Accurate Detection of Mediastinal Lesions with nnDetection
Published in Lesion Segmentation in Surgical and Diagnostic Applications. CuRIOUS KiPA MELA 2022, 2023
Recommended citation: Baumgartner, M., et al. (2023). Accurate Detection of Mediastinal Lesions with nnDetection. In: Xiao, Y., Yang, G., Song, S. (eds) Lesion Segmentation in Surgical and Diagnostic Applications. CuRIOUS KiPA MELA 2022 2022 2022. Lecture Notes in Computer Science, vol 13648. Springer, Cham. https://link.springer.com/chapter/10.1007/978-3-031-27324-7_10
The accurate detection of mediastinal lesions is one of the rarely explored medical object detection problems. In this work, we applied a modified version of the self-configuring method nnDetection to the Mediastinal Lesion Analysis (MELA) Challenge 2022. By incorporating automatically generated pseudo masks, training high capacity models with large patch sizes in a multi GPU setup and an adapted augmentation scheme to reduce localization errors caused by rotations, our method achieved an excellent FROC score of 0.9922 at IoU 0.10 and 0.9880 at IoU 0.3 in our cross-validation experiments. The submitted ensemble ranked third in the competition with a FROC score of 0.9897 on the MELA challenge leaderboard.