A nomogram incorporating CT-based peri-hematoma radiomics features to predict functional outcome in patients with intracerebral hemorrhage.

OBJECTIVE

To evaluate the ability of non-contrast computed tomography based peri-hematoma and intra-hematoma radiomic features to predict the 90-day poor functional outcome for spontaneous intracerebral hemorrhage (sICH) and to present an effective clinically relevant machine learning system to assist in prognosis prediction.

MATERIALS AND METHODS

We retrospectively analyzed the data of 691 patients diagnosed with sICH at two medical centers. Fifteen radiomic features from the intra- and peri-hematoma regions were extracted and selected to build six radiomics models. The clinical-semantic model and nomogram model were constructed to compare prediction abilities. The areas under the curve (AUC) and decision curve analysis were used to evaluate discriminative performance.

RESULTS

Combining radiomics of the intra-hematoma with peri-hematoma regions significantly improved the AUC to 0.843 compared with radiomics of the intra-hematoma region (AUC = 0.780, P ＜ 0.001) in the test set. A similar trend was observed in the external validation cohort (AUC, 0.769 vs. 0.793, P = 0.709). The nomogram, which integrates clinical-semantic signatures with intra-hematoma and peri-hematoma radiomics signatures, accurately predicted a 90-day poor functional outcome in both the test and external validation sets (AUC 0.879 and 0.901, respectively).

CONCLUSION

The nomogram constructed using clinical-semantic signatures and combined intra-hematoma and peri-hematoma radiomics signatures showed the potential to precisely predict 90-day poor functional outcomes for sICH.