Bro, I am starting my master degree in AI, in Mexico, I am very interested in the Image Processing application using Python. Is there any course that you sell, to learn more about this topic?

Gracias! Nice explanation!

Perez Jose Garcia Mary White Laura

Hello, at first thank you for this course. I couldn't find slice.dcm file in this video. Can we access the dataset in this course?

Thank you for this course, it will help me a lot !

Great work bro!! Do you know the easiest way to convert from .nii.gz to .nii for image processing? Anothers question is if you have any full course about this?

thanks!

Do you know how to read the measurements taken by Doctor which is shown on the Dicom image? These values seems to be part of the image and not stored in any of the Attrib values in the Dicom file(unlike values like patient name etc).

your video and code are mostly the same as kzbin.info/www/bejne/g2S9iJmXoryleK8

I used this process for brain tumor .I used the exact same process and got in_channels=4..i have train volume dimensions=(1,4,128,128,155) Test volume dimensions=(1,4,128,128,155) train label dimensions=(1,1,128,128,155) Test label dimensions=(1,1,128,128,155) I got error:error using forward pass.size of tensor must be match except in dimension 1.expected size 39 but got size 40 for tensor number 1 in the list

Very good explanation.

*****Guys this is thecode to convert niftt to dicoms in a single run instead of using 3dslicer every single time**** import nibabel as nib import pydicom import os from glob import glob import numpy as np def nifti_to_dicom(nifti_path, output_path): """Converts a NIfTI file to a series of DICOM files in a separate folder. Args: nifti_path (str): Path to the NIfTI file. output_path (str): Output directory for DICOM files. """ # Extract patient ID from nifti file name patient_id = os.path.basename(nifti_path).split('.')[0] patient_output_path = os.path.join(output_path, patient_id) # Create patient output directory os.makedirs(patient_output_path, exist_ok=True) # Load NIfTI data img = nib.load(nifti_path) data = img.get_fdata() # Basic DICOM metadata (replace with actual values) ds = pydicom.Dataset() ds.PatientID = patient_id ds.StudyInstanceUID = pydicom.uid.generate_uid() ds.SeriesInstanceUID = pydicom.uid.generate_uid() ds.Modality = 'MR' # Replace with appropriate modality ds.PixelSpacing = [0.5, 0.5] # Replace with actual pixel spacing ds.SliceThickness = 3.0 # Replace with actual slice thickness # Set is_little_endian and is_implicit_VR ds.is_little_endian = True # Assuming little-endian byte order (adjust if needed) ds.is_implicit_VR = False # Assuming explicit VR (adjust if needed) # Iterate over slices for i in range(data.shape[2]): slice_data = data[:, :, i] # Create DICOM dataset for the slice ds.ImageInstanceUID = pydicom.uid.generate_uid() ds.InstanceNumber = i + 1 ds.SliceLocation = -(i * ds.SliceThickness) # Adjust based on slice orientation # Convert image data to appropriate format (e.g., int16) slice_data = slice_data.astype(np.int16) # Set pixel data ds.PixelData = slice_data.tobytes() ds.BitsAllocated = 16 ds.SamplesPerPixel = 1 ds.HighBit = 15 ds.PixelRepresentation = 0 # Write DICOM file output_file = os.path.join(patient_output_path, f'image_{i+1}.dcm') pydicom.filewriter.dcmwrite(output_file, ds) # Example usage nifti_folder = 'D:/New folder (5)/Task01_BrainTumour/imagesTr' output_folder = 'D:/New folder (5)/Task01_BrainTumour/Images' # Iterate over NIfTI files for nifti_file in glob(os.path.join(nifti_folder, '*.nii.gz')): nifti_to_dicom(nifti_file, output_folder)

Hey, great tool! Does it work effectively also in MRI images?

It was really helpful, thank you very much.

Thank you for sharing video. How can I get dataset100 file. I tried but I have fault.

Hi dear Mohamed, please I have a question: I paid 1500 dollars to pass the OpenCV certification because I considere it is important to get this certification and that it can help me with my LinkedIn profil. Do you think it is a good choice ? Thank you and great day !

Is it possible to import multiple STL files with this implementation?

hey man, i was using your medical conversion tool on github. I converted my nifti files to dicom using your converter, but now when im trying to convert them back to nifti using the converter its giving me this error: TypeError: '<' not supported between instances of 'NoneType' and 'NoneType' Edit: I found out that this is happening because the InstanceNumber tag is being erased and set to None. I tested this by first converting a dicome (instanceNumber was 183) , I converted it to NIFTI, and the reconverted to Dicom , and I found that the InstanceNumber was set to None. All of this was done by using the "Medical Conversion" application on your github. This is causing the error while converting the DICOM series to NIFTI format. @Pycad please look into this since the conversion of dicom data is messing up the MetaData

mes respects

can you explain.what labels exactly are

Hello, I got a question. I will need to visualize 3D on tkinter frame. Is that possible? I tried to embedding VTK render window in Tkinter frame using vtkTkRenderWindowInteractor but I got this error 'libvtkRenderingTk-9.3.dylib' (no such file), '/usr/lib/libvtkRenderingTk-9.3.dylib' (no such file, not in dyld cache)

Is it possible to install the required packages in normal command prompt rather than a anaconda prompt ?

the waitlist is still there, when are you accepting applications for the course?

Amazing!

Thank you💞👍👏👏

Merci bcp pour vos vidéos.

“Do you encounter errors when installing dependencies on Windows?”

Thanks for sharing!

I recently found your channel. Thank you for the videos they are really helpful 🙏

Hi, thankyou so much for making the video. To visualize the dicom pixel array why we make the negative number to 0? Will it remove the half the picture data from the image? Is it better to shift all the value up until the minimum value is 0 or there is another reason?

Wonderful. Thanks for your sharing.

Thanks a lot for this course!

very good

👍👍👏👏💕

Thank you very much for your help !

🎉🎉🎉🎉

Will we loose information while conversation.how can we over come it

Hi, Thanks for your video. Could you please explain more about four folders of Trainimages, Trainlables, Valimages and Vallables? I followed all the videos regarding the liver segmentation, but when got here I completely lost. you were talking about creating nifti files folder and suddenly jumped into four folders. what are difference between them? Is training folder the same files of niftifolder? what about validation data? where do they come from?

Thank you for your efforts ❤️... Is it possible to create a video demonstrating how to generate a 3D visualization of a NIfTI file or DICOM series using VTK?

Can you talk in detail about the 4 files TrainData, TrainLabels, ValData, ValLabels? For example how different it is

Thank you sir. That "<B1-Motion>" part hinted me of solution to my problem and I fixed it.

Thank you sir for the course. This was really helpful. One suggestion is to please create timestamped index of the video so that it gets easy to check out what all sections are taught in the video.

سلمت اياديك استاذنا

🎉🎉🎉🎉

Suggest the AI tool for annotations

how can i anonymize study instance and series uid .. is changing the value really the proper way for it?

What software is used to create the schematic diagrams at the beginning of the video?

I have paid project bro I need your help Pls share your mail id or telegram

but why your Udemy course does not accept enrolments anymore ;___;