# Interpretable Tile-Based Classification of Paclitaxel Exposure

arXiv: https://arxiv.org/abs/2510.23363 · HTML: https://mlsanity.com/paper/2510.23363/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Classification of breast cancer histology images using transfer learning](https://mlsanity.com/paper/1802.09424/) (2018)
- [A Deep Analysis of Transfer Learning Based Breast Cancer Detection Using Histopathology Images](https://mlsanity.com/paper/2304.05022/) (2023)
- [Evaluating Deep Learning Models for Breast Cancer Classification: A Comparative Study](https://mlsanity.com/paper/2408.16859/) (2024)
- [Deep Learning for Taxol Exposure Analysis: A New Cell Image Dataset and Attention-Based Baseline Model](https://mlsanity.com/paper/2508.14349/) (2025)

## Abstract (arXiv)

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.