Article
Engineering, Biomedical
William C. Walton, Seung-Jun Kim, Lisa A. Mullen
Summary: This paper investigates an automated registration algorithm for 2D X-ray mammographic images using a fully convolutional neural network. The proposed method outperforms state-of-the-art techniques and shows robust performance across various tissue/lesion characteristics.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2022)
Article
Engineering, Biomedical
Gangcheng Cai, Huaying Liu, Wei Zou, Nan Hu, JiaJun Wang
Summary: In this paper, a deformable registration network (DR-Net) and a multi-scale cascading strategy are proposed for the registration of largely deformed 3D medical images. The DR-Net is constructed with a U-shaped convolutional neural network, a pyramidal input module, a light weighted sequential Inception module, and an SCAM convolutional attention module. The multi-scale cascading strategy integrates the deformation field information within and between sub-networks at different scales to synthesize the cascaded deformation fields.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Serhat Kilicarslan, Cemil Kozkurt, Selcuk Bas, Abdullah Elen
Summary: Pneumonia is a major global health problem, and deep learning techniques are proposed to diagnose it. This study suggests a method for detecting pneumonia using a new activation function, and experimental results show that CNN models with this activation function achieve the best performance in both pneumonia detection and traditional benchmark datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
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
Biology
Hua Bao, Yuqing Zhu, Qing Li
Summary: Medical image segmentation results are crucial for disease diagnosis. With the development of convolutional neural networks, medical image processing has made significant progress. However, existing automatic segmentation tasks still face challenges due to variations in position, size, and shape, resulting in poor performance. To address this, we propose a hybrid-scale contextual fusion network to capture richer spatial and semantic information.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Neurosciences
Yiqin Cao, Zhenyu Zhu, Yi Rao, Chenchen Qin, Di Lin, Qi Dou, Dong Ni, Yi Wang
Summary: EPReg is an edge-aware pyramidal deformable network for unsupervised volumetric registration. It utilizes multi-level feature pyramids and integrates edge information to enhance image structure alignment, enabling it to handle large deformations.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Engineering, Biomedical
Kun Tang, Lihui Wang, Xingyu Huang, Xinyu Cheng, Yue-Min Zhu
Summary: Deformable medical image registration is crucial for clinical applications. We propose a multi-dilation spherical graph transformer (MD-SGT) that combines convolutional and graph transformer blocks to effectively distinguish differences between reference and template images at various scales, improving registration performance.
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS
(2023)
Review
Engineering, Biomedical
Padmavathi Kora, Chui Ping Ooi, Oliver Faust, U. Raghavendra, Anjan Gudigar, Wai Yee Chan, K. Meenakshi, K. Swaraja, Pawel Plawiak, U. Rajendra Acharya
Summary: Medical imaging is valuable, and automated medical image analysis techniques can overcome limitations of manual analysis and provide high-quality decision support. Transfer learning has been widely applied in medical image analysis, reducing the need for training data.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2022)
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
Biochemistry & Molecular Biology
Yu-Jiun Fan, I-Shiang Tzeng, Yao-Sian Huang, Yuan-Yu Hsu, Bo-Chun Wei, Shuo-Ting Hung, Yeung-Leung Cheng
Summary: This study trains a CNN to screen for pectus excavatum (PE) using frontal chest radiography, providing a convenient method for diagnosing PE that is not possible with the human eye.
Article
Computer Science, Artificial Intelligence
Hang Yu, Laurence T. Yang, Qingchen Zhang, David Armstrong, M. Jamal Deen
Summary: This paper surveys the applications of convolutional neural networks in medical image analysis, reviews commonly used CNN models and tasks in various medical diagnosis areas. The challenges and future research directions of CNN in medical image analysis are discussed.
Article
Computer Science, Interdisciplinary Applications
Weilin Chen, Rui Zhang, Yunfeng Zhang, Fangxun Bao, Haixia Lv, Longhao Li, Caiming Zhang
Summary: This paper proposes a new medical image segmentation model called Pact-Net, which combines the advantages of CNNs and Transformers to effectively extract local and global features. Experimental results on multiple datasets demonstrate the advanced and effective performance of this model.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Sadaf Kabir, Leily Farrokhvar, Ali Dabouei
Summary: Medical image analysis is crucial for precise clinical diagnosis decisions. This study proposes an online feature selection method and a weakly-supervised approach to improve the performance of thoracic disease prediction.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Moyun Liu, Youping Chen, Jingming Xie, Lei He, Yang Zhang
Summary: In this article, a weld defect detection method LF-YOLO based on convolutional neural network (CNN) is proposed, which plays an important role in quality assurance in the manufacturing industry. The method achieves satisfactory detection performance and consumption in actual industry by using a reinforced multiscale feature (RMF) module and an efficient feature extraction (EFE) module. The method shows outstanding versatility detection performance on the public dataset MS COCO. Rating: 8/10
IEEE SENSORS JOURNAL
(2023)
Review
Biochemical Research Methods
Leandro A. Bugnon, Cristian Yones, Diego H. Milone, Georgina Stegmayer
Summary: Six recent methods for predicting miRNAs in the genome were reviewed and compared on different genome-wide datasets. It was found that all methods performed similarly for smaller genomes and imbalances, but deep learning approaches using raw sequence information achieved the best scores for larger datasets like the human genome.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biology
Alejandro A. Edera, Ian Small, Diego H. Milone, M. Virginia Sanchez-Puerta
Summary: A new method using deep convolutional neural network to predict plant mitochondrial C-to-U RNA editing events was introduced, which showed a significant improvement in predictive performance compared to traditional methods, indicating the potential importance for studying RNA regulation.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Biochemical Research Methods
Jonathan Raad, Leandro A. Bugnon, Diego H. Milone, Georgina Stegmayer
Summary: In this study, the first full end-to-end deep learning model for pre-miRNA prediction, miRe2e, was developed. The model is based on Transformers and can accept raw genome-wide data as input without any preprocessing or feature engineering. Experimental results showed that the model achieved 10 times better performance compared to state-of-the-art algorithms when tested using the human genome.
Article
Biochemical Research Methods
Alejandro A. Edera, Diego H. Milone, Georgina Stegmayer
Summary: A novel protocol anc2vec based on neural networks is proposed for constructing vector representations of GO terms, preserving ontological features and showing better performance on diverse tasks.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Engineering, Biomedical
Victoria Peterson, Nicolas Nieto, Dominik Wyser, Olivier Lambercy, Roger Gassert, Diego H. Milone, Ruben D. Spies
Summary: This paper addresses the cross-sessions variability in electroencephalography-based brain-computer interfaces (BCIs) and proposes a backward method to avoid the need for classifier retraining and reduce calibration time. The results show that the proposed approach can effectively mitigate the variability between sessions while maintaining classification performance.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2022)
Article
Neurosciences
Rodrigo Echeveste, Enzo Ferrante, Diego H. Milone, Ines Samengo
Summary: This study combines two different views of autism, altered probabilistic computations and inhibitory dysfunction, using a trained recurrent neural network model that performs sampling-based inference in a visual setting. The model also captures various experimental observations on neural variability and oscillations in individuals with autism. By linking neural connectivity, dynamics, and function, this work contributes to understanding the physiological underpinnings of perceptual traits in autism spectrum disorder.
NETWORK NEUROSCIENCE
(2022)
Article
Biochemical Research Methods
Gabriela A. Merino, Rabie Saidi, Diego H. Milone, Georgina Stegmayer, Maria J. Martin
Summary: This paper proposes a novel deep learning model called DeeProtGO for predicting GO term annotations by integrating protein knowledge. The experiments show that the prediction quality improves when more protein knowledge is integrated. DeeProtGO is benchmarked against state-of-the-art methods on public datasets and demonstrates effective improvement in the prediction of GO annotations.
Review
Biochemical Research Methods
L. A. Bugnon, A. A. Edera, S. Prochetto, M. Gerard, J. Raad, E. Fenoy, M. Rubiolo, U. Chorostecki, T. Gabaldon, F. Ariel, L. E. Di Persia, D. H. Milone, G. Stegmayer
Summary: This study compares the performance of classical methods and recently proposed approaches for predicting RNA secondary structure, and introduces a new metric based on chemical probing data to assess their predictive performance. The results provide a comprehensive assessment and a benchmark resource for future approaches.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Nicolas Gaggion, Lucas Mansilla, Candelaria Mosquera, Diego H. Milone, Enzo Ferrante
Summary: This study proposes a novel neural architecture, called HybridGNet, which combines graph convolutional neural networks with standard convolutional neural networks for anatomical segmentation. It effectively addresses topological errors and anatomical inconsistencies in medical images. Experimental results demonstrate that HybridGNet outperforms other models in anatomical segmentation of chest x-ray images in various scenarios.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Agricultural Engineering
Jose O. Chelotti, Sebastian R. Vanrell, Luciano S. Martinez-Rau, Julio R. Galli, Santiago A. Utsumi, Alejandra M. Planisich, Suyai A. Almiron, Diego H. Milone, Leonardo L. Giovanini, H. . Leonardo Ruffner
Summary: Precision livestock farming optimizes livestock production through the use of sensor information and communication technologies. This study proposes an algorithm called JMFAR based on jaw movement sounds for detecting rumination and grazing bouts with high accuracy and low computational cost. The algorithm was tested in a free grazing environment and showed improved performance compared to a state-of-the-art algorithm for estimating grazing bouts.
BIOSYSTEMS ENGINEERING
(2023)
Article
Biochemical Research Methods
Leandro Di Persia, Tiago Lopez, Agustin Arce, Diego H. Milone, Georgina Stegmayer
Summary: This work proposes a novel method for predicting gene function annotations based on the inference of GO similarities from expression similarities. The proposed method outperforms other methods on several public biological datasets and effectively improves the prediction of GO annotations. It is also capable of predicting relevant and accurate biological functions in a full genome case.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Editorial Material
Computer Science, Artificial Intelligence
Leandro A. Bugnon, Emilio Fenoy, Alejandro A. Edera, Jonathan Raad, Georgina Stegmayer, Diego H. Milone
Summary: The automatic annotation of the protein universe remains a challenge. Currently, only 0.25% of the 229,149,489 entries in the UniProtKB database have been functionally annotated. Manual annotation processes utilize knowledge from the protein families database Pfam, but the growth of annotations has been slow. Deep learning models offer potential for learning evolutionary patterns, but the lack of large-scale data for many protein families poses a limitation. Transfer learning can overcome this limitation and result in significant improvements in protein family prediction accuracy.
Proceedings Paper
Computer Science, Artificial Intelligence
Lucas Mansilla, Rodrigo Echeveste, Diego H. Milone, Enzo Ferrante
Summary: In real-life applications, machine learning models often face scenarios where there is a change in data distribution between training and test domains. We propose novel gradient agreement strategies based on gradient surgery to alleviate conflicting gradients and enhance the generalization capability of deep learning models in domain shift scenarios.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Article
Biology
Nicolas Gaggion, Federico Ariel, Vladimir Daric, Eric Lambert, Simon Legendre, Thomas Roule, Alejandra Camoirano, Diego H. Milone, Martin Crespi, Thomas Blein, Enzo Ferrante
Summary: This study introduces the ChronoRoot system, combining 3D printing and deep learning techniques for high temporal resolution phenotyping of plant roots in agarized medium. A novel deep learning-based root extraction method was developed, incorporating temporal consistency into root system architecture reconstruction, allowing automatic extraction of phenotypic parameters and derivation of novel time-related parameters from spectral features of temporal signals. The combination of machine intelligence methods and a 3D-printed device expands the possibilities of root high-throughput phenotyping for genetic and natural variation studies.
Proceedings Paper
Computer Science, Artificial Intelligence
Nicolas Gaggion, Lucas Mansilla, Diego H. Milone, Enzo Ferrante
Summary: The study introduces a novel neural architecture HybridGNet, which combines standard convolutions and graph convolutional neural networks for better decoding of anatomical structures and robustness to image occlusions, as well as construction of landmark-based segmentations from pixel level annotations.
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT I
(2021)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.