Article
Computer Science, Artificial Intelligence
James R. Clough, Nicholas Byrne, Ilkay Oksuz, Veronika A. Zimmer, Julia A. Schnabel, Andrew P. King
Summary: This method introduces prior knowledge about the topology of segmented objects into the training process of neural networks for image or volume segmentation. The use of persistent homology allows for specifying desired topological features and driving the proposed segmentations to contain these features. The experiments demonstrate the effectiveness of embedding explicit prior knowledge in challenging segmentation tasks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Engineering, Chemical
Yang Liu, Zelin Zhang, Xiang Liu, Lei Wang, Xuhui Xia
Summary: Mineral image segmentation is crucial for intelligent ore sorting equipment, but current methods struggle with adhesion and overlap issues. A new deep learning-based approach shows improved segmentation performance, effectively solving these problems.
ADVANCED POWDER TECHNOLOGY
(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)
Article
Computer Science, Artificial Intelligence
Fran Huzjan, Filip Juric, Sven Loncaric, Milan Vujanovic
Summary: This paper proposes a method for spray macroscopic parameter estimation that achieves state-of-the-art results. Image segmentation is performed to separate the spray from the rest of the image, and then the macroscopic parameters are estimated from the segmented image. The evaluation of the proposed method shows that Min U-Net achieves a mean dice coefficient of 0.95 with an inference time of 11.94 ms/image, and the estimation of spray macroscopic parameters is highly accurate.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Henry Wing Fung Yeung, Meng Zhou, Yuk Ying Chung, Grant Moule, Wayne Thompson, Wanli Ouyang, Weidong Cai, Mohammed Bennamoun
Summary: Satellite images have become more accessible due to government programs and commercial satellites, leading to the development of fast and accurate methods for image segmentation. However, labelling images manually is time-consuming, and using small datasets can hinder machine learning models. This paper proposes solutions to enhance segmentation performance with limited data through transfer learning and steerable filters.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Aocheng Li, Jie Guo, Yanwen Guo
Summary: A new image stitching method is proposed in this paper, which aligns a set of matched dominant semantic planar regions to improve the precision and accuracy of image stitching, utilizing semantic information and deep Convolutional Neural Network.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Xiaonan Fang, Song-Hai Zhang, Tao Chen, Xian Wu, Ariel Shamir, Shi-Min Hu
Summary: In this paper, a user-guided approach for practical human matting is proposed. The method combines the segmentation and matting stage and introduces a residual-learning module for convenient interaction. It provides a good automatic initial matting and allows users to guide the matting in ambiguous situations.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Engineering, Multidisciplinary
Minsik Seo, Seungjae Min
Summary: DL-MSTO+ is a deep learning-based multi-scale topology optimization framework that improves the efficiency of multi-scale topology optimization by reducing the dimensionality of design variables and predicting homogenized material properties. The framework includes two distinct deep neural networks for learning the low-dimensional representation of material microstructures and predicting the homogenized elasticity matrix. The proposed method demonstrates higher efficiency than the conventional multi-scale approach in numerical experiments and provides connectable multi-scale designs.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2023)
Article
Health Care Sciences & Services
Seung Jae Choi, Dae Kon Kim, Byeong Soo Kim, Minwoo Cho, Joo Jeong, You Hwan Jo, Kyoung Jun Song, Yu Jin Kim, Sungwan Kim
Summary: An artificial intelligence algorithm model was developed to assist medical providers in endotracheal intubation for respiratory emergencies. The model can segment intraoral structures, including the tongue, epiglottis, vocal cord, and corniculate cartilage, from video laryngoscope images. Different models showed variations in segmentation performance and processing speed.
Article
Engineering, Multidisciplinary
Haojie Guo, Dedong Yang
Summary: This paper introduces an improved semantic segmentation model named PRDNet, which utilizes ResNet and dilated convolution to simultaneously extract multi-layer features of medical images. The multi-layer features are fused according to the structure of feature pyramid network in the decoding stage. After experiments on CHAOS and ISIC2017 datasets, the proposed algorithm shows a 1%-4% improvement in different evaluation metrics compared to other algorithms.
Article
Multidisciplinary Sciences
Niharika Das, Sujoy Das
Summary: Cardiac magnetic resonance imaging (CMRI) is a non-invasive imaging technique used to analyze the structure and function of the heart, providing functional information for diagnosing and managing cardiovascular disease. CMRI image segmentation provides quantification parameters and the manual segmentation process is time-consuming and subjective. This study utilizes a convolutional neural network model for segmentation tasks, optimizing parameters and establishing the relationship between the epoch hyperparameter and accuracy, achieving an accuracy of 0.88.
Article
Computer Science, Artificial Intelligence
Mohamed Chala, Benayad Nsiri, My Hachem El Yousfi Alaoui, Abdelmajid Soulaymani, Abdelrhani Mokhtari, Brahim Benaji
Summary: This paper presents an automatic method for blood vessel segmentation in retina images using deep Convolutional Neural Networks (CNN). The proposed multi-encoder decoder architecture shows promising results in terms of specificity, accuracy, and precision. Our method outperforms other CNN-based approaches, with a high precision rate on the DRIVE dataset.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Biomedical
Yanjun Peng, Jindong Sun
Summary: In this study, an automatic weighted dilated convolutional network (AD-Net) is proposed to extract multimodal brain tumor features through channel feature separation learning. The method achieved good performance on the BraTS20 dataset.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Electrical & Electronic
Xiang Chen, Yuanchang Liu, Kamalasudhan Achuthan
Summary: In order to improve obstacle detection at sea-sky line areas, WODIS designed an attention refine module (ARM) activated by both global average pooling and max pooling to capture high-level information. Additionally, a feature fusion module (FFM) is introduced to concatenate multidimensional high-level features in the decoder network. The results of testing and cross-validation on four different types of maritime datasets show that the mean intersection over union (mIoU) of WODIS can achieve superior segmentation effects for sea-level obstacles, up to 91.3%.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Multidisciplinary
Martin Ohrt Elingaard, Niels Aage, Jakob Andreas Baerentzen, Ole Sigmund
Summary: This paper presents a deep learning-based de-homogenization method for structural compliance minimization, showing excellent generalization properties and performance within 7-25% of homogenization-based solutions at a fraction of the computational cost, while being robust and insensitive to domain size, boundary conditions, and loading.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2022)
Article
Chemistry, Inorganic & Nuclear
Sean T. Heffernan, Nhat-Cuong Ly, Brock J. Mower, Clement Vachet, Ian J. Schwerdt, Tolga Tasdizen, Luther W. McDonald
Article
Computer Science, Artificial Intelligence
Yunjun Xiao, Jia Wei, Jiabing Wang, Qianli Ma, Shandian Zhe, Tolga Tasdizen
NEURAL COMPUTING & APPLICATIONS
(2020)
Article
Materials Science, Multidisciplinary
Jeffery A. Aguiar, Matthew L. Gong, Tolga Tasdizen
COMPUTATIONAL MATERIALS SCIENCE
(2020)
Article
Public, Environmental & Occupational Health
Jessica M. Keralis, Mehran Javanmardi, Sahil Khanna, Pallavi Dwivedi, Dina Huang, Tolga Tasdizen, Quynh C. Nguyen
Article
Materials Science, Multidisciplinary
Cuong Ly, Clement Vachet, Ian Schwerdt, Erik Abbott, Alexandria Brenkmann, Luther W. McDonald, Tolga Tasdizen
JOURNAL OF NUCLEAR MATERIALS
(2020)
Article
Environmental Sciences
Lynn Phan, Weijun Yu, Jessica M. Keralis, Krishay Mukhija, Pallavi Dwivedi, Kimberly D. Brunisholz, Mehran Javanmardi, Tolga Tasdizen, Quynh C. Nguyen
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2020)
Article
Computer Science, Artificial Intelligence
Wenguang Yuan, Jia Wei, Jiabing Wang, Qianli Ma, Tolga Tasdizen
MEDICAL IMAGE ANALYSIS
(2020)
Article
Engineering, Electrical & Electronic
Mohammad Mehdi Hosseini, Amarachi Umunnakwe, Masood Parvania, Tolga Tasdizen
IEEE TRANSACTIONS ON SMART GRID
(2020)
Article
Engineering, Chemical
Cody A. Nizinski, Alexa B. Hanson, Branden C. Fullmer, Nicholas J. Mecham, Tolga Tasdizen, Luther W. McDonald
MINERALS ENGINEERING
(2020)
Article
Environmental Sciences
Quynh C Nguyen, Yuru Huang, Abhinav Kumar, Haoshu Duan, Jessica M. Keralis, Pallavi Dwivedi, Hsien-Wen Meng, Kimberly D. Brunisholz, Jonathan Jay, Mehran Javanmardi, Tolga Tasdizen
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2020)
Article
Public, Environmental & Occupational Health
Quynh C. Nguyen, Jessica M. Keralis, Pallavi Dwivedi, Amanda E. Ng, Mehran Javanmardi, Sahil Khanna, Yuru Huang, Kimberly D. Brunisholz, Abhinav Kumar, Tolga Tasdizen
Summary: This study utilized big data sources and computer vision technology to analyze the associations between built environment features and health outcomes in 2916 US counties. The findings showed that counties with more crosswalks were associated with lower adult obesity, physical inactivity, and poor self-rated health, highlighting the importance of pedestrian-friendly built environments in promoting better public health.
PUBLIC HEALTH REPORTS
(2021)
Article
Respiratory System
Joyce D. Schroeder, Ricardo Bigolin Lanfredi, Tao Li, Jessica Chan, Clement Vachet, Robert Paine, Vivek Srikumar, Tolga Tasdizen
INTERNATIONAL JOURNAL OF CHRONIC OBSTRUCTIVE PULMONARY DISEASE
(2020)
Proceedings Paper
Engineering, Biomedical
Ertunc Erdil, A. Ozgur Atigtisah, Tolga Tasdizen, Devrim Unay, Mujdat Cetin
2019 IEEE 16TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2019)
(2019)
Article
Public, Environmental & Occupational Health
Quynh C. Nguyen, Sahil Khanna, Pallavi Dwivedi, Dina Huang, Yuru Huang, Tolga Tasdizen, Kimberly D. Brunisholz, Feifei Li, Wyatt Gorman, Thu T. Nguyen, Chengsheng Jiang
PREVENTIVE MEDICINE REPORTS
(2019)
Review
Computer Science, Software Engineering
Xiaoqun Dai, Yan Hong
Summary: The primary objective of this research is to enhance the understanding of fabric mechanical behaviors, measurement techniques, and parameters essential for cloth simulation. The findings and information presented herein can be effectively utilized to enhance the precision and fidelity of apparel CAD systems, thereby facilitating advancements in virtual garment design and production.
COMPUTER-AIDED DESIGN
(2024)
Article
Computer Science, Software Engineering
Zhen-Pei Wang, Brian N. Cox, Shemuel Joash Kuehsamy, Mark Hyunpong Jhon, Olivier Sudre, N. Sridhar, Gareth J. Conduit
Summary: Three-dimensional non-periodic woven composite preforms have great design flexibility, but the design space is too large. This paper proposes a Background Vector Method (BVM) for generating candidate designs that can adapt to local architecture and global design goals while ensuring fabricability. Examples are provided to illustrate the design scope and speed of the BVM, as well as pathways for incorporating it into optimization algorithms.
COMPUTER-AIDED DESIGN
(2024)
Article
Computer Science, Software Engineering
Mohammad Mahdi Behzadi, Jiangce Chen, Horea T. Ilies
Summary: This paper proposes an approach to enhance the topological accuracy of machine learning-based topology optimization methods. The approach utilizes a predicted dual connectivity graph to improve the connectivity of the predicted designs. Experimental results show that the proposed method significantly improves the connectivity of the final predicted structures.
COMPUTER-AIDED DESIGN
(2024)
Article
Computer Science, Software Engineering
Jiaze Li, Shengfa Wang, Eric Paquette
Summary: In this study, a texture-driven adaptive mesh refinement method is proposed to generate high-quality 3D reliefs. By conducting feature-preserving adaptive sampling of the texture contours and using constraint-driven and feature-adaptive mesh subdivision, the method is able to accurately follow the texture contours and maintain good polygon quality.
COMPUTER-AIDED DESIGN
(2024)
Article
Computer Science, Software Engineering
Xi Zou, Sui Bun Lo, Ruben Sevilla, Oubay Hassan, Kenneth Morgan
Summary: This work presents a new method for generating triangular surface meshes in three dimensions for the NURBS-enhanced finite element method. The method allows for triangular elements that span across multiple NURBS surfaces, while maintaining the exact representation of the CAD geometry. This eliminates the need for de-featuring complex watertight CAD models and ensures compliance with user-specified spacing function requirements.
COMPUTER-AIDED DESIGN
(2024)
Article
Computer Science, Software Engineering
Ulderico Fugacci, Chiara Romanengo, Bianca Falcidieno, Silvia Biasotti
Summary: This paper proposes a method for suitably resampling a 3D point cloud while preserving the feature curves to which some points belong. The method enriches the cloud by approximating curvilinear profiles and allows for point removal or insertion without affecting the approximated profiles. The effectiveness of the method is evaluated through experiments and comparisons.
COMPUTER-AIDED DESIGN
(2024)
Article
Computer Science, Software Engineering
J. Hinz, O. Chanon, A. Arrigoni, A. Buffa
Summary: The objective of this study is to address the difficulty of simplifying a geometric model while maintaining the accuracy of the solution. A goal-oriented adaptive strategy is proposed to reintroduce geometric features in regions with significant impact on the quantity of interest. This approach enables faster and more efficient simulations.
COMPUTER-AIDED DESIGN
(2024)
Article
Computer Science, Software Engineering
Hao Qiu, Yixiong Feng, Yicong Gao, Zhaoxi Hong, Jianrong Tan
Summary: Sandwich panels with excellent mechanical properties are widely used, and kirigami-inspired structural designs are receiving increasing attention. In this study, novel graded self-locking kirigami panels based on a tucked-interleaved pattern are developed and analyzed. The experimental and simulation results demonstrate that the proposed kirigami panels have outstanding load-to-weight ratios and can generate graded stiffness and superior specific energy absorption.
COMPUTER-AIDED DESIGN
(2024)
Article
Computer Science, Software Engineering
Zheng Zhan, Wenping Wang, Falai Chen
Summary: This article proposes a learning based method using a deep neural network to simultaneously parameterize the boundary and interior of a computational domain. The method achieves robust parameterization by optimizing a loss function and fitting a tensor-product B-spline function. Experimental results demonstrate that the proposed approach yields parameterization results with lower distortion and higher bijectivity ratio.
COMPUTER-AIDED DESIGN
(2024)