RESUMEN
Recent advancements in image analysis and interpretation technologies using computer vision techniques have shown potential for novel applications in clinical microbiology laboratories to support task automation aiming for faster and more reliable diagnostics. Deep learning models can be a valuable tool in the screening process, helping technicians spend less time classifying no-growth results and quickly separating the categories of tests that deserve further analysis. In this context, creating datasets with correctly classified images is fundamental for developing and improving such models. Therefore, a dataset of urine test Petri dishes images was collected following a standardized process, with controlled conditions of positioning and lighting. Image acquisition was conducted by applying a hardware chamber equipped with a led lightning source and a smartphone camera with 12 MP resolution. A software application was developed to support image classification and handling. Experienced microbiologists classified the images according to the positive, negative, and uncertain test results. The resulting dataset contains a total of 1500 images and can support the development of deep learning algorithms to classify urine exams according to their microbial growth.
RESUMEN
Carba-NP original report for blood cultures described the need of subculture and mechanical lysis before testing, reaching the turnaround time of approximately 4 hours for sample preparation. We tested 100 consecutive blood cultures positive for Gram-negative bacilli on the Gram stain from a large clinical laboratory. Bacterial pellets were prepared by centrifugation and submitted to Carba-NP and Blue-Carba tests and used further to prepare smears for Vitek MS. Results obtained with colonies grown on sheep blood agar using the same methodologies were used as the gold standard. Carbapenemase genes were confirmed by PCR and DNA sequencing. Vitek MS identified correctly 86% of the samples. Of note, 7% of the samples were incorrectly reported by the instrument as containing a single isolate. KPC-2 was the predominant carbapenemase detected. There was 100% concordance for both negative and positive results for Carba-NP. In contrast, for Blue-Carba the concordance for positive results was 92.8%, and 41% of strains negative for carbapenemases presented a yellowish color on control well turning the test non-interpretable. The turnaround time for sample preparation for preparing the pellet was 13 min, and no subculture or mechanical lysis is needed when detecting KPC production in Enterobacterales.