MelanomavsSeborreic

Melanoma vs Seborreic_Keratosis

Loading data sets

op <- par(no.readonly = TRUE)

MelanomaFeatures <- read.csv("E:/SKINCCANCER/MatlabScripts/MelanomaLesionFeatures.csv", header=FALSE)
SeborrheicFeatures <- read.csv("E:/SKINCCANCER/MatlabScripts/SeborrheicLesionFeatures.csv", header=FALSE)
MelanomaControlFeatures <- read.csv("E:/SKINCCANCER/MatlabScripts/MelanomaControlFeatures.csv", header=FALSE)
SeborrheicControlFeatures <- read.csv("E:/SKINCCANCER/MatlabScripts/SeborrheicControlFeatures.csv", header=FALSE)
LesionFeatureNames <- read_excel("FeatureNames.xlsx")
ControlFeatureNames <- read_excel("FeatureNames.xlsx",sheet = "Control")
FeatureNames <- read_excel("FeatureNames.xlsx",sheet = "PerChannel")

colnames(MelanomaFeatures) <- LesionFeatureNames$FinalName
colnames(SeborrheicFeatures) <- LesionFeatureNames$FinalName
colnames(MelanomaControlFeatures) <- ControlFeatureNames$FinalName
colnames(SeborrheicControlFeatures) <- ControlFeatureNames$FinalName


sum(is.na(MelanomaFeatures))
sum(is.na(SeborrheicFeatures))
sum(is.na(MelanomaControlFeatures))

channel1 <- c(1:32)
channel2 <- c(33:64)
channel3 <- c(65:96)

MMelanomaFeatures <- (  MelanomaFeatures[,channel1] +
                        MelanomaFeatures[,channel2] +
                        MelanomaFeatures[,channel3] )/3.0
SMelanomaFeatures <- (  abs(MelanomaFeatures[,channel1] - MMelanomaFeatures) +
                        abs(MelanomaFeatures[,channel2] - MMelanomaFeatures) +
                        abs(MelanomaFeatures[,channel3] - MMelanomaFeatures) )/3.0

colnames(MMelanomaFeatures) <- paste("M",FeatureNames$Features,sep="")
colnames(SMelanomaFeatures) <- paste("S",FeatureNames$Features,sep="")

MelanomaFeatures <- cbind(MelanomaFeatures,SMelanomaFeatures/(0.001+abs(MMelanomaFeatures)))


MSeborrheicFeatures <- (  SeborrheicFeatures[,channel1] +
                          SeborrheicFeatures[,channel2] +
                          SeborrheicFeatures[,channel3] )/3.0
SSeborrheicFeatures <- (abs(SeborrheicFeatures[,channel1] - MSeborrheicFeatures) +
                        abs(SeborrheicFeatures[,channel2] - MSeborrheicFeatures) +
                        abs(SeborrheicFeatures[,channel3] - MSeborrheicFeatures))/3.0
colnames(MSeborrheicFeatures) <- paste("M",FeatureNames$Features,sep="")
colnames(SSeborrheicFeatures) <- paste("S",FeatureNames$Features,sep="")

SeborrheicFeatures <- cbind(SeborrheicFeatures,SSeborrheicFeatures/(0.001+abs(MSeborrheicFeatures)))

MMelanomaControlFeatures <- (  MelanomaControlFeatures[,channel1] +
                               MelanomaControlFeatures[,channel2] +
                               MelanomaControlFeatures[,channel3] )/3.0

SMelanomaControlFeatures <- (abs(MelanomaControlFeatures[,channel1] - MMelanomaControlFeatures) +
                             abs(MelanomaControlFeatures[,channel2] - MMelanomaControlFeatures) +
                             abs(MelanomaControlFeatures[,channel3] - MMelanomaControlFeatures))/3.0
colnames(MMelanomaControlFeatures) <- paste("M_C",FeatureNames$Features,sep="")
colnames(SMelanomaControlFeatures) <- paste("S_C",FeatureNames$Features,sep="")


MelanomaControlFeatures <- cbind(MelanomaControlFeatures,SMelanomaControlFeatures/(0.001+abs(MMelanomaControlFeatures)))


MSeborrheicControlFeatures <- (  SeborrheicControlFeatures[,channel1] +
                                 SeborrheicControlFeatures[,channel2] +
                                 SeborrheicControlFeatures[,channel3] )/3.0
SSeborrheicControlFeatures <- (abs(SeborrheicControlFeatures[,channel1] - MSeborrheicControlFeatures) +
                               abs(SeborrheicControlFeatures[,channel2] - MSeborrheicControlFeatures) +
                               abs(SeborrheicControlFeatures[,channel3] - MSeborrheicControlFeatures))/3.0
colnames(MSeborrheicControlFeatures) <- paste("M_C",FeatureNames$Features,sep="")
colnames(SSeborrheicControlFeatures) <- paste("S_C",FeatureNames$Features,sep="")

SeborrheicControlFeatures <- cbind(SeborrheicControlFeatures,
                                   SSeborrheicControlFeatures/(0.001+abs(MSeborrheicControlFeatures)))



CtrDiff <- MelanomaFeatures[,1:ncol(MelanomaControlFeatures)] - MelanomaControlFeatures;
colnames(CtrDiff) <- colnames(MelanomaControlFeatures)
MelanomaFeatures <- cbind(MelanomaFeatures,CtrDiff) 


CtrDiff <- SeborrheicFeatures[,1:ncol(MelanomaControlFeatures)] - SeborrheicControlFeatures;
colnames(CtrDiff) <- colnames(SeborrheicControlFeatures)
SeborrheicFeatures <- cbind(SeborrheicFeatures,CtrDiff)

MelanomaFeatures <- MelanomaFeatures[complete.cases(MelanomaFeatures),]
SeborrheicFeatures <- SeborrheicFeatures[complete.cases(SeborrheicFeatures),]

MelanomaFeatures$Class <- rep(1,nrow(MelanomaFeatures))
SeborrheicFeatures$Class <- rep(0,nrow(SeborrheicFeatures))

MelanomaSeborrheic <- rbind(MelanomaFeatures,SeborrheicFeatures)

table(MelanomaSeborrheic$Class)

The Heatmap

par(op)


par(mar=c(10,5,5,5))
boxplot(MelanomaSeborrheic,las=2,cex=0.5,cex.axis=0.5,main="Features")


par(op)

hm <- heatMaps(Outcome = "Class",
               data = MelanomaSeborrheic,
               title = "Heat Map:",Scale = TRUE,
               hCluster = "col",cexRow = 0.75,cexCol = 0.35,srtCol = 45)


uks <- univariate_KS(MelanomaSeborrheic,"Class")

par(mar=c(5,15,5,5))
barplot(-log(1.0e-12+uks[1:20]),las=2,xlab="Log(pvalue)",cex.names = 0.65,main="Top Features",horiz=TRUE)


print(uks[1:20])
#>                 C_Blue_Red_Mean          C_Blue_Red_Compactness 
#>                    0.000000e+00                    0.000000e+00 
#>       C_Blue_Red_GradientRatios             C_Green_Compactness 
#>                    0.000000e+00                    2.864375e-14 
#>                    C_Green_Mean                C_Red_Green_Mean 
#>                    9.166001e-14                    1.145750e-13 
#>             C_Blue_Red_Skewness  C_Blue_Red_Fractal_Homogeneity 
#>                    2.243215e-11                    4.889171e-11 
#>                L_Green_Energy_2                  SHomogeneity_8 
#>                    4.889171e-11                    1.341647e-10 
#>             C_Blue_Red_Gradient                       SEnergy_4 
#>                    1.341647e-10                    2.103335e-10 
#>          S_CFractal_Correlation C_Red_Green_Fractal_Homogeneity 
#>                    3.182850e-10                    3.440306e-10 
#>             SStandard_Deviation                    L_Green_Mean 
#>                    3.440306e-10                    3.771648e-10 
#>                   L_Green_90COV             L_Blue_Red_Gradient 
#>                    3.961532e-10                    4.024909e-10 
#>                     C_Green_COV                           SMean 
#>                    1.079453e-09                    1.746786e-09

par(op)

Learning Melanoma with KNN

cvKNN <- randomCV(MelanomaSeborrheic,"Class",
               KNN_method,
               trainFraction = 0.90,
               repetitions = 100,
               classSamplingType = "Pro",
               featureSelectionFunction = univariate_KS,
               featureSelection.control = list(pvalue=0.05,limit= -1),
               kn=5
               )
#> ..........10  Tested: 342 Avg. Selected: 158.8 Min Tests: 1 Max Tests: 4 Mean Tests: 1.549708 . MAD: 0.3074618 
#> ..........20  Tested: 459 Avg. Selected: 157.1 Min Tests: 1 Max Tests: 6 Mean Tests: 2.309368 . MAD: 0.3129108 
#> ..........30  Tested: 504 Avg. Selected: 157.2667 Min Tests: 1 Max Tests: 9 Mean Tests: 3.154762 . MAD: 0.3126754 
#> ..........40  Tested: 515 Avg. Selected: 157.5 Min Tests: 1 Max Tests: 10 Mean Tests: 4.116505 . MAD: 0.3120033 
#> ..........50  Tested: 520 Avg. Selected: 157.28 Min Tests: 1 Max Tests: 12 Mean Tests: 5.096154 . MAD: 0.3122281 
#> ..........60  Tested: 523 Avg. Selected: 157.15 Min Tests: 1 Max Tests: 14 Mean Tests: 6.080306 . MAD: 0.3149674 
#> ..........70  Tested: 523 Avg. Selected: 157.2 Min Tests: 1 Max Tests: 16 Mean Tests: 7.09369 . MAD: 0.3155163 
#> ..........80  Tested: 523 Avg. Selected: 157.2625 Min Tests: 2 Max Tests: 19 Mean Tests: 8.107075 . MAD: 0.3155763 
#> ..........90  Tested: 523 Avg. Selected: 157.0556 Min Tests: 2 Max Tests: 19 Mean Tests: 9.120459 . MAD: 0.3156714 
#> ..........100  Tested: 523 Avg. Selected: 157.23 Min Tests: 2 Max Tests: 20 Mean Tests: 10.13384 . MAD: 0.3157428

Plot performance

performace <- predictionStats_binary(cvKNN$medianTest,"KNN")
#> KNN

par(op)

cvSVM <- randomCV(MelanomaSeborrheic,"Class",
               e1071::svm,
               asFactor = TRUE,
               trainSampleSets=cvKNN$trainSamplesSets,
               featureSelectionFunction = cvKNN$selectedFeaturesSet,
               probability=TRUE
               )
#> ..........10  Tested: 342 Avg. Selected: 158.8 Min Tests: 1 Max Tests: 4 Mean Tests: 1.549708 . MAD: 0.2848296 
#> ..........20  Tested: 459 Avg. Selected: 157.1 Min Tests: 1 Max Tests: 6 Mean Tests: 2.309368 . MAD: 0.2915987 
#> ..........30  Tested: 504 Avg. Selected: 157.2667 Min Tests: 1 Max Tests: 9 Mean Tests: 3.154762 . MAD: 0.2885078 
#> ..........40  Tested: 515 Avg. Selected: 157.5 Min Tests: 1 Max Tests: 10 Mean Tests: 4.116505 . MAD: 0.2897823 
#> ..........50  Tested: 520 Avg. Selected: 157.28 Min Tests: 1 Max Tests: 12 Mean Tests: 5.096154 . MAD: 0.289232 
#> ..........60  Tested: 523 Avg. Selected: 157.15 Min Tests: 1 Max Tests: 14 Mean Tests: 6.080306 . MAD: 0.2914439 
#> ..........70  Tested: 523 Avg. Selected: 157.2 Min Tests: 1 Max Tests: 16 Mean Tests: 7.09369 . MAD: 0.2912685 
#> ..........80  Tested: 523 Avg. Selected: 157.2625 Min Tests: 2 Max Tests: 19 Mean Tests: 8.107075 . MAD: 0.2913548 
#> ..........90  Tested: 523 Avg. Selected: 157.0556 Min Tests: 2 Max Tests: 19 Mean Tests: 9.120459 . MAD: 0.291551 
#> ..........100  Tested: 523 Avg. Selected: 157.23 Min Tests: 2 Max Tests: 20 Mean Tests: 10.13384 . MAD: 0.2910425

SVM performance

performace <- predictionStats_binary(cvSVM$medianTest,"SVM")
#> SVM

par(op)

LASSO

cvLASSO <- randomCV(MelanomaSeborrheic,"Class",
               LASSO_MIN,
               trainSampleSets=cvKNN$trainSamplesSets,
               featureSelectionFunction = cvKNN$selectedFeaturesSet,
               )
#> ..........10  Tested: 342 Avg. Selected: 42.5 Min Tests: 1 Max Tests: 4 Mean Tests: 1.549708 . MAD: 0.4261405 
#> ..........20  Tested: 459 Avg. Selected: 38.35 Min Tests: 1 Max Tests: 6 Mean Tests: 2.309368 . MAD: 0.428814 
#> ..........30  Tested: 504 Avg. Selected: 37.56667 Min Tests: 1 Max Tests: 9 Mean Tests: 3.154762 . MAD: 0.4280326 
#> ..........40  Tested: 515 Avg. Selected: 38.6 Min Tests: 1 Max Tests: 10 Mean Tests: 4.116505 . MAD: 0.4298079 
#> ..........50  Tested: 520 Avg. Selected: 38.62 Min Tests: 1 Max Tests: 12 Mean Tests: 5.096154 . MAD: 0.4294858 
#> ..........60  Tested: 523 Avg. Selected: 38.71667 Min Tests: 1 Max Tests: 14 Mean Tests: 6.080306 . MAD: 0.4307832 
#> ..........70  Tested: 523 Avg. Selected: 38.44286 Min Tests: 1 Max Tests: 16 Mean Tests: 7.09369 . MAD: 0.4309233 
#> ..........80  Tested: 523 Avg. Selected: 37.2 Min Tests: 2 Max Tests: 19 Mean Tests: 8.107075 . MAD: 0.4309021 
#> ..........90  Tested: 523 Avg. Selected: 37.54444 Min Tests: 2 Max Tests: 19 Mean Tests: 9.120459 . MAD: 0.4311408 
#> ..........100  Tested: 523 Avg. Selected: 38.1 Min Tests: 2 Max Tests: 20 Mean Tests: 10.13384 . MAD: 0.4312076

LASSO performance

performace <- predictionStats_binary(cvLASSO$medianTest,"LASSO")
#> LASSO

par(op)

cvBSWiMS <- randomCV(MelanomaSeborrheic,"Class",
               BSWiMS.model,
               trainSampleSets=cvKNN$trainSamplesSets,
               featureSelectionFunction = cvKNN$selectedFeaturesSet,
               NumberofRepeats=1
               )
#> .[+++++++-].[++++++++++++--]..[+++++++++-].[++++++++--].[++++++-].[++++++++++-]..[++++-].[+++++-+++-].[+++++++-].[++++++++-]10  Tested: 342 Avg. Selected: 35.8 Min Tests: 1 Max Tests: 4 Mean Tests: 1.549708 . MAD: 0.3164306 
#> .[+++++++-].[++++++-+-].[+++++++++-].[+++++++++-].[+++++++-].[++++++++-].[++++++++-].[+++++++++++-]..[++++++++-].[++++++++--]20  Tested: 459 Avg. Selected: 37.65 Min Tests: 1 Max Tests: 6 Mean Tests: 2.309368 . MAD: 0.3226409 
#> .[++++++-].[++++++--].[+++++++---].[++++++-].[+++++++-].[++++++++-].[++++++-].[++++++++-].[++++++-].[++++++-+-]30  Tested: 504 Avg. Selected: 35.26667 Min Tests: 1 Max Tests: 9 Mean Tests: 3.154762 . MAD: 0.3217438 
#> .[+++++++++-].[+++++++-].[+++++---+--].[+++++++++-].[++++++++++-]..[+++++-++-].[++++++++--+-].[++++++++++-]..[+++++-+-+-].[++++++-]40  Tested: 515 Avg. Selected: 35.575 Min Tests: 1 Max Tests: 10 Mean Tests: 4.116505 . MAD: 0.3256902 
#> .[++++++++---].[+++++-].[++++++++-].[++++++-].[+++++++++++---]..[++++++++-].[+++++++++--].[+++++++++-].[++++++---].[+++++++-]50  Tested: 520 Avg. Selected: 35.6 Min Tests: 1 Max Tests: 12 Mean Tests: 5.096154 . MAD: 0.3248811 
#> .[+++++-+-].[++++++-].[+++++++-].[++++++++-].[++++++++--].[+++++++-].[+++++-].[+++++-].[+++++++++-].[+++++++-]60  Tested: 523 Avg. Selected: 34.98333 Min Tests: 1 Max Tests: 14 Mean Tests: 6.080306 . MAD: 0.3233287 
#> .[++++++++++-]..[++++++-].[+++++-].[+++++++--].[++++-+++-].[++-].[+++++++++--].[++++++-++-].[++++++-].[+++++++-]70  Tested: 523 Avg. Selected: 34.34286 Min Tests: 1 Max Tests: 16 Mean Tests: 7.09369 . MAD: 0.3227755 
#> .[+++++++-+-+-].[+++++++-].[+++++++--].[++++++-].[++++++-].[+++++++++++-]..[++++++++++-]..[+++++++++--].[+++++++++--].[+++++++-]80  Tested: 523 Avg. Selected: 34.975 Min Tests: 2 Max Tests: 19 Mean Tests: 8.107075 . MAD: 0.3222344 
#> .[+++++++++-+-]..[+++++++++-].[+++++++-+-].[+++++++-+---].[++-].[+++++++++-].[+++++++++---].[+++++-+++---].[+++++--++--].[++++++++-]90  Tested: 523 Avg. Selected: 35.11111 Min Tests: 2 Max Tests: 19 Mean Tests: 9.120459 . MAD: 0.3223666 
#> .[++++++-].[++++++-++-].[++++++-++-].[+++----].[++++++++----].[++++++++-++-]..[+++++++-].[+++++++-+--].[++++++++-].[+++++--]100  Tested: 523 Avg. Selected: 35.04 Min Tests: 2 Max Tests: 20 Mean Tests: 10.13384 . MAD: 0.3231466

BSWiMS performance

performace <- predictionStats_binary(cvBSWiMS$medianTest,"BSWiMS")
#> BSWiMS

par(op)

MelanomavsSeborreic

Jose Tamez

4/9/2021

Melanoma vs Seborreic_Keratosis

Loading data sets

The Heatmap

Learning Melanoma with KNN

Plot performance

SVM performance

LASSO

LASSO performance

BSWiMS performance