Discriminating solitary cysts from soft tissue lesions in mammography using a pretrained deep convolutional neural network.

PURPOSE: It is estimated that 7% of women in the western world will develop palpable breast cysts in their lifetime. Even though cysts have been correlated with risk of developing breast cancer, many of them are benign and do not require follow-up. We develop a method to discriminate benign solitary cysts from malignant masses in digital mammography. We think a system like this can have merit in the clinic as a decision aid or complementary to specialized modalities. METHODS: We employ a deep convolutional neural network (CNN) to classify cyst and mass patches. Deep CNNs have been shown to be powerful classifiers, but need a large amount of training data for which medical problems are often difficult to come by. The key contribution of this paper is that we show good performance can be obtained on a small dataset by pretraining the network on a large dataset of a related task. We subsequently investigate the following: (a) when a mammographic exam is performed, two different views of the same breast are recorded. We investigate the merit of combining the output of the classifier from these two views. (b) We evaluate the importance of the resolution of the patches fed to the network. (c) A method dubbed tissue augmentation is subsequently employed, where we extract normal tissue from normal patches and superimpose this onto the actual samples aiming for a classifier invariant to occluding tissue. (d) We combine the representation extracted using the deep CNN with our previously developed features. RESULTS: We show that using the proposed deep learning method, an area under the ROC curve (AUC) value of 0.80 can be obtained on a set of benign solitary cysts and malignant mass findings recalled in screening. We find that it works significantly better than our previously developed approach by comparing the AUC of the ROC using bootstrapping. By combining views, the results can be further improved, though this difference was not found to be significant. We find no significant difference between using a resolution of 100 versus 200 micron. The proposed tissue augmentations give a small improvement in performance, but this improvement was also not found to be significant. The final system obtained an AUC of 0.80 with 95% confidence interval [0.78, 0.83], calculated using bootstrapping. The system works best for lesions larger than 27 mm where it obtains an AUC value of 0.87. CONCLUSION: We have presented a computer-aided diagnosis (CADx) method to discriminate cysts from solid lesion in mammography using features from a deep CNN trained on a large set of mass candidates, obtaining an AUC of 0.80 on a set of diagnostic exams recalled from screening. We believe the system shows great potential and comes close to the performance of recently developed spectral mammography. We think the system can be further improved when more data and computational power becomes available.

Large scale deep learning for computer aided detection of mammographic lesions.

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.

Standalone computer-aided detection compared to radiologists' performance for the detection of mammographic masses.

OBJECTIVES: We developed a computer-aided detection (CAD) system aimed at decision support for detection of malignant masses and architectural distortions in mammograms. The effect of this system on radiologists' performance depends strongly on its standalone performance. The purpose of this study was to compare the standalone performance of this CAD system to that of radiologists. METHODS: In a retrospective study, nine certified screening radiologists and three residents read 200 digital screening mammograms without the use of CAD. Performances of the individual readers and of CAD were computed as the true-positive fraction (TPF) at a false-positive fraction of 0.05 and 0.2. Differences were analysed using an independent one-sample t-test. RESULTS: At a false-positive fraction of 0.05, the performance of CAD (TPF = 0.487) was similar to that of the certified screening radiologists (TPF = 0.518, P = 0.17). At a false-positive fraction of 0.2, CAD performance (TPF = 0.620) was significantly lower than the radiologist performance (TPF = 0.736, P <0.001). Compared to the residents, CAD performance was similar for all false-positive fractions. CONCLUSIONS: The sensitivity of CAD at a high specificity was comparable to that of human readers. These results show potential for CAD to be used as an independent reader in breast cancer screening.