Use this tag to ask question about processing/converting/creating/analyzing image instance in-memory/persistence-storage related to medical domain. This include DICOM images/pixel-data as well. Additional tag [tag:dicom] is only needed if question relates to DICOM Specifications. If question can stand without it, avoid using [tag:dicom] tag. This tag is agnostic to programming language or toolkit.
Questions tagged [medical-imaging]
250 questions
0
votes
2 answers
CornerstoneJS select segmentation by mouse and change the color
Im using cornerstoneTools with cornerstoneJS dicom view, I draw multiple segments by cornerstone segment tool and load the segments from RLE, I need to select existing segment by click it by mouse on the dicom viewer
Wimal Weerawansa
- 309
- 2
- 15
- 33
0
votes
0 answers
Draw lines from junction point to endpoints in skeleton image
I'm working on a computer vision project and I want to draw lines from the junction point to endpoints of the skeleton image. In my code I get the endpoints using Harris corner detector. I have attached two images as well.
The above image shows the…
user2381342
- 35
- 7
0
votes
0 answers
Are there any API's or SDK's available to access data from CS 3D Imaging Software
When provided with a CBCT scan, the Carestream 3D Imaging software produces cross-sectional views. I want to access these views directly in Python. Thus, I wanted to know if there are any SDK or APIs available for this exporting of data.
I tried…
Shashank B
- 1
- 1
0
votes
0 answers
why my output of train loader differ from my input? #380
I am feeding my train loader with images(.nii.gz) with slice (240, 240) dim and expected torch.size(1(#batch_size), 3(#RGB) ,256,256) but the output is torch.size((1,240,256,256). where is the problem?
my code is:
import…
0
votes
0 answers
Sizes of tensors must match except in dimension 1. Expected size 16 but got size 32 for tensor number 1 in the list
I have 6464 orginal image dataset and 3232 low_resoluation image that I want to use for high resoluation model with monai package. My problem is that when I run diffusion model for training I got this error:
"Sizes of tensors must match except in…
0
votes
1 answer
AttributeError: module 'numpy' has no attribute 'float' while importing nibabel
When i try to install nibabel lirary i get an error like this. Tried different version of numpy and didn't work out. Any idea how to solve this?
---------------------------------------------------------------------------
AttributeError …
0
votes
0 answers
how to select the transversal plane images from ProstateX dataset
Whenever we use the series description and image orientation patient tag both time it gives different pics list?
import pydicom
import os
def select_transverse_images(root_dir):
transverse_images = []
root_dir = 'D:\\prostate…
Anki
- 1
0
votes
1 answer
In image processing What is Hausdorff’s distance's unit if we don't know the scale?
I have medical images that I resized to fit into my CNN for semantic segmentation, now to evaluate I calculated the DICE coeffitients, and the Hausdorff’s distance, now comparing to the litretures all papers reported their results in length unit…
Jafar M
- 3
- 2
0
votes
1 answer
tensorflow IO dicom reader division by 2 issue?
i also encountered a strange division by 2 problem with my dicom files (I got them from https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=52758026). I am not sure how to upload files, but the following is how I read
image_bytes =…
balcony
- 13
- 3
0
votes
0 answers
Validation metrics for non background classes fluctating epoch to epoch
We are working on semantic segmenation for our thesis, aiming the goal to stratify lesions in T2W 2d-images of the prostate. What we're dealing with is a 3 class problem, having following labels:
0 = background, 1 = insignificant tumor, 2 =…
Philip Thangngat
- 1
- 1
0
votes
0 answers
How to convert the annotation label?
I have a question about the conversion of images.
In segmentation tasks of medical images, if DICOM files are converted to NifTI files with dicom2nifti, discrepancies could occur between original images and annotation labels.
How to correct these…
kodhoi
- 23
- 5
0
votes
0 answers
ValueError(f"x and y must have same first dimension, but " ValueError: x and y must have same first dimension, but have shapes (6,) and (1)
I'm detecting contours in a video and calculating each angular displacement. Now I want to plot the angular velocities over time but I keep getting this error ValueError(f"x and y must have same first dimension, but " ValueError: x and y must have…
user2381342
- 35
- 7
0
votes
0 answers
How to display a 3D numpy array (angiography - dicom file) frame by frame with PyQt?
I am currently started to use PyQt as a GUI. I would like to create a mini application, which can display a 3D numpy array frame by frame, which is actually an angiography Dicom file, it is a time series image sequence.
I searched the internet I…
0
votes
1 answer
I have nii.gz volume and I need to display it as one image
I have nii.gz volume and I need to display it as one image. I could display one slice as shown below.
mri_file = '/tmp/out_img/case0001_gt.nii.gz'
img = nib.load(mri_file)
mg_data = img.get_fdata()
mid_slice_x = img_data[ :,…
user836026
- 10,608
- 15
- 73
- 129
0
votes
1 answer
Image segmentation with UNet is mainly white
I'm working with MONAI library in order to segment brain tumor in MRI images. My dataset is composed of 500 patients and for each patient there're three types of images and the segmentation mask.
I've trained my network (UNet architecture) but I've…
