Accurate Detection of Mediastinal Lesions with nnDetection
This work addresses a specific medical imaging problem for healthcare applications, but it is incremental as it adapts an existing method to a new dataset.
The paper tackled the problem of accurately detecting mediastinal lesions, a rarely explored medical object detection task, by applying a modified version of nnDetection to the MELA Challenge 2022, achieving an FROC score of 0.9922 at IoU 0.10 and ranking third in the competition with a score of 0.9897.
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.