Rationale: The management of indeterminate pulmonary nodules (IPNs) remains challenging, resulting in invasive procedures and delays in diagnosis and treatment. Strategies to decrease the rate of unnecessary invasive procedures and optimize surveillance regimens are needed. Objectives: To develop and validate a deep learning method to improve the management of IPNs. Methods: A Lung Cancer Prediction Convolutional Neural Network model was trained using computed tomography images of IPNs from the National Lung Screening Trial, internally validated, and externally tested on cohorts from two academic institutions. Measurements and Main Results: The areas under the receiver operating characteristic curve in the external validation cohorts were 83.5% (95% confidence interval [CI], 75.4–90.7%) and 91.9% (95% CI, 88.7–94.7%), compared with 78.1% (95% CI, 68.7–86.4%) and 81.9 (95% CI, 76.1–87.1%), respectively, for a commonly used clinical risk model for incidental nodules. Using 5% and 65% malignancy thresholds defining low- and high-risk categories, the overall net reclassifications in the validation cohorts for cancers and benign nodules compared with the Mayo model were 0.34 (Vanderbilt) and 0.30 (Oxford) as a rule-in test, and 0.33 (Vanderbilt) and 0.58 (Oxford) as a rule-out test. Compared with traditional risk prediction models, the Lung Cancer Prediction Convolutional Neural Network was associated with improved accuracy in predicting the likelihood of disease at each threshold of management and in our external validation cohorts. Conclusions: This study demonstrates that this deep learning algorithm can correctly reclassify IPNs into low- or high-risk categories in more than a third of cancers and benign nodules when compared with conventional risk models, potentially reducing the number of unnecessary invasive procedures and delays in diagnosis.

Artificial intelligence (AI) has been present in some guise within the field of radiology for over 50 years. The first studies investigating computer-aided diagnosis in thoracic radiology date back to the 1960s, and in the subsequent years, the main application of these techniques has been the detection and classification of pulmonary nodules. In addition, there have been other less intensely researched applications, such as the diagnosis of interstitial lung disease, chronic obstructive pulmonary disease, and the detection of pulmonary emboli. Despite extensive literature on the use of convolutional neural networks in thoracic imaging over the last few decades, we are yet to see these systems in use in clinical practice. The article reviews current state-of-the-art applications of AI and in detection, classification, and follow-up of pulmonary nodules and how deep-learning techniques might influence these going forward. Finally, we postulate the impact of these advancements on the role of radiologists and the importance of radiologists in the development and evaluation of these techniques.

Albinism refers to a group of genetic abnormalities in melanogenesis that are associated neuronal misrouting through the optic chiasm. We perform quantitative assessment of visual pathway structure and function in 23 persons with albinism (PWA) and 20 matched controls using optical coherence tomography (OCT), volumetric magnetic resonance imaging (MRI), diffusion tensor imaging and visual evoked potentials (VEP). PWA had a higher streamline decussation index (percentage of total tractography streamlines decussating at the chiasm) compared with controls (Z = −2.24, p = .025), and streamline decussation index correlated weakly with inter‐hemispheric asymmetry measured using VEP (r = .484, p = .042). For PWA, a significant correlation was found between foveal development index and total number of streamlines (r = .662, p < .001). Significant positive correlations were found between peri‐papillary retinal nerve fibre layer thickness and optic nerve (r = .642, p < .001) and tract (r = .663, p < .001) width. Occipital pole cortical thickness was 6.88% higher (Z = −4.10, p < .001) in PWA and was related to anterior visual pathway structures including foveal retinal pigment epithelium complex thickness (r = −.579, p = .005), optic disc (r = .478, p = .021) and rim areas (r = .597, p = .003). We were unable to demonstrate a significant relationship between OCT‐derived foveal or optic nerve measures and MRI‐derived chiasm size or streamline decussation index. Our novel tractographic demonstration of altered chiasmatic decussation in PWA corresponds to VEP measured cortical asymmetry and is consistent with chiasmatic misrouting in albinism. We also demonstrate a significant relationship between retinal pigment epithelium and visual cortex thickness indicating that retinal pigmentation defects in albinism lead to downstream structural reorganisation of the visual cortex.

Introduction: Deep Learning has been proposed as promising tool to classify malignant nodules. Our aim was to retrospectively validate our Lung Cancer Prediction Convolutional Neural Network (LCP-CNN), which was trained on US screening data, on an independent dataset of indeterminate nodules in an European multicentre trial, to rule out benign nodules maintaining a high lung cancer sensitivity. Methods: The LCP-CNN has been trained to generate a malignancy score for each nodule using CT data from the U.S. National Lung Screening Trial (NLST), and validated on CT scans containing 2106 nodules (205 lung cancers) detected in patients from from the Early Lung Cancer Diagnosis Using Artificial Intelligence and Big Data (LUCINDA) study, recruited from three tertiary referral centers in the UK, Germany and Netherlands. We pre-defined a benign nodule rule-out test, to identify benign nodules whilst maintaining a high sensitivity, by calculating thresholds on the malignancy score that achieve at least 99 % sensitivity on the NLST data. Overall performance per validation site was evaluated using Area-Under-the-ROC-Curve analysis (AUC). Results: The overall AUC across the European centers was 94.5 % (95 %CI 92.6-96.1). With a high sensitivity of 99.0 %, malignancy could be ruled out in 22.1 % of the nodules, enabling 18.5 % of the patients to avoid followup scans. The two false-negative results both represented small typical carcinoids.