Fully automated AI-based splenic segmentation for predicting survival and estimating the risk of hepatic decompensation in TACE patients with HCC

Abstract

Objectives Splenic volume (SV) was proposed as a relevant prognostic factor for patients with hepatocellular carcinoma (HCC). We trained a deep-learning algorithm to fully automatically assess SV based on computed tomography (CT) scans. Then, we investigated SV as a prognostic factor for patients with HCC undergoing transarterial chemoembolization (TACE). Methods This retrospective study included 327 treatment-naïve patients with HCC undergoing initial TACE at our tertiary care center between 2010 and 2020. A convolutional neural network was trained and validated on the first 100 consecutive cases for spleen segmentation. Then, we used the algorithm to evaluate SV in all 327 patients. Subsequently, we evaluated correlations between SV and survival as well as the risk of hepatic decompensation during TACE. Results The algorithm showed Sørensen Dice Scores of 0.96 during both training and validation. In the remaining 227 patients assessed with the algorithm, spleen segmentation was visually approved in 223 patients (98.2%) and failed in four patients (1.8%), which required manual re-assessments. Mean SV was 551 ml. Survival was significantly lower in patients with high SV (10.9 months), compared to low SV (22.0 months, p = 0.001). In contrast, overall survival was not significantly predicted by axial and craniocaudal spleen diameter. Furthermore, patients with a hepatic decompensation after TACE had significantly higher SV (p < 0.001). Conclusion Automated SV assessments showed superior survival predictions in patients with HCC undergoing TACE compared to two-dimensional spleen size estimates and identified patients at risk of hepatic decompensation. Thus, SV could serve as an automatically available, currently underappreciated imaging biomarker. Key Points • Splenic volume is a relevant prognostic factor for prediction of survival in patients with HCC undergoing TACE, and should be preferred over two-dimensional surrogates for splenic size. • Besides overall survival, progression-free survival and hepatic decompensation were significantly associated with splenic volume, making splenic volume a currently underappreciated prognostic factor prior to TACE. • Splenic volume can be fully automatically assessed using deep-learning methods; thus, it is a promising imaging biomarker easily integrable into daily radiological routine.

Baseline Splenic Volume Outweighs Immuno-Modulated Size Changes with Regard to Survival Outcome in Patients with Hepatocellular Carcinoma under Immunotherapy

“…SV was assessed using an established tool for fully automated segmentation and volumetry of the spleen installed at our institution [ 15 ]. This algorithm employs the open-source MIScnn library, a convolutional neural network with a U-Net architecture, and has previously been trained for spleen segmentation in patients with HCC undergoing transarterial chemoembolization (TACE) [ 29 ].…”

“…This algorithm employs the open-source MIScnn library, a convolutional neural network with a U-Net architecture, and has previously been trained for spleen segmentation in patients with HCC undergoing transarterial chemoembolization (TACE) [ 29 ]. Detailed information on the features of the network, the settings for training and validation, and the model’s performance can be found in the original publication [ 15 ]. The output of the network consisted of graphic overlays, which were reviewed by two independent readers.…”

“…Consensus reading was performed in the case of discrepancies ( n = 2 (4.0%)). Patients with perfect or acceptable SVs were included in the statistical analyses ( n = 48); patients with a poor grade ( n = 2) were manually re-segmented to obtain the proper SV for further analyses as reported previously [ 15 ]. For manual segmentation, the freely available LIFEx software was used ( ) [ 30 ].…”

“…Splenic volume (SV) at baseline and during treatment has also been identified as a surrogate for CRPH in patients with HCC [ 10 ]. Furthermore, it is highly relevant for predicting the prognosis in patients with HCC undergoing curative and palliative treatment [ 11 , 12 , 13 , 14 , 15 ]. Novel AI-based methods enable a fully automated assessment of the SV using computed tomography (CT) data [ 15 , 16 ].…”

“…Furthermore, it is highly relevant for predicting the prognosis in patients with HCC undergoing curative and palliative treatment [ 11 , 12 , 13 , 14 , 15 ]. Novel AI-based methods enable a fully automated assessment of the SV using computed tomography (CT) data [ 15 , 16 ]. Thus, it can be considered a promising imaging biomarker with the potential for full integration into the routine radiology workflow.…”