Eduardo Hirata-Miyasaki comments

Results 37 comments of


                                            Eduardo Hirata-Miyasaki

Organize segmentations, tracking, annotations, and embeddings with DynaCell zarr stores

Also, from our AI@MBL projects phase. It seems `SpatialData` adds a bit of unnecesary overhead. There is a set of transforms that need to be applied or parsed so that...

Organize segmentations, tracking, annotations, and embeddings with DynaCell zarr stores

As a first step for the annotations, we will: - @srivarra check the `EmbeddingWriter()`, `load_annotation()` for writing the Ultrack tracking data and the features. - Standardize the input (e.g `fov_name`...

Organize segmentations, tracking, annotations, and embeddings with DynaCell zarr stores

https://github.com/mehta-lab/VisCy/pull/274 We also identified that this preprocessing file should be appended to the `tracking.csv` used during training. The statistics will vary depending on the `patch_sizes`.

Fix the PC Viewer to support multi-dataset PHATE embedding

@Soorya19Pradeep seems like this is now working. Can we close and merge this PR to main?

Prediction on multiple dataset

This functionality already exists in the PC viewer. We will add a script that recalculates the PHATE for combined datasets. Add the seed 42.

[Question] Is deconvolution required for inference with pre-trained models?

- All our models use the FCMAE pretraining and then virtual staining finetuning step. For the first step, yes, we take images from different contrasts( i.e PhC, QPI, BF,etc). -...

Organelle segmentation and featurization for pseudotime analysis

https://github.com/czbiohub-sf/biahub/pull/176 probably best if it lives in biahub.