AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

HistoSegNet: Semantic Segmentation of Histological Tissue Type in Whole Slide Images

Lyndon Chan, Mahdi S. Hosseini, Corwyn Rowsell, Konstantinos N. Plataniotis, Savvas Damaskinos

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 161 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use HistoSegNet instead of DSRGWSSS on ADP · ADP tuning set, functional typesmIoU: 0.4732 -> 0.5505Improved
use HistoSegNet instead of SECWSSS on ADP · ADP tuning set, functional typesmIoU: 0.3225 -> 0.5505Improved
use HistoSegNet instead of DSRGWSSS on ADP · ADP tuning set, morphological typesmIoU: 0.1375 -> 0.2206Improved
use HistoSegNet instead of SECWSSS on ADP · ADP tuning set, morphological typesmIoU: 0.1628 -> 0.2206Improved
add inter-HTT adjustments after pixel-level segmentation (ablation)HistoSegNet · ADP tuning set, functional typesmIoU: 0.2059 -> 0.5174Improved
add inter-HTT adjustments after pixel-level segmentation (ablation)HistoSegNet · ADP tuning set, morphological typesmIoU: 0.2549 -> 0.2067Hurt
add segmentation post-processing (fully-connected CRF) (ablation)HistoSegNet · ADP tuning set, morphological typesmIoU: 0.2067 -> 0.2206Improved
add segmentation post-processing (fully-connected CRF) (ablation)HistoSegNet · ADP tuning set, functional typesmIoU: 0.5174 -> 0.5505Improved
use functional types instead of morphological typesHistoSegNet · ADP tuning setmIoU: 0.2206 -> 0.5505Improved
increase tumor grade from healthy to poorly differentiatedHistoSegNet · GlaS Challengeaverage G.O confidence score: 0.9750 -> 0.6628Hurt
increase tumor grade from healthy to poorly differentiatedHistoSegNet · GlaS Challenge, single gland modemean Dice: 0.5970 -> 0.4102Hurt
increase tumor grade from healthy to poorly differentiatedHistoSegNet · GlaS Challenge, single gland modemean Hausdorff distance: 130.48 -> 170.20Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy