#computationalpathology

Weakly Supervised Teacher–Student Framework with Progressive Pseudo-mask Refinement for Gland Segmentation Colorectal cancer histopathological grading relies on the accurate segmentation of glandular structures. Current deep learning–based methods depend heavily on large-scale pixel-level annotations that are labor-intensive and not amenable to clinical practice. Weakly supervised semantic segmentation offers a promising alternative; yet, existing class activation map–based weakly supervised semantic segmentation approaches often produce incomplete, low-quality pseudo-masks that overemphasize discriminative regions and fail to provide reliable supervision for unannotated glandular structures, limiting their suitability for dense histopathology segmentation under sparse supervision. We propose a novel weakly supervised teacher–student framework that leverages sparse pathologists’ annotations and an Exponential Moving Average–stabilized teacher network to generate refined pseudo-masks.

🧫 A weakly supervised teacher-student framework pushed gland segmentation forward with limited annotations-good news for scalable pathology AI. @cancerresearchuk.org
#ComputationalPathology
🔗 www.xiahepublishing.com/2771-165X/JC...

GitHub - FraunhoferMEVIS/MedicalMultitaskModeling: Training foundational medical imaging models using multi-task learning. Training foundational medical imaging models using multi-task learning. - FraunhoferMEVIS/MedicalMultitaskModeling

We’re looking for a way to version and catalogue self-trained deep learning models (training data, code revisions, configs, etc.) from our Tissue Concepts/Medical Multitask Modelling family of foundation models.

We briefly …

github.com/FraunhoferME...

#datascience, #computationalpathology
1/3

#SpatialTranscriptomics #SpatialOmics #SpatialBiology #Transcriptomics #SingleCell #IBD #Crohns #UlcerativeColitis #Healthcare #PrecisionMedicine #SystemsBiology #MachineLearning #ArtificialIntelligence #AIinHealthcare #ComputationalPathology #AI

We hope this contributes to open & reproducible research in #ComputationalPathology.

Big thanks to Guillaume Balezo, Albert Pla Planas and Etienne Decencière.

Great collaboration between @sanofifr.bsky.social and @minesparis-psl.bsky.social.

#DigitalPathology #FoundationModels #ViT #HuggingFace

Representation learning for computational pathology and spatial omics – Eduard Chelebian Kocharyan - Uppsala University

Don’t miss today's CBA seminar on 'Representation learning for computational pathology and spatial omics' by Eduard Chelebian at 14.15! More info: uu.se/en/centre/im...

#spatialomics #computationalpathology