Skip to main content

Table 2 Nuclei classification accuracy and comparison against other machine learning and deep learning methods

From: Microscopic nuclei classification, segmentation, and detection with improved deep convolutional neural networks (DCNN)

Methods

Average F1-score

AUC

CRImage [16]

0.488

0.684

Super-pixel descriptor [40]

0.687

0.853

SoftMax CNN + SSPP [39]

0.748

0.893

SoftMax CNN + NEP [39]

0.784

0.917

DenseNet [19]

0.794

0.9523

Proposed (DRCN)

0.811

0.9612