Utilizing Deep Learning and Computed Tomography to Determine Pulmonary Nodule Activity in Patients With Nontuberculous Mycobacterial-Lung Disease.

PURPOSE: To develop and evaluate a deep convolutional neural network (DCNN) model for the classification of acute and chronic lung nodules from nontuberculous mycobacterial-lung disease (NTM-LD) on computed tomography (CT). MATERIALS AND METHODS: We collected a data set of 650 nodules (316 acute and 334 chronic) from the CT scans of 110 patients with NTM-LD. The data set was divided into training, validation, and test sets in a ratio of 4:1:1. Bounding boxes were used to crop the 2D CT images down to the area of interest. A DCNN model was built using 11 convolutional layers and trained on these images. The performance of the model was evaluated on the hold-out test set and compared with that of 3 radiologists who independently reviewed the images. RESULTS: The DCNN model achieved an area under the receiver operating characteristic curve of 0.806 for differentiating acute and chronic NTM-LD nodules, corresponding to sensitivity, specificity, and accuracy of 76%, 68%, and 72%, respectively. The performance of the model was comparable to that of the 3 radiologists, who had area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy of 0.693 to 0.771, 61% to 82%, 59% to 73%, and 60% to 73%, respectively. CONCLUSIONS: This study demonstrated the feasibility of using a DCNN model for the classification of the activity of NTM-LD nodules on chest CT. The model performance was comparable to that of radiologists. This approach can potentially and efficiently improve the diagnosis and management of NTM-LD.

Nebulized Bacteriophage in a Patient With Refractory Mycobacterium abscessus Lung Disease.

An elderly man with refractory Mycobacterium abscessus lung disease previously developed anti-phage neutralizing antibodies while receiving intravenous phage therapy. Subsequent phage nebulization resulted in transient weight gain, decreased C-reactive protein, and reduced Mycobacterium burden. Weak sputum neutralization may have limited the outcomes, but phage resistance was not a contributing factor.

Global phylogenomic analyses of Mycobacterium abscessus provide context for non cystic fibrosis infections and the evolution of antibiotic resistance.

Mycobacterium abscessus (MAB) is an emerging pathogen that leads to chronic lung infections. To date, the global population structure of non-cystic fibrosis (CF) MAB and evolutionary patterns of drug resistance emergence have not been investigated. Here we construct a global dataset of 1,279 MAB whole genomes from CF or non-CF patients. We utilize whole genome analysis to assess relatedness, phylogeography, and drug resistance evolution. MAB isolates from CF and non-CF hosts are interspersed throughout the phylogeny, such that the majority of dominant circulating clones include isolates from both populations, indicating that global spread of MAB clones is not sequestered to CF contexts. We identify a large clade of M. abscessus harboring the erm(41) T28C mutation, predicted to confer macrolide susceptibility in this otherwise macrolide-resistant species. Identification of multiple evolutionary events within this clade, consistent with regain of wild type, intrinsic macrolide resistance, underscores the critical importance of macrolides in MAB.

Potent antibody-mediated neutralization limits bacteriophage treatment of a pulmonary Mycobacterium abscessus infection.

An 81-year-old immunocompetent patient with bronchiectasis and refractory Mycobacterium abscessus lung disease was treated for 6 months with a three-phage cocktail active against the strain. In this case study of phage to lower infectious burden, intravenous administration was safe and reduced the M. abscessus sputum load tenfold within one month. However, after two months, M. abscessus counts increased as the patient mounted a robust IgM- and IgG-mediated neutralizing antibody response to the phages, which was associated with limited therapeutic efficacy.