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.

Keywords: Artificial intelligence; Hepatocellular carcinoma; Splenic volume; Transarterial chemoembolization.

Fig. 1

Flowchart of the patient selection process for this study

Fig. 2

The course of training of the convolutional neural network (A) ((left) Tversky loss values over the number of epochs; (right) Sørensen Dice Scores over the number of epochs; train set: 70 sets of manually segmented spleen data; test set: 30 different sets of manually segmented spleen data); Bland-Altman Plot shows the distribution of manually and automatically assessed splenic volumes (B)

Fig. 3

Representative images of the algorithm’s performance (from left to right images at upper, middle, and lower part of the spleen): A perfect segmentation, B acceptable segmentation (minor segmentation error medially), C poor segmentation (major segmentation error in the upper part with kissing liver and spleen phenomenon)

Fig. 4

Correlation between two-dimensional splenic measurements and splenic volume. A Axial spleen size; B craniocaudal spleen size

Fig. 5

A Kaplan–Meier survival curves show survival of patients with low (green) and high (red) splenic volumes (n = 327); B Kaplan–Meier survival curves show survival of patients with low (green) and high (red) splenic volume-to-BSA ratio (n = 289)

Fig. 6

Boxplot showing the distribution of the splenic volume among patients with a stable/decrease ALBI grade (green) and patients with an increased ALBI grade (red) 3 months after TACE