First results with a deep learning (feed-forward CNN) approach for daily quality control in digital breast tomosynthesis

In digital breast tomosynthesis (DBT) large number of parameters influence system performance and the requirement to achieve high quality images every day suggest the implementation of a daily quality control (DQC) procedure. In 2D digital mammography, daily QC is typically performed with homogenous plates and a minimal amount of technical inserts for assessment of NNPS, signal to noise, uniformity, defective pixels and other artefacts. This work proposes an alternative means of performing DQC in DBT with a 3D structured phantom that also includes a constancy test of reconstruction stability in the analysis. The aim of the study was to explore deep learning techniques to automatically track deviations from the normal or baseline operating point and compare the results to the standard metrics. As a first test case, changes in dose were investigated. Feed-forward convolutional neural networks (CNN) have been successfully applied in the medical imaging domain. A 12 layer CNN model was constructed to extract features for image classification. A structured phantom was scanned on a Siemens DBT system at three dose levels: dose set by the automatic exposure control (AEC) system, half this dose and double. After training the CNN on 36 DBT acquisitions (51840 image segments), newly acquired test images were categorized by the algorithm into the dose categories with an accuracy of 99.7%. Parallel to that the standard methods as NNPS and pixel value (PV) mean and variance calculated for the projection and reconstructed planes also show ability to detect the dose level change with some limitations for the reconstructed planes. This result indicates the potential for further use of deep learning algorithms for DQC when using only the reconstructed DBT planes.

[1]  Gustavo Carneiro,et al.  Automated Mass Detection from Mammograms using Deep Learning and Random Forest , 2015 .

[2]  J H Siewerdsen,et al.  Anatomical background and generalized detectability in tomosynthesis and cone-beam CT. , 2010, Medical physics.

[3]  Consumer Protection,et al.  European guidelines for quality assurance in breast cancer screening and diagnosis. Fourth edition--summary document. , 2008, Annals of oncology : official journal of the European Society for Medical Oncology.

[4]  R Holland,et al.  European guidelines for quality assurance in breast cancer screening and diagnosis. Fourth edition--summary document. , 2008, Annals of Oncology.

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  Xiaogang Wang,et al.  Medical image classification with convolutional neural network , 2014, 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV).

[7]  H. Bosmans,et al.  Toward an international consensus strategy for periodic quality control of digital breast tomosynthesis systems , 2010, Medical Imaging.

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  S. Ciatto,et al.  Integration of 3D digital mammography with tomosynthesis for population breast-cancer screening (STORM): a prospective comparison study. , 2013, The Lancet. Oncology.

[10]  Emily F Conant,et al.  Breast cancer screening using tomosynthesis in combination with digital mammography. , 2014, JAMA.

[11]  D. Dance,et al.  Design and application of a structured phantom for detection performance comparison between breast tomosynthesis and digital mammography , 2017, Physics in medicine and biology.

[12]  Wenqing Sun,et al.  Computer aided lung cancer diagnosis with deep learning algorithms , 2016, SPIE Medical Imaging.

[13]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[14]  H Bosmans,et al.  Comparative power law analysis of structured breast phantom and patient images in digital mammography and breast tomosynthesis. , 2013, Medical physics.