Making Artificial Intelligence Lemonade Out of Data Lemons
| Autor: | Sonia Shah, Yiju Teresa Liu, Joseph L. Thomas, Kabir Yadav, Kendra Campbell, Michael Blaivas, Laura N Blaivas |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Adaptation (eye)
Machine learning computer.software_genre Ventricular Function Left Machine Learning Artificial Intelligence Approximation error Range (statistics) Humans Medicine Radiology Nuclear Medicine and imaging Visual estimation Ejection fraction Radiological and Ultrasound Technology Database business.industry Deep learning Echo (computing) Stroke Volume Echocardiography Algorithm design Artificial intelligence business computer Algorithm Algorithms |
| Zdroj: | Journal of Ultrasound in Medicine. 41:2059-2069 |
| ISSN: | 1550-9613 0278-4297 |
| DOI: | 10.1002/jum.15889 |
| Popis: | OBJECTIVES A paucity of point-of-care ultrasound (POCUS) databases limits machine learning (ML). Assess feasibility of training ML algorithms to visually estimate left ventricular ejection fraction (EF) from a subxiphoid (SX) window using only apical 4-chamber (A4C) images. METHODS Researchers used a long-short-term-memory algorithm for image analysis. Using the Stanford EchoNet-Dynamic database of 10,036 A4C videos with calculated exact EF, researchers tested 3 ML training permeations. First, training on unaltered Stanford A4C videos, then unaltered and 90° clockwise (CW) rotated videos and finally unaltered, 90° rotated and horizontally flipped videos. As a real-world test, we obtained 615 SX videos from Harbor-UCLA (HUCLA) with EF calculations in 5% ranges. Researchers performed 1000 randomizations of EF point estimation within HUCLA EF ranges to compensate for ML and HUCLA EF mismatch, obtaining a mean value for absolute error (MAE) comparison and performed Bland-Altman analyses. RESULTS The ML algorithm EF mean MAE was estimated at 23.0, with a range of 22.8-23.3 using unaltered A4C video, mean MAE was 16.7, with a range of 16.5-16.9 using unaltered and 90° CW rotated video, mean MAE was 16.6, with a range of 16.3-16.8 using unaltered, 90° CW rotated and horizontally flipped video training. Bland-Altman showed weakest agreement at 40-45% EF. CONCLUSIONS Researchers successfully adapted unrelated ultrasound window data to train a POCUS ML algorithm with fair MAE using data manipulation to simulate a different ultrasound examination. This may be important for future POCUS algorithm design to help overcome a paucity of POCUS databases. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text