nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation

Isensee, Fabian; Jaeger, Paul F.; Kohl, Simon A. A.; Petersen, Jens; Maier‐Hein, Klaus H.

doi:10.1038/s41592-020-01008-z

Cited by 4,311 publications

(2,909 citation statements)

References 36 publications

Supporting

Mentioning

2,882

Contrasting

Unclassified

Order By: Relevance

“…(2) A deep learning-based model named AnatomyNet [30], which is a variant of U-Net for OAR segmentation. (3) The first segmentation approach, named, nnU-Net, that was specifically developed to work with the dataset diversity [31]. It simplifies and automates the critical decisions involved in creating a reliable segmentation pipeline for any dataset.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy

Chen

Sun

Bai³

et al. 2021

Radiotherapy and Oncology

110

View full text Add to dashboard Cite

Section: Comparison With Other Methodsmentioning

confidence: 99%

A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy

Chen

Sun

Bai³

et al. 2021

Radiotherapy and Oncology

110

View full text Add to dashboard Cite

“…Recently, deep learning methods with good performance have been proposed for the segmentation of cerebral aneurysms [2][3][4].U-Net network, first published at the MICCAI conference in 2015 by Ronneberger et al [5], is a widely used deep neural network in medical image segmentation due to its good performance [6,7], and many U-Shaped semantic segmentation networks have been proposed. Alom et al [8] used cyclic convolution network and cyclic residual convolution network to improve the accuracy of segmentation networks based on R2U-Net, and tested the model on different medical images such as blood vessels, lungs and skin.…”

Section: Introductionmentioning

confidence: 99%

“…Alom et al [8] used cyclic convolution network and cyclic residual convolution network to improve the accuracy of segmentation networks based on R2U-Net, and tested the model on different medical images such as blood vessels, lungs and skin. Isensee et al [7] proposed a nnU-Net network that allows high flexibility in terms of the input data set. The nnU-Net can automatically adjust the necessary relevant parameters (e.g.…”

Section: Introductionmentioning

confidence: 99%

3D Attention U-Net with Pretraining: A Solution to CADA-Aneurysm Segmentation Challenge

Jia²,

Liao

et al. 2021

Cerebral Aneurysm Detection

View full text Add to dashboard Cite

Early detection and accurate segmentation of cerebral aneurysm is important for clinical diagnosis and prevention of rupture, which would be life threatening. 3D images can provide abundant information for characterizing the aneurysm. But the traditional manual segmentation of aneurysms takes lots of time and effort. Therefore, accurate and rapid automatic algorithm for 3D segmentation of aneurysm is needed. U-Net is a widely used deep learning network in medical image segmentation, but its performance is limited by the amount of data. In this challenge of aneurysm segmentation, we proposed to add attention gate and Models Genesis pretraining mechanisms to the classical U-Net model to improve the results. The dice of 3D U-net, 3D Attention U-Net, pretrained 3D U-Net and pretrained 3D Attention U-Net are 0.881, 0.884, 0.890 and 0.907, respectively. The experimental results show that the use of attention gate and Models Genesis can significantly improve the performance of U-Net model in segmenting aneurysms. This work achieved rank one in CADA 2020-Aneurysm Segmentation Challenge.

show abstract

“…Based on the fact that PCLs are anatomically strictly associated with the pancreas, the first step was automatic segmentation of the organ using a nnU-Net pretrained on the 282 CTs of the pancreas (portal venous phase) from the public Medical Segmentation Decathlon, reaching a DSC of 82% [ 30 ]. Based on the predicted segmentations of the pancreas, the abdominal CT scans were cropped to the CT slices that show the organ.…”

Section: Methodsmentioning

confidence: 99%

Automated Detection of Pancreatic Cystic Lesions on CT Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

Pancreatic cystic lesions (PCL) are a frequent and underreported incidental finding on CT scans and can transform into neoplasms with devastating consequences. We developed and evaluated an algorithm based on a two-step nnU-Net architecture for automated detection of PCL on CTs. A total of 543 cysts on 221 abdominal CTs were manually segmented in 3D by a radiology resident in consensus with a board-certified radiologist specialized in abdominal radiology. This information was used to train a two-step nnU-Net for detection with the performance assessed depending on lesions’ volume and location in comparison to three human readers of varying experience. Mean sensitivity was 78.8 ± 0.1%. The sensitivity was highest for large lesions with 87.8% for cysts ≥220 mm3 and for lesions in the distal pancreas with up to 96.2%. The number of false-positive detections for cysts ≥220 mm3 was 0.1 per case. The algorithm’s performance was comparable to human readers. To conclude, automated detection of PCL on CTs is feasible. The proposed model could serve radiologists as a second reading tool. All imaging data and code used in this study are freely available online.

show abstract

nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation

Cited by 4,311 publications

References 36 publications

A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy

A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy

3D Attention U-Net with Pretraining: A Solution to CADA-Aneurysm Segmentation Challenge

Automated Detection of Pancreatic Cystic Lesions on CT Using Deep Learning

Contact Info

Product

Resources

About