3
$\begingroup$

I am working on a project which involves writing computer software to analyse histological images. A typical image looks like this:

enter image description here

It is a Hematoxylin and Eosin stained biopsy of breast cancer tissue. Being a programmer without biology background, I would like to get insight into how a pathologist analyses such images.

More specifically:

  • Which cells are cancer cells and which are regular cells?
  • Can an invasive margin (a curve marking the boundary of cancer invasion into the tissue) be seen in this image?
  • Can a pathologist provide a TNM classification looking at the image? If yes, what would be the T, N, M, G values for this image?
Improve this question
$\endgroup$
5
  • $\begingroup$ A single image is not enough for a TNM classification. This system requires knowing the size of a tumor (T), the degree of spread to new-by lymph nodes (N), as well as information about metastasis to other organs and tissues besides the lymph nodes (M), none of which are apparent from a single H & E stain image. Also, histological scoring often requires the user to scan around a slide and review many different fields of view. You'll probably want to collaborate closely with a skilled clinical pathologist for the project you've described. $\endgroup$
    – MikeyC
    Commented Apr 21, 2020 at 15:44
  • $\begingroup$ @MikeyC what can be inferred from such image? $\endgroup$
    – mercury0114
    Commented Apr 21, 2020 at 16:27
  • $\begingroup$ @MikeyC i.e. if a single image is not enough for classification, why is it taken? $\endgroup$
    – mercury0114
    Commented Apr 21, 2020 at 18:19
  • $\begingroup$ My histology experience was looking at inflammation and necrosis in animal tissues, which is why I kept my reply to the commets section. I really only know enough about this to know that I would seek expert collaborators if I was doing what you're try to do. Histology often needs to be evaluated in context. A single image might be enough to identify cancerous or pre-cancerous cells, but you'd also need something like X-ray images to determine a T score along with additional biopsies or lab tests to determine N and M scores. $\endgroup$
    – MikeyC
    Commented Apr 22, 2020 at 20:21
  • 1
    $\begingroup$ Here are some reviews I came across that might help give you a sense of similar applications being explored. ncbi.nlm.nih.gov/pmc/articles/PMC2910932 ncbi.nlm.nih.gov/pmc/articles/PMC5556681 $\endgroup$
    – MikeyC
    Commented Apr 22, 2020 at 20:25

0

Reset to default

You must log in to answer this question.

Browse other questions tagged .