NAS-Unet: Neural Architecture Search for Medical Image Segmentation

Yu, Weiren; Zhou, Tianbao; Li, Yujie; Qiu, Xiaoyu

doi:10.1109/access.2019.2908991

Cited by 407 publications

(219 citation statements)

References 38 publications

Supporting

Mentioning

200

Contrasting

Unclassified

Order By: Relevance

“…The reduced feature map was then utilized as an input to the next contraction block. The spatial dimensions of the feature maps were halved and the number of feature maps was doubled repeatedly through the down-sampling layer ( Guan et al., 2019 ; Weng et al., 2019 ). The bottleneck layer, which contained two convolution layers but without max pooling, mediated the contraction section and the expansion layer.…”

Section: Methodsmentioning

confidence: 99%

Sorghum Panicle Detection and Counting Using Unmanned Aerial System Images and Deep Learning

Lin

Guo

2020

Front. Plant Sci.

View full text Add to dashboard Cite

Machine learning and computer vision technologies based on high-resolution imagery acquired using unmanned aerial systems (UAS) provide a potential for accurate and efficient high-throughput plant phenotyping. In this study, we developed a sorghum panicle detection and counting pipeline using UAS images based on an integration of image segmentation and a convolutional neural networks (CNN) model. A UAS with an RGB camera was used to acquire images (2.7 mm resolution) at 10-m height in a research field with 120 small plots. A set of 1,000 images were randomly selected, and a mask was developed for each by manually delineating sorghum panicles. These images and their corresponding masks were randomly divided into 10 training datasets, each with a different number of images and masks, ranging from 100 to 1,000 with an interval of 100. A U-Net CNN model was built using these training datasets. The sorghum panicles were detected and counted by a predicted mask through the algorithm. The algorithm was implemented using Python with the Tensorflow library for the deep learning procedure and the OpenCV library for the process of sorghum panicle counting. Results showed the accuracy had a general increasing trend with the number of training images. The algorithm performed the best with 1,000 training images, with an accuracy of 95.5% and a root mean square error (RMSE) of 2.5. The results indicate that the integration of image segmentation and the U-Net CNN model is an accurate and robust method for sorghum panicle counting and offers an opportunity for enhanced sorghum breeding efficiency and accurate yield estimation.

show abstract

Section: Methodsmentioning

confidence: 99%

Sorghum Panicle Detection and Counting Using Unmanned Aerial System Images and Deep Learning

Lin

Guo

2020

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…In the meantime, there are also some neural architecture search methods applied to image segmentation that have achieved superior segmentation results, especially for medical image segmentation. NAS-Unet [24] searches a U-like backbone network for medical image segmentation, and V-NAS [25] formulates the structure learning as differentiable neural architecture search, allowing the network to choose among 2D, 3D or Pseudo-3D (P3D) convolutions at each layer. Also, structures such as densely connected encoder-decoder CNN [26] are searched for medical image segmentation.…”

Section: Related Workmentioning

confidence: 99%

AutoSegNet: An Automated Neural Network for Image Segmentation

Zuo

Lam

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Neural Architecture Search (NAS) has drawn significant attention as a tool for automatically constructing deep neural networks. The generated neural networks are mainly applied for image classification, and natural language processing. However, there are increasing demands for image segmentation in various areas, such as medical image processing, satellite image object location, and autopilot technology. We propose a NAS method called Automated Segmentation Network (AutoSegNet), targeting industrial and medical image segmentation. The search architectures are constructed by stacking the downsampling layer, the bridge layer, and the upsampling layer, which are explored by a recurrent neural network. Compared with other related methods for image segmentation, the proposed method has a small search space but can explore most of the-state-of-the-art supervised image segmentation models. We perform verification on two datasets, and the results show that AutoSegNet achieves superior segmentation results with clear and continuous segmented edges, as well as better image details. INDEX TERMS Neural architecture search, image segmentation, deep neural network.

show abstract

“…Taking advantage of U-Net's success, multiple variants emerged in order to increase model performance given different tasks [6], [7]. Despite good performance, such networks often require large amounts of annotated training data, which is not easy to obtain given particular domains such as the medical one.…”

Section: Introductionmentioning

confidence: 99%

BB-UNet: U-Net With Bounding Box Prior

Jurdi

Petitjean

Honeiné

et al. 2020

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Medical image segmentation is the process of anatomically isolating organs for analysis and treatment. Leading works within this domain emerged with the well-known U-Net. Despite its success, recent works have shown the limitations of U-Net to conduct segmentation given image particularities such as noise, corruption or lack of contrast. Prior knowledge integration allows to overcome segmentation ambiguities. This paper introduces BB-UNet (Bounding Box U-Net), a deep learning model that integrates location as well as shape prior onto model training. The proposed model is inspired by U-Net and incorporates priors through a novel convolutional layer introduced at the level of skip connections. The proposed architecture helps in presenting attention kernels onto the neural training in order to guide the model on where to look for the organs. Moreover, it finetunes the encoder layers based on positional constraints. The proposed model is exploited within two main paradigms: as a solo model given a fully supervised framework and as an ancillary model, in a weakly supervised setting. In the current experiments, manual bounding boxes are fed at inference and as such BB-Unet is exploited in a semi-automatic setting; however, BB-Unet has the potential of being part of a fully automated process, if it relies on a preliminary step of object detection. To validate the performance of the proposed model, experiments are conducted on two public datasets: the SegTHOR dataset which focuses on the segmentation of thoracic organs at risk in computed tomography (CT) images, and the Cardiac dataset which is a mono-modal MRI dataset released as part of the Decathlon challenge and dedicated to segmentation of the left atrium. Results show that the proposed method outperforms state-of-the-art methods in fully supervised learning frameworks and registers relevant results given the weakly supervised domain.

show abstract

NAS-Unet: Neural Architecture Search for Medical Image Segmentation

Cited by 407 publications

References 38 publications

Sorghum Panicle Detection and Counting Using Unmanned Aerial System Images and Deep Learning

Sorghum Panicle Detection and Counting Using Unmanned Aerial System Images and Deep Learning

AutoSegNet: An Automated Neural Network for Image Segmentation

BB-UNet: U-Net With Bounding Box Prior

Contact Info

Product

Resources

About