Conditional Deep Convolutional Neural Networks for Improving the Automated Screening of Histopathological Images

Semantic segmentation of breast cancer metastases in histopathological slides is a challenging task. In fact, significant variation in data characteristics of histopathology images (domain shift) make generalization of deep learning to unseen data difficult. Our goal is to address this challenge by using a conditional Fully Convolutional Network (coFCN) whose output can be conditioned at run time, and which can improve its performance when a properly selected set of reference slides are used to condition the output. We adapted to our task a coFCN originally applied to organs segmentation in volumetric medical images and we trained it on the Whole Slide Images (WSIs) from three out of five medical centers present in the CAMELYON17 dataset. We tested the performance of the network on the WSIs of the remaining centers. We also developed an automated selection strategy for selecting the conditioning subset, based on an unsupervised clustering process applied to a target-specific set of reference patches, followed by a selection policy that relies on the cluster similarities with the input patch. We benchmarked our proposed method against a U-Net trained on the same dataset with no conditioning. The conditioned network shows better performance that the U-Net on the WSIs with Isolated Tumor Cells and micro-metastases from the medical centers used as test. Our contributions are an architecture which can be applied to the histopathology domain and an automated procedure for the selection of conditioning data.

[1]  Frédo Durand,et al.  Data augmentation using learned transforms for one-shot medical image segmentation , 2019, ArXiv.

[2]  Neofytos Dimitriou,et al.  Deep Learning for Whole Slide Image Analysis: An Overview , 2019, Front. Med..

[3]  Meyke Hermsen,et al.  1399 H&E-stained sentinel lymph node sections of breast cancer patients: the CAMELYON dataset , 2018, GigaScience.

[4]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

[5]  Nassir Navab,et al.  'Squeeze & Excite' Guided Few-Shot Segmentation of Volumetric Images , 2019, Medical Image Anal..

[6]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[7]  Xavier Robin,et al.  pROC: an open-source package for R and S+ to analyze and compare ROC curves , 2011, BMC Bioinformatics.

[8]  S D Walter,et al.  The partial area under the summary ROC curve , 2005, Statistics in medicine.

[9]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[10]  Riccardo Cicchi,et al.  Few Shot Learning in Histopathological Images:Reducing the Need of Labeled Data on Biological Datasets , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[11]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

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

[13]  Alexei A. Efros,et al.  Few-Shot Segmentation Propagation with Guided Networks , 2018, ArXiv.

[14]  Xu Sun,et al.  Fast Implementation of DeLong’s Algorithm for Comparing the Areas Under Correlated Receiver Operating Characteristic Curves , 2014, IEEE Signal Processing Letters.

[15]  Yingli Tian,et al.  Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  B. van Ginneken,et al.  Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis , 2016, Scientific Reports.

[17]  Jose Dolz,et al.  Semi-supervised few-shot learning for medical image segmentation , 2020, ArXiv.

[18]  J. Peterse,et al.  Differences in risk factors for local and distant recurrence after breast-conserving therapy or mastectomy for stage I and II breast cancer: pooled results of two large European randomized trials. , 2001, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[19]  Daisuke Komura,et al.  Machine Learning Methods for Histopathological Image Analysis , 2017, Computational and structural biotechnology journal.

[20]  Ming Li,et al.  Mixed-Supervised Dual-Network for Medical Image Segmentation , 2019, MICCAI.

[21]  Anne L. Martel,et al.  Deep neural network models for computational histopathology: A survey , 2019, Medical Image Anal..

[22]  Sauer,et al.  Breast Diseases , 1989, Springer Berlin Heidelberg.

[23]  David J. Foran,et al.  Unsupervised Domain Adaptation for Classification of Histopathology Whole-Slide Images , 2019, Front. Bioeng. Biotechnol..

[24]  Claes Lundström,et al.  A Closer Look at Domain Shift for Deep Learning in Histopathology , 2019, ArXiv.

[25]  Jon Kleinberg,et al.  Transfusion: Understanding Transfer Learning for Medical Imaging , 2019, NeurIPS.