U-net Segmentation Contains Image Noise (Medical)

The task is to segment vertebrae, the spinal canal, and disks from spine MRI scans. The dataset poses two main challenges: it is relatively small, and it has been collected from different hospitals, resulting in varying sizes, aspect ratios, and resolutions. To address these issues, I used adaptive max pooling to standardize the image sizes. Normalization was applied only to the images. The masks consisted of three channels, each having a value of 1 where segmentation is needed and 0 otherwise.

I implemented a simple U-Net model capable of segmenting the three channels as expected. The model’s input and output shapes were ([4, 1, 16, 256, 256]) and ([4, 3, 16, 256, 256]), respectively. The loss function used was CrossEntropyLoss(). During training, the loss was decreasing, indicating that everything was all right. However, during testing, I observed that all images contained noise, as shown in the attached picture. I am not sure what the exact problem is or why the mask is not binary like the ground truth.

Any help would be greatly appreciated.

Thanks in advance.

Hi @MariemAbdou

Can you provide link to your notebook.


can I know what are you trying to achieve with these images? any classification? any abnormality?

using only crossentropyloss() didn’t understandable though. So require more understanding of your data.

Having smaller data and data from different hospital can be addressed, but what is your aim is not clear.