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

Deep learning progressive distill for predicting clinical response to conversion therapy from preoperative CT images of advanced gastric cancer patients

BACKGROUND AND OBJECTIVE

Identifying patients suitable for conversion therapy through early non-invasive screening is crucial for tailoring treatment in advanced gastric cancer (AGC). This study aimed to develop and validate a deep learning method, utilizing preoperative computed tomography (CT) images, to predict the response to conversion therapy in AGC patients. This retrospective study involved 140 patients. We utilized Progressive Distill (PD) methodology to construct a deep learning model for predicting clinical response to conversion therapy based on preoperative CT images. Patients in the training set (n = 112) and in the test set (n = 28) were sourced from The First Affiliated Hospital of Wenzhou Medical University between September 2017 and November 2023. Our PD models' performance was compared with baseline models and those utilizing Knowledge Distillation (KD), with evaluation metrics including accuracy, sensitivity, specificity, receiver operating characteristic curves, areas under the receiver operating characteristic curve (AUCs), and heat maps. The PD model exhibited the best performance, demonstrating robust discrimination of clinical response to conversion therapy with an AUC of 0.99 and accuracy of 99.11% in the training set, and 0.87 AUC and 85.71% accuracy in the test set. Sensitivity and specificity were 97.44% and 100% respectively in the training set, 85.71% and 85.71% each in the test set, suggesting absence of discernible bias. The deep learning model of PD method accurately predicts clinical response to conversion therapy in AGC patients. Further investigation is warranted to assess its clinical utility alongside clinicopathological parameters.

The artificial intelligence revolution in gastric cancer management: clinical applications

Nowadays, gastric cancer has become a significant issue in the global cancer burden, and its impact cannot be ignored. The rapid development of artificial intelligence technology is attempting to address this situation, aiming to change the clinical management landscape of gastric cancer fundamentally. In this transformative change, machine learning and deep learning, as two core technologies, play a pivotal role, bringing unprecedented innovations and breakthroughs in the diagnosis, treatment, and prognosis evaluation of gastric cancer. This article comprehensively reviews the latest research status and application of artificial intelligence algorithms in gastric cancer, covering multiple dimensions such as image recognition, pathological analysis, personalized treatment, and prognosis risk assessment. These applications not only significantly improve the sensitivity of gastric cancer risk monitoring, the accuracy of diagnosis, and the precision of survival prognosis but also provide robust data support and a scientific basis for clinical decision-making. The integration of artificial intelligence, from optimizing the diagnosis process and enhancing diagnostic efficiency to promoting the practice of precision medicine, demonstrates its promising prospects for reshaping the treatment model of gastric cancer. Although most of the current AI-based models have not been widely used in clinical practice, with the continuous deepening and expansion of precision medicine, we have reason to believe that a new era of AI-driven gastric cancer care is approaching.

Carcinoembryonic antigen trajectory predicts pathological complete response in advanced gastric cancer after neoadjuvant chemotherapy

Aims

This study aims to develop a simple, clinically applicable classification system to predict pCR based on carcinoembryonic antigen (CEA) trajectory during NAC.

Methods

This study included 366 AGC patients who received NAC followed by radical gastrectomy. CEA levels were measured before, during, and after NAC, with changes classified into three trajectory types: Type I (>=80% decline), Type II (>=40% but <80% decline), and Type III (<40% decline or increase). We analyzed associations between these CEA trajectories, pCR, lymph node remission, and survival.

Results

pCR was achieved in 10.4% (38/366) of patients. pCR rates were significantly higher in Type I (41%) and Type II (15.8%) trajectories compared to Type III (6.7%). Lymph node remission also correlated with CEA trajectories, with Type I having the highest proportion of ypN0 (79.2%). Multivariate analysis identified CEA trajectory subtypes and tumor differentiation as independent predictors of pCR. This classification system proved robust across subgroups. Although no significant differences in overall survival were observed between subtypes, higher initial CEA levels were associated with worse survival.

Conclusion

The trajectory of CEA change during NAC is a promising predictor of pCR in AGC. This simple and accessible classification system may facilitate personalized surgical strategies for patients with AGC.

Clinical Applications of Artificial Intelligence (AI) in Human Cancer: Is It Time to Update the Diagnostic and Predictive Models in Managing Hepatocellular Carcinoma (HCC)?

In recent years, novel findings have progressively and promisingly supported the potential role of Artificial intelligence (AI) in transforming the management of various neoplasms, including hepatocellular carcinoma (HCC). HCC represents the most common primary liver cancer. Alarmingly, the HCC incidence is dramatically increasing worldwide due to the simultaneous "pandemic" spreading of metabolic dysfunction-associated steatotic liver disease (MASLD). MASLD currently constitutes the leading cause of chronic hepatic damage (steatosis and steatohepatitis), fibrosis, and liver cirrhosis, configuring a scenario where an HCC onset has been reported even in the early disease stage. On the other hand, HCC represents a serious plague, significantly burdening the outcomes of chronic hepatitis B (HBV) and hepatitis C (HCV) virus-infected patients. Despite the recent progress in the management of this cancer, the overall prognosis for advanced-stage HCC patients continues to be poor, suggesting the absolute need to develop personalized healthcare strategies further. In this "cold war", machine learning techniques and neural networks are emerging as weapons, able to identify the patterns and biomarkers that would have normally escaped human observation. Using advanced algorithms, AI can analyze large volumes of clinical data and medical images (including routinely obtained ultrasound data) with an elevated accuracy, facilitating early diagnosis, improving the performance of predictive models, and supporting the multidisciplinary (oncologist, gastroenterologist, surgeon, radiologist) team in opting for the best "tailored" individual treatment. Additionally, AI can significantly contribute to enhancing the effectiveness of metabolomics-radiomics-based models, promoting the identification of specific HCC-pathogenetic molecules as new targets for realizing novel therapeutic regimens. In the era of precision medicine, integrating AI into routine clinical practice appears as a promising frontier, opening new avenues for liver cancer research and treatment.

Evaluation of EGFR-TKIs and ICIs treatment stratification in non-small cell lung cancer using an encrypted multidimensional radiomics approach

BACKGROUND

Radiomics holds great potential for the noninvasive evaluation of EGFR-TKIs and ICIs responses, but data privacy and model robustness challenges limit its current efficacy and safety. This study aims to develop and validate an encrypted multidimensional radiomics approach to enhance the stratification and analysis of therapeutic responses.

MATERIALS AND METHODS

This multicenter study incorporated various data types from 506 NSCLC patients, which underwent preprocessing through anonymization methods and were securely encrypted using the AES-CBC algorithm. We developed one clinical model and three radiomics models based on clinical factors and radiomics scores (RadScore) of three distinct regions to evaluate treatment response. Additionally, an integrated radiomics-clinical model was created by combining clinical factors with RadScore. The study also explored the association between different EGFR mutations and PD-1/PD-L1 expression in radiomics biomarkers.

FINDINGS

The radiomics-clinical model demonstrated high performance, with AUC values as follows: EGFR (0.884), 19Del (0.894), L858R (0.881), T790M (0.900), and PD-1/PD-L1 expression (0.893) in the test set. This model outperformed both clinical and single radiomics models. Decision curve analysis further supported its superior clinical utility. Additionally, our findings suggest that the efficacy of EGFR-TKIs and ICIs therapy may not depend on detecting a singular tumor feature or cell type.

CONCLUSION

The proposed method effectively balances the level of evidence with privacy protection, enhancing the study's validity and security. Therefore, radiomics biomarkers are expected to complement molecular biology analyses and guide therapeutic strategies for EGFR-TKIs, ICIs, and their combinations.

Development and validation of a deep learning model for predicting gastric cancer recurrence based on CT imaging: a multicenter study

INTRODUCTION

The postoperative recurrence of gastric cancer (GC) has a significant impact on the overall prognosis of patients. Therefore, accurately predicting the postoperative recurrence of GC is crucial.

METHODS

This retrospective study gathered data from 2813 GC patients who underwent radical surgery between 2011 and 2017 at two medical centers. Follow-up was extended until May 2023, and cases were categorized as recurrent or nonrecurrent based on postoperative outcomes. Clinical pathological information and imaging data were collected for all patients. A new deep learning signature (DLS) was generated using pretreatment computed tomography images, based on a pretrained baseline (a customized Resnet50), for predicting postoperative recurrence. The deep learning fusion signature (DLFS) was created by combining the score of DLS with the weighted values of identified clinical features. The predictive performance of the model was evaluated based on discrimination, calibration, and clinical usefulness. Survival curves were plotted to investigate the differences between DLFS and prognosis.

RESULTS

In this study, 2813 patients with GC were recruited and allocated into training, internal validation, and external validation cohorts. The DLFS was developed and assessed for its capability in predicting the risk of postoperative recurrence. The DLFS exhibited excellent performance with AUCs of 0.833 (95% CI: 0.809-0.858) in the training set, 0.831 (95% CI: 0.792-0.871) in the internal validation set, and 0.859 (95% CI: 0.806-0.912) in the external validation set, along with satisfactory calibration across all cohorts ( P >0.05). Furthermore, the DLFS model significantly outperformed both the clinical model and DLS ( P <0.05). High-risk recurrent patients exhibit a significantly poorer prognosis compared to low-risk recurrent patients ( P <0.05).

CONCLUSIONS

The integrated model developed in this study, focusing on GC patients undergoing radical surgery, accurately identifies cases at high-risk of postoperative recurrence and highlights the potential of DLFS as a prognostic factor for GC patients.

Radiomics predicts the prognosis of patients with clear cell renal cell carcinoma by reflecting the tumor heterogeneity and microenvironment

PURPOSE

We aimed to develop and externally validate a CT-based deep learning radiomics model for predicting overall survival (OS) in clear cell renal cell carcinoma (ccRCC) patients, and investigate the association of radiomics with tumor heterogeneity and microenvironment.

METHODS

The clinicopathological data and contrast-enhanced CT images of 512 ccRCC patients from three institutions were collected. A total of 3566 deep learning radiomics features were extracted from 3D regions of interest. We generated the deep learning radiomics score (DLRS), and validated this score using an external cohort from TCIA. Patients were divided into high and low-score groups by the DLRS. Sequencing data from the corresponding TCGA cohort were used to reveal the differences of tumor heterogeneity and microenvironment between different radiomics score groups. What's more, univariate and multivariate Cox regression were used to identify independent risk factors of poor OS after operation. A combined model was developed by incorporating the DLRS and clinicopathological features. The SHapley Additive exPlanation method was used for interpretation of predictive results.

RESULTS

At multivariate Cox regression analysis, the DLRS was identified as an independent risk factor of poor OS. The genomic landscape of different radiomics score groups was investigated. The heterogeneity of tumor cell and tumor microenvironment significantly varied between both groups. In the test cohort, the combined model had a great predictive performance, with AUCs (95%CI) for 1, 3 and 5-year OS of 0.879(0.868-0.931), 0.854(0.819-0.899) and 0.831(0.813-0.868), respectively. There was a significant difference in survival time between different groups stratified by the combined model. This model showed great discrimination and calibration, outperforming the existing prognostic models (all p values < 0.05).

CONCLUSION

The combined model allowed for the prognostic prediction of ccRCC patients by incorporating the DLRS and significant clinicopathologic features. The radiomics features could reflect the tumor heterogeneity and microenvironment.

Predicting gastric cancer response to anti-HER2 therapy or anti-HER2 combined immunotherapy based on multi-modal data

The sole use of single modality data often fails to capture the complex heterogeneity among patients, including the variability in resistance to anti-HER2 therapy and outcomes of combined treatment regimens, for the treatment of HER2-positive gastric cancer (GC). This modality deficit has not been fully considered in many studies. Furthermore, the application of artificial intelligence in predicting the treatment response, particularly in complex diseases such as GC, is still in its infancy. Therefore, this study aimed to use a comprehensive analytic approach to accurately predict treatment responses to anti-HER2 therapy or anti-HER2 combined immunotherapy in patients with HER2-positive GC. We collected multi-modal data, comprising radiology, pathology, and clinical information from a cohort of 429 patients: 310 treated with anti-HER2 therapy and 119 treated with a combination of anti-HER2 and anti-PD-1/PD-L1 inhibitors immunotherapy. We introduced a deep learning model, called the Multi-Modal model (MuMo), that integrates these data to make precise treatment response predictions. MuMo achieved an area under the curve score of 0.821 for anti-HER2 therapy and 0.914 for combined immunotherapy. Moreover, patients classified as low-risk by MuMo exhibited significantly prolonged progression-free survival and overall survival (log-rank test, P < 0.05). These findings not only highlight the significance of multi-modal data analysis in enhancing treatment evaluation and personalized medicine for HER2-positive gastric cancer, but also the potential and clinical value of our model.

Screening of gastric cancer diagnostic biomarkers in the homologous recombination signaling pathway and assessment of their clinical and radiomic correlations

BACKGROUND

Homologous recombination plays a vital role in the occurrence and drug resistance of gastric cancer. This study aimed to screen new gastric cancer diagnostic biomarkers in the homologous recombination pathway and then used radiomic features to construct a prediction model of biomarker expression to guide the selection of chemotherapy regimens.

METHODS

Gastric cancer transcriptome data were downloaded from The Cancer Genome Atlas database. Machine learning methods were used to screen for diagnostic biomarkers of gastric cancer and validate them experimentally. Computed Tomography image data of gastric cancer patients and corresponding clinical data were downloaded from The Cancer Imaging Archive and our imaging centre, and then the Computed Tomography images were subjected to feature extraction, and biomarker expression prediction models were constructed to analyze the correlation between the biomarker radiomics scores and clinicopathological features.

RESULTS

We screened RAD51D and XRCC2 in the homologous recombination pathway as biomarkers for gastric cancer diagnosis by machine learning, and the expression of RAD51D and XRCC2 was significantly positively correlated with pathological T stage, N stage, and TNM stage. Homologous recombination pathway blockade inhibits gastric cancer cell proliferation, promotes apoptosis, and reduces the sensitivity of gastric cancer cells to chemotherapeutic drugs. Our predictive RAD51D and XRCC2 expression models were constructed using radiomics features, and all the models had high accuracy. In the external validation cohort, the predictive models still had decent accuracy. Moreover, the radiomics scores of RAD51D and XRCC2 were also significantly positively correlated with the pathologic T, N, and TNM stages.

CONCLUSIONS

The gastric cancer diagnostic biomarkers RAD51D and XRCC2 that we screened can, to a certain extent, reflect the expression status of genes through radiomic characteristics, which is of certain significance in guiding the selection of chemotherapy regimens for gastric cancer patients.

Predicting bone metastasis-free survival in non-small cell lung cancer from preoperative CT via deep learning

Accurate prediction of bone metastasis-free survival (BMFS) after complete surgical resection in patients with non-small cell lung cancer (NSCLC) may facilitate appropriate follow-up planning. The aim of this study was to establish and validate a preoperative CT-based deep learning (DL) signature to predict BMFS in NSCLC patients. We performed a retrospective analysis of 1547 NSCLC patients who underwent complete surgical resection, followed by at least 36 months of monitoring at two hospitals. We constructed a DL signature from multiparametric CT images using 3D convolutional neural networks, and we integrated this signature with clinical-imaging factors to establish a deep learning clinical-imaging signature (DLCS). We evaluated performance using Harrell's concordance index (C-index) and the time-dependent receiver operating characteristic. We also assessed the risk of bone metastasis (BM) in NSCLC patients at different clinical stages using DLCS. The DL signature successfully predicted BM, with C-indexes of 0.799 and 0.818 for the validation cohorts. DLCS outperformed the DL signature with corresponding C-indexes of 0.806 and 0.834. Ranges for area under the curve at 1, 2, and 3 years were 0.820-0.865 for internal and 0.860-0.884 for external validation cohorts. Furthermore, DLCS successfully stratified patients with different clinical stages of NSCLC as high- and low-risk groups for BM (p < 0.05). CT-based DL can predict BMFS in NSCLC patients undergoing complete surgical resection, and may assist in the assessment of BM risk for patients at different clinical stages.

Deep learning or radiomics based on CT for predicting the response of gastric cancer to neoadjuvant chemotherapy: a meta-analysis and systematic review

Background

Artificial intelligence (AI) models, clinical models (CM), and the integrated model (IM) are utilized to evaluate the response to neoadjuvant chemotherapy (NACT) in patients diagnosed with gastric cancer.

Objective

The objective is to identify the diagnostic test of the AI model and to compare the accuracy of AI, CM, and IM through a comprehensive summary of head-to-head comparative studies.

Methods

PubMed, Web of Science, Cochrane Library, and Embase were systematically searched until September 5, 2023, to compile English language studies without regional restrictions. The quality of the included studies was evaluated using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) criteria. Forest plots were utilized to illustrate the findings of diagnostic accuracy, while Hierarchical Summary Receiver Operating Characteristic curves were generated to estimate sensitivity (SEN) and specificity (SPE). Meta-regression was applied to analyze heterogeneity across the studies. To assess the presence of publication bias, Deeks' funnel plot and an asymmetry test were employed.

Results

A total of 9 studies, comprising 3313 patients, were included for the AI model, with 7 head-to-head comparative studies involving 2699 patients. Across the 9 studies, the pooled SEN for the AI model was 0.75 (95% confidence interval (CI): 0.66, 0.82), and SPE was 0.77 (95% CI: 0.69, 0.84). Meta-regression was conducted, revealing that the cut-off value, approach to predicting response, and gold standard might be sources of heterogeneity. In the head-to-head comparative studies, the pooled SEN for AI was 0.77 (95% CI: 0.69, 0.84) with SPE at 0.79 (95% CI: 0.70, 0.85). For CM, the pooled SEN was 0.67 (95% CI: 0.57, 0.77) with SPE at 0.59 (95% CI: 0.54, 0.64), while for IM, the pooled SEN was 0.83 (95% CI: 0.79, 0.86) with SPE at 0.69 (95% CI: 0.56, 0.79). Notably, there was no statistical difference, except that IM exhibited higher SEN than AI, while maintaining a similar level of SPE in pairwise comparisons. In the Receiver Operating Characteristic analysis subgroup, the CT-based Deep Learning (DL) subgroup, and the National Comprehensive Cancer Network (NCCN) guideline subgroup, the AI model exhibited higher SEN but lower SPE compared to the IM. Conversely, in the training cohort subgroup and the internal validation cohort subgroup, the AI model demonstrated lower SEN but higher SPE than the IM. The subgroup analysis underscored that factors such as the number of cohorts, cohort type, cut-off value, approach to predicting response, and choice of gold standard could impact the reliability and robustness of the results.

Conclusion

AI has demonstrated its viability as a tool for predicting the response of GC patients to NACT Furthermore, CT-based DL model in AI was sensitive to extract tumor features and predict the response. The results of subgroup analysis also supported the above conclusions. Large-scale rigorously designed diagnostic accuracy studies and head-to-head comparative studies are anticipated.

Systematic review registration

PROSPERO, CRD42022377030.

Deep learning-based clinical-radiomics nomogram for preoperative prediction of lymph node metastasis in patients with rectal cancer: a two-center study

Background

Precise preoperative evaluation of lymph node metastasis (LNM) is crucial for ensuring effective treatment for rectal cancer (RC). This research aims to develop a clinical-radiomics nomogram based on deep learning techniques, preoperative magnetic resonance imaging (MRI) and clinical characteristics, enabling the accurate prediction of LNM in RC.

Materials and methods

Between January 2017 and May 2023, a total of 519 rectal cancer cases confirmed by pathological examination were retrospectively recruited from two tertiary hospitals. A total of 253 consecutive individuals were selected from Center I to create an automated MRI segmentation technique utilizing deep learning algorithms. The performance of the model was evaluated using the dice similarity coefficient (DSC), the 95th percentile Hausdorff distance (HD95), and the average surface distance (ASD). Subsequently, two external validation cohorts were established: one comprising 178 patients from center I (EVC1) and another consisting of 88 patients from center II (EVC2). The automatic segmentation provided radiomics features, which were then used to create a Radscore. A predictive nomogram integrating the Radscore and clinical parameters was constructed using multivariate logistic regression. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were employed to evaluate the discrimination capabilities of the Radscore, nomogram, and subjective evaluation model, respectively.

Results

The mean DSC, HD95 and ASD were 0.857 ± 0.041, 2.186 ± 0.956, and 0.562 ± 0.194 mm, respectively. The nomogram, which incorporates MR T-stage, CEA, CA19-9, and Radscore, exhibited a higher area under the ROC curve (AUC) compared to the Radscore and subjective evaluation in the training set (0.921 vs. 0.903 vs. 0.662). Similarly, in both external validation sets, the nomogram demonstrated a higher AUC than the Radscore and subjective evaluation (0.908 vs. 0.735 vs. 0.640, and 0.884 vs. 0.802 vs. 0.734).

Conclusion

The application of the deep learning method enables efficient automatic segmentation. The clinical-radiomics nomogram, utilizing preoperative MRI and automatic segmentation, proves to be an accurate method for assessing LNM in RC. This approach has the potential to enhance clinical decision-making and improve patient care.

Research registration unique identifying number UIN

Research registry, identifier 9158, https://www.researchregistry.com/browse-the-registry#home/registrationdetails/648e813efffa4e0028022796/.

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

Real-time and accurate estimation of surgical hemoglobin (Hb) loss is essential for fluid resuscitation management and evaluation of surgical techniques. In this study, we aimed to explore a novel surgical Hb loss estimation method using deep learning-based medical sponges image analysis. Whole blood samples of pre-measured Hb concentration were collected, and normal saline was added to simulate varying levels of Hb concentration. These blood samples were distributed across blank medical sponges to generate blood-soaked sponges. Eight hundred fifty-one blood-soaked sponges representing a wide range of blood dilutions were randomly divided 7:3 into a training group (n = 595) and a testing group (n = 256). A deep learning model based on the YOLOv5 network was used as the target region extraction and detection, and the three models (Feature extraction technology, ResNet-50, and SE-ResNet50) were trained to predict surgical Hb loss. Mean absolute error (MAE), mean absolute percentage error (MAPE), coefficient (R2) value, and the Bland-Altman analysis were calculated to evaluate the predictive performance in the testing group. The deep learning model based on SE-ResNet50 could predict surgical Hb loss with the best performance (R2 = 0.99, MAE = 11.09 mg, MAPE = 8.6%) compared with other predictive models, and Bland-Altman analysis also showed a bias of 1.343 mg with narrow limits of agreement (- 29.81 to 32.5 mg) between predictive and actual Hb loss. The interactive interface was also designed to display the real-time prediction of surgical Hb loss more intuitively. Thus, it is feasible for real-time estimation of surgical Hb loss using deep learning-based medical sponges image analysis, which was helpful for clinical decisions and technical evaluation.

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

BACKGROUND

To build and validate a radiomics nomogram based on preoperative CT scans and clinical data for detecting synchronous ovarian metastasis (SOM) in female gastric cancer (GC) cases.

METHODS

Pathologically confirmed GC cases in 2 cohorts were retrospectively enrolled. All cases had presurgical abdominal contrast-enhanced CT and pelvis contrast-enhanced MRI and pathological examinations for any suspicious ovarian lesions detected by MRI. Cohort 1 cases (n = 101) were included as the training set. Radiomics features were obtained to develop a radscore. A nomogram combining the radscore and clinical factors was built to detect SOM. The bootstrap method was carried out in cohort 1 as internal validation. External validation was carried out in cohort 2 (n = 46). Receiver operating characteristic (ROC) curve analysis, decision curve analysis (DCA) and the confusion matrix were utilized to assess the performances of the radscore, nomogram and subjective evaluation model.

RESULTS

The nomogram, which combined age and the radscore, displayed a higher AUC than the radscore and subjective evaluation (0.910 vs 0.827 vs 0.773) in the training cohort. In the external validation cohort, the nomogram also had a higher AUC than the radscore and subjective evaluation (0.850 vs 0.790 vs 0.675). DCA and the confusion matrix confirmed the nomogram was superior to the radscore in both cohorts.

CONCLUSIONS

This pilot study showed that a nomogram model combining the radscore and clinical characteristics is useful in detecting SOM in female GC cases. It may be applied to improve clinical treatment and is superior to subjective evaluation or the radscore alone.