Deep Frequency Re-calibration U-Net for Medical Image Segmentation

The human visual cortex is biased towards shape components while CNNs produce texture biased features. This fact may explain why the performance of CNN significantly degrades with low-labeled input data scenarios. In this paper, we propose a frequency re-calibration U-Net (FRCU-Net) for medical image segmentation. Representing an object in terms of frequency may reduce the effect of texture bias, resulting in better generalization for a low data regime. To do so, we apply the Laplacian pyramid in the bottleneck layer of the U-shaped structure. The Laplacian pyramid represents the object proposal in different frequency domains, where the high frequencies are responsible for the texture information and lower frequencies might be related to the shape. Adaptively re-calibrating these frequency representations can produce a more discriminative representation for describing the object of interest. To this end, we first propose to use a channel-wise attention mechanism to capture the relationship between the channels of a set of feature maps in one layer of the frequency pyramid. Second, the extracted features of each level of the pyramid are then combined through a non-linear function based on their impact on the final segmentation output. The proposed FRCU-Net is evaluated on five datasets ISIC 2017, ISIC 2018, the PH2, lung segmentation, and SegPC 2021 challenge datasets and compared to existing alternatives, achieving state-of-the-art results.

[1]  Loïc Le Folgoc,et al.  Attention U-Net: Learning Where to Look for the Pancreas , 2018, ArXiv.

[2]  Pedro M. Ferreira,et al.  PH2 - A dermoscopic image database for research and benchmarking , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[3]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Nima Tajbakhsh,et al.  UNet++: A Nested U-Net Architecture for Medical Image Segmentation , 2018, DLMIA/ML-CDS@MICCAI.

[5]  Noel C. F. Codella,et al.  Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC) , 2019, ArXiv.

[6]  Narendra Ahuja,et al.  Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[8]  Noel C. F. Codella,et al.  Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC) , 2016, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[9]  Ben Glocker,et al.  Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images , 2018, Medical Image Anal..

[10]  Reza Azad,et al.  Multi-scale Regional Attention Deeplab3+: Multiple Myeloma Plasma Cells Segmentation in Microscopic Images , 2021, COMPAY@MICCAI.

[11]  Ling Shao,et al.  PraNet: Parallel Reverse Attention Network for Polyp Segmentation , 2020, MICCAI.

[12]  Jose Dolz,et al.  On the Texture Bias for Few-Shot CNN Segmentation , 2020, 2021 IEEE Winter Conference on Applications of Computer Vision (WACV).

[13]  Xiaolin Ma,et al.  An Enhanced Neural Network Based on Deep Metric Learning for Skin Lesion Segmentation , 2019, 2019 Chinese Control And Decision Conference (CCDC).

[14]  Ritu Gupta,et al.  GCTI-SN: Geometry-inspired chemical and tissue invariant stain normalization of microscopic medical images , 2020, Medical Image Anal..

[15]  Anubha Gupta,et al.  PCSeg: Color model driven probabilistic multiphase level set based tool for plasma cell segmentation in multiple myeloma , 2018, PloS one.

[16]  Ritu Gupta,et al.  EDNFC-Net: Convolutional Neural Network with Nested Feature Concatenation for Nuclei-Instance Segmentation , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Chongruo Wu,et al.  ResNeSt: Split-Attention Networks , 2020, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[18]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Mahmood Fathy,et al.  Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[20]  Mun-Taek Choi,et al.  Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks , 2018, Comput. Methods Programs Biomed..

[21]  Mahmood Fathy,et al.  Attention Deeplabv3+: Multi-level Context Attention Mechanism for Skin Lesion Segmentation , 2020, ECCV Workshops.

[22]  Matthias Bethge,et al.  ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness , 2018, ICLR.

[23]  Vijayan K. Asari,et al.  Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation , 2018, ArXiv.

[24]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[25]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[26]  Chang D. Yoo,et al.  SCNet: Training Inference Sample Consistency for Instance Segmentation , 2020, AAAI.

[27]  Mahmood Fathy,et al.  Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation , 2020, ArXiv.

[28]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[29]  Xiangjian He,et al.  Atrous Convolution for Binary Semantic Segmentation of Lung Nodule , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[30]  Enhua Wu,et al.  Squeeze-and-Excitation Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Sergio Escalera,et al.  Stacked BCDU-Net with Semantic CMR Synthesis: Application to Myocardial Pathology Segmentation Challenge , 2020, MyoPS@MICCAI.