Fatmatülzehra USLU, Cher BASS, Anil A. BHARATH

PERI-Net: a parameter efficient residual inception network for medical image

Recent developments in deep networks allow us to train networks with more parameters by yielding better performance given sufficient amount of data. However, we are still restricted with the availability of labelled data in medical image segmentation, where the problem is exacerbated with high intra- and intervariability of anatomical structures. In order to bypass this problem without compromising network performance, this study introduces a PERI- Net, which promises to achieve higher performance while being with smaller parameter count such as on the order of 0.8 million than its counterparts. The network benefits from rich features generated by our versions of inception modules, better communication between encoding and decoding paths and an effective way of segmentation mask generation. We evaluate the performance of our architecture on the segmentation of retinal vasculature in fundus image datasets of DRIVE, CHASE_DB 1 and IOSTAR and the segmentation of axons in a 2-photon microscopy image dataset. According to the results of our experiments, PERI-Net achieves state of the art performance on sensitivity and G-mean metrics with a significant margin for the 3 datasets, by outperforming our training of a U-net sharing the same properties and training strategies as PERI-Net.

PDF

___

[1] Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B, Rudnicka AR et al. Blood vessel segmentation methodologies in retinal images-a survey. Computer Methods and Programs in Biomedicine 2012; 108 (1): 407-433.
[2] Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F et al. A survey on deep learning in medical image analysis. Medical Image Analysis 2017; 42: 60-88.
[3] Zaimi A, Wabartha M, Herman V, Antonsanti PL, Perone CS et al. AxonDeepSeg: automatic axon and myelin segmentation from microscopy data using convolutional neural networks. Scientific reports 2018; 8 (1): 1-11.
[4] Liskowski P, Krawiec K. Segmenting retinal blood vessels with deep neural networks. IEEE Transactions on Medical Imaging 2016; 35 (11): 2369-2380.
[5] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D et al. Going deeper with convolutions. In: The IEEE Conference on Computer Vision and Pattern Recognition; Boston, Massachusetts, USA; 2015. pp. 1-9.
[6] Chen L, Bentley P, Mori K, Misawa K, Fujiwara M et al. DRINet for medical image segmentation. IEEE Transactions on Medical Imaging 2018; 37 (11): 2453-2462.
[7] Chudzik P, Majumdar S, Caliva F, Al-Diri B, Hunter A. Exudate segmentation using fully convolutional neural networks and inception modules. In: International Society for Optics and Photonics Conference; Houston, Texas, United States; 2018. pp. 1057430.
[8] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition; Las Vegas, NV, USA; 2016. pp. 770-778.
[9] Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: The IEEE Conference on Computer Vision and Pattern Recognition; Honolulu, Hawaii, USA; 2017. pp. 4700-4708
[10] Dolz J, Desrosiers C, Ayed IB. IVD-Net: Intervertebral disc localization and segmentation in MRI with a multi- modal UNet. In: International Workshop and Challenge on Computational Methods and Clinical Applications for Spine Imaging; Granada, Spain; 2018. pp. 130-143.
[11] Bilinski P, Prisacariu V. Dense decoder shortcut connections for single-pass semantic segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition; Salt Lake City, Utah, USA; 2018. pp. 6596-6605.
[12] Zhang J, Jin Y, Xu J, Xu X, Zhang Y. MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation. arXiv preprint 2018; arXiv:1812.00352.
[13] Bass C, Dai T, Billot B, Arulkumaran K, Creswell A et al. Image synthesis with a convolutional capsule generative adversarial network. In:Medical Imaging with Deep Learning; London, UK; 2019. pp. 39-62.
[14] Lin M, Chen Q, Yan S. Network in network. arXiv preprint 2013; arXiv:1312.4400.
[15] Szegedy C, Ioffe S, Vanhoucke V, Alemi A A. Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI Conference on Artificial Intelligence; San Francisco, California, USA; 2017. pp. 4278-4284
[16] Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: The IEEE Conference on Computer Vision and Pattern Recognition; Las Vegas, NV, USA; 2016. pp. 2818-2826.
[17] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: Inter- national Conference on Medical Image Computing and Computer-assisted Intervention; Munich, Germany; 2015. pp. 234-241.
[18] Li X, Chen S, Hu X, Yang J. Understanding the disharmony between dropout and batch normalization by variance shift. In: The IEEE Conference on Computer Vision and Pattern Recognition; Long Beach California, USA; 2019. pp. 2682-2690.
[19] Milletari F, Navab N, Ahmadi SA. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: The Fourth International Conference on 3D Vision; Stanford, CA, USA; 2016. pp. 565-571.
[20] Staal J, Abrámoff MD, Niemeijer M, Viergever MA, Van Ginneken B. Ridge-based vessel segmentation in color images of the retina. IEEE Transactions on Medical Imaging 2004; 23 (4): 501-509.
[21] Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B, Rudnicka AR et al. An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Transactions on Biomedical Engineering 2012; 59 (9): 2538-2548.
[22] Zhang J, Dashtbozorg B, Bekkers E, Pluim J P, Duits R et al. Robust retinal vessel segmentation via locally adaptive derivative frames in orientation scores. IEEE Transactions on Medical Imaging 2016; 35 (12): 2631-2644.
[23] Gadriye D, Khandale G, Nawkhare R. System for diagnosis of diabetic retinopathy using neural network. Interna- tional Journal of Technical Research and Applications 2014; 4 (2): 76-80.
[24] He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: The IEEE International Conference on Computer Vision; Santiago, Chile; 2015. pp. 1026-1034.
[25] Kingma D P, Ba,J. Adam: a method for stochastic optimization. arXiv preprint 2014; arXiv:1412.6980.
[26] Goyal P, Dollár P, Girshick R, Noordhuis P, Wesolowski L et al. Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint 2017; arXiv:1706.02677.
[27] Otsu N. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics 1979; 9 (1): 62-66.
[28] Akosa, J. Predictive accuracy: a misleading performance measure for highly imbalanced data. In: The SAS Global Forum; Orlando, FL, USA; 2017; pp. 2-5.
[29] Alom MZ, Yakopcic C, Hasan M, Taha TM, Asari VK. Recurrent residual U-Net for medical image segmentation. Journal of Medical Imaging 2019; 6 (1): 014006.
[30] Uslu F. An inception inspired deep network to analyse fundus images. arXiv preprint 2019; arXiv:1911.08715.
[31] Orlando JI, Prokofyeva E, Blaschko MB. A discriminatively trained fully connected conditional random field model for blood vessel segmentation in fundus images. IEEE Transactions on Biomedical Engineering 2016; 64 (1): 16-27
32] Oliveira WS, Teixeira JV, Ren TI, Cavalcanti GD, Sijbers J. Unsupervised retinal vessel segmentation using combined filters. PloS One 2016; 11 (2).
[33] Li Q, Feng B, Xie L, Liang P, Zhang H, Wang T. A cross-modality learning approach for vessel segmentation in retinal images. IEEE Transactions on Medical Imaging 2015; 35 (1): 109-118.
[34] Wang S, Yin Y, Cao G, Wei B, Zheng Y et al. Hierarchical retinal blood vessel segmentation based on feature and ensemble learning. Neurocomputing 2015; 149: 708-717.
[35] Cheng E, Du L, Wu Y, Zhu Y J, Megalooikonomou V et al. Discriminative vessel segmentation in retinal images by fusing context-aware hybrid features. Machine Vision and Applications 2014; 25 (7): 1779-1792.
[36] Fraz MM, Basit A, Barman SA. Application of morphological bit planes in retinal blood vessel extraction. Journal of Digital Imaging 2013; 26 (2): 274-286.
[37] Na T, Zhao Y, Zhao Y, Liu Y. Superpixel-based line operator for retinal blood vessel segmentation. In: Annual Conference on Medical Image Understanding and Analysis; Quebec City, QC, Canada; 2017. pp. 15-26.