Region-of-Interest-Based Cardiac Image Segmentation with Deep Learning

Despite the promising results obtained by deep learning methods in the field of medical image segmentation, lack of sufficient data always hinders performance to a certain degree. In this work, we explore the feasibility of applying deep learning methods on a pilot dataset. We present a simple and practical approach to perform segmentation in a 2D, slice-by-slice manner, based on region of interest (ROI) localization, applying an optimized training regime to improve segmentation performance from regions of interest. We start from two popular segmentation networks, the preferred model for medical segmentation, U-Net, and a general-purpose model, DeepLabV3+. Furthermore, we show that ensembling of these two fundamentally different architectures brings constant benefits by testing our approach on two different datasets, the publicly available ACDC challenge, and the imATFIB dataset from our in-house conducted clinical study. Results on the imATFIB dataset show that the proposed approach performs well with the provided training volumes, achieving an average Dice Similarity Coefficient of the whole heart of 89.89% on the validation set. Moreover, our algorithm achieved a mean Dice value of 91.87% on the ACDC validation, being comparable to the second best-performing approach on the challenge. Our approach provides an opportunity to serve as a building block of a computer-aided diagnostic system in a clinical setting.

[1]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[2]  M. Samways,et al.  Asynchrony among insect pollinator groups and flowering plants with elevation , 2020, Scientific Reports.

[3]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Xin Yang,et al.  Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? , 2018, IEEE Transactions on Medical Imaging.

[6]  Massimo Midiri,et al.  A semi-automatic approach for epicardial adipose tissue segmentation and quantification on cardiac CT scans , 2019, Comput. Biol. Medicine.

[7]  Jens Petersen,et al.  nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation , 2020, Nature Methods.

[8]  Guang Yang,et al.  A two-stage 3D Unet framework for multi-class segmentation on full resolution image , 2018, ArXiv.

[9]  R. Khonsari,et al.  Deep learning in medical image analysis: a third eye for doctors. , 2019, Journal of stomatology, oral and maxillofacial surgery.

[10]  Klaus H. Maier-Hein,et al.  Automated Design of Deep Learning Methods for Biomedical Image Segmentation , 2019 .

[11]  Jianxin Wang,et al.  A survey on U-shaped networks in medical image segmentations , 2020, Neurocomputing.

[12]  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.

[13]  Martin Kyncl,et al.  The diagnostic value of MRI fistulogram and MRI distal colostogram in patients with anorectal malformations. , 2013, Journal of pediatric surgery.

[14]  Klaus H. Maier-Hein,et al.  Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges , 2017, Lecture Notes in Computer Science.

[15]  Nima Tajbakhsh,et al.  Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation , 2019, Medical Image Anal..

[16]  Guang Yang,et al.  Evaluation of algorithms for Multi-Modality Whole Heart Segmentation: An open-access grand challenge , 2019, Medical Image Anal..

[17]  Horst Bischof,et al.  Multi-label Whole Heart Segmentation Using CNNs and Anatomical Label Configurations , 2017, STACOM@MICCAI.

[18]  Laura Diosan,et al.  Feasibility of Automatic Seed Generation Applied to Cardiac MRI Image Analysis , 2020, Mathematics.

[19]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Ebrahim Nasr-Esfahani,et al.  Left Ventricle Segmentation in Cardiac MR Images Using Fully Convolutional Network , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[21]  Daniel Rueckert,et al.  Deep Learning for Cardiac Image Segmentation: A Review , 2020, Frontiers in Cardiovascular Medicine.

[22]  Giancarlo Mauri,et al.  A novel framework for MR image segmentation and quantification by using MedGA , 2019, Comput. Methods Programs Biomed..

[23]  Md Zahangir Alom,et al.  Recurrent residual U-Net for medical image segmentation , 2019, Journal of medical imaging.

[24]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[25]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

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

[27]  Giancarlo Mauri,et al.  USE-Net: incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets , 2019, Neurocomputing.

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

[29]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Sebastian Stober,et al.  Automatic prostate and prostate zones segmentation of magnetic resonance images using DenseNet-like U-net , 2020, Scientific Reports.

[31]  Marc Pollefeys,et al.  An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation , 2017, STACOM@MICCAI.

[32]  Naeem Khalid Janjua,et al.  Going Deep in Medical Image Analysis: Concepts, Methods, Challenges, and Future Directions , 2019, IEEE Access.

[33]  D. Dey,et al.  Fully Automated CT Quantification of Epicardial Adipose Tissue by Deep Learning: A Multicenter Study. , 2019, Radiology. Artificial intelligence.

[34]  Su Ruan,et al.  Multiorgan segmentation using distance-aware adversarial networks , 2019, Journal of medical imaging.

[35]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.