Purpose:
We sought to train and validate an automated machine learning algorithm for intracerebral hemorrhage (ICH) segmentation and volume calculation using multicenter data.

Materials and Methods:
An open-source 3D deep machine learning algorithm "DeepMedic" was trained using manually segmented ICH from 208 CT scans (129 patients) from the multicenter PREDICT study. The algorithm was then validated with 215 manually segmented CT scans (97 patients) from the SPOTLIGHT and STOP-IT studies. Manual segmentation was performed with Quantomo semiautomated software. ABC/2 was measured for all studies by two neuroradiologists. Accuracy of DeepMedic segmentation was assessed using the Dice similarity coefficient. Intraclass correlation (ICC) with 95% confidence intervals (CI) assessed agreement between manual vs. DeepMedic segmentation volume; and manual segmentation and ABC/2 volume. Bland-Altman charts were analyzed for ABC/2 and DeepMedic vs. manual segmentation volumes.

Results:
DeepMedic demonstrated high segmentation accuracy in the training cohort (median Dice 0.96; IQR 0.95 - 0.97) and in the validation cohort (median Dice 0.91; IQR 0.86 - 0.94). Agreement was significantly better between DeepMedic and manual segmentation (PREDICT: ICC 0.99 [95%CI 0.99 -1.00]; SPOTLIGHT/STOPIT: ICC 0.96 [95%CI 0.95 - 0.97]) than between ABC/2 and manual segmentation (PREDICT: ICC 0.92 [95%CI 0.89 - 0.95]; SPOTLIGHT/STOPIT: ICC 0.92 [95%CI 0.90-0.94]). Improved accuracy of DeepMedic was demonstrated in Bland-Altman charts.

Conclusions:
ICH machine learning segmentation with DeepMedic is feasible, accurate, and demonstrates greater agreement with manual segmentation compared to ABC/2 volumes.

Training and Validation of DeepMedic Machine Learning Tool for Automated Intracerebral Hemorrhage Segmentation and Volume Analysis on CT Using Multicenter Data

[Virtual Conference Page](https://event.vconferenceonline.com/microsite/html/login.aspx?id=1551&rlp=1)

[ASNR Website] (https://www.asnr.org//annualmeeting)

[Educational Exhibits](https://www.morressier.com/event/asnr2020exhibit/5e5d0be000701ceba4a26941)