Combining State-of-the-Art Pre-Trained Deep Learning Models: A Noble Approach for Skin Cancer Detection Using Max Voting Ensemble

. 2023 Dec 30;14(1):89. doi: 10.3390/diagnostics14010089

Algorithm 1 Max Voting Ensemble Technique for Skin Cancer Classification

Input:- List of pre-trained deep learning models (SelectedModels)

List of skin lesion images (InputImages)

Corresponding ground truth labels (groundTruthLabels)

Output: Ensemble predictions for each input image (ensemble predictions)

Step 1: Model Selection

$SelectedModels \leftarrow [M o b i l e N e t V 2, A l e x N e t, V G G 16, R e s N e t 50, D e n s e N e t 201,$

$D e n s e N e t 121, I n c e p t i o n V 3, R e s N e t 50 V 2, I n c e p t i o n R e s N e t V 2, X c e p t i o n]$

Step 2: Preprocessing

while $I n p u t I m a g e s \neq e a c h I m a g e$ do

$P r e p r o c e s s e d I m a g e \leftarrow p r e p r o c e s s I m a g e (i m a g e)$

$P r e p r o c e s s e d I m a g e s . a p p e n d (P r e p r o c e s s e d I m a g e)$

Step 3: Load Pre-trained Models

$L o a d e d M o d e l s \leftarrow l o a d M o d e l s (S e l e c t e d M o d e l s)$

Step 4: Generate Predictions

while $e a c h p r e p r o c e s s e d \neq P r e p r o c e s s e d I m a g e s$ do

$p r e d i c t i o n s \leftarrow []$

while $e a c h l o a d e d m o d e l \neq L o a d e d M o d e l s$ do

$M o d e l P r e d i c t i o n \leftarrow P r e d i c t I m a g e (L o a d e d M o d e l, P r e p r o c e s s e d I m a g e)$

$p r e d i c t i o n s . a p p e n d (M o d e l P r e d i c t i o n)$

$i n d i v i d u a l P r e d i c t i o n s . a p p e n d (p r e d i c t i o n s)$

Step 5: Max Voting Ensemble Technique

while $e a c h I n d i v i d u a l P r e d i c t i o n s \neq i n d i v i d u a l P r e d i c t i o n s$ do

$a g g r e g a t e d P r e d i c t i o n s \leftarrow []$

while $e a c h I m a g e P r e d i c t i o n \neq s e t o f p r e d i c t i o n s$ do

$m a j o r i t y V o t e \leftarrow c a l c u l a t e M a j o r i t y V o t e (i m a g e P r e d i c t i o n)$

$a g g r e g a t e d P r e d i c t i o n s . a p p e n d (m a j o r i t y V o t e)$

$e n s e m b l e P r e d i c t i o n s . a p p e n d (a g g r e g a t e d P r e d i c t i o n s)$

Step 6: Evaluate Ensemble Performance

$a c c u r a c y \leftarrow e v a l u a t e A c c u r a c y (e n s e m b l e P r e d i c t i o n s, g r o u n d T r u t h L a b e l s)$

Step 7: Display Results

$p r i n t (“ E n s e m b l e A c c u r a c y : ”, a c c u r a c y)$