Machine Learning Model for Chest Radiographs: Using Local Data to Enhance Performance.
Can Assoc Radiol J
; 74(3): 548-556, 2023 Aug.
Article
en En
| MEDLINE
| ID: mdl-36542834
ABSTRACT
PURPOSE:
To develop and assess the performance of a machine learning model which screens chest radiographs for 14 labels, and to determine whether fine-tuning the model on local data improves its performance. Generalizability at different institutions has been an obstacle to machine learning model implementation. We hypothesized that the performance of a model trained on an open-source dataset will improve at our local institution after being fine-tuned on local data.METHODS:
In this retrospective, institutional review board approved study, an ensemble of neural networks was trained on open-source datasets of chest radiographs for the detection of 14 labels. This model was then fine-tuned using 4510 local radiograph studies, using radiologists' reports as the gold standard to evaluate model performance. Both the open-source and fine-tuned models' accuracy were tested on 802 local radiographs. Receiver-operator characteristic curves were calculated, and statistical analysis was completed using DeLong's method and Wilcoxon signed-rank test.RESULTS:
The fine-tuned model identified 12 of 14 pathology labels with area under the curves greater than .75. After fine-tuning with local data, the model performed statistically significantly better overall, and specifically in detecting six pathology labels (P < .01).CONCLUSIONS:
A machine learning model able to accurately detect 14 labels simultaneously on chest radiographs was developed using open-source data, and its performance was improved after fine-tuning on local site data. This simple method of fine-tuning existing models on local data could improve the generalizability of existing models across different institutions to further improve their local performance.Palabras clave
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Aprendizaje Profundo
Tipo de estudio:
Prognostic_studies
Límite:
Humans
Idioma:
En
Revista:
Can Assoc Radiol J
Asunto de la revista:
RADIOLOGIA
Año:
2023
Tipo del documento:
Article
País de afiliación:
Canadá