This study explores the importance of quality assurance when deploying an automatic segmentation model. The authors of this study built a deep-learning model with the goal of estimating the quality of automatically generated contours. They found that the trained model can be used alongside automatic segmentation tools, thus ensuring quality and allowing intervention to prevent undesired segmentation behavior.
Key points
- A deep learning model is trained to predict segmentation quality.
- Data augmentation provides a means to expand the data set almost infinitely.
- The model achieves 99.6% accuracy and 2.2% mean percentage error.
- The model can be used to assure a desired standard is met.
Article: Quality assurance for automatically generated contours with additional deep learning
Authors: Lars Johannes Isaksson, Paul Summers, Abhir Bhalerao, Sara Gandini, Sara Raimondi, Matteo Pepa, Mattia Zaffaroni, Giulia Corrao, Giovanni Carlo Mazzola, Marco Rotondi, Giuliana Lo Presti, Zaharudin Haron, Sara Alessi, Paola Pricolo, Francesco Alessandro Mistretta, Stefano Luzzago, Federica Cattani, Gennaro Musi, Ottavio De Cobelli, Marta Cremonesi, Roberto Orecchia, Giulia Marvaso, Giuseppe Petralia & Barbara Alicja Jereczek-Fossa
