REVIEW 9 cited by
PanNuke Dataset Extension, Insights and Baselines
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The emerging area of computational pathology (CPath) is ripe ground for the application of deep learning (DL) methods to healthcare due to the sheer volume of raw pixel data in whole-slide images (WSIs) of cancerous tissue slides. However, it is imperative for the DL algorithms relying on nuclei-level details to be able to cope with data from `the clinical wild', which tends to be quite challenging. We study, and extend recently released PanNuke dataset consisting of ~200,000 nuclei categorized into 5 clinically important classes for the challenging tasks of segmenting and classifying nuclei in WSIs. Previous pan-cancer datasets consisted of only up to 9 different tissues and up to 21,000 unlabeled nuclei and just over 24,000 labeled nuclei with segmentation masks. PanNuke consists of 19 different tissue types that have been semi-automatically annotated and quality controlled by clinical pathologists, leading to a dataset with statistics similar to the clinical wild and with minimal selection bias. We study the performance of segmentation and classification models when applied to the proposed dataset and demonstrate the application of models trained on PanNuke to whole-slide images. We provide comprehensive statistics about the dataset and outline recommendations and research directions to address the limitations of existing DL tools when applied to real-world CPath applications.
Forward citations
Cited by 9 Pith papers
-
The Good, the Bad, and the Brittle: Benchmarking Robustness and Generalisation of Histopathology Foundation Models
Mid-sized pathology foundation models match or beat billion-parameter ones on clinically realistic perturbations and distribution-shift tests, so scaling alone has largely saturated for robustness.
-
HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy
A DINO-style SSL method with a segmentation teacher and stability-weighted HDBSCAN contrastive loss improves hierarchical morphology-aware single-cell embeddings over strong baselines.
-
Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy
Atlas H&E-TME is a new AI system for cell-level tissue profiling on H&E slides that matches pathologist performance when validated against an IHC-informed consensus and a large multi-cancer H&E annotation set.
-
Evaluating Vision Foundation Models for Pixel and Object Classification in Microscopy
Vision foundation model features improve pixel and object classification in microscopy over hand-crafted features, and object-guided attentive probing (ObAP) can match or beat supervised baselines with very few labels.
-
PhenoBench: A Comprehensive Benchmark for Cell Phenotyping
A new H&E benchmark with 14 fine-grained cell types and biological domain splits shows pathology foundation models scoring around 0.20 to 0.28 macro F1, far below their near-saturated performance on older benchmarks.
-
MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification
MorphGen uses supervised contrastive learning to align histopathology images with nuclear masks and applies SWA, reporting improved out-of-domain cancer classification accuracy on CAMELYON17, BCSS, and OCELOT.
-
Scalable and Loosely-Coupled Multimodal Deep Learning for Breast Cancer Subtyping
A multimodal framework fusing CNV, clinical data, and both image- and graph-based histopathology representations improves PAM50 subtyping accuracy to 78.13% and macro-AUC to 0.9153 on TCGA-BRCA.
-
Cancer cytoplasm segmentation in hyperspectral cell image with data augmentation
Pseudo-hyperspectral images made from CMOS photos plus synthetic line noise improve cancer cytoplasm segmentation IoU from 0.7255 to 0.7362 on a 56-image test set.
-
The Four Color Theorem for Cell Instance Segmentation
FCIS recasts cell instance segmentation as four-class semantic segmentation by four-coloring cell adjacency graphs, and reports top accuracy on DSB2018, PanNuke, BBBC006v1, and YeaZ.
Discussion (0). Continue with ORCID to comment.