Renal Replacement Therapy

Table 3 Evaluate results (dropout 0.7)

From: Study on deep learning-based detection of viable cell count in dialysis fluid images

Input image type	Model 1		Model 2
Input image type	Color	Binary	Color	Binary
Loss	0.1708	0.2498	0.0487	0.0871
Accuracy	0.9328	0.9297	0.9813	0.9766
Precision	0.9609	0.9331	0.9813	0.9803
Recall	0.9179	0.9258	0.9813	0.9766
F1-Score	0.9389	0.9294	0.9813	0.9784

The following figures show the Loss, Acciracy, Precision, Recall, and F1-score of a model (Model 1) using VGG-16 as a feature extractor and transition learning, and a model (Model 2) using some of the weights (fixed up to 15 layers) learned by VGG-16. Dropout is 0.7.

Back to article page

ISSN: 2059-1381

Contact us

Submission enquiries: Access here and click Contact Us
General enquiries: info@biomedcentral.com