the most commonly used programming language, and the majority of the reviewed papers were published recently, focusing on image analysis in medical healthcare domains. The article highlights the latest advancements and practical applications of DL techniques, while addressing the challenges hindering their widespread implementation.
FRONTIERS IN PUBLIC HEALTH
(2023)
Article
Computer Science, Artificial Intelligence
Tianyu Ma, Alan Q. Wang, Adrian V. Dalca, Mert R. Sabuncu
Summary: The convolutional neural network (CNN) is a commonly used architecture for computer vision tasks. A new building block called hyper-convolution is presented in this paper, which encodes the convolutional kernel using spatial coordinates and enables a more flexible architecture design. Experimental results showed that replacing regular convolutions with hyper-convolutions improved performance with fewer parameters and increased robustness against noise.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Artificial Intelligence
Xiyao Liu, Ziping Ma, Zhihong Chen, Fangfang Li, Ming Jiang, Gerald Schaefer, Hui Fang
Summary: This paper proposes an image hiding algorithm based on a joint compressive autoencoder framework, which increases the hidden capacity while maintaining small reconstruction errors. Experimental results show that the proposed method outperforms several state-of-the-art image hiding techniques in terms of imperceptibility and recovery quality.
PATTERN RECOGNITION
(2022)
Review
Mathematics
Gladys W. Muoka, Ding Yi, Chiagoziem C. Ukwuoma, Albert Mutale, Chukwuebuka J. Ejiyi, Asha Khamis Mzee, Emmanuel S. A. Gyarteng, Ali Alqahtani, Mugahed A. Al-antari
Summary: This study investigates the latest advancements, issues, and future directions of adversarial attacks and defense strategies in the field of computer-aided medical image analysis.
Article
Radiology, Nuclear Medicine & Medical Imaging
Xiner Zhu, Yichao Wu, Haoji Hu, Xianwei Zhuang, Jincao Yao, Di Ou, Wei Li, Mei Song, Na Feng, Dong Xu
Summary: Automatic segmentation of medical lesions is crucial for efficient clinic analysis, and various strategies for multimodal combination have been developed, such as the modality weighted UNet (MW-UNet) and attention-based fusion method proposed in this study. The results show that the proposed method performs well on multimodal liver lesion segmentation and has the potential to assist doctors in clinical diagnosis.
Article
Computer Science, Artificial Intelligence
Davood Karimi, Simon K. Warfield, Ali Gholipour
Summary: This study critically evaluates the role of transfer learning in training fully convolutional networks for medical image segmentation. It highlights the importance of task and data dependency in improving segmentation accuracy, with observations on limited changes in convolutional filters during training and the potential for accurate FCNs by freezing the encoder section at random values. Additionally, the research challenges the common belief that the encoder section needs to learn data/task-specific representations, offering new insights and alternative training methods for FCNs.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2021)
Article
Biochemical Research Methods
Yi Ding, Xue Qin, Mingfeng Zhang, Ji Geng, Dajiang Chen, Fuhu Deng, Chunhe Song
Summary: In this paper, we propose an image segmentation network called RLSegNet, which translates the image segmentation process into a series of decision-making problems using reinforcement learning. RLSegNet is a U-shaped network composed of three components: a feature extraction network, a Mask Prediction Network (MPNet), and an up-sampling network with a cascade attention module. Experimental results demonstrate that the proposed method achieves better segmentation performance in brain tumor segmentation.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Review
Computer Science, Artificial Intelligence
Anuj Kumar, Harvendra Singh Bhadauria, Annapurna Singh
Summary: Dental imaging plays a crucial role in diagnosis and treatment planning, but the analysis process is challenging. Automation is essential in order to ensure accurate diagnosis and improved treatment planning.
PEERJ COMPUTER SCIENCE
(2021)
Article
Geochemistry & Geophysics
Haiwen Du, Yu An, Qing Ye, Jiulin Guo, Lu Liu, Dongjie Zhu, Conrad Childs, John Walsh, Ruihai Dong
Summary: Seismic interpretation is a fundamental method for obtaining information about subsurface reservoirs. However, deep learning algorithms often underperform on seismic data due to inconsistent noise patterns. To address this issue, a noise pattern transfer framework is proposed to improve the generality of seismic interpretation algorithms. Experimental results demonstrate the effectiveness of this approach.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Review
Computer Science, Artificial Intelligence
Manar Aljabri, Manal AlGhamdi
Summary: Deep learning algorithms have become a powerful tool for analyzing medical images, particularly in medical image segmentation. This paper reviews major DL models and applications, summarizing over 150 contributions to the field. Brief overviews of articles are provided by application area, and current challenges and future research directions are discussed.
Article
Chemistry, Analytical
Krzysztof Strzepek, Mateusz Salach, Bartosz Trybus, Karol Siwiec, Bartosz Pawlowicz, Andrzej Paszkiewicz
Summary: This article presents an integrated system that utilizes unmanned aerial vehicles to perform comprehensive crop analysis. It combines qualitative and quantitative evaluations for efficient agricultural management. The system uses a convolutional neural network-based model for object detection and segmentation in acquired aerial images, as well as multispectral image processing for analysis and counting.
Review
Computer Science, Artificial Intelligence
Saeid Asgari Taghanaki, Kumar Abhishek, Joseph Paul Cohen, Julien Cohen-Adad, Ghassan Hamarneh
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)
Article
Computer Science, Interdisciplinary Applications
Abhishek Bihani, Hugh Daigle, Javier E. Santos, Christopher Landry, Masa Prodanovic, Kitty Milliken
Summary: The deep learning model MudrockNet successfully applied to the segmentation of scanning electron microscope images, accurately identifying silt grains, clay grains, and pores, achieving high pixel accuracy and prediction results. Compared with the random forest classifier based on Weika segmentation, MudrockNet performed better in most cases.
COMPUTERS & GEOSCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Jin Zhu, Chuan Tan, Junwei Yang, Guang Yang, Pietro Lio
Summary: This paper introduces a novel approach for medical image arbitrary-scale super-resolution, MIASSR, which combines meta-learning and generative adversarial networks (GANs) to achieve super-resolution of medical images at any scale of magnification in (1, 4]. MIASSR shows comparable fidelity performance and the best perceptual quality with the smallest model size compared to state-of-the-art SISR algorithms on single-modal and multi-modal MR brain images. In addition, transfer learning enables MIASSR to handle super-resolution tasks of new medical modalities, with the potential to become a foundational pre-/post-processing step in clinical image analysis tasks.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2021)
Review
Computer Science, Information Systems
Kyriakos D. Apostolidis, George A. Papakostas
Summary: In recent years, deep neural networks have become popular in computer vision and medical image analysis, but also face challenges from adversarial attacks. Processing medical images using convolutional neural networks can help diagnose diseases. Some attack methods, although imperceptible to the naked eye, can significantly degrade model performance.
Article
Surgery
Rodrigo Suarez-Ibarrola, Maximilian Kriegmair, Frank Waldbillig, Britta Gruene, Misgana Negassi, Ujwala Parupalli, Annette Schmit, Alexander Reitere, Christop Mueller, Alexander Scheurer, Stefan Baur, Kirsten Klein, Johannes A. Fallert, Lars Muendermann, Jenshika Yoganathan, Marco Probst, Patrick Ihle, Neven Bobic, Tobias Schumm, Henning Rehn, Alexander Betke, Michael Graurock, Martin Forrer, Christian Gratzke, Arkadiusz Miernik, Simon Hein
Summary: This study proposes a novel endoimaging system and an online documentation platform for improved diagnosis, management, and follow-up of bladder cancer patients. The system tracks the movements of the endoscope and generates 3D reconstructions, while AI-based image segmentation assists in tumor detection. The online platform allows physicians and patients to digitally visualize endoscopic findings using a 3D bladder model.
MINIMALLY INVASIVE THERAPY & ALLIED TECHNOLOGIES
(2022)
Article
Computer Science, Artificial Intelligence
Misgana Negassi, Diane Wagner, Alexander Reiterer
Summary: This paper introduces two new data augmentation methods, SmartAugment and SmartSamplingAugment, and conducts a study on semantic image segmentation tasks. SmartAugment uses Bayesian Optimization for strategy search and achieves state-of-the-art performance in all tasks. SmartSamplingAugment is a simple parameter-free method with a fixed augmentation strategy that competes with existing methods.