Robust breast cancer detection in mammography and digital breast tomosynthesis using an annotation-efficient deep learning approach.

Breast cancer remains a global challenge, causing over 600,000 deaths in 2018 (ref. 1). To achieve earlier cancer detection, health organizations worldwide recommend screening mammography, which is estimated to decrease breast cancer mortality by 20-40% (refs. 2,3). Despite the clear value of screening mammography, significant false positive and false negative rates along with non-uniformities in expert reader availability leave opportunities for improving quality and access4,5. To address these limitations, there has been much recent interest in applying deep learning to mammography6-18, and these efforts have highlighted two key difficulties: obtaining large amounts of annotated training data and ensuring generalization across populations, acquisition equipment and modalities. Here we present an annotation-efficient deep learning approach that (1) achieves state-of-the-art performance in mammogram classification, (2) successfully extends to digital breast tomosynthesis (DBT; '3D mammography'), (3) detects cancers in clinically negative prior mammograms of patients with cancer, (4) generalizes well to a population with low screening rates and (5) outperforms five out of five full-time breast-imaging specialists with an average increase in sensitivity of 14%. By creating new 'maximum suspicion projection' (MSP) images from DBT data, our progressively trained, multiple-instance learning approach effectively trains on DBT exams using only breast-level labels while maintaining localization-based interpretability. Altogether, our results demonstrate promise towards software that can improve the accuracy of and access to screening mammography worldwide.

Multiorgan structures detection using deep convolutional neural networks.

Many automatic image analysis algorithms in medical imaging require a good initialization to work properly. A similar problem occurs in many imaging-based clinical workflows, which depend on anatomical landmarks. The localization of anatomic structures based on a defined context provides with a solution to that problem, which turns out to be more challenging in medical imaging where labeled images are difficult to obtain. We propose a two-stage process to detect and regress 2D bounding boxes of predefined anatomical structures based on a 2D surrounding context. First, we use a deep convolutional neural network (DCNN) architecture to detect the optimal slice where an anatomical structure is present, based on relevant landmark features. After this detection, we employ a similar architecture to perform a 2D regression with the aim of proposing a bounding box where the structure is encompassed. We trained and tested our system for 57 anatomical structures defined in axial, sagittal and coronal planes with a dataset of 504 labeled Computed Tomography (CT) scans. We compared our method with a well-known object detection algorithm (Viola Jones) and with the inter-rater error for two human experts. Despite the relatively small number of scans and the exhaustive number of structures analyzed, our method obtained promising and consistent results, which proves our architecture very generalizable to other anatomical structures.

Respiratory Symptoms in Young Adults and Future Lung Disease. The CARDIA Lung Study.

RATIONALE: There are limited data on factors in young adulthood that predict future lung disease. OBJECTIVES: To determine the relationship between respiratory symptoms, loss of lung health, and incident respiratory disease in a population-based study of young adults. METHODS: We examined prospective data from 2,749 participants in the CARDIA (Coronary Artery Risk Development in Young Adults) study who completed respiratory symptom questionnaires at baseline and 2 years later and repeated spirometry measurements over 30 years. MEASUREMENTS AND MAIN RESULTS: Cough or phlegm, episodes of bronchitis, wheeze, shortness of breath, and chest illnesses at both baseline and Year 2 were the main predictor variables in models assessing decline in FEV1 and FVC from Year 5 to Year 30, incident obstructive and restrictive lung physiology, and visual emphysema on thoracic computed tomography scan. After adjustment for covariates, including body mass index, asthma, and smoking, report of any symptom was associated with -2.71 ml/yr excess decline in FEV1 (P < 0.001) and -2.18 in FVC (P < 0.001) as well as greater odds of incident (prebronchodilator) obstructive (odds ratio [OR], 1.63; 95% confidence interval [CI], 1.24-2.14) and restrictive (OR, 1.40; 95% CI, 1.09-1.80) physiology. Cough-related symptoms (OR, 1.56; 95% CI, 1.13-2.16) were associated with greater odds of future emphysema. CONCLUSIONS: Persistent respiratory symptoms in young adults are associated with accelerated decline in lung function, incident obstructive and restrictive physiology, and greater odds of future radiographic emphysema.

Diffeomorphic Lung Registration Using Deep CNNs and Reinforced Learning.

Image registration is a well-known problem in the field of medical imaging. In this paper, we focus on the registration of chest inspiratory and expiratory computed tomography (CT) scans from the same patient. Our method recovers the diffeomorphic elastic displacement vector field (DVF) by jointly regressing the direct and the inverse transformation. Our architecture is based on the RegNet network but we implement a reinforced learning strategy that can accommodate a large training dataset. Our results show that our method performs with a lower estimation error for the same number of epochs than the RegNet approach.