Dataset Information

Computed tomography radiomics for the prediction of thymic epithelial tumor histology, TNM stage and myasthenia gravis.

ABSTRACT:

Objectives

To evaluate CT-derived radiomics for machine learning-based classification of thymic epithelial tumor (TET) stage (TNM classification), histology (WHO classification) and the presence of myasthenia gravis (MG).

Methods

Patients with histologically confirmed TET in the years 2000-2018 were retrospectively included, excluding patients with incompatible imaging or other tumors. CT scans were reformatted uniformly, gray values were normalized and discretized. Tumors were segmented manually; 15 scans were re-segmented after 2 weeks by two readers. 1316 radiomic features were calculated (pyRadiomics). Features with low intra-/inter-reader agreement (ICC<0.75) were excluded. Repeated nested cross-validation was used for feature selection (Boruta algorithm), model training, and evaluation (out-of-fold predictions). Shapley additive explanation (SHAP) values were calculated to assess feature importance.

Results

105 patients undergoing surgery for TET were identified. After applying exclusion criteria, 62 patients (28 female; mean age, 57±14 years; range, 22-82 years) with 34 low-risk TET (LRT; WHO types A/AB/B1), 28 high-risk TET (HRT; WHO B2/B3/C) in early stage (49, TNM stage I-II) or advanced stage (13, TNM III-IV) were included. 14(23%) of the patients had MG. 334(25%) features were excluded after intra-/inter-reader analysis. Discriminatory performance of the random forest classifiers was good for histology(AUC, 87.6%; 95% confidence interval, 76.3-94.3) and TNM stage(AUC, 83.8%; 95%CI, 66.9-93.4) but poor for the prediction of MG (AUC, 63.9%; 95%CI, 44.8-79.5).

Conclusions

CT-derived radiomic features may be a useful imaging biomarker for TET histology and TNM stage.

SUBMITTER: Bluthgen C

PROVIDER: S-EPMC8687592 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The thymus is involved in autoimmune Myasthenia gravis (MG) associated with anti-acetylcholine (AChR) antibodies. In MG, thymic regulatory T cells (Treg) are not efficiently suppressive, and conventional T cells (Tconv) are resistant to suppression. To better understand the specific role of the thymus in MG, we compared the phenotype and function of peripheral and thymic Treg and Tconv from controls and MG patients. Suppression assays with thymic or peripheral CD4 + T cells showed that the functional impairment in MG was more pronounced in the thymus than in the periphery. Phenotypic analysis of Treg showed a significant reduction of resting and effector Treg in the thymus but not in the periphery of MG patients. CD31, a marker lost with excessive immunoreactivity, was significantly reduced in thymic but not blood resting Treg. These results suggest that an altered thymic environment may explain Treg differences between MG patients and controls. Since thymic epithelial cells (TECs) play a major role in the generation of Treg, we co-cultured healthy thymic CD4 + T cells with control or MG TECs and tested their suppressive function. Co-culture with MG TECs consistently hampers regulatory activity, as compared with control TECs, suggesting that MG TECs contribute to the immune regulation defects of MG CD4 + T cells. MG TECs produced significantly higher thymic stromal lymphopoietin (TSLP) than control TECs, and a neutralizing anti-TSLP antibody partially restored the suppressive capacity of Treg derived from co-cultures with MG TECs, suggesting that TSLP contributed to the defect of thymic Treg in MG patients. Finally, a co-culture of MG CD4 + T cells with control TECs restored numbers and function of MG Treg, demonstrating that a favorable environment could correct the immune regulation defects of T cells in MG. Altogether, our data suggest that the severe defect of thymic Treg is at least partially due to MG TECs that overproduce TSLP. The Treg defects could be corrected by replacing dysfunctional TECs by healthy TECs. These findings highlight the role of the tissue environment on the immune regulation.

Project description:In the present study, we aimed to construct a radiomics model using contrast‑enhanced computed tomography (CT) to predict the pathological invasiveness of thymic epithelial tumors (TETs). We retrospectively reviewed the records of 179 consecutive patients (89 females) with histologically confirmed TETs from two hospitals. The 82 low‑ and 97 high‑risk TETs were assigned to training (90 tumors), internal validation (49 tumors) and external validation (40 tumors) cohorts. Radiomics features extracted from preoperative contrast‑enhanced chest CT were selected using least absolute shrinkage and selection operator logistic regression. Three prediction models were developed using multivariate logistic regression analysis. Their performance and clinical utility were assessed using receiver operating characteristic curves and the DeLong test, respectively. Eight radiomics features with non‑zero coefficients were used to develop a radiomics score, which significantly differed between low‑ and high‑risk TETs (P<0.001). The subjective finding, infiltration, was independently associated with high‑risk TETs. Prediction models based on infiltration alone, the radiomics signature alone, and both these parameters showed diagnostic accuracies of 72.2% [area under curve (AUC), 0.731; 95% confidence interval (CI): 0.627‑0.819; sensitivity, 85.7%; specificity, 60.4%], 88.9% (AUC, 0.944; 95% CI: 0.874‑0.981; sensitivity, 92.9%; specificity, 85.4%), and 90.0% (AUC, 0.953; 95% CI: 0.887‑0.987; sensitivity, 92.9%; specificity, 87.5%), respectively. Decision‑curve analysis showed that the combined model added more net benefit than the single‑parameter models. In conclusion, a radiomics signature based on contrast‑enhanced CT has the potential to differentiate between low‑ and high‑risk TETs. The model incorporating the radiomics signature and subjective finding may facilitate the individualized, preoperative prediction of the pathological invasiveness of TETs.