search

AIRMEC / im4MEC

Code for the im4MEC model described in the paper 'Interpretable deep learning model to predict the molecular classification of endometrial cancer from haematoxylin and eosin-stained whole-slide images: a combined analysis of the PORTEC randomised trials and clinical cohorts'.
https://doi.org/10.1016/S2589-7500(22)00210-2
GNU General Public License v3.0
32 stars 13 forks source link

MOCO v2 #3

Closed Rainydu184 closed 1 year ago

Rainydu184 commented 1 year ago

Hi, you really did a good job. Would you please share the MOCO pth file ？

jjhbw commented 1 year ago

Hi @Rainydu184 , thanks for you kind words. I'm afraid we're not planning to publish the trained model weights for the foreseeable future.

Rainydu184 commented 1 year ago

Hi, @jjhbw . I am downloading the TCGA_UCEC datasets, but the label perplex me. I find the label _UCEC_CN_HIGH UCEC_CN_LOW UCEC_POLE UCEC_MSI UCECPOLE ， how do the lable transfer to POLE, p53, MMRd, NSMP。 Is it just a different name for the same thing?

Rainydu184 commented 1 year ago

I found the words in the paper: POLE mutational status is assessed by use of targeted DNA sequencing of exons 9–14 (POLEmut ). Loss of expression of mismatch repair proteins (MMR deficient [MMRd]) by immunohistochemistry is an excellent surrogate for microsatellite instability. Tumours with a high copy number are characterised by TP53 mutations and can be identified by abnormal, mutant-like cellular tumour antigen p53 expression (p53abn). Tumours with a low copy number are referred to as having no specific molecular profile (NSMP).