AI-assisted report generation offers the opportunity to reduce radiologists' workload stemming from expanded screening guidelines, complex cases and workforce shortages, while maintaining diagnostic accuracy. In addition to describing pathological findings in chest X-ray reports, interpreting lines and tubes (L&T) is demanding and repetitive for radiologists, especially with high patient volumes. We introduce MAIRA-X, a clinically evaluated multimodal AI model for longitudinal chest X-ray (CXR) report generation, that encompasses both clinical findings and L&T reporting. Developed using a large-scale, multi-site, longitudinal dataset of 3.1 million studies (comprising 6 million images from 806k patients) from Mayo Clinic, MAIRA-X was evaluated on three holdout datasets and the public MIMIC-CXR dataset, where it significantly improved AI-generated reports over the state of the art on lexical quality, clinical correctness, and L&T-related elements. A novel L&T-specific metrics framework was developed to assess accuracy in reporting attributes such as type, longitudinal change and placement. A first-of-its-kind retrospective user evaluation study was conducted with nine radiologists of varying experience, who blindly reviewed 600 studies from distinct subjects. The user study found comparable rates of critical errors (3.0% for original vs. 4.6% for AI-generated reports) and a similar rate of acceptable sentences (97.8% for original vs. 97.4% for AI-generated reports), marking a significant improvement over prior user studies with larger gaps and higher error rates. Our results suggest that MAIRA-X can effectively assist radiologists, particularly in high-volume clinical settings.

Segmentation of lung gross tumour volumes is an important first step in radiotherapy and surgical intervention, and is starting to play a role in assessing chemotherapy response. Response to a drug is measured by tracking the tumour volumes over a series of CT scans over a time period i.e. a longitudinal study. However, there currently exist few solutions for automated or semi-automated longitudinal tumour segmentation. This paper introduces LinGuinE, an automated method to segment a longitudinal series of lung tumours. A radiologist must provide an initial input, indicating the location of the tumour in a CT scan at an arbitrary time point. LinGuinE samples points inside this tumour and propagates them to another time point using rigid registration. A click validity classifier selects points which still fall within the tumour; these are used to automatically create a segmentation in the new time point. We test LinGuinE on a dataset acquired from a phase 3 clinical trial for lung tumours and the publicly available 4-D lung CBCT dataset. We find that LinGuinE improves the Dice on both test sets by over 20% (p< 0.05) across 63 longitudinal studies. We show that any time point can be used as a starting point, conduct ablation experiments, and find that our LinGuinE setup yields the best results on both test datasets.

As reported by PwC and CB Insights' MoneyTree Report, the overall growth of Venture Capital investments activity in the United States reached $100 billion in 2018 - a truly watershed moment. And as U.S. Senator, Everett Dirksen once said: "A billion here, a billion there, pretty soon, you're talking real money"... So, since we are talking about so many billions, it's more important than ever for the VC community to make smarter investments. Instead of relying on startup founder's charisma, or the quality of his/her pitch deck, well-trained AI can help to predict investment's success probability much faster than going through manual analysis, and with far fewer emotions while at it. All business plans should meet the same rigorous and unbiased investment criteria - and this is where AI comes handy. It can be used all across the board: to discover, evaluate and support VC's investments! For example blogs, posts and other social media sources can be successfully scanned using Natural Language Processing - to identify early-stage companies searching for CVC/IVC investors. And since AI can be constantly fed with new data sets and new information, it can follow the emerging trends - accurately.

Cross-validation is one of the most popular model selection methods in statistics and machine learning. Despite its wide applicability, traditional cross validation methods tend to select overfitting models, due to the ignorance of the uncertainty in the testing sample. We develop a new, statistically principled inference tool based on cross-validation that takes into account the uncertainty in the testing sample. This new method outputs a set of highly competitive candidate models containing the best one with guaranteed probability. As a consequence, our method can achieve consistent variable selection in a classical linear regression setting, for which existing cross-validation methods require unconventional split ratios. When used for regularizing tuning parameter selection, the method can provide a further trade-off between prediction accuracy and model interpretability. We demonstrate the performance of the proposed method in several simulated and real data examples.

Many machine learning algorithms require precise estimates of covariance matrices. The sample covariance matrix performs poorly in high-dimensional settings, which has stimulated the development of alternative methods, the majority based on factor models and shrinkage. Recent work of Ledoit and Wolf has extended the shrinkage framework to Nonlinear Shrinkage (NLS), a more powerful covariance estimator based on Random Matrix Theory. Our contribution shows that, contrary to claims in the literature, cross-validation based covariance matrix estimation (CVC) yields comparable performance at strongly reduced complexity and runtime. On two real world data sets, we show that the CVC estimator yields superior results than competing shrinkage and factor based methods.