Dataset Information

Hierarchical AI enables global interpretation of culture plates in the era of digital microbiology.

ABSTRACT: Full Laboratory Automation is revolutionizing work habits in an increasing number of clinical microbiology facilities worldwide, generating huge streams of digital images for interpretation. Contextually, deep learning architectures are leading to paradigm shifts in the way computers can assist with difficult visual interpretation tasks in several domains. At the crossroads of these epochal trends, we present a system able to tackle a core task in clinical microbiology, namely the global interpretation of diagnostic bacterial culture plates, including presumptive pathogen identification. This is achieved by decomposing the problem into a hierarchy of complex subtasks and addressing them with a multi-network architecture we call DeepColony. Working on a large stream of clinical data and a complete set of 32 pathogens, the proposed system is capable of effectively assist plate interpretation with a surprising degree of accuracy in the widespread and demanding framework of Urinary Tract Infections. Moreover, thanks to the rich species-related generated information, DeepColony can be used for developing trustworthy clinical decision support services in laboratory automation ecosystems from local to global scale.

SUBMITTER: Signoroni A

PROVIDER: S-EPMC10613199 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Hierarchical AI enables global interpretation of culture plates in the era of digital microbiology.

Signoroni Alberto A Ferrari Alessandro A Lombardi Stefano S Savardi Mattia M Fontana Stefania S Culbreath Karissa K

Nature communications 20231028 1

Full Laboratory Automation is revolutionizing work habits in an increasing number of clinical microbiology facilities worldwide, generating huge streams of digital images for interpretation. Contextually, deep learning architectures are leading to paradigm shifts in the way computers can assist with difficult visual interpretation tasks in several domains. At the crossroads of these epochal trends, we present a system able to tackle a core task in clinical microbiology, namely the global interpr ...[more]

PMID: 37898607

Similar Datasets

Project description:Aims and objectivesTo assess formative and summative milestones in a digital course and the reach to low- and middle-income countries of a Massive Open Online Course focussing on supporting nurses dealing with an emerging pandemic.BackgroundThe severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has ravaged the globe and increased the need for timely and accurate information from reliable sources. Access to reliable and accurate information, as well as support, is important in achieving health systems strengthening. Using a Massive Open Online Course format, an educational resource aimed at large-scale interactive participation via the Internet, and participants were engaged in a course focussing on nursing in a time of crisis and involved using social learning principles.DesignObservational descriptive study.MethodRoutinely collected data were collated during the period of 18 May-18 July 2020 focused on both formative and summative milestones in the course. Data were separated and classified by income in accordance with the publicly accessible 2020 World Bank Open Dataset.ResultsDuring the 2-month period of observation (18 May-18 July 2020), 10,130 individuals from 156 countries enrolled in the course. More than 51% of participants were Active Learners. Thirty per cent completed over 90% of the course content by the end. There was widespread distribution of learners in low- and middle-income countries across Asia, Africa and Latin America.ConclusionThe COVID-19 pandemic has underscored the importance of reliable and valid information sources. The use of Massive Open Online Course format can facilitate dissemination.Relevance to clinical practiceIn the context of a dynamic global pandemic, leveraging digital resources to allow access to reliable information and resources is important. Incentivising participation through recognition of learning is important. Engaging in a social learning platform also has the power for reflection, promotion of resilience and capacity for health systems strengthening.

Dataset Information

Hierarchical AI enables global interpretation of culture plates in the era of digital microbiology.

Publications

Hierarchical AI enables global interpretation of culture plates in the era of digital microbiology.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets