Shape-Aware Organ Segmentation by Predicting Signed Distance Maps DOI Open Access
Yuan Xue, Hui Tang, Zhi Qiao

et al.

Proceedings of the AAAI Conference on Artificial Intelligence, Journal Year: 2020, Volume and Issue: 34(07), P. 12565 - 12572

Published: April 3, 2020

In this work, we propose to resolve the issue existing in current deep learning based organ segmentation systems that they often produce results do not capture overall shape of target and lack smoothness. Since there is a rigorous mapping between Signed Distance Map (SDM) calculated from object boundary contours binary map, exploit feasibility SDM directly medical scans. By converting task into predicting an SDM, show our proposed method retains superior performance has better smoothness continuity shape. To leverage complementary information traditional training, introduce approximated Heaviside function train model by SDMs maps simultaneously. We validate models conducting extensive experiments on hippocampus dataset public MICCAI 2015 Head Neck Auto Segmentation Challenge with multiple organs. While carefully designed backbone 3D network improves Dice coefficient more than 5% compared state-of-the-arts, produces smoother smaller Hausdorff distance average surface distance, thus proving effectiveness method.

Language: Английский

A review of deep learning based methods for medical image multi-organ segmentation DOI
Yabo Fu, Yang Lei, Tonghe Wang

et al.

Physica Medica, Journal Year: 2021, Volume and Issue: 85, P. 107 - 122

Published: May 1, 2021

Language: Английский

Citations

181
Attention-Enriched Deep Learning Model for Breast Tumor Segmentation in Ultrasound Images DOI
Aleksandar Vakanski, Min Xian,

Phoebe E. Freer

et al.

Ultrasound in Medicine & Biology, Journal Year: 2020, Volume and Issue: 46(10), P. 2819 - 2833

Published: July 21, 2020

Language: Английский

Citations

159
How Well Do Deep Learning-Based Methods for Land Cover Classification and Object Detection Perform on High Resolution Remote Sensing Imagery? DOI Creative Commons
Xin Zhang, Liangxiu Han, Lianghao Han

et al.

Remote Sensing, Journal Year: 2020, Volume and Issue: 12(3), P. 417 - 417

Published: Jan. 28, 2020

Land cover information plays an important role in mapping ecological and environmental changes Earth’s diverse landscapes for ecosystem monitoring. Remote sensing data have been widely used the study of land cover, enabling efficient Earth surface from Space. Although availability high-resolution remote imagery increases significantly every year, traditional analysis approaches based on pixel object levels are not optimal. Recent advancement deep learning has achieved remarkable success image recognition field shown potential high spatial resolution applications, including classification detection. In this paper, a comprehensive review detection using is provided. Through two case studies, we demonstrated applications state-of-the-art models to evaluated their performances against approaches. For task, deep-learning-based methods provide end-to-end solution by both spectral information. They better performance than pixel-based method, especially categories different vegetation. objective method more 98% accuracy large area; its efficiency could relieve burden traditional, labour-intensive method. However, considering diversity data, training datasets required order improve generalisation robustness learning-based models.

Language: Английский

Citations

150
A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy DOI Creative Commons
Xuming Chen, Shanlin Sun,

Narisu Bai

et al.

Radiotherapy and Oncology, Journal Year: 2021, Volume and Issue: 160, P. 175 - 184

Published: May 4, 2021

Delineating organs at risk (OARs) on computed tomography (CT) images is an essential step in radiation therapy; however, it notoriously time-consuming and prone to inter-observer variation. Herein, we report a deep learning-based automatic segmentation (AS) algorithm (WBNet) that can accurately efficiently delineate all major OARs the entire body directly CT scans.We collected 755 scans of head neck, thorax, abdomen, pelvis manually delineated 50 images. The with contours were split into training test sets consisting 505 250 cases, respectively, develop validate WBNet. volumetric Dice similarity coefficient (DSC) 95th-percentile Hausdorff distance (95% HD) calculated evaluate delineation quality for each OAR. We compared performance WBNet three AS algorithms: one commercial multi-atlas-based (ABAS) software, two algorithms, namely, AnatomyNet nnU-Net. have also evaluated time saving dose accuracy WBNet.WBNet achieved average DSCs 0.84 0.81 in-house public datasets, which outperformed ABAS, AnatomyNet, could reduce significantly perform well treatment planning, clinically acceptable differences those manual delineation.This study shows feasibility benefits using clinical practice.

Language: Английский

Citations

120
Deep-Learning-Based Multispectral Satellite Image Segmentation for Water Body Detection DOI Creative Commons
Kunhao Yuan,

Xu Zhuang,

Gerald Schaefer

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2021, Volume and Issue: 14, P. 7422 - 7434

Published: Jan. 1, 2021

Automated water body detection from satellite imagery is a fundamental stage for urban hydrological studies. In recent years, various deep convolutional neural network (DCNN)-based methods have been proposed to segment remote sensing data collected by conventional RGB or multispectral such However, how effectively explore the wider spectrum bands of sensors achieve significantly better performance compared use only has left underexplored. this article, we propose novel DCNN model-multichannel (MC-WBDN)-that incorporates three innovative components, i.e., multichannel fusion module, an Enhanced Atrous Spatial Pyramid Pooling and Space-to-Depth/Depth-to-Space operations, outperform state-of-the-art DCNN-based methods. Experimental results convincingly show that our MC-WBDN model achieves remarkable performance, more robust light weather variations, can distinguish tiny bodies other models.

Language: Английский

Citations

114
Recent advances on loss functions in deep learning for computer vision DOI
Yingjie Tian, Duo Su, Stanislao Lauria

et al.

Neurocomputing, Journal Year: 2022, Volume and Issue: 497, P. 129 - 158

Published: May 5, 2022

Language: Английский

Citations

95
CariesNet: a deep learning approach for segmentation of multi-stage caries lesion from oral panoramic X-ray image DOI Open Access
Haihua Zhu, Zheng Cao, Luya Lian

et al.

Neural Computing and Applications, Journal Year: 2022, Volume and Issue: 35(22), P. 16051 - 16059

Published: Jan. 7, 2022

Language: Английский

Citations

89
Deep learning empowered volume delineation of whole-body organs-at-risk for accelerated radiotherapy DOI Creative Commons
Feng Shi,

Weigang Hu,

Jiaojiao Wu

et al.

Nature Communications, Journal Year: 2022, Volume and Issue: 13(1)

Published: Nov. 2, 2022

In radiotherapy for cancer patients, an indispensable process is to delineate organs-at-risk (OARs) and tumors. However, it the most time-consuming step as manual delineation always required from radiation oncologists. Herein, we propose a lightweight deep learning framework treatment planning (RTP), named RTP-Net, promote automatic, rapid, precise initialization of whole-body OARs Briefly, implements cascade coarse-to-fine segmentation, with adaptive module both small large organs, attention mechanisms organs boundaries. Our experiments show three merits: 1) Extensively evaluates on 67 tasks large-scale dataset 28,581 cases; 2) Demonstrates comparable or superior accuracy average Dice 0.95; 3) Achieves near real-time in <2 s. This could be utilized accelerate contouring All-in-One scheme, thus greatly shorten turnaround time patients.

Language: Английский

Citations

77
A review on the use of deep learning for medical images segmentation DOI

Manar Aljabri,

Manal Alghamdi

Neurocomputing, Journal Year: 2022, Volume and Issue: 506, P. 311 - 335

Published: July 28, 2022

Language: Английский

Citations

73
Enhancing head and neck tumor management with artificial intelligence: Integration and perspectives DOI
Nian‐Nian Zhong, Hanqi Wang, Xinyue Huang

et al.

Seminars in Cancer Biology, Journal Year: 2023, Volume and Issue: 95, P. 52 - 74

Published: July 18, 2023

Language: Английский

Citations

45