# Low-Magnification SEM May Suffice: Interpretable Deep Learning for Multi-Scale Fracture-Cause Classification in Zirconia-Toughened Alumina

arXiv: https://arxiv.org/abs/2605.29798 · HTML: https://mlsanity.com/paper/2605.29798/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 7 of 7)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [How You Split Matters: Data Leakage and Subject Characteristics Studies in Longitudinal Brain MRI Analysis](https://mlsanity.com/paper/2309.00350/) (2023)
- [Toward quantitative fractography using convolutional neural networks](https://mlsanity.com/paper/1908.02242/) (2019)
- [Identifying document similarity using a fast estimation of the Levenshtein Distance based on compression and signatures](https://mlsanity.com/paper/2307.11496/) (2023)
- [Automated Detection of Defects on Metal Surfaces using Vision Transformers](https://mlsanity.com/paper/2410.04440/) (2024)
- [Semiconductor SEM Image Defect Classification Using Supervised and Semi-Supervised Learning with Vision Transformers](https://mlsanity.com/paper/2506.03345/) (2025)

## Abstract (arXiv)

Reliable identification of fracture origins in alumina matrix composite hip and knee implants is critical for quality assurance and patient safety, yet current fractographic workflows are time-consuming, partly subjective, and reliant on high-magnification scanning electron microscopy (SEM). We present an interpretable vision-transformer (ViT) workflow for automated classification of fracture causes in an alumina matrix composite (BIOLOX delta, CeramTec GmbH) widely used in total joint replacements. A dataset of 8,493 SEM images (50x-10,000x) was curated from five years of in-production burst and proof tests and annotated into three defect categories defined along the manufacturing chain: green body, hard machining, and material defects. Under severe class imbalance, the fine-tuned ViT reached an accuracy of 0.907 and a macro-F1 of 0.888 in stratified five-fold cross-validation, with a two-stage perceptual-hash/SSIM leakage audit confirming negligible specimen overlap. Notably, performance at low magnification (50x) was comparable to that at high magnification (1k-10kx), indicating that macro-scale features - mirror geometry and hackle line fields - already encode sufficient diagnostic signal. Grad-CAM attributions consistently localised on canonical fractographic cues (mirrors, hackles, pores, machining marks), aligning with established fractographic criteria. Together, these results position interpretable ViTs as a complementary tool for ceramic-implant quality assurance, enabling low-magnification pre-screening and reducing reliance on time-intensive high-magnification inspection.