Attention-Guided Transfer Learning for Identification of Filamentous Fungi Encountered in the Clinical Laboratory.

This study addresses the challenge of accurately identifying filamentous fungi in medical laboratories using transfer learning with convolutional neural networks (CNNs). The study uses microscopic images from touch-tape slides with lactophenol cotton blue staining, the most common method in clinical settings, to classify fungal genera and identify Aspergillus species. The training and test data sets included 4,108 images with representative microscopic morphology for each genus, and a soft attention mechanism was incorporated to enhance classification accuracy. As a result, the study achieved an overall classification accuracy of 94.9% for four frequently encountered genera and 84.5% for Aspergillus species. One of the distinct features is the involvement of medical technologists in developing a model that seamlessly integrates into routine workflows. In addition, the study highlights the potential of merging advanced technology with medical laboratory practices to diagnose filamentous fungi accurately and efficiently. IMPORTANCE This study utilizes transfer learning with CNNs to classify fungal genera and identify Aspergillus species using microscopic images from touch-tape preparation and lactophenol cotton blue staining. The training and test data sets included 4,108 images with representative microscopic morphology for each genus, and a soft attention mechanism was incorporated to enhance classification accuracy. As a result, the study achieved an overall classification accuracy of 94.9% for four frequently encountered genera and 84.5% for Aspergillus species. One of the distinct features is the involvement of medical technologists in developing a model that seamlessly integrates into routine workflows. In addition, the study highlights the potential of merging advanced technology with medical laboratory practices to diagnose filamentous fungi accurately and efficiently.

Detection of carbapenem-resistant Klebsiella pneumoniae on the basis of matrix-assisted laser desorption ionization time-of-flight mass spectrometry by using supervised machine learning approach.

BACKGROUND: Carbapenem-resistant Klebsiella pneumoniae (CRKP) is emerging as a significant pathogen causing healthcare-associated infections. Matrix-assisted laser desorption/ionisation mass spectrometry time-of-flight mass spectrometry (MALDI-TOF MS) is used by clinical microbiology laboratories to address the need for rapid, cost-effective and accurate identification of microorganisms. We evaluated application of machine learning methods for differentiation of drug resistant bacteria from susceptible ones directly using the profile spectra of whole cells MALDI-TOF MS in 46 CRKP and 49 CSKP isolates. METHODS: We developed a two-step strategy for data preprocessing consisting of peak matching and a feature selection step before supervised machine learning analysis. Subsequently, five machine learning algorithms were used for classification. RESULTS: Random forest (RF) outperformed other four algorithms. Using RF algorithm, we correctly identified 93% of the CRKP and 100% of the CSKP isolates with an overall classification accuracy rate of 97% when 80 peaks were selected as input features. CONCLUSIONS: We conclude that CRKPs can be differentiated from CSKPs through RF analysis. We used direct colony method, and only one spectrum for an isolate for analysis, without modification of current protocol. This allows the technique to be easily incorporated into clinical practice in the future.