Quantitative Impact of Label Noise on the Quality of Segmentation of Brain Tumors on MRI scans
Autor: | M. Marcinkiewicz, Grzegorz Mrukwa |
---|---|
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Machine learning computer.software_genre Machine Learning (cs.LG) 030218 nuclear medicine & medical imaging Task (project management) 03 medical and health sciences 0302 clinical medicine FOS: Electrical engineering electronic engineering information engineering 0202 electrical engineering electronic engineering information engineering Segmentation Artificial neural network business.industry Deep learning Image and Video Processing (eess.IV) Image segmentation Electrical Engineering and Systems Science - Image and Video Processing Data quality Benchmark (computing) 020201 artificial intelligence & image processing Artificial intelligence Noise (video) business computer |
Zdroj: | FedCSIS |
ISSN: | 2300-5963 |
DOI: | 10.15439/2019f273 |
Popis: | Over the last few years, deep learning has proven to be a great solution to many problems, such as image or text classification. Recently, deep learning-based solutions have outperformed humans on selected benchmark datasets, yielding a promising future for scientific and real-world applications. Training of deep learning models requires vast amounts of high quality data to achieve such supreme performance. In real-world scenarios, obtaining a large, coherent, and properly labeled dataset is a challenging task. This is especially true in medical applications, where high-quality data and annotations are scarce and the number of expert annotators is limited. In this paper, we investigate the impact of corrupted ground-truth masks on the performance of a neural network for a brain tumor segmentation task. Our findings suggest that a) the performance degrades about 8% less than it could be expected from simulations, b) a neural network learns the simulated biases of annotators, c) biases can be partially mitigated by using an inversely-biased dice loss function. |
Databáze: | OpenAIRE |
Externí odkaz: |