Dataset Information

CT-based multimodal deep learning for non-invasive overall survival prediction in advanced hepatocellular carcinoma patients treated with immunotherapy.

ABSTRACT:

Objectives

To develop a deep learning model combining CT scans and clinical information to predict overall survival in advanced hepatocellular carcinoma (HCC).

Methods

This retrospective study included immunotherapy-treated advanced HCC patients from 52 multi-national in-house centers between 2018 and 2022. A multi-modal prognostic model using baseline and the first follow-up CT images and 7 clinical variables was proposed. A convolutional-recurrent neural network (CRNN) was developed to extract spatial-temporal information from automatically selected representative 2D CT slices to provide a radiological score, then fused with a Cox-based clinical score to provide the survival risk. The model's effectiveness was assessed using a time-dependent area under the receiver operating curve (AUC), and risk group stratification using the log-rank test. Prognostic performances of multi-modal inputs were compared to models of missing modality, and the size-based RECIST criteria.

Results

Two-hundred seven patients (mean age, 61 years ± 12 [SD], 180 men) were included. The multi-modal CRNN model reached the AUC of 0.777 and 0.704 of 1-year overall survival predictions in the validation and test sets. The model achieved significant risk stratification in validation (hazard ratio [HR] = 3.330, p = 0.008), and test sets (HR = 2.024, p = 0.047) based on the median risk score of the training set. Models with missing modalities (the single-modal imaging-based model and the model incorporating only baseline scans) can still achieve favorable risk stratification performance (all p < 0.05, except for one, p = 0.053). Moreover, results proved the superiority of the deep learning-based model to the RECIST criteria.

Conclusion

Deep learning analysis of CT scans and clinical data can offer significant prognostic insights for patients with advanced HCC.

Critical relevance statement

The established model can help monitor patients' disease statuses and identify those with poor prognosis at the time of first follow-up, helping clinicians make informed treatment decisions, as well as early and timely interventions.

Key points

An AI-based prognostic model was developed for advanced HCC using multi-national patients. The model extracts spatial-temporal information from CT scans and integrates it with clinical variables to prognosticate. The model demonstrated superior prognostic ability compared to the conventional size-based RECIST method.

SUBMITTER: Xia Y

PROVIDER: S-EPMC11347550 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

CT-based multimodal deep learning for non-invasive overall survival prediction in advanced hepatocellular carcinoma patients treated with immunotherapy.

Xia Yujia Y Zhou Jie J Xun Xiaolei X Zhang Jin J Wei Ting T Gao Ruitian R Reddy Bobby B Liu Chao C Kim Geoffrey G Yu Zhangsheng Z

Insights into imaging 20240826 1

<h4>Objectives</h4>To develop a deep learning model combining CT scans and clinical information to predict overall survival in advanced hepatocellular carcinoma (HCC).<h4>Methods</h4>This retrospective study included immunotherapy-treated advanced HCC patients from 52 multi-national in-house centers between 2018 and 2022. A multi-modal prognostic model using baseline and the first follow-up CT images and 7 clinical variables was proposed. A convolutional-recurrent neural network (CRNN) was devel ...[more]

PMID: 39186192

Similar Datasets

Project description:BackgroundLung cancer (LC) is a leading cause of cancer-related mortality, and immunotherapy (IO) has shown promise in treating advanced-stage LC. However, identifying patients likely to benefit from IO and monitoring treatment response remains challenging. This study aims to develop a predictive model for progression-free survival (PFS) in LC patients with IO based on clinical features and advanced imaging biomarkers.Materials and methodsA retrospective analysis was conducted on a cohort of 206 LC patients receiving IO treatment. Pre-treatment computed tomography images were used to extract advanced imaging biomarkers, including intratumoral and peritumoral-vasculature radiomics. Clinical features, including age, gene status, hematology, and staging, were also collected. Key radiomic and clinical features for predicting IO outcomes were identified using a two-step feature selection process, including univariate Cox regression and chi-squared test, followed by sequential forward selection. The DeepSurv model was constructed to predict PFS based on clinical and radiomic features. Model performance was evaluated using the area under the time-dependent receiver operating characteristic curve (AUC) and concordance index (C-index).ResultsCombining radiomics of intratumoral heterogeneity and peritumoral-vasculature with clinical features demonstrated a significant enhancement (p < 0.001) in predicting IO response. The proposed DeepSurv model exhibited a prediction performance with AUCs ranging from 0.76 to 0.80 and a C-index of 0.83. Furthermore, the predicted personalized PFS curves revealed a significant difference (p < 0.05) between patients with favorable and unfavorable prognoses.ConclusionsIntegrating intratumoral and peritumoral-vasculature radiomics with clinical features enabled the development of a predictive model for PFS in LC patients with IO. The proposed model's capability to estimate individualized PFS probability and differentiate the prognosis status held promise to facilitate personalized medicine and improve patient outcomes in LC.

Project description:IntroductionFirst-line systemic therapy (ST) options for advanced hepatocellular carcinoma (HCC) include tyrosine kinase inhibitors and immunotherapy (IO). Evolving data suggest prolonged overall survival (OS) when ST is combined with stereotactic body radiation therapy (SBRT), although evidence is significantly limited in HCC populations. We hypothesized that advanced HCC patients in the National Cancer Database (NCDB) would have improved OS when receiving ST+SBRT vs ST alone.MethodsStage III/IV HCC patients diagnosed from 2010-2020 and treated with first-line ST±SBRT were identified from the NCDB. The primary endpoint was OS from date of diagnosis stratified by the receipt of SBRT (ST+SBRT vs ST alone). Survival was estimated using Kaplan-Meier methodology and compared via log-rank. Multivariate analysis (MVA) was performed by Cox regression.ResultsOf 10,505 eligible patients with stage III disease, 115 (1.1%) received ST+SBRT and 10,390 (98.9%) received ST alone. Of 9,617 eligible patients with stage IV disease, 127 (1.3%) received ST+SBRT and 9,490 (98.7%) received ST alone. Median follow-up time was 6.8 months. Baseline characteristics were similar between cohorts. Patients with stage III disease receiving ST+SBRT had improved median OS (12.62 months vs 8.38 months) and higher rates of survival at 1-year (53.0% vs 38.7%) and 2-years (27.0% vs 20.7%) compared to those receiving ST alone (log-rank P=0.0054). Similarly, patients with stage IV disease receiving ST+SBRT had improved median OS (11.79 months vs 5.72 months) and higher rates of survival at 1-year (49.6% vs 26.2%) and 2-years (23.6% vs 12.0%) (log-rank P<0.0001). On MVA, receipt of SBRT predicted improved OS (HR=0.748, 95%CI 0.588-0.951; P=0.0178) and receipt of IO trended towards improved OS (HR=0.859, 95%CI 0.735-1.003; P=0.0538).ConclusionIn advanced HCC, patients receiving ST+SBRT had improved OS compared to those receiving ST alone. Prospective clinical trials are warranted to better identify HCC populations which may benefit from combined modality therapy.

Dataset Information

CT-based multimodal deep learning for non-invasive overall survival prediction in advanced hepatocellular carcinoma patients treated with immunotherapy.

Objectives

Methods

Results

Conclusion

Critical relevance statement

Key points

Publications

CT-based multimodal deep learning for non-invasive overall survival prediction in advanced hepatocellular carcinoma patients treated with immunotherapy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets