The evaluation of mediastinal nodal involvement in oncologic patients is of the utmost importance, being the lymph nodes a possible site of metastatic seeding in lung cancer and other thoracic and extra-thoracic tumors. Nodal assessment is generally performed on CT scans by radiologists as part of the radiologic workup through the analysis of medical images, employing different diagnostic criteria with Response Evaluation Criteria In Solid Tumors (RECIST) accounting for the most used. Recent studies suggested that the radiomic/quantitative analysis of lymph nodes may outperform the...

For the training and validation, we used the publicly available CT Lymph Nodes dataset [3](90 CECTs with manual segmentations performed by radiologists). The authors revised each mask to add every mediastinal lymph node (minor axis > 10 mm) that was not segmented initially and the ones showing distinctive pathological features (minor axis range: 5-10 mm) (See example in Fig.1).[Fig 1] Particular attention was used to be as adherent as possible to lymph nodes borders. Lymph nodes with the tendency to merge into conglomerates were preferentially...

The final training set was composed of 89 CT scans. One scan was excluded because it did not contain the full lungs in the field of view. Slice thickness ranged from 1 to 5 mm (87 CT scans with a slice thickness of 1 or 1.5 mm and 2 CT scans with a slice thickness of 5 mm) while in-slice resolution was between 0.63 and 0.98 mm. The difference in performance between the model trained on the original and the improved dataset is relevant, with...

The improvement and refinement of manual segmentation ground truths used for model training improved sensibly the model performances. Given the complexity of lymph nodes segmentation also for the radiologist, this model can be seen as a support tool to expedite the workflow and ease the manual work required. Contrary to other reported models, the improvement in performances is modest but our results are consistent regardless of the lymph node size or station. The limitation of the current study is the lack of external validation, essential...

A. Corsi: Nothing to disclose F. Belmans: Employee: Radiomics F. Blistein: Employee: Radiomics S. Ahmed Ali: Employee: Radiomics W. Vos: CEO: Radiomics S. Sironi: Nothing to disclose M. Occhipinti: Employee: Radiomics

Shin H-C, Roth HR, Gao M, Lu L, Xu Z, Nogues I, Yao J, Mollura D, Summers RM. Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning. IEEE Trans Med Imaging (2016) 35:1285–1298. Tekchandani H, Verma S, Londhe N. Performance improvement of mediastinal lymph node severity detection using GAN and Inception network. Comput Methods Programs Biomed (2020) 194:105478. doi:https://doi.org/10.1016/j.cmpb.2020.105478 Roth HR, Lu L, Seff A, Cherry KM, Hoffman J, Wang S, Liu J, Turkbey E, Summers RM. A New 2.5D...