The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methods
This provides a standardized dataset for researchers in medical imaging to fairly evaluate reconstruction methods, though it is incremental as it builds on existing data.
The authors tackled the challenge of comparing deep learning methods for low-dose CT reconstruction by creating the LoDoPaB-CT dataset, which includes over 40,000 scan slices from 800 patients and simulated low-dose measurements to serve as a benchmark.
Deep Learning approaches for solving Inverse Problems in imaging have become very effective and are demonstrated to be quite competitive in the field. Comparing these approaches is a challenging task since they highly rely on the data and the setup that is used for training. We provide a public dataset of computed tomography images and simulated low-dose measurements suitable for training this kind of methods. With the LoDoPaB-CT Dataset we aim to create a benchmark that allows for a fair comparison. It contains over 40,000 scan slices from around 800 patients selected from the LIDC/IDRI Database. In this paper we describe how we processed the original slices and how we simulated the measurements. We also include first baseline results.