Filters








379 Hits in 3.6 sec

Deep Learning-based Segmentation of Cerebral Aneurysms in 3D TOF-MRA using Coarse-to-Fine Framework [article]

Meng Chen, Chen Geng, Dongdong Wang, Jiajun Zhang, Ruoyu Di, Fengmei Li, Zhiyong Zhou, Sirong Piao, Yuxin Li, Yaikang Dai
2021 arXiv   pre-print
CONCLUSIONS: The coarse-to-fine framework, which composed of DeepMedic and dual-channel SE_3D U-Net can segment cerebral aneurysms in 3D TOF-MRA with a superior accuracy.  ...  Existing automatic segmentation methods based on DLMs with TOF-MRA modality could not segment edge voxels very well, so that our goal is to realize more accurate segmentation of cerebral aneurysms in 3D  ...  After training and validation on 113 cases of data, this study proved that our deep learning model can accurately segment cerebral aneurysms in 3D TOF-MRA.  ... 
arXiv:2110.13432v1 fatcat:pqtyus7p5newflkoonxu7d4cj4

An Automatic Detection Method Of Cerebral Aneurysms In Time-Of-Flight Magnetic Resonance Angiography Images Based On Attention 3D U-Net [article]

Chen Geng, Meng Chen, Ruoyu Di, Dongdong Wang, Liqin Yang, Wei Xia, Yuxin Li, Daoying Geng
2021 arXiv   pre-print
the 3D U-Net was improved by the 3D SENet module to establish an aneurysm detection model.Eventually a set of fully automated,end-to-end aneurysm detection methods have been formed.  ...  deep learning technology in aneurysm detection can effectively improve the screening effect of aneurysm.Existing studies have found that three-dimensional features play an important role in aneurysm detection  ...  3: The proposed attention 3D U-Net network architecture In this step, we designed an attention 3D U-Net network for the detection of aneurysms.  ... 
arXiv:2110.13367v1 fatcat:kv2ihx74dzdfzdr2uktsusg3ae

A Two-step Surface-based 3D Deep Learning Pipeline for Segmentation of Intracranial Aneurysms [article]

Xi Yang, Ding Xia, Taichi Kin, Takeo Igarashi
2021 arXiv   pre-print
In this study, we offer a two-step surface-based deep learning pipeline that achieves significantly higher performance.  ...  While voxel-based deep learning frameworks have been proposed for this segmentation task, their performance remains limited.  ...  Comparison experiments 4.5.1 3D U-Net.  ... 
arXiv:2006.16161v2 fatcat:dt4tazh26vag5mnj3yzxglkreq

Automated computer-assisted detection system for cerebral aneurysms in time-of-flight magnetic resonance angiography using fully convolutional network

Geng Chen, Xia Wei, Huang Lei, Yang Liqin, Li Yuxin, Dai Yakang, Geng Daoying
2020 BioMedical Engineering OnLine  
The system first extracts the volume of interest with a fully automatic vessel segmentation algorithm, then uses 3D-UNet-based fully convolutional network to detect the aneurysm areas.  ...  As the rupture of cerebral aneurysm may lead to fatal results, early detection of unruptured aneurysms may save lives.  ...  Inspired by U-Net, this network could process 3D input blocks of 128*128*128 voxels, and also comprised a context aggregation pathway as U-Net.  ... 
doi:10.1186/s12938-020-00770-7 pmid:32471439 fatcat:rg6awts3czdbbk7dbouzu3icyy

Front Matter: Volume 12036

Barjor S. Gimi, Andrzej Krol
2022 Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging  
.  The last two digits indicate publication order within the volume using a Base 36 numbering system employing both numerals and letters. These two-number sets start with 00,  ...  alveoli cluster analysis of 3D human lung microstructure using synchrotron radiation micro-CT [12036-18] 0H Counting of alveoli in synchrotron radiation 3D CT images using U-Net [12036-19] OPTICAL IMAGING  ...  0I Automated optic disk detection in fundus images using a combination of deep learning and local histogram matching [12036-6] 0J Ex vivo sensing of primordial follicles in ovarian tissues by spectral-domain  ... 
doi:10.1117/12.2638100 fatcat:n63ddu4nkndbfbmf4mmjchujci

MixMicrobleedNet: segmentation of cerebral microbleeds using nnU-Net [article]

Hugo J. Kuijf
2021 arXiv   pre-print
The final method consists of nnU-Net in the "3D full resolution U-Net" configuration trained on all data (fold = 'all'). No post-processing options of nnU-Net were used.  ...  Assessment of cerebral microbleeds is mostly performed by visual inspection.  ...  The final method consists of nnU-Net in the "3D full resolution U-Net" configuration trained on all data (fold = 'all'). No post-processing options of nnU-Net were used.  ... 
arXiv:2108.01389v1 fatcat:rz5t7ptpezcbdecyw4cbfq76hi

Automatic Cerebral Vessel Extraction in TOF-MRA Using Deep Learning [article]

V. de Vos, K.M. Timmins, I.C. van der Schaaf, Y. Ruigrok, B.K. Velthuis, H.J. Kuijf
2021 arXiv   pre-print
All experiments were performed by patch-training both a 2D and 3D U-Net and predicted on a test set of MRAs.  ...  Deep learning approaches may help radiologists in the early diagnosis and timely treatment of cerebrovascular diseases.  ...  (a) 2D U-Net, (b) 3D U-Net. (a) 2D U-Net  ... 
arXiv:2101.09253v1 fatcat:ujyahqkiajav7eo74p44mwm674

Modality agnostic intracranial aneurysm detection through supervised vascular surface classification [article]

Žiga Bizjak, Boštjan Likar, Franjo Pernuš, Žiga Špiclin
2020 arXiv   pre-print
Intracranial aneurysms (IAs) are generally asymptomatic and thus often discovered incidentally on angiographic scans like 3D DSA, CTA and MRA.  ...  Deep learning models trained and executed on angiographic scans seem best-suited for IA detection, however, reported performances across different modalities is currently insufficient for clinical application  ...  [12] employed the "Deepmedic" dual-pathway CNN with 11 layers and validated on 1.5T and 3T 3D TOF-MRA images. Jin et al. [8] trained and tested a combined U-net and BiConvLSTM on 2D DSA images.  ... 
arXiv:2005.14467v1 fatcat:bympww3tunbefimth2zgl73cra

Intracranial Aneurysm Detection from 3D Vascular Mesh Models with Ensemble Deep Learning [chapter]

Mingsong Zhou, Xingce Wang, Zhongke Wu, Jose M. Pozo, Alejandro F. Frangi
2019 Lecture Notes in Computer Science  
We jointly utilize all these five models to detect aneurysms with adaptive weights learning based on back propagation.  ...  We detect the intracranial aneurysms in 3D cerebrovascular mesh models after the segmentation of the brain vessel from the medical images, which can break the barriers of the data format and data distribution  ...  Sichtermann [12] utilized "DeepMedic" with 2 pathways 11 layers network to deal both 3T and 1.5T 3D TOF-MRA together. Jin [5] detected IAs with 2D-DSA sequences combining U-net and BiConvLSTM.  ... 
doi:10.1007/978-3-030-32251-9_27 fatcat:37lja32slnfq5adpxg666b75rm

Deep Learning Based Detection and Localization of Intracranial Aneurysms in Computed Tomography Angiography [article]

Dufan Wu, Daniel Montes, Ziheng Duan, Yangsibo Huang, Javier M. Romero, Ramon Gilberto Gonzalez, Quanzheng Li
2021 arXiv   pre-print
Purpose: To develop CADIA, a supervised deep learning model based on a region proposal network coupled with a false-positive reduction module for the detection and localization of intracranial aneurysms  ...  A two-step model was implemented: a 3D region proposal network for initial aneurysm detection and 3D DenseNetsfor false-positive reduction and further determination of suspicious IA.  ...  a Deep learning for automated cerebral aneurysm detection standardized approach for aneurysm follow-up.  ... 
arXiv:2005.11098v2 fatcat:dkxpigcjejgxni3qcuqp5xfn2a

Deep learning for cerebral angiography segmentation from non-contrast computed tomography

Michał Klimont, Agnieszka Oronowicz-Jaśkowiak, Mateusz Flieger, Jacek Rzeszutek, Robert Juszkat, Katarzyna Jończyk-Potoczna, Yi Su
2020 PLoS ONE  
A deep learning model based on the U-net architecture was trained to perform the segmentation of blood vessels on non-contrast computed tomography.  ...  The aim of this research was to apply deep learning methods to segment cerebral arteries on non-contrast computed tomography scans and consequently, generate angiographies without the need for contrast  ...  Although aneurysms as big as 2.3 cm are not common, in our opinion, it is also not a valid exclusion criterion, as this method could someday be used to detect those aneurysms; however, the aneurysm this  ... 
doi:10.1371/journal.pone.0237092 pmid:32735633 fatcat:kq73n3piq5cojbyq5nz4up5azm

Clinically Applicable Deep Learning for Intracranial Aneurysm Detection in Computed Tomography Angiography Images: A Comprehensive Multicohort Study [article]

Zhao SHI, Chong Chang Miao, Cheng Wei Pan, Xue Chai, Xiu Li Li, Shuang Xia, Yan Gu, Yong Gang Zhang, Bin Hu, Wen Da Xu, Chang Sheng Zhou, Song Luo (+6 others)
2020 medRxiv   pre-print
We presented a novel deep-learning-based framework trained on 1,177 DSA verified bone-removal CTA cases.  ...  The framework had excellent tolerance to the influence of occult cases of CTA-negative but DSA-positive aneurysms, image quality, and manufacturers.  ...  Deep learning for MR angiography: Automated detection of cerebral aneurysms. Radiology 290, 187-194 (2019). 24. Nakao, T. et al.  ... 
doi:10.1101/2020.03.21.20040063 fatcat:24rsr23qxfevblr3fnvkqq244i

3D Intracranial Aneurysm Classification and Segmentation via Unsupervised Dual-branch Learning [article]

Di Shao, Xuequan Lu, Xiao Liu
2022 arXiv   pre-print
While most existing deep learning research focused on medical images in a supervised way, we introduce an unsupervised method for the detection of intracranial aneurysms based on 3D point cloud data.  ...  Intracranial aneurysms are common nowadays and how to detect them intelligently is of great significance in digital health.  ...  Due to the excellent performance of deep learning in processing medical images, there are many deep learning methods to detect intracranial aneurysms [24] . [18] proposed a convolutional neural network-based  ... 
arXiv:2201.02198v2 fatcat:p2tykgne3vaqdnuvzfbvmdeyni

Automatic detection of intracranial aneurysms in 3D-DSA based on a Bayesian optimized filter

Tao Hu, Heng Yang, Wei Ni, Yu Lei, Zhuoyun Jiang, Keke Shi, Jinhua Yu, Yuxiang Gu, Yuanyuan Wang
2020 BioMedical Engineering OnLine  
Aneurysms are detected in 2D or 3D images from different modalities. 3D images can provide more vascular information than 2D images, and it is more difficult to detect.  ...  In this study, we proposed an adaptive multiscale filter to detect intracranial aneurysms on 3D-DSA. Methods Adaptive aneurysm detection consists of three parts.  ...  They combined a deep learning model (U-net) with long short-term memory (LSTM) and obtained an aneurysm detection sensitivity of 89.3%. Rahmany et al.  ... 
doi:10.1186/s12938-020-00817-9 pmid:32933534 fatcat:34tzcpurdbb35nb4ov6auf6sxq

Automatic and Efficient Prediction of Hematoma Expansion in Patients with Hypertensive Intracerebral Hemorrhage Using Deep Learning Based on CT Images

Chao Ma, Liyang Wang, Chuntian Gao, Dongkang Liu, Kaiyuan Yang, Zhe Meng, Shikai Liang, Yupeng Zhang, Guihuai Wang
2022 Journal of Personalized Medicine  
An end-to-end deep learning method based on CT was proposed to automatically segment the hematoma region, region of interest (ROI) feature extraction, and HE prediction.  ...  U-Net with attention performs best in the task of segmenting hematomas, with the mean Intersection overUnion (mIoU) of 0.9025.  ...  After analyzing the image features, the U-Net deep learning architecture was chosen. U-Net, U-Net++, and U-Net with attention were proposed for training and testing.  ... 
doi:10.3390/jpm12050779 fatcat:pkkxaw2p7jgkperw5xiyopeogy
« Previous Showing results 1 — 15 out of 379 results