DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation

By Debesh Jha, Michael Alexander Riegler, Dag Johansen, Pål Halvorsen, Haavard D. Johansen. 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), 2020

819 citations recorded by the source corpus.

Semantic image segmentation is the process of labeling each pixel of an image with its corresponding class. An encoder-decoder based approach, like U-Net and its variants, is a popular strategy for solving medical image segmentation tasks. To improve the performance of U-Net on various segmentation tasks, we propose a novel architecture called DoubleU-Net, which is a combination of two U-Net architectures stacked on top of each other. The first U-Net uses a pre-trained VGG-19 as the encoder, which has already learned features from ImageNet and can be transferred to another task easily. To capture more semantic information efficiently, we added another U-Net at the bottom. We also adopt Atrous Spatial Pyramid Pooling (ASPP) to capture contextual information within the network. We have evaluated DoubleU-Net using four medical segmentation datasets, covering various imaging modalities such as colonoscopy, dermoscopy, and microscopy. Experiments on the MICCAI 2015 segmentation challenge, the CVC-ClinicDB, the 2018 Data Science Bowl challenge, and the Lesion boundary segmentation datasets demonstrate that the DoubleU-Net outperforms U-Net and the baseline models. Moreover, DoubleU-Net produces more accurate segmentation masks, especially in the case of the CVC-ClinicDB and MICCAI 2015 segmentation challenge datasets, which have challenging images such as smaller and flat polyps. These results show the improvement over the existing U-Net model. The encouraging results, produced on various medical image segmentation datasets, show that DoubleU-Net can be used as a strong baseline for both medical image segmentation and cross-dataset evaluation testing to measure the generalizability of Deep Learning (DL) models.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/61af9ff6ec3dbb5299455746a1c63588ccf62cf8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Medical Image Segmentation Review: The Success of U-Net (2022, background): “Dozens of studies modiﬁed the vanilla U-Net main blocks to broaden the receptive ﬁelds of convolution operations and extract rich and ﬁne-grained semantic representations for challenging multi-class problems, e.g., [60], [100], [101], [102], [103].”
DS-TransUNet: Dual Swin Transformer U-Net for Medical Image Segmentation (2021, methodology): “The split and training settings of these datasets are different in [38], [24] and [39], so we conduct experiments according to these three articles respectively.”
DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation (2022, methodology): “The VGGNet [39] and typical residual structures [23] have been applied in many previous semantic segmentation networks, such as DoubleUnet [22] and ResUnet [40].”
A Comprehensive Study on Colorectal Polyp Segmentation With ResUNet++, Conditional Random Field and Test-Time Augmentation (2021, background): “Additionally, there are several recent interesting studies on polyp segmentation [27]–[30].”
U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications (2020, methodology): “U-net has been applied to endoscopy images for segmentation of polyps in the gastrointestinal tract [97], [274], [301], [334], colon objects [59], detection of laryngeal leukoplakia [65], and detection of surgical instruments [335].”
TransAttUnet: Multi-Level Attention-Guided U-Net With Transformer for Medical Image Segmentation (2021, methodology): “(cid:2) Multi-scalecontextapproaches: Meanwhile, severalmulti-scale context models are used as the major contenders, including Unet++ [9], R2U-Net [38] ResUNet [41], ResUNet++ [42], BCDU-Net [43], KiU-Net [37], and DoubleU-Net [36].”