Article
Computer Science, Information Systems
Marwa Obayya, Muhammad Kashif Saeed, Nuha Alruwais, Saud S. Alotaibi, Mohammed Assiri, Ahmed S. Salama
Summary: Biomedical image analysis is crucial in modern healthcare for automated analysis and interpretation of medical images. The field of biomedical image classification has gained attention due to the abundance of image data and the potential of deep learning algorithms. The HMDL-MFMBIA technique, which combines multiple DL models and employs a hybrid salp swarm algorithm for hyperparameter selection, shows promising results in improving biomedical image classification.
Article
Computer Science, Artificial Intelligence
Fernando J. Rendon-Segador, Juan A. Alvarez-Garcia, Jose L. Salazar-Gonzalez, Tatiana Tommasi
Summary: The state of the art in violence detection in videos has been improved by using deep learning models, but it still faces challenges in terms of high false alarm rates and security guard intervention. In this study, a new neural network named CrimeNet, based on Vision Transformer (ViT) and Neural Structured Learning (NSL) with adversarial training, is proposed. CrimeNet outperforms previous works and significantly reduces false positives. Tests on challenging violence-related datasets show that CrimeNet improves the state of the art by a large margin and demonstrates remarkable robustness.
Article
Biochemical Research Methods
Fabian Isensee, Paul F. Jaeger, Simon A. A. Kohl, Jens Petersen, Klaus H. Maier-Hein
Summary: nnU-Net is a deep learning-based image segmentation method that automatically configures itself for diverse biological and medical image segmentation tasks, offering state-of-the-art performance as an out-of-the-box tool.
Article
Computer Science, Artificial Intelligence
Narinder Singh Punn, Sonali Agarwal
Summary: This article presents the application of U-Net architecture in biomedical image segmentation and provides a comprehensive analysis of U-Net variants. It highlights the success of these approaches in the ongoing pandemic and other areas, while also discussing the challenges and future research directions in biomedical image segmentation.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Mathematics
Stefano Berrone, Francesco Della Santa, Antonio Mastropietro, Sandra Pieraccini, Francesco Vaccarino
Summary: In this work, a new architecture called graph-informed neural network (GINN) is proposed to extend the application of spatial-based graph convolutional networks. This new architecture is specifically designed for regression tasks on graph-structured data that are not suitable for traditional graph neural networks. By formulating a new graph-informed (GI) layer that utilizes the adjacent matrix of a given graph, GINN demonstrates promising regression abilities and potentialities. A real-world application of GINN in flux regression problem in underground networks of fractures is also presented.
Article
Environmental Sciences
Lingjun Zhao, Yuli Sun, Lin Lei, Siqian Zhang
Summary: This paper proposes an auto-weighted structured graph (AWSG)-based regression method for heterogeneous change detection using remote sensing images. The method learns the image structure and performs structure regression to detect changes. Experimental results and comparisons demonstrate the effectiveness of the proposed approach.
Article
Computer Science, Information Systems
Kyeong-Ri Ko, Sung Bum Pan
Summary: This study overcomes the limitations of the existing three-dimensional golf swing analysis system by utilizing deep learning technology to analyze three-dimensional quantitative information from sequence images acquired with a single camera. The results demonstrate the feasibility and accuracy of three-dimensional quantitative analysis based on sequence images.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Ruyi Zhang, Dingcheng Tian, Dechao Xu, Wei Qian, Yudong Yao
Summary: This paper studies the current research on deep learning in the field of wound image analysis, including classification, detection, and segmentation. It reviews publicly available datasets and investigates the preprocessing methods used in wound image analysis. Various models used in different deep learning tasks and their applications in different types of wounds are explored. The challenges in the field of wound image analysis using deep learning are discussed, and the research and development prospects are provided.
Article
Computer Science, Information Systems
Esam A. Al Qaralleh, Halah Nassif, Bassam A. Y. Alqaralleh
Summary: Tongue diagnosis is commonly used in a non-invasive manner for supplementary diagnosis globally. This paper presents a novel FHDF-TCIA technique that combines handcrafted features with deep learning for biomedical applications, achieving high accuracy in disease detection.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Automation & Control Systems
Zhiyang Zheng, Hao Yan, Frank C. Setzer, Katherine J. Shi, Mel Mupparapu, Jing Li
Summary: Unlike other branches of healthcare, the development of AI capabilities in dental care is relatively slow, particularly in the automation of CBCT segmentation and lesion detection. Challenges such as content-rich oral cavity, significant within-label variation, and obtaining high-quality labeled images hinder research progress in this area. Integration of oral-anatomical knowledge into deep learning algorithms can improve the accuracy of lesion detection and segmentation, even with limited training samples. This can benefit practitioners by reducing labeling efforts and enhancing the advantages of AI in dental care automation.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2021)
Article
Environmental Sciences
Lu Fan, Xiaoying Chen, Yong Wan, Yongshou Dai
Summary: Since the Industrial Revolution, methane has become the second most important greenhouse gas component, causing serious climate change problems. Storage tanks play a significant role in methane emissions during oil and gas extraction and processing. Therefore, using high-resolution remote sensing image data to accurately monitor storage tanks is crucial to achieve carbon neutrality and carbon peaking.
Article
Biochemical Research Methods
Yue Ming, Xiying Dong, Jihuai Zhao, Zefu Chen, Hao Wang, Nan Wu
Summary: This study proposes a computer-aided deep learning framework for detecting cervical cancer, aiming to improve the efficiency of clinical diagnosis. By fusing multimodal medical images, the proposed method improves the recognition accuracy on multiple object detection models by an average of 6.06% compared to PET and 8.9% compared to other multimodal fusion methods.
Article
Geography, Physical
Yuli Sun, Lin Lei, Xiang Tan, Dongdong Guan, Junzheng Wu, Gangyao Kuang
Summary: This research proposes an unsupervised image regression method based on the inherent structure consistency between heterogeneous images for change detection in multimodal remote sensing images. The proposed method effectively addresses the problem of comparing heterogeneous images and achieves improved detection accuracy compared to state-of-the-art algorithms.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Review
Biochemical Research Methods
Soumyabrata Banik, Sindhoora Kaniyala Melanthota, Arbaaz, Joel Markus Vaz, Vishak Madhwaraj Kadambalithaya, Iftak Hussain, Sibasish Dutta, Nirmal Mazumder
Summary: Smartphone-based imaging devices have a wide range of biomedical applications, including histopathological examination, detection of bacteria and viruses, food technology, and routine diagnosis. The optical arrangement of these devices can be adjusted based on specific requirements, enhancing their versatility and applicability in various settings. These devices are also enhanced with deep learning methods to improve efficiency.
ANALYTICAL AND BIOANALYTICAL CHEMISTRY
(2021)
Article
Chemistry, Analytical
Firat Hardalac, Fatih Uysal, Ozan Peker, Murat Ciceklidag, Tolga Tolunay, Nil Tokgoz, Ugurhan Kutbay, Boran Demirciler, Fatih Mert
Summary: This study aims to perform fracture detection using deep-learning on wrist X-ray images to support physicians in diagnosing fractures, particularly in emergency services. The research achieved the highest detection result of 0.8639 average precision (AP50) in the developed ensemble model 'wrist fracture detection-combo (WFD-C)'. Huawei Turkey R&D Center supports this study in collaboration with Gazi University and Medskor.
Article
Computer Science, Software Engineering
Tian Bai, Chunyu Wang, Ye Wang, Lan Huang, Fuyong Xing
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2020)
Article
Computer Science, Artificial Intelligence
Xiaoshuang Shi, Zhenhua Guo, Fuyong Xing, Yun Liang, Lin Yang
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2020)
Article
Computer Science, Artificial Intelligence
Xiaoshuang Shi, Hai Su, Fuyong Xing, Yun Liang, Gang Qu, Lin Yang
MEDICAL IMAGE ANALYSIS
(2020)
Article
Computer Science, Interdisciplinary Applications
Fuyong Xing, Toby C. Cornish, Tellen D. Bennett, Debashis Ghosh
Summary: This study introduces a method for nucleus detection in cross-modality microscopy image data through bidirectional adversarial domain adaptation, extending unsupervised domain adaptation to semi-supervised learning to improve nucleus detection performance.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jonathan Wehrend, Michael Silosky, Fuyong Xing, Bennett B. Chin
Summary: This study developed a rapid and specific method using a 2D U-Net convolutional neural network to identify hepatic lesions in Ga-68-DOTATATE PET/CT images. The results showed promising performance metrics, indicating the potential for automatic detection of lesions in future studies.
Article
Radiology, Nuclear Medicine & Medical Imaging
Sarah M. Ryan, Nichole E. Carlson, Harris Butler, Tasha E. Fingerlin, Lisa A. Maier, Fuyong Xing
Summary: CLAM is a transparent methodology for identifying explainable groupings of medical imaging data, which is critical for understanding cluster assignments. In medical imaging applications, CLAM performs well in image clusters with different sizes, locations, and intensities of abnormalities, and identifies two pathological subtypes in computed tomography scans of sarcoidosis patients.
JOURNAL OF MEDICAL IMAGING
(2022)
Article
Computer Science, Interdisciplinary Applications
Jiawei Liu, Fuyong Xing, Abbas Shaikh, Brooke French, Marius George Linguraru, Antonio R. Porras
Summary: Image segmentation, labeling, and landmark detection are important for pediatric craniofacial evaluation. This paper proposes a novel end-to-end neural network architecture based on DenseNet that incorporates context regularization to improve the performance of bone labeling and landmark identification.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Fuyong Xing, Toby C. Cornish
Summary: This paper explores a more realistic and challenging scenario for unsupervised domain adaptation in nucleus detection, where target training data is very scarce. The proposed method augments a dual GAN network with a task-specific model and a stochastic, differentiable data augmentation module, achieving competitive or superior performance over fully supervised models on multiple microscopy image datasets.
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT VII
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiawei Liu, Fuyong Xing, Abbas Shaikh, Marius George Linguraru, Antonio R. Porras
Summary: This paper proposes a novel neural network approach for cranial bone labeling and landmark localization, which can perform anatomical segmentation and localization more accurately in medical images.
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT VIII
(2022)
Article
Computer Science, Artificial Intelligence
Xiaoshuang Shi, Fuyong Xing, Kaidi Xu, Pingjun Chen, Yun Liang, Zhiyong Lu, Zhenhua Guo
Summary: The paper proposes a novel loss-based attention mechanism for deep neural networks to mine significant image patches, achieving impressive results in explaining image decision-making.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Xiaoshuang Shi, Fuyong Xing, Zizhao Zhang, Manish Sapkota, Zhenhua Guo, Lin Yang
Summary: By introducing a novel alternative optimization mechanism to linearize the quartic problem, a scalable symmetric discrete hashing algorithm is proposed to gradually and smoothly update each batch of binary codes. The method also includes a greedy symmetric discrete hashing algorithm to update each bit of batch binary codes for further smoothness. The optimization mechanism can be extended to solve non-convex optimization problems in various pairwise based hashing algorithms, showing superior performance in similarity and ranking order retrieval tasks compared to recent methods.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaoshuang Shi, Fuyong Xing, Yuanpu Xie, Zizhao Zhang, Lei Cui, Lin Yang
THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
(2020)
Article
Oncology
Xuhong Zhang, Toby C. Cornish, Lin Yang, Tellen D. Bennett, Debashis Ghosh, Fuyong Xing
JCO CLINICAL CANCER INFORMATICS
(2020)
Article
Medicine, General & Internal
Premanand Tiwari, Kathryn L. Colborn, Derek E. Smith, Fuyong Xing, Debashis Ghosh, Michael A. Rosenberg
Article
Computer Science, Artificial Intelligence
Zizhao Zhang, Pingjun Chen, Mason McGough, Fuyong Xing, Chunbao Wang, Marilyn Bui, Yuanpu Xie, Manish Sapkota, Lei Cui, Jasreman Dhillon, Nazeel Ahmad, Farah K. Khalil, Shohreh I. Dickinson, Xiaoshuang Shi, Fujun Liu, Hai Su, Jinzheng Cai, Lin Yang
NATURE MACHINE INTELLIGENCE
(2019)
Article
Computer Science, Artificial Intelligence
Hong Liu, Dong Wei, Donghuan Lu, Xiaoying Tang, Liansheng Wang, Yefeng Zheng
Summary: This study proposes a framework based on hybrid 2D-3D convolutional neural networks for obtaining continuous 3D retinal layer surfaces from OCT volumes. The framework works well with both full and sparse annotations and utilizes alignment displacement vectors and layer segmentation to align the B-scans and segment the layers. Experimental results show that the framework outperforms state-of-the-art 2D deep learning methods in terms of layer segmentation accuracy and cross-B-scan 3D continuity.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Simon Oxenford, Ana Sofia Rios, Barbara Hollunder, Clemens Neudorfer, Alexandre Boutet, Gavin J. B. Elias, Jurgen Germann, Aaron Loh, Wissam Deeb, Bryan Salvato, Leonardo Almeida, Kelly D. Foote, Robert Amaral, Paul B. Rosenberg, David F. Tang-Wai, David A. Wolk, Anna D. Burke, Marwan N. Sabbagh, Stephen Salloway, M. Mallar Chakravarty, Gwenn S. Smith, Constantine G. Lyketsos, Michael S. Okun, William S., Zoltan Mari, Francisco A. Ponce, Andres Lozano, Wolf-Julian Neumann, Bassam Al-Fatly, Andreas Horn
Summary: Spatial normalization is a method to map subject brain images to an average template brain, allowing comparison of brain imaging results. We introduce a novel tool called WarpDrive, which enables manual refinements of image alignment after automated registration. The tool improves accuracy of data representation and aids in understanding patient outcomes.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Ricards Marcinkevics, Patricia Reis Wolfertstetter, Ugne Klimiene, Kieran Chin-Cheong, Alyssia Paschke, Julia Zerres, Markus Denzinger, David Niederberger, Sven Wellmann, Ece Ozkan, Christian Knorr, Julia E. Vogt
Summary: This study presents interpretable machine learning models for predicting the diagnosis, management, and severity of suspected appendicitis using ultrasound images. The proposed models utilize concept bottleneck models (CBM) that facilitate interpretation and intervention by clinicians, without compromising performance or requiring time-consuming image annotation.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Jian-Qing Zheng, Ziyang Wang, Baoru Huang, Ngee Han Lim, Bartlomiej W. Papiez
Summary: This article introduces a new method for medical image registration, which utilizes a separable motion backbone and a residual aligner module to better handle the discontinuous motion of multiple neighboring objects. The proposed method achieves excellent registration results on abdominal CT scans and lung CT scans.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Xiangqiong Wu, Guanghua Tan, Hongxia Luo, Zhilun Chen, Bin Pu, Shengli Li, Kenli Li
Summary: This study develops a user-friendly framework for the automated diagnosis of thyroid nodules in ultrasound videos, simulating the diagnostic workflow of radiologists. By interpreting image characteristics and modeling temporal contextual information, the efficiency and generalizability of the diagnosis can be improved.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Riddhish Bhalodia, Shireen Elhabian, Jadie Adams, Wenzheng Tao, Ladislav Kavan, Ross Whitaker
Summary: This paper introduces DeepSSM, a deep learning-based framework for image-to-shape modeling. By learning the functional mapping from images to low-dimensional shape descriptors, DeepSSM can directly infer statistical representation of anatomy from 3D images. Compared to traditional methods, DeepSSM eliminates the need for heavy manual preprocessing and segmentation, and significantly improves computational time.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Florentin Liebmann, Marco von Atzigen, Dominik Stutz, Julian Wolf, Lukas Zingg, Daniel Suter, Nicola A. Cavalcanti, Laura Leoty, Hooman Esfandiari, Jess G. Snedeker, Martin R. Oswald, Marc Pollefeys, Mazda Farshad, Philipp Furnstahl
Summary: This study presents a marker-less approach for automatic registration and real-time navigation of lumbar spinal fusion surgery using a deep neural network, avoiding radiation exposure and surgical errors. The method was validated on an ex-vivo surgery and a public dataset.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Piyush Tiwary, Kinjawl Bhattacharyya, A. P. Prathosh
Summary: Domain shift refers to the change of distributional characteristics between training and testing datasets, leading to performance drop. For medical image tasks, domain shift can be caused by changes in imaging modalities, devices, and staining mechanisms. Existing approaches based on generative models suffer from training difficulties and lack of diversity. In this paper, the authors propose the use of energy-based models (EBMs) for unpaired image-to-image translation in medical images. The proposed method, called Cycle Consistent Twin EBMs (CCT-EBM), employs a pair of EBMs in the latent space of an Auto-Encoder to ensure translation symmetry and coupling between domains.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Yutong Xie, Jianpeng Zhang, Lingqiao Liu, Hu Wang, Yiwen Ye, Johan Verjans, Yong Xia
Summary: This paper proposes a hybrid pre-training paradigm that combines self-supervised learning and supervised learning to improve the representation quality for medical image segmentation tasks. It introduces a reference task in self-supervised learning and optimizes the model using a gradient matching method. The experimental results demonstrate the effectiveness of this approach on multiple medical image segmentation benchmarks.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Youyi Song, Jing Zou, Kup-Sze Choi, Baiying Lei, Jing Qin
Summary: Cell classification is crucial for intelligent cervical cancer screening, but the variation in cells' appearance and shape poses challenges. A new learning algorithm, worse-case boosting, is proposed to improve classification accuracy for under-represented data. Experimental results demonstrate the effectiveness of this algorithm in two publicly available datasets, achieving a 4% improvement in accuracy.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Sangjoon Park, Eun Sun Lee, Kyung Sook Shin, Jeong Eun Lee, Jong Chul Ye
Summary: The increasing demand for AI systems to monitor human errors and abnormalities in healthcare presents challenges. This study presents a model called Medical X-VL, which is tailored for the medical domain and outperformed current state-of-the-art models in two medical image datasets. The model enables various zero-shot tasks for monitoring AI in the medical domain.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Anna Klimovskaia Susmelj, Berkan Lafci, Firat Ozdemir, Neda Davoudi, Xose Luis Dean-Ben, Fernando Perez-Cruz, Daniel Razansky
Summary: Optoacoustic imaging is a technique that uses optical excitation and ultrasound detection for biological tissue imaging. The quality of the images depends on the extent of tomographic coverage provided by the ultrasound detector arrays. However, full coverage is not always possible due to experimental constraints. The proposed signal domain adaptation network aims to reduce limited-view artifacts in the images.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Srijay Deshpande, Muhammad Dawood, Fayyaz Minhas, Nasir Rajpoot
Summary: In this work, a novel framework called SynCLay is proposed for automated synthesis of histology images based on user-defined cellular layouts. The framework can generate realistic and high-quality histology images with different cellular arrangements, which is helpful for studying the role of cells in the tumor microenvironment. The framework integrates a nuclear segmentation and classification model to refine nuclear structures and generate nuclear masks. Evaluation using quantitative metrics and feedback from pathologists shows that the synthetic images generated by SynCLay have high realism scores and can accurately differentiate between benign and malignant tumors.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Ahmed H. Shahin, An Zhao, Alexander C. Whitehead, Daniel C. Alexander, Joseph Jacob, David Barber
Summary: Survival analysis is a valuable tool in healthcare for predicting the time to specific events. This paper introduces CenTime, a novel approach that directly estimates the time to event. The method performs well with censored data and can be easily integrated with deep learning models. Compared to standard methods, CenTime offers superior performance in predicting event time while maintaining comparable ranking performance.
MEDICAL IMAGE ANALYSIS
(2024)
Article
Computer Science, Artificial Intelligence
Bingyuan Liu, Jose Dolz, Adrian Galdran, Riadh Kobbi, Ismail Ben Ayed
Summary: Most segmentation losses, such as CE and Dice, are variants of the Cross-Entropy or Dice losses. This work provides a theoretical analysis that shows a deeper connection between CE and Dice than previously thought. From a constrained-optimization perspective, both CE and Dice decompose into similar ground-truth matching terms and region-size penalty terms. The analysis uncovers hidden region-size biases: Dice has an intrinsic bias towards extremely imbalanced solutions, while CE implicitly encourages the ground-truth region proportions. Based on this analysis, a principled and simple solution is proposed to explicitly control the region-size bias.
MEDICAL IMAGE ANALYSIS
(2024)