Summary of Cross-vendor Reproducibility Of Radiomics-based Machine Learning Models For Computer-aided Diagnosis, by Jatin Chaudhary et al.
Cross-Vendor Reproducibility of Radiomics-based Machine Learning Models for Computer-aided Diagnosis
by Jatin Chaudhary, Ivan Jambor, Hannu Aronen, Otto Ettala, Jani Saunavaara, Peter Boström, Jukka Heikkonen, Rajeev Kanth, Harri Merisaari
First submitted to arxiv on: 25 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 A machine learning paper investigates the reproducibility of models for detecting prostate cancer using MRI scans from different vendors. The authors trained Support Vector Machines (SVM) and Random Forest (RF) models on radiomic features extracted from T2-weighted MRI images. They used libraries like Pyradiomics and MRCradiomics to extract features, and the maximum relevance minimum redundancy (MRMR) technique for feature selection. The goal was to enhance clinical decision support through multimodal learning and feature fusion. The results show that the SVM model achieved an AUC of 0.74 on one dataset but decreased to 0.60 on another. The RF model showed similar trends, with notable robustness when using features from Pyradiomics alone. These findings demonstrate the potential of multimodal feature integration to improve the robustness and generalizability of machine-learning models for clinical decision support in prostate cancer detection. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study helps doctors use machines to detect prostate cancer more accurately. Researchers trained two types of computer programs, called Support Vector Machines (SVM) and Random Forest (RF), using special features from MRI scans. They wanted to make sure the computers could work with different kinds of MRI scanners. The results showed that one program did better on some tests but not others, while the other program was more reliable. This study helps doctors use machines to diagnose prostate cancer more accurately. |
Keywords
» Artificial intelligence » Auc » Feature selection » Machine learning » Random forest
