# CAIPI in Practice: Towards Explainable Interactive Medical Image Classification

arXiv: https://arxiv.org/abs/2204.02661 · HTML: https://mlsanity.com/paper/2204.02661/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 6 Apr 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis](https://mlsanity.com/paper/2010.14925/) (2020)
- [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020)
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://mlsanity.com/paper/1711.03705/) (2017)
- [Model Agnostic Supervised Local Explanations](https://mlsanity.com/paper/1807.02910/) (2018)
- [Interpreting Blackbox Models via Model Extraction](https://mlsanity.com/paper/1705.08504/) (2017)

## Built on by (most cited first, 5 of 5)

- [Leveraging Explanations in Interactive Machine Learning: An Overview](https://mlsanity.com/paper/2207.14526/) (2022)
- [Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning](https://mlsanity.com/paper/2403.07078/) (2024)
- [Interactive Explainable Anomaly Detection for Industrial Settings](https://mlsanity.com/paper/2410.12817/) (2024)
- [Human Cognitive Biases in Explanation-Based Interaction: The Case of Within and Between Session Order Effect](https://mlsanity.com/paper/2512.04764/) (2025)
- [LVLM-Aided Alignment of Task-Specific Vision Models](https://mlsanity.com/paper/2512.21985/) (2025)

## Abstract (arXiv)

Would you trust physicians if they cannot explain their decisions to you? Medical diagnostics using machine learning gained enormously in importance within the last decade. However, without further enhancements many state-of-the-art machine learning methods are not suitable for medical application. The most important reasons are insufficient data set quality and the black-box behavior of machine learning algorithms such as Deep Learning models. Consequently, end-users cannot correct the model's decisions and the corresponding explanations. The latter is crucial for the trustworthiness of machine learning in the medical domain. The research field explainable interactive machine learning searches for methods that address both shortcomings. This paper extends the explainable and interactive CAIPI algorithm and provides an interface to simplify human-in-the-loop approaches for image classification. The interface enables the end-user (1) to investigate and (2) to correct the model's prediction and explanation, and (3) to influence the data set quality. After CAIPI optimization with only a single counterexample per iteration, the model achieves an accuracy of 97.48% on the Medical MNIST and 95.02% on the Fashion MNIST. This accuracy is approximately equal to state-of-the-art Deep Learning optimization procedures. Besides, CAIPI reduces the labeling effort by approximately 80%.