A Pipelined Tracer-Aware Approach for Lesion Segmentation in Breast DCE-MRI

The recent spread of Deep Learning (DL) in medical imaging is pushing researchers to explore its suitability for lesion segmentation in Dynamic Contrast-Enhanced Magnetic-Resonance Imaging (DCE-MRI), a complementary imaging procedure increasingly used in breast-cancer analysis. Despite some promising proposed solutions, we argue that a “naive” use of DL may have limited effectiveness as the presence of a contrast agent results in the acquisition of multimodal 4D images requiring thorough processing before training a DL model. We thus propose a pipelined approach where each stage is intended to deal with or to leverage a peculiar characteristic of breast DCE-MRI data: the use of a breast-masking pre-processing to remove non-breast tissues; the use of Three-Time-Points (3TP) slices to effectively highlight contrast agent time course; the application of a motion-correction technique to deal with patient involuntary movements; the leverage of a modified U-Net architecture tailored on the problem; and the introduction of a new “Eras/Epochs” training strategy to handle the unbalanced dataset while performing a strong data augmentation. We compared our pipelined solution against some literature works. The results show that our approach outperforms the competitors by a large margin (+9.13% over our previous solution) while also showing a higher generalization ability.

[1]  Stuart Crozier,et al.  Fully automatic lesion segmentation in breast MRI using mean‐shift and graph‐cuts on a region adjacency graph , 2014, Journal of magnetic resonance imaging : JMRI.

[2]  Jagadaeesan Jayender,et al.  Automatic segmentation of invasive breast carcinomas from dynamic contrast‐enhanced MRI using time series analysis , 2014, Journal of magnetic resonance imaging : JMRI.

[3]  Shan Jiang,et al.  Design and implementation of a new cable‐driven robot for MRI‐guided breast biopsy , 2019, The international journal of medical robotics + computer assisted surgery : MRCAS.

[4]  B. Ponder Cancer genetics , 2001, Nature.

[5]  Scott Fields,et al.  Mapping pathophysiological features of breast tumors by MRI at high spatial resolution , 1997, Nature Medicine.

[6]  Sidi Ahmed Mahmoudi,et al.  MRI Breast Tumor Segmentation Using Different Encoder and Decoder CNN Architectures , 2019, Comput..

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

[8]  A. Bert,et al.  Performance of a fully automatic lesion detection system for breast DCE‐MRI , 2011, Journal of magnetic resonance imaging : JMRI.

[9]  M. Giger,et al.  Cancerous breast lesions on dynamic contrast-enhanced MR images: computerized characterization for image-based prognostic markers. , 2010, Radiology.

[10]  Li Li,et al.  Diagnosis of Breast Masses from Dynamic Contrast-Enhanced and Diffusion-Weighted MR: A Machine Learning Approach , 2014, PloS one.

[11]  Yuanjie Zheng,et al.  STEP: Spatiotemporal enhancement pattern for MR-based breast tumor diagnosis , 2009 .

[12]  Yi Wang,et al.  3D multi-parametric breast MRI segmentation using hierarchical support vector machine with coil sensitivity correction. , 2013, Academic radiology.

[13]  Aboul Ella Hassanien,et al.  Breast cancer MRI diagnosis approach using support vector machine and pulse coupled neural networks , 2012, J. Appl. Log..

[14]  Lia Morra,et al.  A fully automatic lesion detection method for DCE-MRI fat-suppressed breast images , 2009, Medical Imaging.

[15]  Stefano Marrone,et al.  Comprehensive computer-aided diagnosis for breast T1-weighted DCE-MRI through quantitative dynamical features and spatio-temporal local binary patterns , 2018, IET Comput. Vis..

[16]  Aboul Ella Hassanien,et al.  Adaptive k-means clustering algorithm for MR breast image segmentation , 2013, Neural Computing and Applications.

[17]  Carlo Sansone,et al.  Multi-planar 3D breast segmentation in MRI via deep convolutional neural networks , 2020, Artif. Intell. Medicine.

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

[19]  Jacob Antunes,et al.  Texture kinetic features from pre-treatment DCE MRI for predicting pathologic tumor stage regression after neoadjuvant chemoradiation in rectal cancers , 2020, Medical Imaging: Image-Guided Procedures.

[20]  Ruey-Feng Chang,et al.  Computer-aided diagnosis of breast DCE-MRI using pharmacokinetic model and 3-D morphology analysis. , 2014, Magnetic resonance imaging.

[21]  N. Karssemeijer,et al.  A computer-aided diagnosis system for breast DCE-MRI at high spatiotemporal resolution. , 2015, Medical physics.

[22]  Hao Zheng,et al.  Accurate breast lesion segmentation by exploiting spatio-temporal information with deep recurrent and convolutional network , 2019, J. Ambient Intell. Humaniz. Comput..

[23]  Jie Ding,et al.  Task‐based assessment of a convolutional neural network for segmenting breast lesions for radiomic analysis , 2019, Magnetic resonance in medicine.

[24]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[25]  E. Giovannucci,et al.  The World Cancer Research Fund/American Institute for Cancer Research Third Expert Report on Diet, Nutrition, Physical Activity, and Cancer: Impact and Future Directions. , 2019, The Journal of nutrition.

[26]  R. Anderson,et al.  Cancer screening guidelines. , 2001, American family physician.

[27]  Daniel Rueckert,et al.  Nonrigid registration using free-form deformations: application to breast MR images , 1999, IEEE Transactions on Medical Imaging.

[28]  Jong Hyo Kim,et al.  Multilevel analysis of spatiotemporal association features for differentiation of tumor enhancement patterns in breast DCE-MRI. , 2010, Medical physics.