I need to segment my input image using unet segmentation

where inp is my input image

inp=b
DatasetPath=fullfile('C:\Users\Desktop\to');
imds=imageDatastore(DatasetPath, 'IncludeSubfolders', true,...
    'LabelSource','foldernames','fileextension',{'.dcm'});

labelDir = fullfile(DatasetPath,'testImages');

I = readimage(imds,1);
I = histeq(I);
imshow(I)

classes = [
    "MALIGNANT","BENIGN"
    ];

labelIDs=[255 0]

inputlayer = imageInputLayer([512 512 1],'Name','inp')
numFilters = 64;
numLayers = 16;
layers = [ ...
    imageInputLayer([512 512 1])
    convolution2dLayer(5,20)
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(5,20)
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    transposedConv2dLayer(4,numFilters,'Stride',2,'Cropping',1);
     convolution2dLayer(5,20)
    batchNormalizationLayer
    reluLayer
    transposedConv2dLayer(4,numFilters,'Stride',2,'Cropping',1);
    convolution2dLayer(5,20)
    batchNormalizationLayer
    reluLayer
    convolution2dLayer(5,20) 
    fullyConnectedLayer(4)
    softmaxLayer
    pixelClassificationLayer
    ]

% pxds = pixelLabelDatastore(labelDir,classes,labelIDs);

options = trainingOptions('sgdm', ...
    'InitialLearnRate',0.01, ...
    'MaxEpochs',1, ...
    'Shuffle','every-epoch', ...
    'ValidationFrequency',30, ...
    'Verbose',false);
 

net=trainNetwork(imds,layers,options);

res = activations(net,inp,net.Layers(numLayers-1).Name,'OutputAs','channels');
  I = read(imds);
%   C = read(pxds)
  C = semanticseg(I, net);
  
  % Overlay pixel label data on the image and display.
  B = labeloverlay(I, C);
  figure(12)
  imshow(B)

I got error @

Error using trainNetwork

Not enough input arguments.

Error in

net=trainNetwork(imds,layers,options);I

[SARAH LONER]

my input image was dicom image.

when i remove comment at pixelLabelDatastore it shows an eror that my

Input folders or files do not contain specified file extensions:

.bmp,.cur,.fts,.fits,.gif,.hdf,.ico,.j2c,.j2k,.jp2,.jpf,.jpx,.jpg,.jpeg,.pbm,.pcx,.pgm,.png,.pnm,.ppm,.ras,.tif,.tiff,.xwd

can any1 suggest me a solution for this?

[Manjunath R V]

have u got solution for the above query sarah if so please share it

Answer 1

[Image Analyst]

In the imageDatastore() function there is an option to specify the reader. For example, try something like:

imds = imageDatastore('*.dcm','ReadFcn',@dicomread);

[SARAH LONER]

it showing error

[Image Analyst]

You're right. I guess that since it's not in the list given by imformats, it doesn't list them.

Try fileDatastore() instead:

imds = fileDatastore('*.dcm', 'ReadFcn', @dicomread)
fileNames = imds.Files

I tried it and that does retrieve the file names.

[SARAH LONER]

HAI SIR CAN U GUIDE ME ONCE AGAIN ON ANOTHER ERROR I CANT ABLE TO TRAIN IMAGE

i cant able to read image at pxds in above code and once i cleared that i cant able to train network at

net=trainNetwork(pxds,layers,options);

kindly guide me to solve this error

[Image Analyst]

Sorry, I can't do that. If you need help, the Mathworks can help you. Contact them here: Mathworks Consulting