Algorithm 1: The proposed fine-tuned DL model
1	Input $\to$ LC25000 dataset $DL$
2	Output $\leftarrow$ Fine-tuned DL model for lung and colon prediction
3	BEGIN
4	STEP 1: Pre-Processing of HIs
5	FOR EACH image IN the $DL$ DO
6	Resize HI to 224 × 224
7	Normalize HI pixel values from [0, 255] to [0, 1]
8	END FOR
9	STEP 2: DL Splitting
10	SPLIT $DL$ INTO
11	Training se$t\to$ 9$0\%$
12	Testing set $\to$ $5\%$
13	Validation set $\to$ $5\%$
14	STEP 3: Model Pre-Training
15	FOR EACH ML IN [ResNet-101V2, NASNetMobile, EfficientNet-B0] DO
16	Load and pre-train ML on the ImageNet dataset
17	Remove the layer of classification from ML for feature extraction
18	END FOR
19	FOR EACH pre-trained ML DO
20	Feed ML with 224 × 224 × 3 HIs
21	Feed GlobalAveragePooling2D with the features of ML to smooth them into vectors
22	END FOR
23	Connect the smoothed feature vectors from the three models into one vector
24	Add a SoftMax layer for classification to the connected vector
25	STEP 4: Proposed Model Training and Validating
26	FOR I = 1 to $\mathbf{N}$ where $\mathbf{N}=5$
27	FOR EACH I DO
28	Fine-tune the connected feature vector on the training set
29	Use a validation set for early halting, according to the best model performance
30	Assess the performance on the test set
31	Record the test accuracies
32	END FOR
33	Get the average of the recorded test accuracies
34	END FOR
35	STEP 5: Proposed Model Evaluation
36	Evaluate the accuracy of the proposed DL model using the average test accuracies
37	END