How to use dicom images for training?

[ghost]

How to use dicom images for training?❔

I'm using lung cancer images which is of the format of .dcm not .png or any other image format.
Is there any way to use .dcm images?

[github-actions]

Hello @asim266, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.

If this is a bug report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom model or data training question, please note Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

@asim266 I'm not familiar with that format, but if cv2 can read it you can add it to the dataloader acceptable formats list here:

yolov5/utils/datasets.py

Lines 24 to 28 in df0e408

	# Parameters
	help_url = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
	img_formats = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng'] # acceptable image suffixes
	vid_formats = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv'] # acceptable video suffixes

[ghost]

@glenn-jocher .dcm is not supported by cv2 we need to convert the image from .dcm to cv2 supported format please check the link.
https://stackoverflow.com/questions/53707851/using-dicom-images-with-opencv-in-python
or by adding the following code in the dataset.py I guess.

import cv2 import pydicom as dicom ds = dicom.dcmread('sample.dcm') dcm_sample = ds.pixel_array * 128 cv2.imshow('sample image dicom', dcm_sample) cv2.waitKey()

[glenn-jocher]

@asim266 since it's not supported your best best is to simply export all your images to jpg offline, and then present the jpg dataset for training.