Implement or fix tuning of spatial smooting in spatialDGMM

[mciach]

As far as I remember, in older versions of spatialDGMM, the r parameter could be used to increase or decrease the amount of spatial smoothing (higher r values gave smoother segments). This was a very useful feature. In the current version, the segmentation is almost identical for different values of r.

An example to reproduce the issue:

set.seed(2020)
mse <- simulateImage(preset=3, dim=c(30,30), npeaks=9, 
                     peakheight=c(3,6,9), centroided=TRUE, from=495, to=505)
peaks <- mz(metadata(mse)$design$featureData)
peak_IDs <- sapply(peaks, function(x) which.min(abs(x-mse@featureData$mz)))
for(r in c(1,2,5,10,15)) {
  gmm <- spatialDGMM(mse, r=r, k=4, weights="adaptive")
  show(image(gmm, i=peak_IDs))
}

The segments produced for these five values of r are nearly identical, only individual pixels change between them. In particular, even for r=15 many segments are very rugged.

My session info:

> sessionInfo()
R version 4.4.1 (2024-06-14)
Platform: x86_64-pc-linux-gnu
Running under: Ubuntu 22.04.5 LTS

Matrix products: default
BLAS:   /home/mciach/Programs/R/4.4.1/lib/libRblas.so 
LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C               LC_TIME=pl_PL.UTF-8       
 [4] LC_COLLATE=en_US.UTF-8     LC_MONETARY=pl_PL.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=pl_PL.UTF-8       LC_NAME=C                  LC_ADDRESS=C              
[10] LC_TELEPHONE=C             LC_MEASUREMENT=pl_PL.UTF-8 LC_IDENTIFICATION=C       

time zone: Europe/Warsaw
tzcode source: system (glibc)

attached base packages:
[1] stats4    stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] Cardinal_3.6.5      S4Vectors_0.42.1    BiocParallel_1.38.0 BiocGenerics_0.50.0
[5] ProtGenerics_1.36.0

loaded via a namespace (and not attached):
 [1] nlme_3.1-166       cli_3.6.3          knitr_1.48         rlang_1.1.4       
 [5] xfun_0.48          DBI_1.2.3          tiff_0.1-12        png_0.1-8         
 [9] RCurl_1.98-1.16    htmltools_0.5.8.1  ontologyIndex_2.12 Biobase_2.64.0    
[13] locfit_1.5-9.10    rmarkdown_2.28     grid_4.4.1         evaluate_1.0.1    
[17] abind_1.4-8        bitops_1.0-9       fastmap_1.2.0      yaml_2.3.10       
[21] compiler_4.4.1     codetools_0.2-20   CardinalIO_1.2.1   irlba_2.3.5.1     
[25] htmlwidgets_1.6.4  fftwtools_0.9-11   EBImage_4.46.0     lattice_0.22-6    
[29] digest_0.6.37      matter_2.6.3       parallel_4.4.1     Matrix_1.7-1      
[33] tools_4.4.1        jpeg_0.1-10        biglm_0.9-3