Chest radiographs are commonly performed low-cost exams for screening and diagnosis. However, radiographs are 2D representations of 3D structures causing considerable clutter impeding visual inspection and automated image analysis. Here, we propose a Fully Convolutional Network to suppress, for a specific task, undesired visual structure from radiographs while retaining the relevant image information such as lung-parenchyma. The proposed algorithm creates reconstructed radiographs and ground-truth data from high resolution CT-scans. Results show that removing visual variation that is irrelevant for a classification task improves the performance of a classifier when only limited training data are available. This is particularly relevant because a low number of ground-truth cases is common in medical imaging.
--Automated segmentation of anatomical structures is a crucial step in many medical image analysis tasks. For lung segmentation, a variety of approaches exist, involving sophisticated pipelines trained and validated on a range of different data sets. However, during translation to clinical routine the applicability of these approaches across diseases remains limited. Here, we show that the accuracy and reliability of lung segmentation algorithms on demanding cases primarily does not depend on methodology, but on the diversity of training data. We compare 4 generic deep learning approaches and 2 published lung segmentation algorithms on routine imaging data with more than 6 different disease patterns and 3 published data sets. We show that a basic approach - U-net - performs either better, or competitively with other approaches on both routine data and published data sets, and outperforms published approaches once trained on a diverse data set covering multiple diseases. Training data composition consistently has a bigger impact than algorithm choice on accuracy across test data sets. We carefully analyse the impact of data diversity, and the specifications of annotations on both training and validation sets to provide a reference for algorithms, training data, and annotation. Results on a seemingly well understood task of lung segmentation suggest the critical importance of training data diversity compared to model choice. The translation of machine-learning approaches developed on specific data sets to the variety of routine clinical data is of increasing importance. As methodology matures across different fields, means to render algorithms robust for the transition from the lab to the clinic become critical.
The advent of large data sets from many sources (big data), machine learning, and artificial intelligence (AI) are poised to revolutionize asthma care on both the investigative and clinical levels, according to an article published in the Journal of Allergy and Clinical Immunology. During 15-minute clinic visits, only a short amount of time is spent understanding and treating what is a complex disease, and only a fraction of the necessary data is captured in the electronic health record. "Our patients and the pace of data growth are compelling us to incorporate insights from Big Data to inform care," the researchers posit. "Predictive analytics, using machine learning and artificial intelligence has revolutionized many industries," including the healthcare industry. When used effectively, big data, in conjunction with electronic health record data, can transform the patient's healthcare experience.
While deep learning has shown promise in the domain of disease classification from medical images, models based on state-of-the-art convolutional neural network architectures often exhibit performance loss due to dataset shift. Models trained using data from one hospital system achieve high predictive performance when tested on data from the same hospital, but perform significantly worse when they are tested in different hospital systems. Furthermore, even within a given hospital system, deep learning models have been shown to depend on hospital- and patient-level confounders rather than meaningful pathology to make classifications. In order for these models to be safely deployed, we would like to ensure that they do not use confounding variables to make their classification, and that they will work well even when tested on images from hospitals that were not included in the training data. We attempt to address this problem in the context of pneumonia classification from chest radiographs. We propose an approach based on adversarial optimization, which allows us to learn more robust models that do not depend on confounders. Specifically, we demonstrate improved out-of-hospital generalization performance of a pneumonia classifier by training a model that is invariant to the view position of chest radiographs (anterior-posterior vs. posterior-anterior). Our approach leads to better predictive performance on external hospital data than both a standard baseline and previously proposed methods to handle confounding, and also suggests a method for identifying models that may rely on confounders. Code available at https://github.com/suinleelab/cxr_adv.
The hope of The Human Genome Project was that it would herald a new age of precision medicine. However, the challenge turned out to be more complex and nuanced than had been imagined. Of nearly 25,000 human genes, only 2,418 have been associated with specific diseases, explaining only a small fraction of all human pathologies. In 2020, we will begin to harness the power of artificial intelligence (AI) to create new, life-saving medicine. In the past decade, we have learned a great deal about the complexity of diseases.
In recent years, interest in monitoring air quality has been growing. Traditional environmental monitoring stations are very expensive, both to acquire and to maintain, therefore their deployment is generally very sparse. This is a problem when trying to generate air quality maps with a fine spatial resolution. Given the general interest in air quality monitoring, low-cost air quality sensors have become an active area of research and development. Low-cost air quality sensors can be deployed at a finer level of granularity than traditional monitoring stations. Furthermore, they can be portable and mobile. Low-cost air quality sensors, however, present some challenges: they suffer from cross-sensitivities between different ambient pollutants; they can be affected by external factors such as traffic, weather changes, and human behavior; and their accuracy degrades over time. Some promising machine learning approaches can help us obtain highly accurate measurements with low-cost air quality sensors. In this article, we present low-cost sensor technologies, and we survey and assess machine learning-based calibration techniques for their calibration. We conclude by presenting open questions and directions for future research.
I am involved with a group called the Astrological Investigators or The Gators for short (www.astroinvestigators.com). The Gators are led by a fellow engineer and astrologer Alphee Lavoie. Alphee brings his engineering analytics skills to a field that sometimes can be considered a bit flakey from the scientific community point of view. That is why Alphee has developed research software employing statistical analysis. The astrological chart is an assessment of a person's potential in various facets of life including health.
In this article, we focus on the analysis of the potential factors driving the spread of influenza, and possible policies to mitigate the adverse effects of the disease. To be precise, we first invoke discrete Fourier transform (DFT) to conclude a yearly periodic regional structure in the influenza activity, thus safely restricting ourselves to the analysis of the yearly influenza behavior. Then we collect a massive number of possible region-wise indicators contributing to the influenza mortality, such as consumption, immunization, sanitation, water quality, and other indicators from external data, with $1170$ dimensions in total. We extract significant features from the high dimensional indicators using a combination of data analysis techniques, including matrix completion, support vector machines (SVM), autoencoders, and principal component analysis (PCA). Furthermore, we model the international flow of migration and trade as a convolution on regional influenza activity, and solve the deconvolution problem as higher-order perturbations to the linear regression, thus separating regional and international factors related to the influenza mortality. Finally, both the original model and the perturbed model are tested on regional examples, as validations of our models. Pertaining to the policy, we make a proposal based on the connectivity data along with the previously extracted significant features to alleviate the impact of influenza, as well as efficiently propagate and carry out the policies. We conclude that environmental features and economic features are of significance to the influenza mortality. The model can be easily adapted to model other types of infectious diseases.
We developed an explainable artificial intelligence (AI) early warning score (xAI-EWS) system for early detection of acute critical illness. While maintaining a high predictive performance, our system explains to the clinician on which relevant electronic health records (EHRs) data the prediction is grounded. Acute critical illness is often preceded by deterioration of routinely measured clinical parameters, e.g., blood pressure and heart rate. Early clinical prediction is typically based on manually calculated screening metrics that simply weigh these parameters, such as Early Warning Scores (EWS). The predictive performance of EWSs yields a tradeoff between sensitivity and specificity that can lead to negative outcomes for the patient. Previous work on EHR-trained AI systems offers promising results with high levels of predictive performance in relation to the early, real-time prediction of acute critical illness. However, without insight into the complex decisions by such system, clinical translation is hindered. In this letter, we present our xAI-EWS system, which potentiates clinical translation by accompanying a prediction with information on the EHR data explaining it.
No predictive biomarkers can robustly identify non-small cell lung cancer (NSCLC) patients who will benefit from immune checkpoint inhibitor (ICI) therapies. Here, in a machine learning setting, we compared changes ("delta") in the radiomic texture (DelRADx) of computed tomography (CT) patterns both within and outside tumor nodules before and after 2-3 cycles of ICI therapy. We found that DelRADx patterns could predict response to ICI therapy and overall survival (OS) for patients with NSCLC. We retrospectively analyzed data acquired from 139 NSCLC patients at two institutions, who were divided into a discovery set (D1 50) and two independent validation sets (D2 62, D3 27). Intranodular and perinodular texture descriptors were extracted and the relative differences were computed.