search

nyukat / breast_cancer_classifier

Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
https://ieeexplore.ieee.org/document/8861376
GNU Affero General Public License v3.0
840 stars 269 forks source link

Working with my own images #20

Closed jeromejarre closed 5 years ago

jeromejarre commented 5 years ago

Hi, I am trying to produce a result from your single image model. However, when I try to use my own DICOM images, my images are failed when it comes to use your cropping script. The cropped output is the same as the 16 bit png input. And also, when I tried to load it into the model to make an inference, I just saw almost fully black image when I wanted to try visualizing the tensor batch. Long story short, I cannot obtain a consistent raw image, cropped image and a tensor batch trio. I am working with uint16 image data. What can be the reason for this? Many thanks. Kindest regards.

jeromejarre commented 5 years ago

Interestingly, I can make an inference using uint8 images.

kjgeras commented 5 years ago

Hi,

My guess is that your images have some artifact (e.g. a one-pixel thin white frame around the image) that is preventing the cropping algorithm from working. You should investigate this kind of things by checking carefully what our cropping code is executing step by step. You should also read this report https://cs.nyu.edu/~kgeras/reports/datav1.0.pdf for details on what data we rejected and our cropping algorithm won't work with.

It doesn't sound like anything related to the model itself.

jeromejarre commented 5 years ago

Big thanks, Professor Geras. Admired your and your team's work. Inspirational.