Automated ischemic stroke lesion segmentation from 3D MRI
- URL: http://arxiv.org/abs/2209.09546v2
- Date: Wed, 21 Sep 2022 08:42:03 GMT
- Title: Automated ischemic stroke lesion segmentation from 3D MRI
- Authors: Md Mahfuzur Rahman Siddique, Dong Yang, Yufan He, Daguang Xu, Andriy
Myronenko
- Abstract summary: Ischemic Stroke Lesion challenge (ISLES 2022) offers a platform for researchers to compare their solutions to 3D segmentation of ischemic stroke regions from 3D MRIs.
We re-sample all images to a common resolution, use two input MRI modalities (DWI and ADC) and train SegResNet semantic segmentation network from MONAI.
- Score: 8.52488593202588
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Ischemic Stroke Lesion Segmentation challenge (ISLES 2022) offers a platform
for researchers to compare their solutions to 3D segmentation of ischemic
stroke regions from 3D MRIs. In this work, we describe our solution to ISLES
2022 segmentation task. We re-sample all images to a common resolution, use two
input MRI modalities (DWI and ADC) and train SegResNet semantic segmentation
network from MONAI. The final submission is an ensemble of 15 models (from 3
runs of 5-fold cross validation). Our solution (team name NVAUTO) achieves the
top place in terms of Dice metric (0.824), and overall rank 2 (based on the
combined metric ranking).
Related papers
- TotalSegmentator MRI: Sequence-Independent Segmentation of 59 Anatomical Structures in MR images [62.53931644063323]
In this study we extended the capabilities of TotalSegmentator to MR images.
We trained an nnU-Net segmentation algorithm on this dataset and calculated similarity coefficients (Dice) to evaluate the model's performance.
The model significantly outperformed two other publicly available segmentation models (Dice score 0.824 versus 0.762; p0.001 and 0.762 versus 0.542; p)
arXiv Detail & Related papers (2024-05-29T20:15:54Z) - Automated 3D Segmentation of Kidneys and Tumors in MICCAI KiTS 2023
Challenge [11.820386742605539]
We describe our submission to the Kidney and Kidney Tumor Challenge (KiTS) 2023.
Our solution achieves the average dice of 0.835 and surface dice of 0.723, which ranks first and wins the KiTS 2023 challenge.
arXiv Detail & Related papers (2023-10-06T09:20:22Z) - 3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic
Segmentation on VSPW [68.56017675820897]
In this paper, we introduce 3rd place solution for PVUW2023 VSS track.
We have explored various image-level visual backbones and segmentation heads to tackle the problem of video semantic segmentation.
arXiv Detail & Related papers (2023-06-04T07:50:38Z) - Automated head and neck tumor segmentation from 3D PET/CT [9.814838162752112]
Head and neck tumor segmentation challenge (HECKTOR) 2022 offers a platform to compare solutions to segmentation of tumors and lymph nodes from 3D CT and PET images.
We re-sample all images to a common resolution, crop around head and neck region, and train SegResNet semantic segmentation network from MONAI.
Our solution achieves the 1st place on the HECKTOR22 challenge leaderboard with an aggregated dice score of 0.78802.
arXiv Detail & Related papers (2022-09-22T06:24:09Z) - Automated segmentation of intracranial hemorrhages from 3D CT [9.814838162752114]
Intracranial hemorrhage segmentation challenge (INSTANCE 2022) offers a platform for researchers to compare their solutions to segmentation of hemorrhage stroke regions from 3D CTs.
We use a 2D segmentation network, SegResNet from MONAI, operating slice-wise without resampling.
arXiv Detail & Related papers (2022-09-21T20:37:32Z) - COSMOS: Cross-Modality Unsupervised Domain Adaptation for 3D Medical
Image Segmentation based on Target-aware Domain Translation and Iterative
Self-Training [6.513315990156929]
We propose a self-training based unsupervised domain adaptation framework for 3D medical image segmentation named COSMOS.
Our target-aware contrast conversion network translates source domain annotated T1 MRI to pseudo T2 MRI to enable segmentation training on target domain.
COSMOS won the 1textsuperscriptst place in the Cross-Modality Domain Adaptation (crossMoDA) challenge held in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021)
arXiv Detail & Related papers (2022-03-30T18:00:07Z) - 3-Dimensional Deep Learning with Spatial Erasing for Unsupervised
Anomaly Segmentation in Brain MRI [55.97060983868787]
We investigate whether using increased spatial context by using MRI volumes combined with spatial erasing leads to improved unsupervised anomaly segmentation performance.
We compare 2D variational autoencoder (VAE) to their 3D counterpart, propose 3D input erasing, and systemically study the impact of the data set size on the performance.
Our best performing 3D VAE with input erasing leads to an average DICE score of 31.40% compared to 25.76% for the 2D VAE.
arXiv Detail & Related papers (2021-09-14T09:17:27Z) - DivergentNets: Medical Image Segmentation by Network Ensemble [0.6372261626436676]
Detection of colon polyps has become a trending topic in the fields of machine learning and gastrointestinal endoscopy.
polyp segmentation has the advantage of being more accurate than per-frame classification or object detection as it can show the affected area in greater detail.
We propose a segmentation model named TriUNet composed of three separate UNet models.
We combine TriUNet with an ensemble of well-known segmentation models, namely UNet++, FPN, DeepLabv3, and DeepLabv3+, into a model called DivergentNets to produce more generalizable medical image segmentation masks.
arXiv Detail & Related papers (2021-07-01T08:15:00Z) - Cross-Modality Brain Tumor Segmentation via Bidirectional
Global-to-Local Unsupervised Domain Adaptation [61.01704175938995]
In this paper, we propose a novel Bidirectional Global-to-Local (BiGL) adaptation framework under a UDA scheme.
Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor.
The proposed method outperforms several state-of-the-art unsupervised domain adaptation methods by a large margin.
arXiv Detail & Related papers (2021-05-17T10:11:45Z) - H2NF-Net for Brain Tumor Segmentation using Multimodal MR Imaging: 2nd
Place Solution to BraTS Challenge 2020 Segmentation Task [96.49879910148854]
Our H2NF-Net uses the single and cascaded HNF-Nets to segment different brain tumor sub-regions.
We trained and evaluated our model on the Multimodal Brain Tumor Challenge (BraTS) 2020 dataset.
Our method won the second place in the BraTS 2020 challenge segmentation task out of nearly 80 participants.
arXiv Detail & Related papers (2020-12-30T20:44:55Z) - VerSe: A Vertebrae Labelling and Segmentation Benchmark for
Multi-detector CT Images [121.31355003451152]
Large Scale Vertebrae Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020.
We present the the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at different fields-of-view.
arXiv Detail & Related papers (2020-01-24T21:09:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.