TY  - JOUR
AU  - Kim, Hee
AU  - Ganslandt, Thomas
AU  - Miethke, Thomas
AU  - Neumaier, Michael
AU  - Kittel, Maximilian
PY  - 2020
DA  - 2020/7/13
TI  - Deep Learning Frameworks for Rapid Gram Stain Image Data Interpretation: Protocol for a Retrospective Data Analysis
JO  - JMIR Res Protoc
SP  - e16843
VL  - 9
IS  - 7
KW  - high performance computing
KW  - rapid Gram stain classification
KW  - image data analysis
KW  - deep learning
KW  - convolutional neural network
AB  - Background: In recent years, remarkable progress has been made in deep learning technology and successful use cases have been introduced in the medical domain. However, not many studies have considered high-performance computing to fully appreciate the capability of deep learning technology. Objective: This paper aims to design a solution to accelerate an automated Gram stain image interpretation by means of a deep learning framework without additional hardware resources. Methods: We will apply and evaluate 3 methodologies, namely fine-tuning, an integer arithmetic–only framework, and hyperparameter tuning. Results: The choice of pretrained models and the ideal setting for layer tuning and hyperparameter tuning will be determined. These results will provide an empirical yet reproducible guideline for those who consider a rapid deep learning solution for Gram stain image interpretation. The results are planned to be announced in the first quarter of 2021. Conclusions: Making a balanced decision between modeling performance and computational performance is the key for a successful deep learning solution. Otherwise, highly accurate but slow deep learning solutions can add value to routine care. International Registered Report Identifier (IRRID): DERR1-10.2196/16843 
SN  - 1929-0748
UR  - http://www.researchprotocols.org/2020/7/e16843/
UR  - https://doi.org/10.2196/16843
UR  - http://www.ncbi.nlm.nih.gov/pubmed/32673276
DO  - 10.2196/16843
ID  - info:doi/10.2196/16843
ER  -