Goto

Collaborating Authors

Results


How artificial intelligence is poised to reshape medicine

#artificialintelligence

In a recent review published in the journal of Nature Medicine, scientists discussed the results of a two-year weekly effort to track and communicate significant developments in medical (artificial intelligence) AI. They included prospective studies as well as developments in medical image analysis that have narrowed the gap between research and implementation. They also discuss non-image data sources, innovative issue formulations, and human-AI collaboration as prospective pathways for novel medical AI research. As the medical AI community navigates the many ethical, technical, and human-centered issues required for safe and successful translation, the deployment of medical AI systems in routine clinical care presents an important but largely unrealized opportunity. Many randomized controlled trials (RCTs) have been used to assess the utility of AI systems in healthcare.


How artificial intelligence is poised to reshape medicine

#artificialintelligence

In a recent review published in the journal of Nature Medicine, scientists discussed the results of a two-year weekly effort to track and communicate significant developments in medical (artificial intelligence) AI. They included prospective studies as well as developments in medical image analysis that have narrowed the gap between research and implementation. They also discuss non-image data sources, innovative issue formulations, and human-AI collaboration as prospective pathways for novel medical AI research. As the medical AI community navigates the many ethical, technical, and human-centered issues required for safe and successful translation, the deployment of medical AI systems in routine clinical care presents an important but largely unrealized opportunity. Many randomized controlled trials (RCTs) have been used to assess the utility of AI systems in healthcare.


An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization

arXiv.org Machine Learning

Medical images differ from natural images in significantly higher resolutions and smaller regions of interest. Because of these differences, neural network architectures that work well for natural images might not be applicable to medical image analysis. In this work, we extend the globally-aware multiple instance classifier, a framework we proposed to address these unique properties of medical images. This model first uses a low-capacity, yet memory-efficient, network on the whole image to identify the most informative regions. It then applies another higher-capacity network to collect details from chosen regions. Finally, it employs a fusion module that aggregates global and local information to make a final prediction. While existing methods often require lesion segmentation during training, our model is trained with only image-level labels and can generate pixel-level saliency maps indicating possible malignant findings. We apply the model to screening mammography interpretation: predicting the presence or absence of benign and malignant lesions. On the NYU Breast Cancer Screening Dataset, consisting of more than one million images, our model achieves an AUC of 0.93 in classifying breasts with malignant findings, outperforming ResNet-34 and Faster R-CNN. Compared to ResNet-34, our model is 4.1x faster for inference while using 78.4% less GPU memory. Furthermore, we demonstrate, in a reader study, that our model surpasses radiologist-level AUC by a margin of 0.11. The proposed model is available online: https://github.com/nyukat/GMIC.


Causality matters in medical imaging

arXiv.org Artificial Intelligence

This article discusses how the language of causality can shed new light on the major challenges in machine learning for medical imaging: 1) data scarcity, which is the limited availability of high-quality annotations, and 2) data mismatch, whereby a trained algorithm may fail to generalize in clinical practice. Looking at these challenges through the lens of causality allows decisions about data collection, annotation procedures, and learning strategies to be made (and scrutinized) more transparently. We discuss how causal relationships between images and annotations can not only have profound effects on the performance of predictive models, but may even dictate which learning strategies should be considered in the first place. For example, we conclude that semi-supervision may be unsuitable for image segmentation---one of the possibly surprising insights from our causal analysis, which is illustrated with representative real-world examples of computer-aided diagnosis (skin lesion classification in dermatology) and radiotherapy (automated contouring of tumours). We highlight that being aware of and accounting for the causal relationships in medical imaging data is important for the safe development of machine learning and essential for regulation and responsible reporting. To facilitate this we provide step-by-step recommendations for future studies.


Globally-Aware Multiple Instance Classifier for Breast Cancer Screening

arXiv.org Machine Learning

Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles in medical image analysis tasks. To address these unique properties of medical images, we propose a neural network that is able to classify breast cancer lesions utilizing information from both a global saliency map and multiple local patches. The proposed model outperforms the ResNet-based baseline and achieves radiologist-level performance in the interpretation of screening mammography. Although our model is trained only with image-level labels, it is able to generate pixel-level saliency maps that provide localization of possible malignant findings.