Deep learning radio-clinical signature for predicting neoadjuvant chemotherapy response and prognosis from pretreatment CT images of locally advanced gastric cancer patients

Abstract

Background: Early noninvasive screening of patients who would benefit from neoadjuvant chemotherapy (NCT) is essential for personalized treatment of locally advanced gastric cancer (LAGC). The aim of this study was to identify radio-clinical signatures from pretreatment oversampled computed tomography (CT) images to predict the response to NCT and prognosis of LAGC patients. Methods: LAGC patients were retrospectively recruited from six hospitals from January 2008 to December 2021. An SE-ResNet50-based chemotherapy response prediction system was developed from pretreatment CT images preprocessed with an imaging oversampling method (i.e. DeepSMOTE). Then, the deep learning (DL) signature and clinic-based features were fed into the deep learning radio-clinical signature (DLCS). The predictive performance of the model was evaluated based on discrimination, calibration, and clinical usefulness. An additional model was built to predict overall survival (OS) and explore the survival benefit of the proposed DL signature and clinicopathological characteristics. Results: A total of 1060 LAGC patients were recruited from six hospitals; the training cohort (TC) and internal validation cohort (IVC) patients were randomly selected from center I. An external validation cohort (EVC) of 265 patients from five other centers was also included. The DLCS exhibited excellent performance in predicting the response to NCT in the IVC [area under the curve (AUC), 0.86] and EVC (AUC, 0.82), with good calibration in all cohorts ( P >0.05). Moreover, the DLCS model outperformed the clinical model ( P <0.05). Additionally, we found that the DL signature could serve as an independent factor for prognosis [hazard ratio (HR), 0.828, P =0.004]. The concordance index (C-index), integrated area under the time-dependent ROC curve (iAUC), and integrated Brier score (IBS) for the OS model were 0.64, 1.24, and 0.71 in the test set. Conclusion: The authors proposed a DLCS model that combined imaging features with clinical risk factors to accurately predict tumor response and identify the risk of OS in LAGC patients prior to NCT, which can then be used to guide personalized treatment plans with the help of computerized tumor-level characterization.

A CT-based deep learning model predicts overall survival in patients with muscle invasive bladder cancer after radical cystectomy: a multicenter retrospective cohort study

“…We then customized the loss function based on Cox partial likelihood, and constructed an end-to-end DL models to predict survival outcome. Previous studies suggested that attentional mechanisms, such as squeeze-and-excitation (SE) module and CBAM, may improve the prediction performance of convolutional neural networks 20 , 21 . Our results found that the CBAM-based DL model outperformed the traditional radiomics model and clinical model in predicting postcystectomy prognosis.…”

“…DL has even achieved excellent performance in medical image analysis tasks for various tumors for nearly a decade 17 – 19 . In addition, many studies have also found that attention-based convolutional neural network (CNN), which can focus the network’s attention on objects of interest, can achieve advanced performance in many tasks 20 , 21 . These technological advances in image analysis show promise in identifying tumor categories, differentiating pathological grades, predicting treatment efficacy, and may be helpful in risk stratification of patients with MIBC using preoperative enhanced CT and clinical data.…”

Assessing synchronous ovarian metastasis in gastric cancer patients using a clinical-radiomics nomogram based on baseline abdominal contrast-enhanced CT: a two-center study

“…Furthermore, deep learning tools were not developed and validated for the detection of SOM or even peritoneal metastasis [ 32 ]. This application of artificial intelligence method could be used to guide personalized treatment plans with the help of computerized tumor-level characterization [ 33 ]. Finally, this study did not include relevant molecular biological indicators.…”

Real-time and accurate estimation of surgical hemoglobin loss using deep learning-based medical sponges image analysis

“…The AUC was further improved to 0.84 after integrating SE CT and SE PET with stacked generalization, which is capable to predict the EGFR mutation status of patients with lung adenocarcinoma automatically and non-invasively 34 . Hu et.al also developed the SE-ResNet50-based chemotherapy response prediction system from pretreatment CT images preprocessed with an imaging oversampling method, and then the deep learning signature and clinic-based features were fed into the deep learning radio-clinical signature, which accurately predicts tumor response and identifies the risk of overall survival in locally advanced gastric cancer patient priors to neoadjuvant chemotherapy 35 . In addition, we have designed an interactive interface to further realize real-time and accurate surgical Hb loss.…”