Downloads · 30 days
26
39% of all-time downloads
IshaChhikara/cx-uni-abmil-21cohort
cx-uni-abmil-21cohort is a machine learning model from IshaChhikara. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
--- license: mit libraryname: pytorch tags: - medical-imaging - histopathology - whole-slide-image - chromosomal-instability - copy-number-signatures - attention-mil pipelinetag: image-classification language: - en ---
Downloads · 30 days
26
39% of all-time downloads
All-time downloads
67
Public
Repo size
37 MB
Likes
1
Public
Click a slice to open those files.
.pt37 MB · 100%
From the Hugging Face model README
license: mit library_name: pytorch tags:
Authors: Isha, Dr. Narendra Kumar Sharma
A Gated Attention-MIL head that predicts the 17 Drews 2022 chromosomal-instability
signatures (CX1–CX17) from whole-slide H&E pathology images, using frozen
MahmoodLab/UNI tile embeddings.
This is the largest of the three cohort variants in the cx-histology series:
21 TCGA cohorts, fold-parallel trained across 5 GPUs. It supersedes
cx-uni-abmil-15cohort
and cx-uni-abmil-7cohort
for the most cohort-diverse training distribution.
WSI -> tile (224 px @ 0.5 mpp, Macenko-normalized)
-> UNI (frozen) -> (N tiles, 1024)
-> GatedABMIL (this model) -> (17,) CX activity prediction
from huggingface_hub import snapshot_download
from modeling_cx_abmil import CXEnsemble
local = snapshot_download("IshaChhikara/cx-uni-abmil-21cohort")
model = CXEnsemble.from_pretrained(local, device="cpu")
cx = model.predict(my_uni_embeddings) # (B, N, 1024) -> (B, 17)
Held-out test on 283 CPTAC-3 patients with paired UNI tile embeddings and recomputed CX activities (CINSignatureQuantification v1.2.0 on GDC ASCAT2 seg files, build hg38, DCIN=10) meets the pre-registered acceptance criterion |ρ_TCGA − ρ_CPTAC| ≤ 0.15 for all 14 active signatures:
| Signature | ρ_TCGA | ρ_CPTAC | |Δρ| |
|---|---|---|---|
| CX6 | +0.056 | +0.058 | 0.002 |
| CX3 | +0.114 | +0.102 | 0.012 |
| CX9 | +0.026 | +0.010 | 0.017 |
| CX8 | +0.096 | +0.068 | 0.027 |
| CX2 | +0.053 | +0.013 | 0.040 |
| CX12 | +0.130 | +0.062 | 0.069 |
| CX4 | +0.060 | −0.014 | 0.074 |
| CX1 | +0.137 | +0.056 | 0.081 |
| CX11 | +0.069 | −0.019 | 0.088 |
| CX17 | +0.044 | +0.133 | 0.090 |
| CX16 | +0.078 | +0.176 | 0.098 |
| CX13 | +0.017 | −0.097 | 0.114 |
| CX10 | +0.101 | −0.014 | 0.114 |
| CX5 | +0.147 | +0.021 | 0.125 |
CX16 and CX17 generalise better on CPTAC than on TCGA. The remaining twelve signatures retain the sign and rough magnitude of the TCGA estimates, with absolute ρ_CPTAC values smaller than ρ_TCGA in ten of fourteen cases.
| Variant | n | Mean ρ | H1 hits |
|---|---|---|---|
| 7-cohort | 289 | +0.219 | 3 |
| 15-cohort | 1,454 | +0.138 | 0 |
| 21-cohort | 3,855 | +0.106 | 0 |
Smaller cohort sets achieve larger pan-cohort ρ partly because cancer-type heterogeneity is doing the work. As cohorts are added, the within-biology signal becomes the dominant explanation. The 21-cohort number is the most honest estimate of the H&E→CIN biology link.
modeling_cx_abmil.py — model + CXEnsemble 5-fold ensemble wrapperinference_example.pyconfig.jsonfold0.pt … fold4.ptLICENSE (MIT)In preparation. Code: github.com/ishaschhikara316/cx-histology.