Skip to main content

Table 1 Unmixing results using a single image of cultured mouse neuron smFISH data

From: SUFI: an automated approach to spectral unmixing of fluorescent multiplex images captured in mouse and post-mortem human brain tissues

Method

DAPI

Opal 520

Opal 570

Opal 620

Opal 690

Mean

Root mean squared error (RMSE)

 FCLSU

0.0055

0.0020

0.0031

0.0012

0.0015

0.0027

 ELMM

0.0049

0.0025

0.0022

0.0012

0.0012

0.0024

 GELMM

0.0048

0.0020

0.0033

0.0012

0.0015

0.0026

SØrensen–Dice similarity coefficient

 FCLSU

0.9582

0.9739

0.4296

0.6551

0.8803

0.7794

 ELMM

0.9715

0.9680

0.7547

0.2146

0.6683

0.7154

 GELMM

0.9650

0.9745

0.2584

0.5778

0.8783

0.7308

Structural similarity index (SSIM)

 FCLSU

0.8953

0.9961

0.9909

0.9865

0.9817

0.9701

 ELMM

0.8984

0.9961

0.9914

0.9879

0.9875

0.9723

 GELMM

0.8963

0.9959

0.9909

0.9865

0.9812

0.9702

  1. Here we compare the performance of SUFI against the ZEN unmixed image using three metrics (RMSE, dice similarity, SSIM) for all three methods (FCLSU, ELMM, GELMM). For the three metrics, values range between 0 and 1 with better performance indicated by lower RMSE values and higher SSIM and dice similarity values. Mean over all channels is presented as last column