Chromosomal radiosensitivity in oncological and non-oncological patients with rheumatoid arthritis and connective tissue diseases.

BACKGROUND: The risk of developing late radiotoxicity after radiotherapy in patients with high chromosomal radiosensitivity after radiotherapy could potentially be higher compared to the risk in patients with average radiosensitivity. In case of extremely high radiosensitivity, dose reduction may be appropriate. Some rheumatic diseases (RhD), including connective tissue diseases (CTDs) appear to be associated with higher radiosensitivity. The question arises as to whether patients with rheumatoid arthritis (RA) also generally have a higher radiosensitivity and whether certain parameters could indicate clues to high radiosensitivity in RA patients which would then need to be further assessed before radiotherapy. METHODS: Radiosensitivity was determined in 136 oncological patients with RhD, 44 of whom were RA patients, and additionally in 34 non-oncological RA patients by three-colour fluorescence in situ hybridization (FiSH), in which lymphocyte chromosomes isolated from peripheral blood are analysed for their chromosomal aberrations of an unirradiated and an with 2 Gy irradiated blood sample. The chromosomal radiosensitivity was determined by the average number of breaks per metaphase. In addition, correlations between certain RA- or RhD-relevant disease parameters or clinical features such as the disease activity score 28 and radiosensitivity were assessed. RESULTS: Some oncological patients with RhD, especially those with connective tissue diseases have significantly higher radiosensitivity compared with oncology patients without RhD. In contrast, the mean radiosensitivity of the oncological patients with RA and other RhD and the non-oncological RA did not differ. 14 of the 44 examined oncological RA-patients (31.8%) had a high radiosensitivity which is defined as ≥ 0.5 breaks per metaphase. No correlation of laboratory parameters with radiosensitivity could be established. CONCLUSIONS: It would be recommended to perform radiosensitivity testing in patients with connective tissue diseases in general. We did not find a higher radiosensitivity in RA patients. In the group of RA patients with an oncological disease, a higher percentage of patients showed higher radiosensitivity, although the average radiosensitivity was not high.

Deep learning for automatic head and neck lymph node level delineation provides expert-level accuracy.

Background: Deep learning-based head and neck lymph node level (HN_LNL) autodelineation is of high relevance to radiotherapy research and clinical treatment planning but still underinvestigated in academic literature. In particular, there is no publicly available open-source solution for large-scale autosegmentation of HN_LNL in the research setting. Methods: An expert-delineated cohort of 35 planning CTs was used for training of an nnU-net 3D-fullres/2D-ensemble model for autosegmentation of 20 different HN_LNL. A second cohort acquired at the same institution later in time served as the test set (n = 20). In a completely blinded evaluation, 3 clinical experts rated the quality of deep learning autosegmentations in a head-to-head comparison with expert-created contours. For a subgroup of 10 cases, intraobserver variability was compared to the average deep learning autosegmentation accuracy on the original and recontoured set of expert segmentations. A postprocessing step to adjust craniocaudal boundaries of level autosegmentations to the CT slice plane was introduced and the effect of autocontour consistency with CT slice plane orientation on geometric accuracy and expert rating was investigated. Results: Blinded expert ratings for deep learning segmentations and expert-created contours were not significantly different. Deep learning segmentations with slice plane adjustment were rated numerically higher (mean, 81.0 vs. 79.6, p = 0.185) and deep learning segmentations without slice plane adjustment were rated numerically lower (77.2 vs. 79.6, p = 0.167) than manually drawn contours. In a head-to-head comparison, deep learning segmentations with CT slice plane adjustment were rated significantly better than deep learning contours without slice plane adjustment (81.0 vs. 77.2, p = 0.004). Geometric accuracy of deep learning segmentations was not different from intraobserver variability (mean Dice per level, 0.76 vs. 0.77, p = 0.307). Clinical significance of contour consistency with CT slice plane orientation was not represented by geometric accuracy metrics (volumetric Dice, 0.78 vs. 0.78, p = 0.703). Conclusions: We show that a nnU-net 3D-fullres/2D-ensemble model can be used for highly accurate autodelineation of HN_LNL using only a limited training dataset that is ideally suited for large-scale standardized autodelineation of HN_LNL in the research setting. Geometric accuracy metrics are only an imperfect surrogate for blinded expert rating.