Entropy Bootstrapping for Weakly Supervised Nuclei Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Willoughby, James, Voiculescu, Irina
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909399607410688
author Willoughby, James
Voiculescu, Irina
author_facet Willoughby, James
Voiculescu, Irina
contents Microscopy structure segmentation, such as detecting cells or nuclei, generally requires a human to draw a ground truth contour around each instance. Weakly supervised approaches (e.g. consisting of only single point labels) have the potential to reduce this workload significantly. Our approach uses individual point labels for an entropy estimation to approximate an underlying distribution of cell pixels. We infer full cell masks from this distribution, and use Mask-RCNN to produce an instance segmentation output. We compare this point--annotated approach with training on the full ground truth masks. We show that our method achieves a comparatively good level of performance, despite a 95% reduction in pixel labels.
format Preprint
id arxiv_https___arxiv_org_abs_2411_13528
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Entropy Bootstrapping for Weakly Supervised Nuclei Detection
Willoughby, James
Voiculescu, Irina
Computer Vision and Pattern Recognition
Artificial Intelligence
Microscopy structure segmentation, such as detecting cells or nuclei, generally requires a human to draw a ground truth contour around each instance. Weakly supervised approaches (e.g. consisting of only single point labels) have the potential to reduce this workload significantly. Our approach uses individual point labels for an entropy estimation to approximate an underlying distribution of cell pixels. We infer full cell masks from this distribution, and use Mask-RCNN to produce an instance segmentation output. We compare this point--annotated approach with training on the full ground truth masks. We show that our method achieves a comparatively good level of performance, despite a 95% reduction in pixel labels.
title Entropy Bootstrapping for Weakly Supervised Nuclei Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.13528