Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Releases: KatherLab/STAMP

2.4.0

26 Nov 12:34
95e6a10

Choose a tag to compare

  • Added support for regression (MAE loss) and Cox-based survival analysis for tile-, slide-, and patient-level tasks.
  • Added evaluation metrics:
    • Regression: R², Pearson r, Pearson p, MAE, RMSE
    • Survival: Kaplan–Meier curve (optional: low/high risk using a median cut-off computed from train predictions), log-rank p-value, C-index
  • Added probability heatmaps for regression and survival tasks.
  • Training now supports Attention (ViT), TransMIL, and MLP backbones.
  • All backbones support tile-level modeling; slide/patient-level modeling is supported via MLP
  • Automatic model class selection based on feature type and task.

2.3.0

12 Aug 07:34
78af2f2

Choose a tag to compare

  • Modeling and statistics support for patient-level features.
  • MCP support for all STAMP features.
  • Fixed heatmaps and top tiles
  • Overlayed heatmaps on thumbnail.
  • Easier installation steps.
  • Restored Learning Rate Scheduler and original STAMPv1 hyperparams.
  • Advanced params section in config file for easier tuning without modifying the code.
  • Added PRISM.

2.2.0

15 Jul 14:25
24b91ba

Choose a tag to compare

  • Slide and patient level encoding support with:
    • COBRA
    • EAGLE
    • CHIEF
    • TITAN
    • GIGAPATH
    • MADELEINE
  • New tile-level feature extractors:
    • Virchow
    • mSTAR
    • PLIP
    • MUSK
  • Fixed high memory usage disabling attention masking on validation and testing.
  • Option to add hash to output folder.
  • Option to change cached tiles to png.
  • Updated docs.
  • Minor bug fixes.

2.1.0

10 Apr 11:15
0042e6f

Choose a tag to compare

  • New feature extractors:
    • UNI2
    • chief_ctranspath
    • conch v1.5
    • gigapath
    • h_optimus_0
    • h_optimus_1
  • Tile size in pixels is now saved on h5 feature file metadata.

v2.0.0

28 Jan 14:01

Choose a tag to compare

  • Better and stricter config parsing
  • Significantly faster preprocessing
  • No more dependency on fastai
  • Lots of code cleanup, refactoring, documentation and tests

2.0.0.dev14

15 Jan 15:59

Choose a tag to compare

2.0.0.dev14 Pre-release
Pre-release
Add tests for heatmaps

2.0.0-dev8

13 Jan 17:36

Choose a tag to compare

2.0.0-dev8 Pre-release
Pre-release
Implement masking

STAMP v1.1.1

12 Jul 11:50
5bb263e

Choose a tag to compare

  • Deploy now happens on GPU when available
  • Minor heatmap bug fix for resizing a PIL image using a tuple instead of an array

STAMP v1.1.0

11 Jun 14:34
01cab87

Choose a tag to compare

  • Replace MultiHeadAttention with PyTorch nn.MultiHeadAttention which uses FlashAttentionV2, thus requiring less memory while being faster;
  • Enabled usage of TensorFloat32 on CUDA devices, resulting in faster performance;
  • Changed optimizer from Adam to AdamW.

STAMP v1.0.3

14 Apr 21:20
c71e04d

Choose a tag to compare

  • Integration of UNI feature extractor
  • Move download of UNI model weights to stamp setup
  • Add process ID to logfile name to avoid two slurm processes writing to same logfile
  • Ignore missing normalization template / weights if not required by config
  • Remove lock files older than 20 seconds before beginning preprocessing
  • Fix of error in heatmaps script
  • Set norm: false in the default config
  • Set version to 1.0.3
  • Update installation instructions in README