A deep learning approach for the analysis of masses in mammograms with minimal user intervention

By Neeraj Dhungel, Gustavo Carneiro, Andrew P. Bradley. 2017

302 citations recorded by the source corpus.

HighlightsWe introduce a novel automated CAD system with minimal user intervention that can detect, segment and classify breast masses from mammograms. We explore deep learning and structured output models for the design and development of the proposed CAD system. More specifically for the detection, we propose a cascade of deep learning methods to select hypotheses that are refined based on Bayesian optimization. For the segmentation, we propose the use of deep structured output learning that is subsequently refined by a level set method. Finally, for the classification, we propose a deep learning classifier that is pre‐trained with a regression to hand‐crafted feature values and fine‐tuned based on the annotations of the breast mass classification dataset. Our proposed CAD system produces the current state‐of‐the‐art detection, segmentation and classification results for the INbreast dataset. Graphical abstract Figure. No Caption available. Abstract We present an integrated methodology for detecting, segmenting and classifying breast masses from mammograms with minimal user intervention. This is a long standing problem due to low signal‐to‐noise ratio in the visualisation of breast masses, combined with their large variability in terms of shape, size, appearance and location. We break the problem down into three stages: mass detection, mass segmentation, and mass classification. For the detection, we propose a cascade of deep learning methods to select hypotheses that are refined based on Bayesian optimisation. For the segmentation, we propose the use of deep structured output learning that is subsequently refined by a level set method. Finally, for the classification, we propose the use of a deep learning classifier, which is pre‐trained with a regression to hand‐crafted feature values and fine‐tuned based on the annotations of the breast mass classification dataset. We test our proposed system on the publicly available INbreast dataset and compare the results with the current state‐of‐the‐art methodologies. This evaluation shows that our system detects 90% of masses at 1 false positive per image, has a segmentation accuracy of around 0.85 (Dice index) on the correctly detected masses, and overall classifies masses as malignant or benign with sensitivity (Se) of 0.98 and specificity (Sp) of 0.7.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Artificial intelligence in oncology (2020, background): “22,43 A second strategy, known as transfer learning, involves reuse for the new purpose of medical imaging of features extracted by deep learning from natu-ral image datasets such as ImageNet.”
Deep learning-based breast cancer classification through medical imaging modalities: state of the art and research challenges (2019, methodology): “…et al. 2017; Arefan et al. 2015; Bakkouri and Afdel 2017; Bayramoglu et al. 2017; Carneiro et al. 2017; Chang et al. 2017; Cheng et al. 2016; Dhungel et al. 2017; Duraisamy and Emperumal 2017; Fonseca et al. 2015; Gandomkar et al. 2018; Han et al. 2017b; Jaffar 2017; Kim et al. 2016; Kumar…”
Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, unknown): “INBreast database (RF-CNNPT: 95%, CNNPT: 91%, RF-HF: 90%, SFS-LDA: 89%) [155].”
A fully integrated computer-aided diagnosis system for digital X-ray mammograms via deep learning detection, segmentation, and classification (2018, background): “Breast mass segmentation also plays a crucial role in accurately extracting discriminative shape features of speci ﬁ c mass regions, while excluding surrounding tissues [19,25].”