Published July 11, 2023 | Version v1

LUNA16 converted dataset

Description

Previously, the work of collecting and processing medical image data, especially the LUNA16 dataset, required a lot of effort and was time-consuming and costly. This work studied the dataset LUNA16 carefully, programmatically converted the LUNA16 database, which was stored in the .mhd/.raw format to the .jpg format, using the Hounsfield Unit scale in combination with Simple ITK library. At the end of the conversion, the new dataset has less storage required than the original dataset, and the research community will be able to access to a preprocessed and prepared data source, reduce the effort and time required for traditional data preprocessing. This not only speeds up the research process, but also gives a great impetus to the development and evaluation of new deep learning methods later on.

Files

anatomical_info.json

Files (21.0 GB)

Name Size
md5:ff5d139c95a5afe8d6b526aaef173289
203.9 kB Preview Download
md5:be02630872358ae32f17989c887eb969
119.1 kB Preview Download
md5:7f602e04fd67acf4bba74208a316160b
62.6 MB Preview Download
md5:67e84dbea07cd3c24e96e16154e888d2
20.9 GB Preview Download

Additional details

References

  • A. A. A. Setio et al., "Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge," Med. Image Anal., vol. 42, pp. 1–13, Dec. 2017, doi: 10.1016/j.media.2017.06.015.