Learning to detect chest radiographs containing pulmonary lesions using visual attention networks.

Machine learning approaches hold great potential for the automated detection of lung nodules on chest radiographs, but training algorithms requires very large amounts of manually annotated radiographs, which are difficult to obtain. The increasing availability of PACS (Picture Archiving and Communication System), is laying the technological foundations needed to make available large volumes of clinical data and images from hospital archives. Binary labels indicating whether a radiograph contains a pulmonary lesion can be extracted at scale, using natural language processing algorithms. In this study, we propose two novel neural networks for the detection of chest radiographs containing pulmonary lesions. Both architectures make use of a large number of weakly-labelled images combined with a smaller number of manually annotated x-rays. The annotated lesions are used during training to deliver a type of visual attention feedback informing the networks about their lesion localisation performance. The first architecture extracts saliency maps from high-level convolutional layers and compares the inferred position of a lesion against the true position when this information is available; a localisation error is then back-propagated along with the softmax classification error. The second approach consists of a recurrent attention model that learns to observe a short sequence of smaller image portions through reinforcement learning; the reward function penalises the exploration of areas, within an image, that are unlikely to contain nodules. Using a repository of over 430,000 historical chest radiographs, we present and discuss the proposed methods over related architectures that use either weakly-labelled or annotated images only.

Predicting Response to Neoadjuvant Chemotherapy with PET Imaging Using Convolutional Neural Networks.

Imaging of cancer with 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) has become a standard component of diagnosis and staging in oncology, and is becoming more important as a quantitative monitor of individual response to therapy. In this article we investigate the challenging problem of predicting a patient's response to neoadjuvant chemotherapy from a single 18F-FDG PET scan taken prior to treatment. We take a "radiomics" approach whereby a large amount of quantitative features is automatically extracted from pretherapy PET images in order to build a comprehensive quantification of the tumor phenotype. While the dominant methodology relies on hand-crafted texture features, we explore the potential of automatically learning low- to high-level features directly from PET scans. We report on a study that compares the performance of two competing radiomics strategies: an approach based on state-of-the-art statistical classifiers using over 100 quantitative imaging descriptors, including texture features as well as standardized uptake values, and a convolutional neural network, 3S-CNN, trained directly from PET scans by taking sets of adjacent intra-tumor slices. Our experimental results, based on a sample of 107 patients with esophageal cancer, provide initial evidence that convolutional neural networks have the potential to extract PET imaging representations that are highly predictive of response to therapy. On this dataset, 3S-CNN achieves an average 80.7% sensitivity and 81.6% specificity in predicting non-responders, and outperforms other competing predictive models.

Prediction of Outcome in Acute Lower Gastrointestinal Bleeding Using Gradient Boosting.

BACKGROUND: There are no widely used models in clinical care to predict outcome in acute lower gastro-intestinal bleeding (ALGIB). If available these could help triage patients at presentation to appropriate levels of care/intervention and improve medical resource utilisation. We aimed to apply a state-of-the-art machine learning classifier, gradient boosting (GB), to predict outcome in ALGIB using non-endoscopic measurements as predictors. METHODS: Non-endoscopic variables from patients with ALGIB attending the emergency departments of two teaching hospitals were analysed retrospectively for training/internal validation (n=170) and external validation (n=130) of the GB model. The performance of the GB algorithm in predicting recurrent bleeding, clinical intervention and severe bleeding was compared to a multiple logic regression (MLR) model and two published MLR-based prediction algorithms (BLEED and Strate prediction rule). RESULTS: The GB algorithm had the best negative predictive values for the chosen outcomes (>88%). On internal validation the accuracy of the GB algorithm for predicting recurrent bleeding, therapeutic intervention and severe bleeding were (88%, 88% and 78% respectively) and superior to the BLEED classification (64%, 68% and 63%), Strate prediction rule (78%, 78%, 67%) and conventional MLR (74%, 74% 62%). On external validation the accuracy was similar to conventional MLR for recurrent bleeding (88% vs. 83%) and therapeutic intervention (91% vs. 87%) but superior for severe bleeding (83% vs. 71%). CONCLUSION: The gradient boosting algorithm accurately predicts outcome in patients with acute lower gastrointestinal bleeding and outperforms multiple logistic regression based models. These may be useful for risk stratification of patients on presentation to the emergency department.