Intelligence analysts have long struggled with an abundance of data that must be investigated on a daily basis. In the U.S. Army, this activity involves reconciling information from various sources, a process that has been automated to a certain exte
nt, but which remains highly manual. To promote automation, a semantic analysis prototype was designed to aid in the intelligence analysis process. This tool, called Selective Plotting of Interconnected Data and Entity Relations (SPIDER), extracts entities and their relationships from text in order to streamline investigations. SPIDER is a web application that can be remotely-accessed via a web browser, and has three major components: (1) a Java API that reads documents, extracts entities and relationships using Stanford CoreNLP, (2) a Neo4j graph database that stores entities, relationships, and properties; (3) a JavaScript-based SigmaJS visualization tool for displaying the graph on the browser. SPIDER can scale document analysis to thousands of files for quick visualization, making the intelligence analysis process more efficient, and allowing military leadership quicker insights into a vast array of potentially-hidden knowledge.
Data scarcity and class imbalance are two fundamental challenges in many machine learning applications to healthcare. Breast cancer classification in mammography exemplifies these challenges, with a malignancy rate of around 0.5% in a screening popul
ation, which is compounded by the relatively small size of lesions (~1% of the image) in malignant cases. Simultaneously, the prevalence of screening mammography creates a potential abundance of non-cancer exams to use for training. Altogether, these characteristics lead to overfitting on cancer cases, while under-utilizing non-cancer data. Here, we present a novel generative adversarial network (GAN) model for data augmentation that can realistically synthesize and remove lesions on mammograms. With self-attention and semi-supervised learning components, the U-net-based architecture can generate high resolution (256x256px) outputs, as necessary for mammography. When augmenting the original training set with the GAN-generated samples, we find a significant improvement in malignancy classification performance on a test set of real mammogram patches. Overall, the empirical results of our algorithm and the relevance to other medical imaging paradigms point to potentially fruitful further applications.
A key promise of AI applications in healthcare is in increasing access to quality medical care in under-served populations and emerging markets. However, deep learning models are often only trained on data from advantaged populations that have the in
frastructure and resources required for large-scale data collection. In this paper, we aim to empirically investigate the potential impact of such biases on breast cancer detection in mammograms. We specifically explore how a deep learning algorithm trained on screening mammograms from the US and UK generalizes to mammograms collected at a hospital in China, where screening is not widely implemented. For the evaluation, we use a top-scoring model developed for the Digital Mammography DREAM Challenge. Despite the change in institution and population composition, we find that the model generalizes well, exhibiting similar performance to that achieved in the DREAM Challenge, even when controlling for tumor size. We also illustrate a simple but effective method for filtering predictions based on model variance, which can be particularly useful for deployment in new settings. While there are many components in developing a clinically effective system, these results represent a promising step towards increasing access to life-saving screening mammography in populations where screening rates are currently low.
Computerized automatic methods have been employed to boost the productivity as well as objectiveness of hand bone age assessment. These approaches make predictions according to the whole X-ray images, which include other objects that may introduce di
stractions. Instead, our framework is inspired by the clinical workflow (Tanner-Whitehouse) of hand bone age assessment, which focuses on the key components of the hand. The proposed framework is composed of two components: a Mask R-CNN subnet of pixelwise hand segmentation and a residual attention network for hand bone age assessment. The Mask R-CNN subnet segments the hands from X-ray images to avoid the distractions of other objects (e.g., X-ray tags). The hierarchical attention components of the residual attention subnet force our network to focus on the key components of the X-ray images and generate the final predictions as well as the associated visual supports, which is similar to the assessment procedure of clinicians. We evaluate the performance of the proposed pipeline on the RSNA pediatric bone age dataset and the results demonstrate its superiority over the previous methods.
Deep learning approaches to breast cancer detection in mammograms have recently shown promising results. However, such models are constrained by the limited size of publicly available mammography datasets, in large part due to privacy concerns and th
e high cost of generating expert annotations. Limited dataset size is further exacerbated by substantial class imbalance since normal images dramatically outnumber those with findings. Given the rapid progress of generative models in synthesizing realistic images, and the known effectiveness of simple data augmentation techniques (e.g. horizontal flipping), we ask if it is possible to synthetically augment mammogram datasets using generative adversarial networks (GANs). We train a class-conditional GAN to perform contextual in-filling, which we then use to synthesize lesions onto healthy screening mammograms. First, we show that GANs are capable of generating high-resolution synthetic mammogram patches. Next, we experimentally evaluate using the augmented dataset to improve breast cancer classification performance. We observe that a ResNet-50 classifier trained with GAN-augmented training data produces a higher AUROC compared to the same model trained only on traditionally augmented data, demonstrating the potential of our approach.
Advancements in convolutional neural networks (CNNs) have made significant strides toward achieving high performance levels on multiple object recognition tasks. While some approaches utilize information from the entire scene to propose regions of in
terest, the task of interpreting a particular region or object is still performed independently of other objects and features in the image. Here we demonstrate that a scenes gist can significantly contribute to how well humans can recognize objects. These findings are consistent with the notion that humans foveate on an object and incorporate information from the periphery to aid in recognition. We use a biologically inspired two-part convolutional neural network (GistNet) that models the fovea and periphery to provide a proof-of-principle demonstration that computational object recognition can significantly benefit from the gist of the scene as contextual information. Our model yields accuracy improvements of up to 50% in certain object categories when incorporating contextual gist, while only increasing the original model size by 5%. This proposed model mirrors our intuition about how the human visual system recognizes objects, suggesting specific biologically plausible constraints to improve machine vision and building initial steps towards the challenge of scene understanding.
