Article
Radiology, Nuclear Medicine & Medical Imaging
Joshua R. Astley, Alberto M. Biancardi, Paul J. C. Hughes, Helen Marshall, Guilhem J. Collier, Ho-Fung Chan, Laura C. Saunders, Laurie J. Smith, Martin L. Brook, Roger Thompson, Sarah Rowland-Jones, Sarah Skeoch, Stephen M. Bianchi, Matthew Q. Hatton, Najib M. Rahman, Ling-Pei Ho, Chris E. Brightling, Louise V. Wain, Amisha Singapuri, Rachael A. Evans, Alastair J. Moss, Gerry P. McCann, Stefan Neubauer, Betty Raman, Jim M. Wild, Bilal A. Tahir
Summary: A generalizable 3D CNN was developed for lung segmentation in 1H-MRI, demonstrating robustness to pathology, acquisition protocol, vendor, and center.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Multidisciplinary Sciences
Yun Jiang, Wenhuan Liu, Chao Wu, Huixiao Yao
Summary: This study proposes a multi-scale and multi-branch convolutional neural network model (MSMB-Net) for retinal image segmentation, which captures global context information on domains of different sizes, integrates shallow and deep semantic information, and embeds an improved attention mechanism to improve segmentation accuracy. Experimental results demonstrate that our proposed method has good segmentation performance in all four benchmark tests compared to existing retinal image segmentation methods.
Article
Neurosciences
Yang Xu, Xianyu He, Guofeng Xu, Guanqiu Qi, Kun Yu, Li Yin, Pan Yang, Yuehui Yin, Hao Chen
Summary: In the field of medical image segmentation, traditional solutions mainly adopt convolutional neural networks (CNNs). This paper proposes a hybrid feature extraction network that combines CNNs and Transformer to better utilize global information for feature extraction and improve the segmentation performance of medical images. Additionally, a multi-dimensional statistical feature extraction module is also introduced to enhance low-dimensional texture features and further improve the segmentation results.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Liwen Zhang, Lianzhen Zhong, Cong Li, Wenjuan Zhang, Chaoen Hu, Di Dong, Zaiyi Liu, Junlin Zhou, Jie Tian
Summary: This study proposes a novel approach for predicting the overall survival risk of human cancer patients based on CT images. By using a multi-task network with tailored attention modules, the method improves the accuracy of OS risk prediction and achieves good results in clinical stage prediction.
Article
Biology
Xunli Fan, Shixi Shan, Xianjun Li, Jinhang Li, Jizong Mi, Jian Yang, Yongqin Zhang
Summary: The study introduces a novel multi-branch convolutional neural network for neonatal brain tissue segmentation, utilizing multi-scale feature extraction and multi-branch attention mechanisms to achieve competitive segmentation results.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Otorhinolaryngology
Andy S. Ding, Alexander Lu, Zhaoshuo Li, Manish Sahu, Deepa Galaiya, Jeffrey H. Siewerdsen, Mathias Unberath, Russell H. Taylor, Francis X. Creighton
Summary: This study evaluates a state-of-the-art deep learning pipeline for semantic segmentation of temporal bone anatomy. The results show that this method has consistently submillimeter accuracy compared to hand-segmented labels, which can greatly improve preoperative planning workflows.
OTOLARYNGOLOGY-HEAD AND NECK SURGERY
(2023)
Article
Environmental Sciences
Zhiying Cao, Wenhui Diao, Xian Sun, Xiaode Lyu, Menglong Yan, Kun Fu
Summary: The study introduces an efficient C3Net model for semantic segmentation of multi-modal remote sensing images, striking a balance between speed and accuracy. By utilizing backbone networks and plug-and-play modules, it effectively extracts and recalibrates multi-modal features, while reducing the number of model parameters by redesigning the semantic contextual extraction module based on lightweight convolutional groups. Additionally, a multi-level knowledge distillation strategy is proposed to enhance the performance of the compact model.
Article
Computer Science, Artificial Intelligence
Yang Qu, Xiaomin Li, Zhennan Yan, Liang Zhao, Lichi Zhang, Chang Liu, Shuaining Xie, Kang Li, Dimitris Metaxas, Wen Wu, Yongqiang Hao, Kerong Dai, Shaoting Zhang, Xiaofeng Tao, Songtao Ai
Summary: The study introduces a deep learning-based method for accurately segmenting pelvic bone tumors in MRI images, which shows superior segmentation accuracy on independent datasets, significant reduction in time consumption, and successful application in improving surgical planning workflow.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Muhammad Junaid Umer, Muhammad Sharif, Mudassar Raza
Summary: This paper proposes a new deep learning-based breast cancer segmentation model, which captures diverse image features using a multi-scale encoder and triple decoder network, and highlights the tumor region using a multi-attention mechanism. The experimental results show that the model achieves good segmentation performance.
COGNITIVE COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Sulaiman Vesal, Iani Gayo, Indrani Bhattacharya, Shyam Natarajan, Leonard S. Marks, Dean C. Barratt, Richard E. Fan, Yipeng Hu, Geoffrey A. Sonn, Mirabela Rusu
Summary: This study introduces a novel 2.5D deep neural network for prostate segmentation on ultrasound images, addressing the challenges of reduced signal-to-noise ratio and artifacts. By combining supervised domain adaptation technique and knowledge distillation loss, the performance drop after model finetuning on new datasets is reduced. The approach achieves high segmentation accuracy and generalizes well in multi-center studies, demonstrating its potential for clinical application.
MEDICAL IMAGE ANALYSIS
(2022)
Article
Chemistry, Multidisciplinary
Wooseok Shin, Min Seok Lee, Sung Won Han
Summary: Colonoscopy is an effective method for detecting polyps to prevent colon cancer. This study proposes a network model called COMMA, which reduces distribution discrepancies by propagating complementary information and achieves good performance.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Interdisciplinary Applications
Dustin Bielecki, Darshil Patel, Rahul Rai, Gary F. Dargush
Summary: This paper introduces a novel deep learning approach that utilizes neural networks to generate fine resolution structures that preserve information from topology optimization. By predicting optimized topologies using parameters like density and nodal deflections, this approach speeds up TO computations and captures essential physics.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
Article
Computer Science, Software Engineering
Pengfei Wang, Yunqi Li, Yaru Sun, Dongzhi He, Zhiqiang Wang
Summary: This paper presents a gastric cancer lesion dataset for gastric tumor image segmentation research and proposes a multiscale boundary neural network (MBNet) for automatically segmenting real tumor area in gastric cancer images. The experimental results demonstrate that the proposed method achieves high accuracy and similarity coefficient, outperforming existing approaches.
Article
Agriculture, Multidisciplinary
Hengxiang He, Yulong Qiao, Ximeng Li, Chunyu Chen, Xingfu Zhang
Summary: By flexibly cascading deconvolution layers and atrous convolution layers, we improved the mask generation branch, resulting in more precise weight measurement of pigs.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Engineering, Biomedical
Bangcheng Zhan, Enmin Song, Hong Liu, Zhenyu Gong, Guangzhi Ma, Chih-Cheng Hung
Summary: This study proposes a medical image segmentation method CFNet based on the multi-view attention mechanism and adaptive fusion strategy. CFNet utilizes the U-Net as the basic network structure, extracts features using the multi-view attention mechanism and feature fusion method, and solves the semantic gap issue through the fusion weight adaptive allocation strategy. Experimental results demonstrate that CFNet outperforms the current state-of-the-art methods in medical image segmentation.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Chemistry, Multidisciplinary
Bo-Yeon Hwang, Jae-Yeol Lee, Junho Jung, Joo-Young Ohe, Young-Gyu Eun, YoungChan Lee, Jung-Woo Lee
APPLIED SCIENCES-BASEL
(2020)
Article
Computer Science, Interdisciplinary Applications
Hyunseok Seo, Charles Huang, Maxime Bassenne, Ruoxiu Xiao, Lei Xing
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2020)
Article
Surgery
Bo-Yeon Hwang, Jung-Woo Lee
JOURNAL OF CRANIOFACIAL SURGERY
(2020)
Article
Chemistry, Multidisciplinary
Min-Soo Kwon, Hyunwoo Lee, Bo-Yeon Hwang, Jung-Woo Lee
APPLIED SCIENCES-BASEL
(2020)
Article
Computer Science, Interdisciplinary Applications
Hyunseok Seo, Maxime Bassenne, Lei Xing
Summary: Deep learning plays a crucial role in various scientific and engineering tasks, with the selection of an optimal loss function being essential for constructing reliable deep learning models. A generalized loss function with adaptive functional parameters is proposed in this study to provide a versatile framework for optimal neural network-based decision-making in small target segmentation. The method demonstrates improved detection and segmentation of lung and liver cancer tumors compared to current state-of-the-art techniques, opening up new opportunities for practical applications including disease diagnosis, treatment planning, and prognosis.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Computer Science, Interdisciplinary Applications
Hyunseok Seo, Lequan Yu, Hongyi Ren, Xiaomeng Li, Liyue Shen, Lei Xing
Summary: The study introduces a new neural network architecture utilizing multiple output channels and implementing consistency regularization through residual learning to improve image segmentation performance. Validation on public data shows significant improvement in tumor detection and delineation, with potential broad applications in various deep learning problems.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Hyunseok Seo, Seohee So, Sojin Yun, Seokjun Lee, Jiseong Barg
Summary: In this study, a spatial feature conservative design for feature extraction in deep neural networks was proposed for target delineation in medical images. The model utilizes multi-scale dilated convolutions and a compensation module to enhance learning efficiency and prevent signal loss, achieving accurate delineation of breast cancer in the images.
APPLICATIONS OF MEDICAL ARTIFICIAL INTELLIGENCE, AMAI 2022
(2022)
Article
Dentistry, Oral Surgery & Medicine
Suyun Seon, Baek-Soo Lee, Byung-Joon Choi, Joo-Young Ohe, Jung-Woo Lee, Junho Jung, Bo-Yeon Hwang, Min-Ah Kim, Yong-Dae Kwon
Summary: Foreign bodies may be left behind in the oral cavity during oral surgical procedures, causing symptoms such as inflammation and pain. Accurate localization and retrieval of lost suture needles may require up-to-date radiographic devices and methods.
MAXILLOFACIAL PLASTIC AND RECONSTRUCTIVE SURGERY
(2021)
Article
Engineering, Biomedical
Hannah Kim, Tae-Geun Son, Hyunchul Cho, Eungjune Shim, Bo-Yeon Hwang, Jung-Woo Lee, Youngjun Kim
COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION
(2020)
Article
Automation & Control Systems
Xiao Jia, Xiaochun Mai, Yi Cui, Yixuan Yuan, Xiaohan Xing, Hyunseok Seo, Lei Xing, Max Q. -H. Meng
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2020)
Review
Dentistry, Oral Surgery & Medicine
Min-Soo Kwon, Baek-Soo Lee, Byung-Joon Choi, Jung-Woo Lee, Joo-Young Ohe, Jun-Ho Jung, Bo-Yeon Hwang, Yong-Dae Kwon
JOURNAL OF THE KOREAN ASSOCIATION OF ORAL AND MAXILLOFACIAL SURGEONS
(2020)