BiaPy is an open source Python library for building bioimage analysis pipelines

What's Changed Added Add process to download pretrained models by @alihamraoui in #37 Add GPU support for Cellpose by @alihamraoui in #39 Add a parameter to pass kwargs to the sopa reader by @quen...

Hi all 👋 Ever had Cellpose look at your 400 GB light-sheet stack or multi tiles 3D acquisition and quietly reply with an out-of-memory error? Us too. So we built patchworks. What it does: it cu...

We evaluated 11 segmentation methods (Watershed, BIDCell, Cellpose, SCS, SAM, SAM2, mSAM, Baysor, CelloType, Swin-s and Mask R-CNN) across 15 spatial transcriptomics datasets generated using 5 different technologies: Stereo-seq, Xenium, CosMx, STARmap PLUS and MERFISH (Fig. 1a, Supplementary Table 1 and Methods). The datasets span two species (mouse and human), 12 tissue types (brain, breast, embryo, lung, pancreas, skin, colon, stomach, ovarian, kidney, prostate and utero) and a wide range of cell counts, from around 700 cells in an ovarian cancer dataset to large cohorts of more than 800,000 cells in a prostate cancer dataset. We selected this diversity to reflect the breadth of contemporary spatial transcriptomics applications and to challenge segmentation robustness under heterogeneous biological and technical conditions (Supplementary Fig. 1a,b). We also performed cross-technology benchmarking (Fig. 1b) to account for discrepancies between platforms. This design separated algorithm-specific effects from platform-dependent biases. We conducted all the analysis using a unified benchmarking pipeline (Fig. 1c) that applies standardized quality control (QC), patch-based processing and consistent preprocessing across methods to ensure fair and reproducible comparisons. During preprocessing, we established data subsetting criteria for each dataset and method based on technical limitations (Methods). For methods that explicitly integrate transcriptomic information into their...

YouTube video by Ask Erin, Dear Beth