Comparison of Gray-scale Inversion to Improve Detection of Pulmonary Nodules on Chest X-rays Between Radiologists and a Deep Convolutional Neural Network.

Detection of pulmonary nodules on chest x-rays is an important task for radiologists. Previous studies have shown improved detection rates using gray-scale inversion. The purpose of our study was to compare the efficacy of gray-scale inversion in improving the detection of pulmonary nodules on chest x-rays for radiologists and machine learning models (ML). We created a mixed dataset consisting of 60, 2-view (posteroanterior view - PA and lateral view) chest x-rays with computed tomography confirmed nodule(s) and 62 normal chest x-rays. Twenty percent of the cases were separated for a testing dataset (24 total images). Data augmentation through mirroring and transfer learning was used for the remaining cases (784 total images) for supervised training of 4 ML models (grayscale PA, grayscale lateral, gray-scale inversion PA, and gray-scale inversion lateral) on Google's cloud-based AutoML platform. Three cardiothoracic radiologists analyzed the complete 2-view dataset (n=120) and, for comparison to the ML, the single-view testing subsets (12 images each). Gray-scale inversion (area under the curve (AUC) 0.80, 95% confidence interval (CI) 0.75-0.85) did not improve diagnostic performance for radiologists compared to grayscale (AUC 0.84, 95% CI 0.79-0.88). Gray-scale inversion also did not improve diagnostic performance for the ML. The ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5% respectively). In the limited testing dataset, the ML did demonstrate higher sensitivity and negative predictive value for grayscale PA (72.7% and 75.0%), grayscale lateral (63.6% and 66.6%), and gray-scale inversion lateral views (72.7% and 76.9%), comparing favorably to the radiologists (63.9% and 72.3%, 27.8% and 58.3%, 19.5% and 50.5%, respectively). Further investigation of other post-processing algorithms to improve diagnostic performance of ML is warranted.

Multimodality Imaging of Pleuropulmonary Blastoma: Pearls, Pitfalls, and Differential Diagnosis.

Pleuropulmonary blastomas are rare, potentially aggressive embryonal cancers of the lung parenchyma and pleural surfaces that account for 0.25%-0.5% of primary pulmonary malignancies in children. Pleuropulmonary blastomas are classified as cystic (type I), mixed cystic and solid (type II), and solid (type III). Pleuropulmonary blastoma occurs in the same age group (0-6 years) as other more common solid tumors such as neuroblastoma and Wilms tumor. Differential diagnosis includes metastasis from Wilms tumor and macrocystic congenital pulmonary airway malformation (CPAM). A key pathologic and genetic discriminator is the DICER1 germline mutation found in patients with pleuropulmonary blastoma. Imaging, histopathologic, and clinical data are important to use in conjunction in order to determine the diagnosis and risk stratification of pleuropulmonary blastomas. Survival varies from poor to good, depending on type. However, the spectrum of pleuropulmonary blastoma is insufficiently understood due to the variable presentation of this rare disease. We present a current review of the literature regarding pleuropulmonary blastomas in this article.

Crowdsourcing pneumothorax annotations using machine learning annotations on the NIH chest X-ray dataset.

Pneumothorax is a potentially life-threatening condition that requires prompt recognition and often urgent intervention. In the ICU setting, large numbers of chest radiographs are performed and must be interpreted on a daily basis which may delay diagnosis of this entity. Development of artificial intelligence (AI) techniques to detect pneumothorax could help expedite detection as well as localize and potentially quantify pneumothorax. Open image analysis competitions are useful in advancing state-of-the art AI algorithms but generally require large expert annotated datasets. We have annotated and adjudicated a large dataset of chest radiographs to be made public with the goal of sparking innovation in this space. Because of the cumbersome and time-consuming nature of image labeling, we explored the value of using AI models to generate annotations for review. Utilization of this machine learning annotation (MLA) technique appeared to expedite our annotation process with relatively high sensitivity at the expense of specificity. Further research is required to confirm and better characterize the value of MLAs. Our adjudicated dataset is now available for public consumption in the form of a challenge.