Abstract:Deep learning produces advantages in solving class imbalance due to its powerful ability to extract features. However, its segmentation accuracy and efficiency can still be improved. A medical image segmentation algorithm via triplet interactive attention network is proposed in this paper. A triplet interactive attention module is designed and embedded into the feature extraction process. The module is focused on features in the channel and spatial dimensions jointly, capturing cross-dimensional interactive information. Thus, important features are in focus and target locations are highlighted. Moreover, pixel position-aware loss is employed to further mitigate the impact of class imbalance. Experiments on medical image datasets show that the proposed method yields better performance.
[1] LITJENS G,KOOI T,BEJNORDI B E,et al.A Survey on Deep Learning in Medical Image Analysis.Medical Image Analysis,2017,42:60-88. [2] LONG J,SHELHAMER E,DARRELL T.Fully Convolutional Networks for Semantic Segmentation//Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2015:3431-3440. [3] RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolutional Networks for Biomedical Image Segmentation//Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin,Germany:Springer,2015:234-241. [4] IBTEHAZ N,RAHMAN M S.MultiResUNet:Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation.Neural Networks,2020,121:74-87. [5] AZAD R,ASADI-AGHBOLAGHI M,FATHY M,et al.Bi-directional ConvLSTM U-Net with Densley Connected Convolutions//Proc of the IEEE/CVF International Conference on Computer Vision Workshop.Washington,USA:IEEE,2019:406-415. [6] SHI X J,CHEN Z R,WANG H,et al.Convolutional LSTM Network:A Machine Learning Approach for Precipitation Nowcasting//Proc of the 28th International Conference on Neural Information Processing Systems.Cambridge,USA:The MIT Press,2015:802-810. [7] ZHOU Z W,SIDDIQUEE M M R,TAJBAKHSH N,et al.UNet++:Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation.IEEE Transactions on Medical Imaging,2020,39(6):1856-1867. [8] BRIA A,MARROCCO C,TORTORELLA F.Addressing Class Imbalance in Deep Learning for Small Lesion Detection on Medical Images.Computers in Biology and Medicine,2020,120.DOI:10.1016/j.compbiomed.2020.103735. [9] YU Q H,XIE L X,WANG Y,et al. Recurrent Saliency Transformation Network:Incorporating Multi-stage Visual Cues for Small Organ Segmentation//Proc of the IEEE/CVF Conference on Compu-ter Vision and Pattern Recognition.Washington,USA:IEEE,2018:8280-8289. [10] ZHAO Y,LI P C,CAO C Q,et al. TSASNet:Tooth Segmentation on Dental Panoramic X-Ray Images by Two-Stage Attention Seg-mentation Network.Knowledge-Based Systems,2020,206.DOI:10.1016/j.knosys.2020.106338. [11] ZHOU C H,DING C X,WANG X C,et al.One-Pass Multi-task Networks with Cross-Task Guided Attention for Brain Tumor Segmentation.IEEE Transactions on Image Processing,2020,29:4516-4529. [12] SINHA A,DOLZ J.Multi-scale Self-guided Attention for Medical Image Segmentation.IEEE Journal of Biomedical and Health Informatics,2021,25(1):121-130. [13] HU J,SHEN L,ALABNIE S,et al.Squeeze-and-Excitation Networks.IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(8):2011-2023. [14] LI C,TAN Y S,CHEN W,et al.ANU-Net:Attention-Based Nested U-Net to Exploit Full Resolution Features for Medical Image Segmentation.Computers and Graphics,2020,90:11-20. [15] WOO S,PARK J,LEE J Y,et al. CBAM:Convolutional Block Attention Module//Proc of the European Conference on Computer Vision.Berlin,Germany:Springer,2018:3-19. [16] ROY A G,NAVAB N,WACHINGER C.Recalibrating Fully Convolutional Networks with Spatial and Channel "Squeeze and Excita-tion"Blocks.IEEE Transactions on Medical Imaging,2019,38(2):540-549. [17] ZHAO T,WU X Q.Pyramid Feature Attention Network for Saliency Detection//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE,2019:3080-3089. [18] PEREIRA S,PINTO A,AMORIM J,et al.Adaptive Feature Re-combination and Recalibration for Semantic Segmentation with Fully Convolutional Networks.IEEE Transactions on Medical Imaging,2019,38(12):2914-2925. [19] SUDRE C H,LI W Q,VERCAUTEREN T,et al.Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unba-lanced Segmentations//Proc of the International Workshop on Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Berlin,Germany: Springer,2017:240-248. [20] MILLETARI F,NAVAB N,AHMADI S A.V-Net:Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation//Proc of the 4th International Conference on 3D Vision.Washington,USA:IEEE,2016:565-571. [21] RAHMAN M A,WANG Y.Optimizing Intersection-over-Union in Deep Neural Networks for Image Segmentation//Proc of the International Symposium on Visual Computing.Berlin,Germany: Springer,2016:234-244. [22] LEE C Y,XIE S N,GALLAGHER P,et al.Deeply-Supervised Nets//Proc of the 18th International Conference on Artificial Intelligence and Statistics.Berlin,Germany:Springer,2015:562-570. [23] WEI J,WANG S H,HUANG Q M.F3Net:Fusion,Feedback and Focus for Salient Object Detection//Proc of the AAAI Conference on Artificial Intelligence.Palo Alto,USA:AAAI Press,2020:12321-12328. [24] YAP M H,PONS G,MARTI J,et al. Automated Breast Ultra-sound Lesions Detection Using Convolutional Neural Networks.IEEE Journal of Biomedical and Health Informatics,2018,22(4):1218-1226. [25] BERNAL J,SANCHEZ F J,FERNÁNDEZ-ESPARRACH G,et al.WM-DOVA Maps for Accurate Polyp Highlighting in Colonoscopy:Validation vs.Saliency Maps from Physicians.Computerized Medical Imaging and Graphics,2015,43:99-111. [26] LU Z,CARNEIRO G,BRADLEY A P.An Improved Joint Optimization of Multiple Level Set Functions for the Segmentation of Overlapping Cervical Cells.IEEE Transactions on Image Processing,2015,24(4):1261-1272. [27] JHA D,SMEDSRUD P H,RIEGLER M A,et al.ResUNet++:An Advanced Architecture for Medical Image Segmentation//Proc of the IEEE International Symposium on Multimedia.Washington,USA:IEEE,2019:225-255. [28] ABRAHAM N,KHAN N M.A Novel Focal Tversky Loss Function with Improved Attention U-Net for Lesion Segmentation//Proc of the 16th IEEE International Symposium on Biomedical Imaging.Washington,USA:IEEE,2019:683-687. [29] JHA D,RIEGLER M A,JOHANSEN D,et al. DoubleU-Net:A Deep Convolutional Neural Network for Medical Image Segmentation//Proc of the 33rd IEEE International Symposium on Compu-ter-Based Medical Systems.Washington,USA:IEEE,2020:558-564. [30] YIN Z J,LIANG K M,MA Z Y,et al.Duplex Contextual Relation Network for Polyp Segmentation[C/OL].[2021-01-30].https://arxiv.org/pdf/2103.06725.pdf.