Dowrick, Thomas; Chen, Long; Ramalhinho, Joao; Puyal, Juana Gonzalez-Bueno; Clarkson, Matthew J; (2023) Procedurally Generated Colonoscopy and Laparoscopy Data for Improved Model Training Performance. In: Bhattarai, B and Ali, S and Rau, A and Nguyen, A and Namburete, A and Caramalau, R and Stoyanov, D, (eds.) Data Engineering in Medical Imaging, DEMI 2023. (pp. pp. 67-77). Springer, Cham: Cham, Switzerland.

Preview

Text dowrick_demi_2023[9].pdf - Accepted Version Download (3MB) | Preview

Abstract

The use of synthetic/simulated data can greatly improve model training performance, especially in areas such as image guided surgery, where real training data can be difficult to obtain, or of limited size. Procedural generation of data allows for large datasets to be rapidly generated and automatically labelled, while also randomising relevant parameters within the simulation to provide a wide variation in models and textures used in the scene. A method for procedural generation of both textures and geometry for IGS data is presented, using Blender Shader Graphs and Geometry Nodes, with synthetic datasets used to pre-train models for polyp detection (YoloV7) and organ segmentation (UNet), with performance evaluated on open-source datasets. Pre-training models with synthetic data significantly improves both model performance and generalisability (i.e. performance when evaluated on other datasets). Mean DICE score across all models for liver segmentation increased by 15% (p=0.02) after pre-training on synthetic data. For polyp detection, Precision increased by 11% (p=0.002), Recall by 9% (p=0.01), mAP@.5 by 10% (p=0.01) and mAP@[.5:95] by 8% (p-0.003). All synthetic data, as well as examples of different Shader Graph/Geometry Node operations can be downloaded at https://doi.org/10.5522/04/23843904.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item