Summary of Interpretable Solutions For Breast Cancer Diagnosis with Grammatical Evolution and Data Augmentation, by Yumnah Hasan et al.
Interpretable Solutions for Breast Cancer Diagnosis with Grammatical Evolution and Data Augmentation
by Yumnah Hasan, Allan de Lima, Fatemeh Amerehi, Darian Reyes Fernandez de Bulnes, Patrick Healy, Conor Ryan
First submitted to arxiv on: 25 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Neural and Evolutionary Computing (cs.NE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a novel approach to medical imaging diagnosis using Machine Learning (ML) models that are inherently understandable and address issues with imbalanced datasets. The authors utilize a synthetic data generation technique called STEM, which combines Synthetic Minority Oversampling Technique (SMOTE), Edited Nearest Neighbour (ENN), and Mixup, to produce data for training Grammatical Evolution (GE) models. These models demonstrate better Area Under the Curve (AUC) results compared to standard ML classifiers while maintaining interpretability. The technique is tested on the Digital Database for Screening Mammography (DDSM) and Wisconsin Breast Cancer (WBC) datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps doctors make better decisions about medical images by using special machine learning models that are easy to understand. These models can learn from small amounts of training data, which is important because many medical imaging datasets are very imbalanced. The researchers use a new way to create synthetic data called STEM, which combines different techniques to make the data more balanced and realistic. They show that these new models work better than other machine learning models on two important medical image datasets. |
Keywords
* Artificial intelligence * Auc * Machine learning * Synthetic data
