Key Points
• The use of screening breast MRI is expanding beyond high-risk women to include intermediate- and average-risk women.
• The study by Pötsch et al uses a radiomics-based method to decrease ...the number of benign biopsies while maintaining high sensitivity.
• Future studies will likely increasingly focus on deep learning methods and abbreviated MRI data.
Machine learning in breast MRI Reig, Beatriu; Heacock, Laura; Geras, Krzysztof J. ...
Journal of magnetic resonance imaging,
October 2020, Letnik:
52, Številka:
4
Journal Article
Recenzirano
Odprti dostop
Machine‐learning techniques have led to remarkable advances in data extraction and analysis of medical imaging. Applications of machine learning to breast MRI continue to expand rapidly as ...increasingly accurate 3D breast and lesion segmentation allows the combination of radiologist‐level interpretation (eg, BI‐RADS lexicon), data from advanced multiparametric imaging techniques, and patient‐level data such as genetic risk markers. Advances in breast MRI feature extraction have led to rapid dataset analysis, which offers promise in large pooled multiinstitutional data analysis. The object of this review is to provide an overview of machine‐learning and deep‐learning techniques for breast MRI, including supervised and unsupervised methods, anatomic breast segmentation, and lesion segmentation. Finally, it explores the role of machine learning, current limitations, and future applications to texture analysis, radiomics, and radiogenomics.
Level of Evidence: 3
Technical Efficacy Stage: 2
J. Magn. Reson. Imaging 2019. J. Magn. Reson. Imaging 2020;52:998–1018.
Though consistently shown to detect mammographically occult cancers, breast ultrasound has been noted to have high false-positive rates. In this work, we present an AI system that achieves ...radiologist-level accuracy in identifying breast cancer in ultrasound images. Developed on 288,767 exams, consisting of 5,442,907 B-mode and Color Doppler images, the AI achieves an area under the receiver operating characteristic curve (AUROC) of 0.976 on a test set consisting of 44,755 exams. In a retrospective reader study, the AI achieves a higher AUROC than the average of ten board-certified breast radiologists (AUROC: 0.962 AI, 0.924 ± 0.02 radiologists). With the help of the AI, radiologists decrease their false positive rates by 37.3% and reduce requested biopsies by 27.8%, while maintaining the same level of sensitivity. This highlights the potential of AI in improving the accuracy, consistency, and efficiency of breast ultrasound diagnosis.
We present a deep convolutional neural network for breast cancer screening exam classification, trained, and evaluated on over 200000 exams (over 1000000 images). Our network achieves an AUC of 0.895 ...in predicting the presence of cancer in the breast, when tested on the screening population. We attribute the high accuracy to a few technical advances. 1) Our network's novel two-stage architecture and training procedure, which allows us to use a high-capacity patch-level network to learn from pixel-level labels alongside a network learning from macroscopic breast-level labels. 2) A custom ResNet-based network used as a building block of our model, whose balance of depth and width is optimized for high-resolution medical images. 3) Pretraining the network on screening BI-RADS classification, a related task with more noisy labels. 4) Combining multiple input views in an optimal way among a number of possible choices. To validate our model, we conducted a reader study with 14 readers, each reading 720 screening mammogram exams, and show that our model is as accurate as experienced radiologists when presented with the same data. We also show that a hybrid model, averaging the probability of malignancy predicted by a radiologist with a prediction of our neural network, is more accurate than either of the two separately. To further understand our results, we conduct a thorough analysis of our network's performance on different subpopulations of the screening population, the model's design, training procedure, errors, and properties of its internal representations. Our best models are publicly available at https://github.com/nyukat/breast_cancer_classifier .
Deep neural networks (DNNs) show promise in image-based medical diagnosis, but cannot be fully trusted since they can fail for reasons unrelated to underlying pathology. Humans are less likely to ...make such superficial mistakes, since they use features that are grounded on medical science. It is therefore important to know whether DNNs use different features than humans. Towards this end, we propose a framework for comparing human and machine perception in medical diagnosis. We frame the comparison in terms of perturbation robustness, and mitigate Simpson's paradox by performing a subgroup analysis. The framework is demonstrated with a case study in breast cancer screening, where we separately analyze microcalcifications and soft tissue lesions. While it is inconclusive whether humans and DNNs use different features to detect microcalcifications, we find that for soft tissue lesions, DNNs rely on high frequency components ignored by radiologists. Moreover, these features are located outside of the region of the images found most suspicious by radiologists. This difference between humans and machines was only visible through subgroup analysis, which highlights the importance of incorporating medical domain knowledge into the comparison.
Lessons from the first DBTex Challenge Park Jungkyu; Shoshan Yoel; Martí, Robert ...
Nature machine intelligence,
08/2021, Letnik:
3, Številka:
8
Journal Article
Recenzirano
A new international competition aims to speed up the development of AI models that can assist radiologists in detecting suspicious lesions from hundreds of millions of pixels in 3D mammograms. The ...top three winning teams compare notes.
The goals of imaging after neoadjuvant therapy for breast cancer are to monitor the response to therapy and facilitate surgical planning. MRI has been found to be more accurate than mammography, ...ultrasound, or clinical exam in evaluating treatment response. However, MRI may both overestimate and underestimate residual disease. The accuracy of MRI is dependent on tumor morphology, histology, shrinkage pattern, and molecular subtype. Emerging MRI techniques that combine functional information such as diffusion, metabolism, and hypoxia may improve MR accuracy. In addition, machine‐learning techniques including radiomics and radiogenomics are being studied with the goal of predicting response on pretreatment imaging. This article comprehensively reviews response assessment on breast MRI and highlights areas of ongoing research.
Level of Evidence
3
Technical Efficacy Stage
3 J. MAGN. RESON. IMAGING 2020;52:1587–1606.