Enregistré dans:
Détails bibliographiques
Auteurs principaux: Fletcher, Sean, Scott, Gabby, Currie, Douglas, Zhang, Xin, Song, Yuqi, MacLeod, Bruce
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.23363
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911249890017280
author Fletcher, Sean
Scott, Gabby
Currie, Douglas
Zhang, Xin
Song, Yuqi
MacLeod, Bruce
author_facet Fletcher, Sean
Scott, Gabby
Currie, Douglas
Zhang, Xin
Song, Yuqi
MacLeod, Bruce
contents Medical image analysis is central to drug discovery and preclinical evaluation, where scalable, objective readouts can accelerate decision-making. We address classification of paclitaxel (Taxol) exposure from phase-contrast microscopy of C6 glioma cells -- a task with subtle dose differences that challenges full-image models. We propose a simple tiling-and-aggregation pipeline that operates on local patches and combines tile outputs into an image label, achieving state-of-the-art accuracy on the benchmark dataset and improving over the published baseline by around 20 percentage points, with trends confirmed by cross-validation. To understand why tiling is effective, we further apply Grad-CAM and Score-CAM and attention analyses, which enhance model interpretability and point toward robustness-oriented directions for future medical image research. Code is released to facilitate reproduction and extension.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23363
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interpretable Tile-Based Classification of Paclitaxel Exposure
Fletcher, Sean
Scott, Gabby
Currie, Douglas
Zhang, Xin
Song, Yuqi
MacLeod, Bruce
Computer Vision and Pattern Recognition
Medical image analysis is central to drug discovery and preclinical evaluation, where scalable, objective readouts can accelerate decision-making. We address classification of paclitaxel (Taxol) exposure from phase-contrast microscopy of C6 glioma cells -- a task with subtle dose differences that challenges full-image models. We propose a simple tiling-and-aggregation pipeline that operates on local patches and combines tile outputs into an image label, achieving state-of-the-art accuracy on the benchmark dataset and improving over the published baseline by around 20 percentage points, with trends confirmed by cross-validation. To understand why tiling is effective, we further apply Grad-CAM and Score-CAM and attention analyses, which enhance model interpretability and point toward robustness-oriented directions for future medical image research. Code is released to facilitate reproduction and extension.
title Interpretable Tile-Based Classification of Paclitaxel Exposure
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.23363