Assessment of inspiration and technical quality in anteroposterior thoracic radiographs using machine learning.

INTRODUCTION: Chest radiographs are the most performed radiographic procedure, but suboptimal technical factors can impact clinical interpretation. A deep learning model was developed to assess technical and inspiratory adequacy of anteroposterior chest radiographs. METHODS: Adult anteroposterior chest radiographs (n = 2375) were assessed for technical adequacy, and if otherwise technically adequate, for adequacy of inspiration. Images were labelled by an experienced radiologist with one of three ground truth labels: inadequate technique (n = 605, 25.5 %), adequate inspiration (n = 900, 37.9 %), and inadequate inspiration (n = 870, 36.6 %). A convolutional neural network was then iteratively trained to predict these labels and evaluated using recall, precision, F1 and micro-F1, and Gradient-weighted Class Activation Mapping analysis on a hold-out test set. Impact of kyphosis on model accuracy was assessed. RESULTS: The model performed best for radiographs with adequate technique, and worst for images with inadequate technique. Recall was highest (89 %) for radiographs with both adequate technique and inspiration, with recall of 81 % for images with adequate technique and inadequate inspiration, and 60 % for images with inadequate technique, although precision was highest (85 %) for this category. Per-class F1 was 80 %, 81 % and 70 % for adequate inspiration, inadequate inspiration, and inadequate technique respectively. Weighted F1 and Micro F1 scores were 78 %. Presence or absence of kyphosis had no significant impact on model accuracy in images with adequate technique. CONCLUSION: This study explores the promising performance of a machine learning algorithm for assessment of inspiratory adequacy and overall technical adequacy for anteroposterior chest radiograph acquisition. IMPLICATIONS FOR PRACTICE: With further refinement, machine learning can contribute to education and quality improvement in radiology departments.

Coat formation of surface-active proteins on aqueous surfaces during drying.

Segregation of the protein bovine serum albumin (BSA) and lactose in thin aqueous films during drying was investigated by examining the composition of the dried films using inverse micro Raman spectroscopy (IMRS) and X-ray photoelectron spectroscopy (XPS) sputter-depth profiling. The composition was uniform through the thickness of the dried films except within a 10nm region at the exposed surface where BSA had accumulated, most likely due to its surface activity. The thickness of the BSA layer was similar to the diameter of a BSA molecule, which suggests that a single monolayer of BSA adsorbed at the exposed surface. The BSA surface concentration of the dried films was constant over a wide range of BSA bulk concentrations, indicating that the aqueous surface became saturated with BSA during drying. The BSA surface layer of order 10nm was significantly thinner than the film thickness of order 10 µm, which implies that BSA formed a surface coating rather than a shell, and thus lent no structural rigidity to the film.

Safety studies of the oral rabies vaccine SAD B19 in striped skunk (Mephitis mephitis).

Safety of the modified live rabies virus vaccine, SAD B19, was studied in striped skunks (Mephitis mephitis). Seven skunks received 10(7.9) foci formatting units by direct oral administration. In four cages, a vaccinated animal was placed with a control animal, the other three vaccinated skunks were housed individually. Saliva and nasal swabs were collected 1, 2, 4, 24, 48, and 72 hr post-vaccination. From all vaccinated and control animals (n = 11) blood samples were collected 0, 28, 56, 84, and 296 days post-vaccination. Three of seven vaccinated skunks seroconverted. None of the control animals had detectable levels of rabies virus neutralizing antibodies. Also no vaccine virus was isolated from the nasal and saliva swabs collected from any animal. Thus, SAD B19 was innocuous for skunks in our study after direct oral administration at field concentration.