Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Rui, Liu, Pei, Ji, Luping
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2304.06652
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909175965024256
author Yang, Rui
Liu, Pei
Ji, Luping
author_facet Yang, Rui
Liu, Pei
Ji, Luping
contents Due to the limitations of inadequate Whole-Slide Image (WSI) samples with weak labels, pseudo-bag-based multiple instance learning (MIL) appears as a vibrant prospect in WSI classification. However, the pseudo-bag dividing scheme, often crucial for classification performance, is still an open topic worth exploring. Therefore, this paper proposes a novel scheme, ProtoDiv, using a bag prototype to guide the division of WSI pseudo-bags. Rather than designing complex network architecture, this scheme takes a plugin-and-play approach to safely augment WSI data for effective training while preserving sample consistency. Furthermore, we specially devise an attention-based prototype that could be optimized dynamically in training to adapt to a classification task. We apply our ProtoDiv scheme on seven baseline models, and then carry out a group of comparison experiments on two public WSI datasets. Experiments confirm our ProtoDiv could usually bring obvious performance improvements to WSI classification.
format Preprint
id arxiv_https___arxiv_org_abs_2304_06652
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ProtoDiv: Prototype-guided Division of Consistent Pseudo-bags for Whole-slide Image Classification
Yang, Rui
Liu, Pei
Ji, Luping
Computer Vision and Pattern Recognition
Due to the limitations of inadequate Whole-Slide Image (WSI) samples with weak labels, pseudo-bag-based multiple instance learning (MIL) appears as a vibrant prospect in WSI classification. However, the pseudo-bag dividing scheme, often crucial for classification performance, is still an open topic worth exploring. Therefore, this paper proposes a novel scheme, ProtoDiv, using a bag prototype to guide the division of WSI pseudo-bags. Rather than designing complex network architecture, this scheme takes a plugin-and-play approach to safely augment WSI data for effective training while preserving sample consistency. Furthermore, we specially devise an attention-based prototype that could be optimized dynamically in training to adapt to a classification task. We apply our ProtoDiv scheme on seven baseline models, and then carry out a group of comparison experiments on two public WSI datasets. Experiments confirm our ProtoDiv could usually bring obvious performance improvements to WSI classification.
title ProtoDiv: Prototype-guided Division of Consistent Pseudo-bags for Whole-slide Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2304.06652