Large scale deep learning for computer aided detection of mammographic lesions

• Published in: Medical image analysis Vol. 35; pp. 303 - 312
• Main Authors: Kooi, Thijs, Litjens, Geert, van Ginneken, Bram, Gubern-Mérida, Albert, Sánchez, Clara I., Mann, Ritse, den Heeten, Ard, Karssemeijer, Nico
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.01.2017; Elsevier BV
• Subjects: Artificial intelligence; Artificial neural networks; Breast - diagnostic imaging; Breast - pathology; Breast cancer; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - pathology; Computer aided detection; Convolutional neural networks; Deep learning; Humans; Learning algorithms; Lesions; Machine Learning; Mammography; Mammography - methods; Neural networks; Neural Networks (Computer); Object recognition; Pattern recognition; Radiographic Image Interpretation, Computer-Assisted - methods; Readers; Sensitivity; Sensitivity and Specificity; Speech; Speech recognition; Voice recognition; Computer aided detection; Deep learning; Mammography; Breast cancer; Convolutional neural networks; Machine learning
• ISSN: 1361-8415; 1361-8423; 1361-8431; 1361-8423
• DOI: 10.1016/j.media.2016.07.007

•A system based on deep learning is shown to outperform a state-of-the art CAD system.•Adding complementary handcrafted features to the CNN is shown to increase performance.•The system based on deep learning is shown to perform at the level of a radiologist. [Display omitted] Recent advances in machine learning yielded new techniques to train deep neural networks, which resulted in highly successful applications in many pattern recognition tasks such as object detection and speech recognition. In this paper we provide a head-to-head comparison between a state-of-the art in mammography CAD system, relying on a manually designed feature set and a Convolutional Neural Network (CNN), aiming for a system that can ultimately read mammograms independently. Both systems are trained on a large data set of around 45,000 images and results show the CNN outperforms the traditional CAD system at low sensitivity and performs comparable at high sensitivity. We subsequently investigate to what extent features such as location and patient information and commonly used manual features can still complement the network and see improvements at high specificity over the CNN especially with location and context features, which contain information not available to the CNN. Additionally, a reader study was performed, where the network was compared to certified screening radiologists on a patch level and we found no significant difference between the network and the readers.