Radiomic signature of 18F fluorodeoxyglucose PET/CT for prediction of gastric cancer survival and chemotherapeutic benefits

Multisequence MRI-Based Radiomic Features Combined with Inflammatory Indices for Predicting the Overall Survival of HCC Patients After TACE

Objective

To develop a model for predicting the overall survival (OS) of hepatocellular carcinoma (HCC) patients after transarterial chemoembolization (TACE) on the basis of multisequence MRI radiomic features and clinical variables.

Methods

The DCE-MRI and clinical data of 116 HCC patients treated with TACE for the first time were retrospectively analyzed. The included patients were randomly divided into training and validation cohorts at a ratio of 7:3. Univariate and multivariate Cox proportional hazards regression models were used to identify independent risk factors that affect the OS of patients with HCC after TACE. Radiomic features were extracted from the sequences of FS-T2W images and arterial-phase (A) and portal venous-phase (P) axial DCE-MR images. The LASSO method was used to select the best radiomic features. Logistic regression was used to establish a radiomic model of each sequence, a joint model of MRI features (M model) combined the radiomic features of all the sequences, and a radiomic-clinical model (M-C model) that integrated the radiomic signatures and clinically independent predictors. The diagnostic performance of each model was evaluated as the area under the receiver operating characteristic (ROC) curve (AUC).

Results

The Child-Turcotte-Pugh (CTP) score and neutrophil-to-lymphocyte ratio (NLR) -platelet-to-lymphocyte ratio (PLR) were found to be independent risk factors that affect the OS of patients with HCC treated with TACE. The AUCs of the FS-T2WI, A, P, M, and M-C models for predicting the OS of HCC patients after TACE treatment were 0.779, 0.803, 0.745, 0.858 and 0.893, respectively, in the training group and 0.635, 0.651, 0.644, 0.778 and 0.803, respectively, in the validation group. The M-C model had the best predictive performance.

Conclusion

Multiparameter MRI-based radiomic features may be helpful for predicting OS after TACE treatment in HCC patients. The inclusion of clinical indicators such as inflammation scores can improve the predictive performance.

Prognostic Significance of 18 F-FDG PET/CT Radiomics in Patients With Resectable Pancreatic Ductal Adenocarcinoma Undergoing Curative Surgery

PURPOSE

This study aimed to investigate the prognostic significance of PET/CT radiomics to predict overall survival (OS) in patients with resectable pancreatic ductal adenocarcinoma (PDAC).

METHODS

We enrolled 627 patients with resectable PDAC who underwent preoperative 18 F-FDG PET/CT and subsequent curative surgery. Radiomics analysis of the PET/CT images for the primary tumor was performed using the Chang-Gung Image Texture Analysis toolbox. Radiomics features were subjected to least absolute shrinkage and selection operator (LASSO) regression to select the most valuable imaging features of OS. The prognostic significance was evaluated by Cox proportional hazards regression analysis. Conventional PET parameters and LASSO score were assessed as predictive factors for OS by time-dependent receiver operating characteristic curve analysis.

RESULTS

During a mean follow-up of 28.8 months, 378 patients (60.3%) died. In the multivariable Cox regression analysis, tumor differentiation, resection margin status, tumor stage, and LASSO score were independent prognostic factors for OS (HR, 1.753, 1.669, 2.655, and 2.946; all P < 0.001, respectively). The time-dependent receiver operating characteristic curve analysis showed that the LASSO score had better predictive performance for OS than conventional PET parameters.

CONCLUSIONS

The LASSO score using the 18 F-FDG PET/CT radiomics of the primary tumor was the independent prognostic factor for predicting OS in patients with resectable PDAC and may be helpful in determining therapeutic and follow-up plans for these patients.

Construction and evaluation of a polygenic hazard score for prognostic assessment in localized gastric cancer

To investigate whether genetic variants may provide additional prognostic value to improve the existing clinical staging system for gastric cancer (GC), we performed two genome-wide association studies (GWASs) of GC survival in the Jiangsu (N = 1049) and Shanghai (N = 1405) cohorts. By using a TCGA dataset, we validated genetic markers identified from a meta-analysis of these two Chinese cohorts to determine GC survival-associated loci. Then, we constructed a weighted polygenic hazard score (PHS) and developed a nomogram in combination with clinical variables. We also evaluated prognostic accuracy with the time-dependent receiver operating characteristic (ROC) curve, net reclassification improvement (NRI) and integrated discrimination improvement (IDI). We identified a single nucleotide polymorphism (SNP) of rs1618332 at 15q15.1 that was associated with the survival of GC patients with a P value of 4.12 × 10-8, and we also found additional 25 SNPs having consistent associations among these two Chinese cohort and TCGA cohort. The PHS derived from these 26 SNPs (PHS-26) was an independent prognostic factor for GC survival (all P < 0.001). The 5-year AUC of PHS-26 was 0.68, 0.66 and 0.67 for Jiangsu, Shanghai and their pooled cohorts, respectively, which increased to 0.80, 0.82 and 0.81, correspondingly, after being integrated into a nomogram together with variables of the clinical model. The PHS-26 could improve the NRIs by 16.20%, 4.90% and 8.70%, respectively, and the IDIs by 11.90%, 8.00% and 9.70%, respectively. The 26-SNP based PHS could substantially improve the accuracy of prognostic assessment and might facilitate precision medicine for GC patients.

Construction of a predictive model for gastric cancer neuroaggression and clinical validation analysis: A single-center retrospective study

BACKGROUND

This study investigated the construction and clinical validation of a predictive model for neuroaggression in patients with gastric cancer. Gastric cancer is one of the most common malignant tumors in the world, and neuroinvasion is the key factor affecting the prognosis of patients. However, there is a lack of systematic analysis on the construction and clinical application of its prediction model. This study adopted a single-center retrospective study method, collected a large amount of clinical data, and applied statistics and machine learning technology to build and verify an effective prediction model for neuroaggression, with a view to providing scientific basis for clinical treatment decisions and improving the treatment effect and survival rate of patients with gastric cancer.

AIM

To investigate the value of a model based on clinical data, spectral computed tomography (CT) parameters and image omics characteristics for the preoperative prediction of nerve invasion in patients with gastric cancer.

METHODS

A retrospective analysis was performed on 80 gastric cancer patients who underwent preoperative energy spectrum CT at our hospital between January 2022 and August 2023, these patients were divided into a positive group and a negative group according to their pathological results. Clinicopathological data were collected, the energy spectrum parameters of primary gastric cancer lesions were measured, and single factor analysis was performed. A total of 214 image omics features were extracted from two-phase mixed energy images, and the features were screened by single factor analysis and a support vector machine. The variables with statistically significant differences were included in logistic regression analysis to construct a prediction model, and the performance of the model was evaluated using the subject working characteristic curve.

RESULTS

There were statistically significant differences in sex, carbohydrate antigen 199 expression, tumor thickness, Lauren classification and Borrmann classification between the two groups (all P < 0.05). Among the energy spectrum parameters, there were statistically significant differences in the single energy values (CT60-CT110 keV) at the arterial stage between the two groups (all P < 0.05) and statistically significant differences in CT values, iodide group values, standardized iodide group values and single energy values except CT80 keV at the portal vein stage between the two groups (all P < 0.05). The support vector machine model with the largest area under the curve was selected by image omics analysis, and its area under the curve, sensitivity, specificity, accuracy, P value and parameters were 0.843, 0.923, 0.714, 0.925, < 0.001, and c:g 2.64:10.56, respectively. Finally, based on the logistic regression algorithm, a clinical model, an energy spectrum CT model, an imaging model, a clinical + energy spectrum model, a clinical + imaging model, an energy spectrum + imaging model, and a clinical + energy spectrum + imaging model were established, among which the clinical + energy spectrum + imaging model had the best efficacy in diagnosing gastric cancer nerve invasion. The area under the curve, optimal threshold, Youden index, sensitivity and specificity were 0.927 (95%CI: 0.850-1.000), 0.879, 0.778, 0.778, and 1.000, respectively.

CONCLUSION

The combined model based on clinical features, spectral CT parameters and imaging data has good value for the preoperative prediction of gastric cancer neuroinvasion.

Computed tomography-based radiomics nomogram for predicting therapeutic response to neoadjuvant chemotherapy in locally advanced gastric cancer : A scale for treatment predicting

BACKGROUND AND OBJECTIVE

Neoadjuvant chemotherapy results in various responses when used to treat locally advanced gastric cancer, we aimed to develop and validate a predictive model of the response to neoadjuvant chemotherapy in patients with gastric cancer.

METHODS

A total of 128 patients with locally advanced gastric cancer who underwent pre-treatment computed tomography (CT) scanning followed by neoadjuvant chemoradiotherapy were included (training cohort: n = 64; validation cohort: n = 64). We built a radiomics score combined with laboratory parameters to create a nomogram for predicting the efficacy of neoadjuvant chemotherapy and calculating scores for risk factors.

RESULTS

The radiomics score system demonstrated good stability and prediction performance for the response to neoadjuvant chemotherapy, with the area under the curve of the training and validation cohorts being 0.8 and 0.64, respectively. The radiomics score proved to be an independent risk factor affecting the efficacy of neoadjuvant chemotherapy. In addition to the radiomics score, four other risk factors were included in the nomogram, namely the platelet-to-lymphocyte ratio, total bilirubin, ALT/AST, and CA199. The model had a C-index of 0.8.

CONCLUSIONS

Our results indicated that radiomics features could be potential biomarkers for the early prediction of the response to neoadjuvant treatment.

Development and validation of a machine learning-based 18F-fluorodeoxyglucose PET/CT radiomics signature for predicting gastric cancer survival

BACKGROUND

Survival prognosis of patients with gastric cancer (GC) often influences physicians' choice of their follow-up treatment. This study aimed to develop a positron emission tomography (PET)-based radiomics model combined with clinical tumor-node-metastasis (TNM) staging to predict overall survival (OS) in patients with GC.

METHODS

We reviewed the clinical information of a total of 327 patients with pathological confirmation of GC undergoing 18 F-fluorodeoxyglucose (18 F-FDG) PET scans. The patients were randomly classified into training (n = 229) and validation (n = 98) cohorts. We extracted 171 PET radiomics features from the PET images and determined the PET radiomics scores (RS) using the least absolute shrinkage and selection operator (LASSO) and random survival forest (RSF). A radiomics model, including PET RS and clinical TNM staging, was constructed to predict the OS of patients with GC. This model was evaluated for discrimination, calibration, and clinical usefulness.

RESULTS

On multivariate COX regression analysis, the difference between age, carcinoembryonic antigen (CEA), clinical TNM, and PET RS in GC patients was statistically significant (p < 0.05). A radiomics model was developed based on the results of COX regression. The model had the Harrell's concordance index (C-index) of 0.817 in the training cohort and 0.707 in the validation cohort and performed better than a single clinical model and a model with clinical features combined with clinical TNM staging. Further analyses showed higher PET RS in patients who were older (p < 0.001) and those who had elevated CEA (p < 0.001) and higher clinical TNM (p < 0.001). At different clinical TNM stages, a higher PET RS was associated with a worse survival prognosis.

CONCLUSIONS

Radiomics models based on PET RS, clinical TNM, and clinical features may provide new tools for predicting OS in patients with GC.

MRI- and DWI-Based Radiomics Features for Preoperatively Predicting Meningioma Sinus Invasion

The aim of this study was to use multimodal imaging (contrast-enhanced T1-weighted (T1C), T2-weighted (T2), and diffusion-weighted imaging (DWI)) to develop a radiomics model for preoperatively predicting venous sinus invasion in meningiomas. This prediction would assist in selecting the appropriate surgical approach and forecasting the prognosis of meningiomas. A retrospective analysis was conducted on 331 participants who had been pathologically diagnosed with meningiomas. For each participant, 3948 radiomics features were acquired from the T1C, T2, and DWI images. Minimum redundancy maximum correlation, rank sum test, and multi-factor recursive elimination were used to extract the most significant features of different models. Then, multivariate logistic regression was used to build classification models to predict meningioma venous sinus invasion. The diagnostic capabilities were assessed using receiver operating characteristic (ROC) analysis. In addition, a nomogram was constructed by incorporating clinical and radiological characteristics and a radiomics signature. To assess the clinical usefulness of the nomogram, a decision curve analysis (DCA) was performed. Tumor shape, boundary, and enhancement features were independent predictors of meningioma venous sinus invasion (p = 0.013, p = 0.013, p = 0.005, respectively). Eleven (T2:1, T1C:4, DWI:6) of the 3948 radiomics features were screened for strong association with meningioma sinus invasion. The areas under the ROC curves for the training and external test sets were 0.946 and 0.874, respectively. The clinicoradiomic model showed excellent predictive performance for invasive meningioma, which may help to guide surgical approaches and predict prognosis.

Noninvasive Assessment of HER2 Expression Status in Gastric Cancer Using 18F-FDG Positron Emission Tomography/Computed Tomography-Based Radiomics: A Pilot Study

Purpose: Immunohistochemistry (IHC) is the main method to detect human epidermal growth factor receptor 2 (HER2) expression levels. However, IHC is invasive and cannot reflect HER2 expression status in real time. The aim of this study was to construct and verify three types of radiomics models based on 18F-fuorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) imaging and to evaluate the predictive ability of these radiomics models for the expression status of HER2 in patients with gastric cancer (GC). Patients and Methods: A total of 118 patients with GC were enrolled in this study. 18F-FDG PET/CT imaging was performed prior to surgery. The LIFEx software package was applied to extract PET and CT radiomics features. The minimum absolute contraction and selection operator (least absolute shrinkage and selection operator [LASSO]) algorithm was used to select the best radiomics features. Three machine learning methods, logistic regression (LR), support vector machine (SVM), and random forest (RF) models, were constructed and verified. The Synthetic Minority Oversampling Technique (SMOTE) was applied to address data imbalance. Results: In the training and test sets, the area under the curve (AUC) values of the LR, SVM, and RF models were 0.809, 0.761, 0.861 and 0.628, 0.993, 0.717, respectively, and the Brier scores were 0.118, 0.214, and 0.143, respectively. Among the three models, the LR and RF models exhibited extremely good prediction performance. The AUC values of the three models significantly improved after SMOTE balanced the data. Conclusions: 18F-FDG PET/CT-based radiomics models, especially LR and RF models, demonstrate good performance in predicting HER2 expression status in patients with GC and can be used to preselect patients who may benefit from HER2-targeted therapy.

A 3 M Evaluation Protocol for Examining Lymph Nodes in Cancer Patients: Multi-Modal, Multi-Omics, Multi-Stage Approach

Through meticulous examination of lymph nodes, the stage and severity of cancer can be determined. This information is invaluable for doctors to select the most appropriate treatment plan and predict patient prognosis; however, any oversight in the examination of lymph nodes may lead to cancer metastasis and poor prognosis. In this review, we summarize a significant number of articles supported by statistical data and clinical experience, proposing a standardized evaluation protocol for lymph nodes. This protocol begins with preoperative imaging to assess the presence of lymph node metastasis. Radiomics has replaced the single-modality approach, and deep learning models have been constructed to assist in image analysis with superior performance to that of the human eye. The focus of this review lies in intraoperative lymphadenectomy. Multiple international authorities have recommended specific numbers for lymphadenectomy in various cancers, providing surgeons with clear guidelines. These numbers are calculated by applying various statistical methods and real-world data. In the third chapter, we mention the growing concern about immune impairment caused by lymph node dissection, as the lack of CD8 memory T cells may have a negative impact on postoperative immunotherapy. Both excessive and less lymph node dissection have led to conflicting findings on postoperative immunotherapy. In conclusion, we propose a protocol that can be referenced by surgeons. With the systematic management of lymph nodes, we can control tumor progression with the greatest possible likelihood, optimize the preoperative examination process, reduce intraoperative risks, and improve postoperative quality of life.

The value of an MRI-based radiomics model in predicting the survival and prognosis of patients with extrahepatic cholangiocarcinoma

OBJECTIVES

The study aimed to establish radiomics models based on magnetic resonance imaging (MRI) multiparameter images to predict the survival and prognosis of patients with extrahepatic cholangiocarcinoma (ECC).

METHODS

Seventy-eight patients with ECC confirmed by pathology were collected retrospectively. The radiomics model_a/b/c were constructed based on the 1/2/3-year survival of patients with ECC. The best texture features were selected according to postoperative survival time and ECC patient status to calculate the radiomics score (Rad-score). A cutoff value was selected, and patients were divided into high-risk and low-risk groups.

RESULTS

Model_a, model_b, and model_c were used to predict 1-, 2-, and 3-year postoperative survival rates, respectively. The area under the curve values in the training and test groups were 1.000 and 0.933 for model_a, 0.909 and 0.907 for model_b, 1.000 and 0.975 for model_c, respectively. The survival prediction model based on the Rad-score showed that the postoperative mortality risk differed significantly between risk groups (p < 0.0001).

CONCLUSIONS

The MRI radiomics model could be used to predict the survival and prognosis of patients with ECC.

Predicting efficacy and guiding procedure choice in non-vascularized bone grafting: a CT Radiomics and clinical predictor approach

OBJECTIVES

There is no practical approach for accurately predicting the efficacy of non-vascularized bone grafting (NVBG) and guiding its optimal procedure.

MATERIALS AND METHODS

This study enrolled 153 patients with 182 hips that underwent NVBG procedures. The patients were randomly divided into a training cohort (n = 130) and a validation cohort (n = 52). In the training cohort, radiomics model, clinical model, and combined radiomics-clinical (C-R) model were constructed using Rad-scores and clinical predictors to predict the efficacy of NVBG. The optimal model was visualized by a nomogram and assessed by decision curve analysis (DCA). 128 hips that underwent successful NVBG were then randomized into a new training cohort (n = 92) and a new validation cohort (n = 36), and three models were constructed and validated to predict the choice of NVBG procedure.

RESULTS

Japanese Investigation Committee (JIC) classification, exposure to risk factors postoperative, and Rad-scores consisting of four radiomics features were independent predictors for the efficacy of NVBG (P < 0.05). The C-R model provided better performance in both the training cohort (AUC: 0.818) and validation cohort (AUC: 0.747). To predict the choice of NVBG procedure, the C-R model built by JIC classification and Rad-scores consisting of five radiomics features showed the finest performance in both cohorts (AUC: 0.860 and 0.800, respectively). DCA showed great benefit using the C-R model for the choice of NVBG procedure.

CONCLUSION

The approach integrated by CT radiomics and clinical predictors can be visually and quantitatively applied to predict the efficacy and guide the choice of NVBG procedure with great predictive accuracy.

Nuclear medicine radiomics in digestive system tumors: Concept, applications, challenges, and future perspectives

Radiomics aims to develop novel biomarkers and provide relevant deeper subvisual information about pathology, immunophenotype, and tumor microenvironment. It uses automated or semiautomated quantitative analysis of high-dimensional images to improve characterization, diagnosis, and prognosis. Recent years have seen a rapid increase in radiomics applications in nuclear medicine, leading to some promising research results in digestive system oncology, which have been driven by big data analysis and the development of artificial intelligence. Although radiomics advances one step further toward the non-invasive precision medical analysis, it is still a step away from clinical application and faces many challenges. This review article summarizes the available literature on digestive system tumors regarding radiomics in nuclear medicine. First, we describe the workflow and steps involved in radiomics analysis. Subsequently, we discuss the progress in clinical application regarding the utilization of radiomics for distinguishing between various diseases and evaluating their prognosis, and demonstrate how radiomics advances this field. Finally, we offer our viewpoint on how the field can progress by addressing the challenges facing clinical implementation.

Prognostic 18F-FDG Radiomic Features in Advanced High-Grade Serous Ovarian Cancer

High-grade serous ovarian cancer (HGSOC) is an aggressive disease with different clinical outcomes and poor prognosis. This could be due to tumor heterogeneity. The 18F-FDG PET radiomic parameters permit addressing tumor heterogeneity. Nevertheless, this has been not well studied in ovarian cancer. The aim of our work was to assess the prognostic value of pretreatment 18F-FDG PET radiomic features in patients with HGSOC. A review of 36 patients diagnosed with advanced HGSOC between 2016 and 2020 in our center was performed. Radiomic features were obtained from pretreatment 18F-FDGPET. Disease-free survival (DFS) and overall survival (OS) were calculated. Optimal cutoff values with receiver operating characteristic curve/median values were used. A correlation between radiomic features and DFS/OS was made. The mean DFS was 19.6 months and OS was 37.1 months. Total Lesion Glycolysis (TLG), GLSZM_ Zone Size Non-Uniformity (GLSZM_ZSNU), and GLRLM_Run Length Non-Uniformity (GLRLM_RLNU) were significantly associated with DFS. The survival-curves analysis showed a significant difference of DSF in patients with GLRLM_RLNU > 7388.3 versus patients with lower values (19.7 months vs. 31.7 months, p = 0.035), maintaining signification in the multivariate analysis (p = 0.048). Moreover, Intensity-based Kurtosis was associated with OS (p = 0.027). Pretreatment 18F-FDG PET radiomic features GLRLM_RLNU, GLSZM_ZSNU, and Kurtosis may have prognostic value in patients with advanced HGSOC.

A radiomics nomogram based on 18 F-FDG PET/CT and clinical risk factors for the prediction of peritoneal metastasis in gastric cancer

PURPOSE

Peritoneal metastasis (PM) is usually considered an incurable factor of gastric cancer (GC) and not fit for surgery. The aim of this study is to develop and validate an 18 F-FDG PET/CT-derived radiomics model combining with clinical risk factors for predicting PM of GC.

METHOD

In this retrospective study, 410 GC patients (PM - = 281, PM + = 129) who underwent preoperative 18 F-FDG PET/CT images from January 2015 to October 2021 were analyzed. The patients were randomly divided into a training cohort (n = 288) and a validation cohort (n = 122). The maximum relevance and minimum redundancy (mRMR) and the least shrinkage and selection operator method were applied to select feature. Multivariable logistic regression analysis was preformed to develop the predicting model. Discrimination, calibration, and clinical usefulness were used to evaluate the performance of the nomogram.

RESULT

Fourteen radiomics feature parameters were selected to construct radiomics model. The area under the curve (AUC) of the radiomics model were 0.86 [95% confidence interval (CI), 0.81-0.90] in the training cohort and 0.85 (95% CI, 0.78-0.92) in the validation cohort. After multivariable logistic regression, peritoneal effusion, mean standardized uptake value (SUVmean), carbohydrate antigen 125 (CA125) and radiomics signature showed statistically significant differences between different PM status patients( P  < 0.05). They were chosen to construct the comprehensive predicting model which showed a performance with an AUC of 0.92 (95% CI, 0.89-0.95) in the training cohort and 0.92 (95% CI, 0.86-0.98) in the validation cohort, respectively.

CONCLUSION

The nomogram based on 18 F-FDG PET/CT radiomics features and clinical risk factors can be potentially applied in individualized treatment strategy-making for GC patients before the surgery.

Methodological quality of radiomic-based prognostic studies in gastric cancer: a cross-sectional study

Background

Machine learning radiomics models are increasingly being used to predict gastric cancer prognoses. However, the methodological quality of these models has not been evaluated. Therefore, this study aimed to evaluate the methodological quality of radiomics studies in predicting the prognosis of gastric cancer, summarize their methodological characteristics and performance.

Methods

The PubMed and Embase databases were searched for radiomics studies used to predict the prognosis of gastric cancer published in last 5 years. The characteristics of the studies and the performance of the models were extracted from the eligible full texts. The methodological quality, reporting completeness and risk of bias of the included studies were evaluated using the RQS, TRIPOD and PROBAST. The discrimination ability scores of the models were also compared.

Results

Out of 283 identified records, 22 studies met the inclusion criteria. The study endpoints included survival time, treatment response, and recurrence, with reported discriminations ranging between 0.610 and 0.878 in the validation dataset. The mean overall RQS value was 15.32 ± 3.20 (range: 9 to 21). The mean adhered items of the 35 item of TRIPOD checklist was 20.45 ± 1.83. The PROBAST showed all included studies were at high risk of bias.

Conclusion

The current methodological quality of gastric cancer radiomics studies is insufficient. Large and reasonable sample, prospective, multicenter and rigorously designed studies are required to improve the quality of radiomics models for gastric cancer prediction.

Study registration

This protocol was prospectively registered in the Open Science Framework Registry (https://osf.io/ja52b).

Non-invasive tumor microenvironment evaluation and treatment response prediction in gastric cancer using deep learning radiomics

The tumor microenvironment (TME) plays a critical role in disease progression and is a key determinant of therapeutic response in cancer patients. Here, we propose a noninvasive approach to predict the TME status from radiological images by combining radiomics and deep learning analyses. Using multi-institution cohorts of 2,686 patients with gastric cancer, we show that the radiological model accurately predicted the TME status and is an independent prognostic factor beyond clinicopathologic variables. The model further predicts the benefit from adjuvant chemotherapy for patients with localized disease. In patients treated with checkpoint blockade immunotherapy, the model predicts clinical response and further improves predictive accuracy when combined with existing biomarkers. Our approach enables noninvasive assessment of the TME, which opens the door for longitudinal monitoring and tracking response to cancer therapy. Given the routine use of radiologic imaging in oncology, our approach can be extended to many other solid tumor types.

Development and validation of a multiphase CT radiomics nomogram for the preoperative prediction of lymphovascular invasion in patients with gastric cancer

AIM

To develop a nomogram to predict lymphovascular invasion (LVI) in gastric cancer by integrating multiphase computed tomography (CT) radiomics and clinical risk factors.

MATERIALS AND METHODS

One hundred and seventy-two gastric cancer patients (121 training and 51 validation) with preoperative contrast-enhanced CT images and clinicopathological data were collected retrospectively. The clinical risk factors were selected by univariate and multivariate regression analysis. Radiomic features were extracted and selected from the arterial phase (AP), venous phase (VP), and delayed phase (DP) CT images of each patient. Clinical risk factors, radiomic features, and integration of both were used to develop the clinical model, radiomic models, and nomogram, respectively.

RESULTS

Radiomic features from AP (n=6), VP (n=6), DP (n=7) CT images and three selected clinical risk factors were used for model development. The nomogram showed better performance than the AP, VP, DP, and clinical models in the training and validation datasets, providing areas under the curves (AUCs) of 0.890 (95% CI: 0.820-0.940) and 0.885 (95% CI:0.765-0.957), respectively. All models indicated good calibration, and decision curve analysis proved that the net benefit of the nomogram was superior to that of the clinical and radiomic models throughout the vast majority of the threshold probabilities.

CONCLUSIONS

The nomogram integrating multiphase CT radiomics and clinical risk factors showed favourable performance in predicting LVI of gastric cancer, which may benefit clinical practice.

Radiomic signatures based on pretreatment 18F-FDG PET/CT, combined with clinicopathological characteristics, as early prognostic biomarkers among patients with invasive breast cancer

Purpose

The aim of this study was to investigate the predictive role of fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) in the prognostic risk stratification of patients with invasive breast cancer (IBC). To achieve this, we developed a clinicopathologic-radiomic-based model (C-R model) and established a nomogram that could be utilized in clinical practice.

Methods

We retrospectively enrolled a total of 91 patients who underwent preoperative 18F-FDG PET/CT and randomly divided them into training (n=63) and testing cohorts (n=28). Radiomic signatures (RSs) were identified using the least absolute shrinkage and selection operator (LASSO) regression algorithm and used to compute the radiomic score (Rad-score). Patients were assigned to high- and low-risk groups based on the optimal cut-off value of the receiver operating characteristic (ROC) curve analysis for both Rad-score and clinicopathological risk factors. Univariate and multivariate Cox regression analyses were performed to determine the association between these variables and progression-free survival (PFS) or overall survival (OS). We then plotted a nomogram integrating all these factors to validate the predictive performance of survival status.

Results

The Rad-score, age, clinical M stage, and minimum standardized uptake value (SUVmin) were identified as independent prognostic factors for predicting PFS, while only Rad-score, age, and clinical M stage were found to be prognostic factors for OS in the training cohort. In the testing cohort, the C-R model showed superior performance compared to single clinical or radiomic models. The concordance index (C-index) values for the C-R model, clinical model, and radiomic model were 0.816, 0.772, and 0.647 for predicting PFS, and 0.882, 0.824, and 0.754 for OS, respectively. Furthermore, decision curve analysis (DCA) and calibration curves demonstrated that the C-R model had a good ability for both clinical net benefit and application.

Conclusion

The combination of clinicopathological risks and baseline PET/CT-derived Rad-score could be used to evaluate the prognosis in patients with IBC. The predictive nomogram based on the C-R model further enhanced individualized estimation and allowed for more accurate prediction of patient outcomes.

Preoperative prediction of Lauren classification in gastric cancer: a radiomics model based on dual-energy CT iodine map

OBJECTIVE

To investigate the value of a radiomics model based on dual-energy computed tomography (DECT) venous-phase iodine map (IM) and 120 kVp equivalent mixed images (MIX) in predicting the Lauren classification of gastric cancer.

METHODS

A retrospective analysis of 240 patients undergoing preoperative DECT and postoperative pathologically confirmed gastric cancer was done. Training sets (n = 168) and testing sets (n = 72) were randomly assigned with a ratio of 7:3. Patients are divided into intestinal and non-intestinal groups. Traditional features were analyzed by two radiologists, using logistic regression to determine independent predictors for building clinical models. Using the Radiomics software, radiomics features were extracted from the IM and MIX images. ICC and Boruta algorithm were used for dimensionality reduction, and a random forest algorithm was applied to construct the radiomics model. ROC and DCA were used to evaluate the model performance.

RESULTS

Gender and maximum tumor thickness were independent predictors of Lauren classification and were used to build a clinical model. Separately establish IM-radiomics (R-IM), mixed radiomics (R-MIX), and combined IM + MIX image radiomics (R-COMB) models. In the training set, each radiomics model performed better than the clinical model, and the R-COMB model showed the best prediction performance (AUC: 0.855). In the testing set also, the R-COMB model had better prediction performance than the clinical model (AUC: 0.802).

CONCLUSION

The R-COMB radiomics model based on DECT-IM and 120 kVp equivalent MIX images can effectively be used for preoperative noninvasive prediction of the Lauren classification of gastric cancer.

CRITICAL RELEVANCE STATEMENT

The radiomics model based on dual-energy CT can be used for Lauren classification prediction of preoperative gastric cancer and help clinicians formulate individualized treatment plans and assess prognosis.

The Efficacy of Pretreatment 18F-FDG PET-CT-Based Deep Learning Network Structure to Predict Survival in Nasopharyngeal Carcinoma

Background

Previous studies have shown that the 5-year survival rates of patients with nasopharyngeal carcinoma (NPC) were still not ideal despite great improvement in NPC treatments. To achieve individualized treatment of NPC, we have been looking for novel models to predict the prognosis of patients with NPC. The objective of this study was to use a novel deep learning network structural model to predict the prognosis of patients with NPC and to compare it with the traditional PET-CT model combining metabolic parameters and clinical factors.

Methods

A total of 173 patients were admitted to 2 institutions between July 2014 and April 2020 for the retrospective study; each received a PET-CT scan before treatment. The least absolute shrinkage and selection operator (LASSO) was employed to select some features, including SUVpeak-P, T3, age, stage II, MTV-P, N1, stage III and pathological type, which were associated with overall survival (OS) of patients. We constructed 2 survival prediction models: an improved optimized adaptive multimodal task (a 3D Coordinate Attention Convolutional Autoencoder and an uncertainty-based jointly Optimizing Cox Model, CACA-UOCM for short) and a clinical model. The predictive power of these models was assessed using the Harrell Consistency Index (C index). Overall survival of patients with NPC was compared by Kaplan-Meier and Log-rank tests.

Results

The results showed that CACA-UOCM model could estimate OS (C index, 0.779 for training, 0.774 for validation, and 0.819 for testing) and divide patients into low and high mortality risk groups, which were significantly associated with OS (P < .001). However, the C-index of the model based only on clinical variables was only 0.42.

Conclusions

The deep learning network model based on ¹⁸F-FDG PET/CT can serve as a reliable and powerful predictive tool for NPC and provide therapeutic strategies for individual treatment.

Prediction of Microsatellite Instability in Colorectal Cancer Using a Machine Learning Model Based on PET/CT Radiomics

PURPOSE

We investigated the feasibility of preoperative ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography (CT) radiomics with machine learning to predict microsatellite instability (MSI) status in colorectal cancer (CRC) patients.

MATERIALS AND METHODS

Altogether, 233 patients with CRC who underwent preoperative FDG PET/CT were enrolled and divided into training (n=139) and test (n=94) sets. A PET-based radiomics signature (rad_score) was established to predict the MSI status in patients with CRC. The predictive ability of the rad_score was evaluated using the area under the receiver operating characteristic curve (AUROC) in the test set. A logistic regression model was used to determine whether the rad_score was an independent predictor of MSI status in CRC. The predictive performance of rad_score was compared with conventional PET parameters.

RESULTS

The incidence of MSI-high was 15 (10.8%) and 10 (10.6%) in the training and test sets, respectively. The rad_score was constructed based on the two radiomic features and showed similar AUROC values for predicting MSI status in the training and test sets (0.815 and 0.867, respectively; p=0.490). Logistic regression analysis revealed that the rad_score was an independent predictor of MSI status in the training set. The rad_score performed better than metabolic tumor volume when assessed using the AUROC (0.867 vs. 0.794, p=0.015).

CONCLUSION

Our predictive model incorporating PET radiomic features successfully identified the MSI status of CRC, and it also showed better performance than the conventional PET image parameters.

Radiomics Analysis of 18F-FDG PET/CT for Prognosis Prediction in Patients with Stage III Non-Small Cell Lung Cancer Undergoing Neoadjuvant Chemoradiation Therapy Followed by Surgery

We investigated the prognostic significance of radiomic features from 18F-FDG PET/CT to predict overall survival (OS) in patients with stage III NSCLC undergoing neoadjuvant chemoradiation therapy followed by surgery. We enrolled 300 patients with stage III NSCLC who underwent PET/CT at the initial work-up (PET1) and after neoadjuvant concurrent chemoradiotherapy (PET2). Radiomic primary tumor features were subjected to LASSO regression to select the most useful prognostic features of OS. The prognostic significance of the LASSO score and conventional PET parameters was assessed by Cox proportional hazards regression analysis. In conventional PET parameters, metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of each PET1 and PET2 were significantly associated with OS. In addition, both the PET1-LASSO score and the PET2-LASSO score were significantly associated with OS. In multivariate Cox regression analysis, only the PET2-LASSO score was an independently significant factor for OS. The LASSO score showed better predictive performance for OS regarding the time-dependent receiver operating characteristic curve and decision curve analysis than conventional PET parameters. Radiomic features from PET/CT were an independent prognostic factor for the estimation of OS in stage III NSCLC. The newly developed LASSO score using radiomic features showed better prognostic results for individualized OS estimation than conventional PET parameters.

Application of radiomics in precision prediction of diagnosis and treatment of gastric cancer

Gastric cancer is one of the most common malignant tumors. Although some progress has been made in chemotherapy and surgery, it is still one of the highest mortalities in the world. Therefore, early detection, diagnosis and treatment are very important to improve the prognosis of patients. In recent years, with the proposal of the concept of radiomics, it has been gradually applied to histopathological grading, differential diagnosis, therapeutic efficacy and prognosis evaluation of gastric cancer, whose advantage is to comprehensively quantify the tumor phenotype using a large number of quantitative image features, so as to predict and diagnose the lesion area of gastric cancer early. The purpose of this review is to evaluate the research status and progress of radiomics in gastric cancer, and reviewed the workflow and clinical application of radiomics. The 27 original studies on the application of radiomics in gastric cancer were included from web of science database search results from 2017 to 2021, the number of patients included ranged from 30 to 1680, and the models used were based on the combination of radiomics signature and clinical factors. Most of these studies showed positive results, the median radiomics quality score (RQS) for all studies was 36.1%, and the development prospect and challenges of radiomics development were prospected. In general, radiomics has great potential in improving the early prediction and diagnosis of gastric cancer, and provides an unprecedented opportunity for clinical practice to improve the decision support of gastric cancer treatment at a low cost.

The Applications of Artificial Intelligence in Digestive System Neoplasms: A Review

Importance

Digestive system neoplasms (DSNs) are the leading cause of cancer-related mortality with a 5-year survival rate of less than 20%. Subjective evaluation of medical images including endoscopic images, whole slide images, computed tomography images, and magnetic resonance images plays a vital role in the clinical practice of DSNs, but with limited performance and increased workload of radiologists or pathologists. The application of artificial intelligence (AI) in medical image analysis holds promise to augment the visual interpretation of medical images, which could not only automate the complicated evaluation process but also convert medical images into quantitative imaging features that associated with tumor heterogeneity.

Highlights

We briefly introduce the methodology of AI for medical image analysis and then review its clinical applications including clinical auxiliary diagnosis, assessment of treatment response, and prognosis prediction on 4 typical DSNs including esophageal cancer, gastric cancer, colorectal cancer, and hepatocellular carcinoma.

Conclusion

AI technology has great potential in supporting the clinical diagnosis and treatment decision-making of DSNs. Several technical issues should be overcome before its application into clinical practice of DSNs.

CT-based radiomics nomogram for differentiating gastric hepatoid adenocarcinoma from gastric adenocarcinoma: a multicentre study

BACKGROUND

To develop a CT-based radiomics nomogram for the high-precision preoperative differentiation of gastric hepatoid adenocarcinoma (GHAC) patients from gastric adenocarcinoma (GAC) patients.

RESEARCH DESIGN AND METHODS

108 patients with GHAC from 6 centers and 108 GAC patients matched by age, sex and T stage undergoing pathological examination were retrospectively reviewed. Patients from 5 centers were divided into two cohorts (training and internal validation) at a 7:3 ratio, the remaining patients were external test cohort. Venous-phase CT images were retrieved for tumor segmentation and feature extraction. A radiomics model was developed by the least absolute shrinkage and selection operator method. The nomogram was developed by clinical factors and the radiomics score.

RESULTS

1409 features were extracted and a radiomics model consisting of 19 features was developed, which showed a favorable performance in discriminating GHAC from GAC (AUC_{training cohort} = 0.998, AUC_{internal validation set} = 0.942, AUC_{external test cohort} = 0.731). The radiomics nomogram, including the radiomics score, AFP, and CA72_4, achieved good calibration and discrimination (AUC_{training cohort} = 0.998, AUC_{internal validation set} = 0.954, AUC_{external test cohort} = 0.909).

CONCLUSIONS

The noninvasive CT-based nomogram, including radiomics score, AFP, and CA72_4, showed favorable predictive efficacy for differentiating GHAC from GAC and might be useful for clinical decision-making.

Development and validation of nomograms by radiomic features on ultrasound imaging for predicting overall survival in patients with primary nodal diffuse large B-cell lymphoma

Objectives

To develop and validate a nomogram to predict the overall survival (OS) of patients with primary nodal diffuse large B-cell lymphoma(N-DLBCL) based on radiomic features and clinical features.

Materials and methods

A retrospective analysis was performed on 145 patients confirmed with N-DLBCL and they were randomly assigned to training set(n=78), internal validation set(n=33), external validation set(n=34). First, a clinical model (model 1) was established according to clinical features and ultrasound (US) results. Then, based on the radiomics features extracted from conventional ultrasound images, a radiomic signature was constructed (model 2), and the radiomics score (Rad-Score) was calculated. Finally, a comprehensive model was established (model 3) combined with Rad-score and clinical features. Receiver operating characteristic (ROC) curves were employed to evaluate the performance of model 1, model 2 and model 3. Based on model 3, we plotted a nomogram. Calibration curves were used to test the effectiveness of the nomogram, and decision curve analysis (DCA) was used to asset the nomogram in clinical use.

Results

According to multivariate analysis, 3 clinical features and Rad-score were finally selected to construct the model 3, which showed better predictive value for OS in patients with N-DLBCL than mode 1 and model 2 in training (AUC,0. 891 vs. 0.779 vs.0.756), internal validation (AUC, 0.868 vs. 0.713, vs.0.756) and external validation (AUC, 914 vs. 0.866, vs.0.789) sets. Decision curve analysis demonstrated that the nomogram based on model 3 was more clinically useful than the other two models.

Conclusion

The developed nomogram is a useful tool for precisely analyzing the prognosis of N-DLBCL patients, which could help clinicians in making personalized survival predictions and assessing individualized clinical options.

Evaluation of multiple biological indicators for combined diagnosis of gastric cancer: A retrospective analysis

To assess carcinoembryonic antigen (CEA), carbohydrate antigen 19-9 (CA19-9), platelet distribution width (PDW), neutrophil-to-lymphocyte ratio (NLR), and platelet-lymphocyte ratio (PLR) for gastric cancer's (GC) diagnostic efficiency, and the use of receiver operating characteristic curves (ROC) combined with logistic regression to evaluate multi-index combination's diagnostic value of GC. 773 GC patients' clinical data were retrospectively collected in the Weihai Municipal Hospital, affiliated hospital of Shandong University from April 2018 to May 2021, and selected 2368 healthy physical examination patients during the same period as the control group. A total of 3141 samples was included in this study, including 773 cases in the GC group and 2368 cases in the healthy physical examination group. The results of the overall comparison between groups showed that apart from gender, the age differences, CEA, CA19-9, PDW, NLR, and PLR were statistically significant (P < .001). Spearman ranks correlation analysis's results showed that CA19-9, CEA, PLR, and NLR were correlated with GC patients' clinical-stage positively, and the correlation coefficients r was 0.249, 0.280, 0.252, 0.262 (all P < .001), and PDW was correlated with the clinical stage negatively (r = -0.186, P < .001). The ROC curve analysis results of CEA, CA19-9, PDW, NLR and PLR showed that CEA's diagnostic cutoff value for GC was 3.175 (area under the curve [AUC] = 0.631, 95% CI: 0.606-0.655, P < .001), the CA19-9's diagnostic cutoff value is 19.640 (AUC = 0.589, 95% CI: 0.563-0.615, P < .001), PDW's diagnostic cutoff value is 15.750 (AUC = 0.799, 95% CI: 0.778-0.820, P < .001), NLR's diagnostic cutoff value was 2.162 (AUC = 0.699, 95% CI: 0.675-0.721, P < .001), and PLR's diagnostic cutoff value was 149.540 (AUC = 0.709, 95% CI: 0.688-0.732, P < .001). The area under the ROC curve for the combined diagnosis of GC with 5 indicators was 0.877 (95% CI: 0.860-0.894, P < .001), which was better than a single indicator (P < .05). The diagnostic efficiency of combined detection of CEA, CA19-9, PDW, NLR, and PLR is better than that of single index detection alone, which can reduce the misdiagnosis rate of GC effectively.

Prognostic value of 18F-FDG PET/CT radiomic model based on primary tumor in patients with non-small cell lung cancer: A large single-center cohort study

Objectives

In the present study, we aimed to determine the prognostic value of the 18F-FDG PET/CT-based radiomics model when predicting progression-free survival (PFS) and overall survival (OS) in patients with non-small cell lung cancer (NSCLC).

Methods

A total of 368 NSCLC patients who underwent 18F-FDG PET/CT before treatment were randomly assigned to the training (n = 257) and validation (n = 111) cohorts. Radiomics signatures from PET and CT images were obtained using LIFEx software, and then clinical and complex models were constructed and validated by selecting optimal parameters based on PFS and OS to construct radiomics signatures.

Results

In the training cohort, the C-index of the clinical model for predicting PFS and OS in NSCLC patients was 0.748 and 0.834, respectively, and the AUC values ​​were 0.758 and 0.846, respectively. The C-index of the complex model for predicting PFS and OS was 0.775 and 0.881, respectively, and the AUC values ​​were 0.780 and 0.891, respectively. The C-index of the clinical model for predicting PFS and OS in the validation group was 0.729 and 0.832, respectively, and the AUC values ​​were 0.776 and 0.850, respectively. The C-index of the complex model for predicting PFS and OS was 0.755 and 0.867, respectively, and the AUC values ​​were 0.791 and 0.874, respectively. Moreover, decision curve analysis showed that the complex model had a higher net benefit than the clinical model.

Conclusions

18F-FDG PET/CT radiomics before treatment could predict PFS and OS in NSCLC patients, and the predictive power was higher when combined with clinical factors.

Role of radiomics in the diagnosis and treatment of gastrointestinal cancer

Gastrointestinal cancer (GIC) has high morbidity and mortality as one of the main causes of cancer death. Preoperative risk stratification is critical to guide patient management, but traditional imaging studies have difficulty predicting its biological behavior. The emerging field of radiomics allows the conversion of potential pathophysiological information in existing medical images that cannot be visually recognized into high-dimensional quantitative image features. Tumor lesion characterization, therapeutic response evaluation, and survival prediction can be achieved by analyzing the relationships between these features and clinical and genetic data. In recent years, the clinical application of radiomics to GIC has increased dramatically. In this editorial, we describe the latest progress in the application of radiomics to GIC and discuss the value of its potential clinical applications, as well as its limitations and future directions.

Non-invasive measurement of tumor immune microenvironment and prediction of survival and chemotherapeutic benefits from 18F fluorodeoxyglucose PET/CT images in gastric cancer

BACKGROUND

The tumor immune microenvironment could provide prognostic and predictive information. It is necessary to develop a noninvasive radiomics-based biomarker of a previously validated tumor immune microenvironment signature of gastric cancer (GC) with immunohistochemistry staining.

METHODS

A total of 230 patients (training (n = 153) or validation (n = 77) cohort) with gastric cancer were subjected to (Positron Emission Tomography-Computed Tomography) radiomics feature extraction (80 features). A radiomics tumor immune microenvironment score (RTIMS) was developed to predict the tumor immune microenvironment signature with LASSO logistic regression. Furthermore, we evaluated its relation with prognosis and chemotherapy benefits.

RESULTS

A 8-feature radiomics signature was established and validated (area under the curve=0.692 and 0.713). The RTIMS signature was significantly associated with disease-free survival and overall survival both in the training and validation cohort (all P<0.001). RTIMS was an independent prognostic factor in the Multivariate analysis. Further analysis revealed that high RTIMS patients benefitted from adjuvant chemotherapy (for DFS, stage II: HR 0.208(95% CI 0.061-0.711), p=0.012; stage III: HR 0.321(0.180-0.570), p<0.001, respectively); while there were no benefits from chemotherapy in a low RTIMS patients.

CONCLUSION

This PET/CT radiomics model provided a promising way to assess the tumor immune microenvironment and to predict clinical outcomes and chemotherapy response. The RTIMS signature could be useful in estimating tumor immune microenvironment and predicting survival and chemotherapy benefit for patients with gastric cancer, when validated by further prospective randomized trials.

Predicting the Recurrence of Gastric Cancer Using the Textural Features of Perigastric Adipose Tissue on [18F]FDG PET/CT

This study aimed to assess the relationship between the histopathological and textural features of perigastric adipose tissue (AT) on 2-deoxy-2-[¹⁸F]fluoro-D-glucose ([¹⁸F]FDG) positron emission tomography/computed tomography (PET/CT) and to evaluate the prognostic significance of perigastric AT textural features in predicting recurrence-free survival (RFS) in patients with gastric cancer. Sixty-nine patients with gastric cancer who underwent staging [¹⁸F]FDG PET/CT and subsequent curative surgery were retrospectively reviewed. Textural features of perigastric AT were extracted from PET images. On histopathological analysis, CD4, CD8, and CD163 cell infiltration and matrix metalloproteinase-11 and interleukin-6 (IL-6) expression in perigastric AT were graded. The degree of CD163 cell infiltration in perigastric AT was significantly correlated with the mean standardized uptake value (SUV), SUV histogram entropy, grey-level co-occurrence matrix (GLCM) energy, and GLCM entropy of perigastric AT. The degree of IL-6 expression in the perigastric AT was significantly correlated with the mean and median SUVs of perigastric AT. In multivariate survival analysis, GLCM entropy, GLCM dissimilarity, and GLCM homogeneity of perigastric AT were significant predictors of RFS. The textural features of perigastric AT on [¹⁸F]FDG PET/CT significantly correlated with inflammatory response in perigastric AT and were significant prognostic factors for predicting RFS in patients with gastric cancer.

PET/CT for Predicting Occult Lymph Node Metastasis in Gastric Cancer

A portion of gastric cancer patients with negative lymph node metastasis at an early stage eventually die from tumor recurrence or advanced metastasis. Occult lymph node metastasis (OLNM] is a potential risk factor for the recurrence and metastasis in these patients, and it is highly important for clinical prognosis. Positron emission tomography (PET)/computed tomography (CT) is used to assess lymph node metastasis in gastric cancer due to its advantages in anatomical and functional imaging and non-invasive nature. Among the major metabolic parameters of PET, the maximum standardized uptake value (SUVmax) is commonly used for examining lymph node status. However, SUVmax is susceptible to interference by a variety of factors. In recent years, the exploration of new PET metabolic parameters, new PET imaging agents and radiomics, has become an active research topic. This paper aims to explore the feasibility and predict the effectiveness of using PET/CT to detect OLNM. The current landscape and future trends of primary metabolic parameters and new imaging agents of PET are reviewed. For gastric cancer patients, the possibility to detect OLNM non-invasively will help guide surgeons to choose the appropriate lymph node dissection area, thereby reducing unnecessary dissections and providing more reasonable, personalized and comprehensive treatments.

Efficacy and prognostic value of delta radiomics on dual-energy computed tomography for gastric cancer with neoadjuvant chemotherapy: a preliminary study

BACKGROUND

A non-invasive tool for tumor regression grade (TRG) evaluation is urgently needed for gastric cancer (GC) treated with neoadjuvant chemotherapy (NAC).

PURPOSE

To develop and validate a radiomics signature (RS) to evaluate TRG for locally advanced GC after NAC and assess its prognostic value.

MATERIAL AND METHODS

A total of 103 patients with GC treated with NAC were retrospectively recruited from April 2018 to December 2019 and were randomly allocated into a training cohort (n = 69) and a validation cohort (n = 34). Delineation was performed on both mixed and iodine-uptake images based on dual-energy computed tomography (DECT). A total of 4094 radiomics features were extracted from the pre-NAC, post-NAC, and delta feature sets. Spearman correlation and the least absolute shrinkage and selection operator were used for dimensionality reduction. Multivariable logistic regression was used for TRG evaluation and generated the optimal RS. Kaplan-Meier survival analysis with the log-rank test was implemented in an independent cohort of 40 patients to validate the prognostic value of the optimal RS.

RESULTS

Three, five, and six radiomics features were finally selected for the pre-NAC, post-NAC, and delta feature sets. The delta model demonstrated the best performance in assessing TRG in both the training and the validation cohorts (AUCs=0.91 and 0.76, respectively; P>0.1). The optimal RS from the delta model showed a significant capability to predict survival in the independent cohort (P<0.05).

CONCLUSION

Delta radiomics based on DECT images serves as a potential biomarker for TRG evaluation and shows prognostic value for patients with GC treated with NAC.

Prognostic nomograms for lung neuroendocrine carcinomas based on lymph node ratio: a SEER database analysis

Objective

The current study aimed to explore the prognostic value of the lymph node ratio (LNR) in patients with lung neuroendocrine carcinomas (LNECs).

Methods

Data for 1564 elderly patients with LNECs between 1998 and 2016 were obtained from the Surveillance, Epidemiology, and End Results database. The cases were assigned randomly to training (n = 1086) and internal validation (n = 478) sets. The association between LNR and survival was investigated by Cox regression.

Results

Multivariate analyses identified age, tumor grade, summary stage, M stage, surgery, and LNR as independent prognostic factors for both overall survival (OS) and lung cancer-specific survival (LCSS). Tumor size was also a prognostic determinant for LCSS. Prognostic nomograms combining LNR with other informative variables showed good discrimination and calibration abilities in both the training and validation sets. In addition, the C-index of the nomograms was statistically superior to the American Joint Committee on Cancer (AJCC) staging system in both the training and validation cohorts.

Conclusions

These nomograms, based on LNR, showed superior prognostic predictive accuracy compared with the AJCC staging system for predicting OS and LCSS in patients with LNECs.

Radiomics in precision medicine for gastric cancer: opportunities and challenges

OBJECTIVES

Radiomic features derived from routine medical images show great potential for personalized medicine in gastric cancer (GC). We aimed to evaluate the current status and quality of radiomic research as well as its potential for identifying biomarkers to predict therapy response and prognosis in patients with GC.

METHODS

We performed a systematic search of the PubMed and Embase databases for articles published from inception through July 10, 2021. The phase classification criteria for image mining studies and the radiomics quality scoring (RQS) tool were applied to evaluate scientific and reporting quality.

RESULTS

Twenty-five studies consisting of 10,432 patients were included. 96% of studies extracted radiomic features from CT images. Association between radiomic signature and therapy response was evaluated in seven (28%) studies; association with survival was evaluated in 17 (68%) studies; one (4%) study analyzed both. All results of the included studies showed significant associations. Based on the phase classification criteria for image mining studies, 18 (72%) studies were classified as phase II, with two, four, and one studies as discovery science, phase 0 and phase I, respectively. The median RQS score for the radiomic studies was 44.4% (range, 0 to 55.6%). There was extensive heterogeneity in the study population, tumor stage, treatment protocol, and radiomic workflow amongst the studies.

CONCLUSIONS

Although radiomic research in GC is highly heterogeneous and of relatively low quality, it holds promise for predicting therapy response and prognosis. Efforts towards standardization and collaboration are needed to utilize radiomics for clinical application.

KEY POINTS

• Radiomics application of gastric cancer is increasingly being reported, particularly in predicting therapy response and survival. • Although radiomics research in gastric cancer is highly heterogeneous and relatively low quality, it holds promise for predicting clinical outcomes. • Standardized imaging protocols and radiomic workflow are needed to facilitate radiomics into clinical use.

Relationship of FDG PET/CT Textural Features with the Tumor Microenvironment and Recurrence Risks in Patients with Advanced Gastric Cancers

The relationship between 2-deoxy-2-[18F]fluoro-D-glucose (FDG) positron emission tomography/computed tomography (PET/CT) textural features and histopathological findings in gastric cancer has not been fully evaluated. We investigated the relationship between the textural features of primary tumors on FDG PET/CT with histopathological findings and recurrence-free survival (RFS) in patients with advanced gastric cancer (AGC). Fifty-six patients with AGC who underwent FDG PET/CT for staging work-ups were retrospectively enrolled. Conventional parameters and the first- and second-order textural features of AGC were extracted using PET textural analysis. Upon histopathological analysis, along with histopathological classification and staging, the degree of CD4, CD8, and CD163 cell infiltrations and expressions of interleukin-6 and matrix-metalloproteinase-11 (MMP-11) in the primary tumor were assessed. The histopathological classification, Lauren classification, lymph node metastasis, CD8 T lymphocyte and CD163 macrophage infiltrations, and MMP-11 expression were significantly associated with the textural features of AGC. The multivariate survival analysis showed that increased FDG uptake and intra-tumoral metabolic heterogeneity were significantly associated with an increased risk of recurrence after curative surgery. Textural features of AGC on FDG PET/CT showed significant correlations with the inflammatory response in the tumor microenvironment and histopathological features of AGC, and they showed significant prognostic values for predicting RFS.

18F-FDG PET/CT-based radiomics nomogram for the preoperative prediction of lymph node metastasis in gastric cancer

Objective

Lymph node metastasis (LNM) is not only one of the important factors affecting the prognosis of gastric cancer but also an important basis for treatment decisions. The purpose of this study was to investigate the value of the radiomics nomogram based on preoperative ¹⁸F-deoxyglucose (FDG) PET/CT primary lesions and clinical risk factors for predicting LNM in gastric cancer (GC).

Methods

We retrospectively analyzed radiomics features of preoperative ¹⁸F-FDG PET/CT images in 224 gastric cancer patients from two centers. The prediction model was developed in the training cohort (n = 134) and validated in the internal (n = 59) and external validation cohorts (n = 31). The least absolute shrinkage and selection operator (LASSO) regression was used to select features and build radiomics signatures. The radiomics feature score (Rad-score) was calculated and established a radiomics signature. Multivariate logistic regression analysis was used to screen independent risk factors for LNM. The minimum Akaike’s information criterion (AIC) was used to select the optimal model parameters to construct a radiomics nomogram. The performance of the nomogram was assessed with calibration, discrimination, and clinical usefulness.

Results

There was no significant difference between the internal verification and external verification of the clinical data of patients (all p > 0.05). The areas under the curve (AUCs) (95% CI) for predicting LNM based on the ¹⁸F-FDG PET/CT radiomics signature in the training cohort, internal validation cohort, and external validation cohort were 0.792 (95% CI: 0.712–0.870), 0.803 (95% CI: 0.681–0.924), and 0.762 (95% CI: 0.579–0.945), respectively. Multivariate logistic regression showed that carbohydrate antigen (CA) 19-9 [OR (95% CI): 10.180 (1.267–81.831)], PET/CT diagnosis of LNM [OR (95% CI): 6.370 (2.256–17.984)], PET/CT Rad-score [OR (95% CI): 16.536 (5.506–49.660)] were independent influencing factors of LNM (all p < 0.05), and a radiomics nomogram was established based on those factors. The AUCs (95% CI) for predicting LNM were 0.861 (95% CI: 0.799–0.924), 0.889 (95% CI: 0.800–0.976), and 0.897 (95% CI: 0.683–0.948) in the training cohort, the internal validation cohort, and the external validation cohort, respectively. Decision curve analysis (DCA) indicated that the ¹⁸F-FDG PET/CT-based radiomics nomogram has good clinical utility.

Conclusions

Radiomics nomogram based on the primary tumor of ¹⁸F-FDG PET/CT could facilitate the preoperative individualized prediction of LNM, which is helpful for risk stratification in GC patients.

Abdominal Computed Tomography Enhanced Image Features under an Automatic Segmentation Algorithm in Identification of Gastric Cancer and Gastric Lymphoma

To analyze the application value of CT-enhanced scanning based on artificial intelligence algorithm in the diagnosis of gastric cancer and gastric lymphoma, the CT images of 80 patients with Borrmann type IV gastric cancer or primary gastric lymphoma diagnosed by endoscopic pathology were retrospectively collected. Meanwhile, a lymph node recognition algorithm based on OTSU threshold segmentation was proposed for CT image processing. The results showed that the missed diagnosis rate of suspected lymph nodes and the missed lymph node detection rate of this algorithm were substantially lower than those of other algorithms (P < 0.05). The probability of gastric wall motility disappearance, perigastric fat infiltration, and type A enhancement pattern in the Borrmann type IV gastric cancer group was higher than that in the gastric lymphoma group, with remarkable differences (P < 0.05). There was no remarkable difference between the Borrmann type IV gastric cancer group and the gastric lymphoma group in the probability of swollen lymph nodes under the renal hilum (P > 0.05). In addition, 5the sensitivity (83.17%), specificity (95.52%), and accuracy (93.08%) of the combined detection of the three CT signs (stomach wall motility, perigastric fat infiltration, and enhancement mode) were substantially improved compared with those of a single sign (P < 0.05). To sum up, the lymph node recognition algorithm based on OTSU threshold segmentation had better performance in detecting gastric lymph nodes than traditional algorithms. The CT image characteristics of gastric wall motility, perigastric fat infiltration, and enhancement pattern based on artificial intelligence algorithms were effective indicators for distinguishing gastric cancer and gastric lymphoma.

Radiomics in Oncological PET Imaging: A Systematic Review-Part 2, Infradiaphragmatic Cancers, Blood Malignancies, Melanoma and Musculoskeletal Cancers

The objective of this review was to summarize published radiomics studies dealing with infradiaphragmatic cancers, blood malignancies, melanoma, and musculoskeletal cancers, and assess their quality. PubMed database was searched from January 1990 to February 2022 for articles performing radiomics on PET imaging of at least 1 specified tumor type. Exclusion criteria includd: non-oncological studies; supradiaphragmatic tumors; reviews, comments, cases reports; phantom or animal studies; technical articles without a clinically oriented question; studies including <30 patients in the training cohort. The review database contained PMID, first author, year of publication, cancer type, number of patients, study design, independent validation cohort and objective. This database was completed twice by the same person; discrepant results were resolved by a third reading of the articles. A total of 162 studies met inclusion criteria; 61 (37.7%) studies included >100 patients, 13 (8.0%) were prospective and 61 (37.7%) used an independent validation set. The most represented cancers were esophagus, lymphoma, and cervical cancer (n = 24, n = 24 and n = 19 articles, respectively). Most studies focused on 18F-FDG, and prognostic and response to treatment objectives. Although radiomics and artificial intelligence are technically challenging, new contributions and guidelines help improving research quality over the years and pave the way toward personalized medicine.

Machine learning for optimized individual survival prediction in resectable upper gastrointestinal cancer

PURPOSE

Surgical oncologists are frequently confronted with the question of expected long-term prognosis. The aim of this study was to apply machine learning algorithms to optimize survival prediction after oncological resection of gastroesophageal cancers.

METHODS

Eligible patients underwent oncological resection of gastric or distal esophageal cancer between 2001 and 2020 at Heidelberg University Hospital, Department of General Surgery. Machine learning methods such as multi-task logistic regression and survival forests were compared with usual algorithms to establish an individual estimation.

RESULTS

The study included 117 variables with a total of 1360 patients. The overall missingness was 1.3%. Out of eight machine learning algorithms, the random survival forest (RSF) performed best with a concordance index of 0.736 and an integrated Brier score of 0.166. The RSF demonstrated a mean area under the curve (AUC) of 0.814 over a time period of 10 years after diagnosis. The most important long-term outcome predictor was lymph node ratio with a mean AUC of 0.730. A numeric risk score was calculated by the RSF for each patient and three risk groups were defined accordingly. Median survival time was 18.8 months in the high-risk group, 44.6 months in the medium-risk group and above 10 years in the low-risk group.

CONCLUSION

The results of this study suggest that RSF is most appropriate to accurately answer the question of long-term prognosis. Furthermore, we could establish a compact risk score model with 20 input parameters and thus provide a clinical tool to improve prediction of oncological outcome after upper gastrointestinal surgery.

Radiomics in Gastric Cancer: First Clinical Investigation to Predict Lymph Vascular Invasion and Survival Outcome Using 18F-FDG PET/CT Images

Background

Lymph vascular invasion (LVI) is an unfavorable prognostic indicator in gastric cancer (GC). However, there are no reliable clinical techniques for preoperative predictions of LVI. The aim of this study was to develop and validate PET/CT-based radiomics signatures for predicting LVI of GC preoperatively. Radiomics nomograms were also established to predict patient survival outcomes.

Methods

This retrospective study registered 148 GC patients with histopathological confirmation for LVI status, who underwent pre-operative PET/CT scans (Discovery VCT 64 PET/CT system) from December 2014 to June 2019. Clinic-pathological factors (age, gender, and tumor grade, etc.) and metabolic PET data (maximum and mean standardized uptake value, total lesion glycolysis and metabolic tumor volume) were analyzed to identify independent LVI predictors. The dataset was randomly assigned to either the training set or test set in a 7:3 ratios. Three-dimensional (3D) radiomics features were extracted from each PET- and CT-volume of interests (VOI) singularly, and then a radiomics signature (RS) associated with LVI status is built by feature selection. Four models with different modalities (PET-RS: only PET radiomics features; CT-RS: only CT radiomics features; PET/CT-RS: both PET and CT radiomics features; PET/CT-RS plus clinical data) were developed to predict LVI. Patients were postoperatively followed up with PET/CT every 6-12 months for the first two years and then annually up to five years after surgery. The PET/CT radiomics score (Rad-scores) was calculated to assess survival outcome, and corresponding nomograms with radiomics (NWR) or without radiomics (NWOR) were established.

Results

Tumor grade and maximum standardized uptake value (SUVmax) were the independent LVI predictor. 1037 CT and PET 3D radiomics features were extracted separately and reduced to 4 and 5 features to build CT-RS and PET-RS, respectively. PET/CT-RS and PET/CT-RS plus clinical data (tumor grade and SUVmax) were also developed. The ROC analysis demonstrated clinical usefulness of PET/CT-RS plus clinical data (AUC values for training and validation, respectively 0.936 and 0.914) and PET/CT-RS (AUC values for training and validation, respectively 0.881 and 0.854), which both are superior to CT-RS (0.838 and 0.824) and PET-RS (0.821 and 0.812). SUVmax and LVI were independent prognostic indicators of both OS and PFS. Decision curve analysis (DCA) demonstrated NWR outperformed NWOR and was established to assess survival outcomes. For estimation of OS and PFS, the C-indexes of the NWR were 0. 88 and 0.88 in the training set, respectively, while the C-indexes of the NWOR were 0. 82 and 0.85 in the training set, respectively.

Conclusions

The PET/CT-based radiomics analysis might serve as a non-invasive approach to predict LVI status in GC patients and provide effective predictors of patient survival outcomes.

Machine learning analysis for the noninvasive prediction of lymphovascular invasion in gastric cancer using PET/CT and enhanced CT-based radiomics and clinical variables

PURPOSE

Lymphovascular invasion (LVI) is associated with metastasis and poor survival in patients with gastric cancer, yet the noninvasive diagnosis of LVI is difficult. This study aims to develop predictive models using different machine learning (ML) classifiers based on both enhanced CT and PET/CT images and clinical variables for preoperatively predicting lymphovascular invasion (LVI) status of gastric cancer.

METHODS

A total of 101 patients with gastric cancer who underwent surgery were retrospectively recruited, and the LVI status was confirmed by pathological analysis. Patients were randomly divided into a training dataset (n = 76) and a validation dataset (n = 25). By 3D manual segmentation, radiomics features were extracted from the PET and venous phase CT images. Image models, clinical models, and combined models were constructed by selected enhanced CT-based and PET-based radiomics features, clinical factors, and a combination of both, respectively. Three ML classifiers including adaptive boosting (AdaBoost), linear discriminant analysis (LDA), and logistic regression (LR) were used for model development. The performance of these predictive models was evaluated with respect to discrimination, calibration, and clinical usefulness.

RESULTS

Ten radiomics features and eight clinical factors were selected for the development of predictive models. In the validation dataset, the area under curve (AUC) values of clinical models using AdaBoost, LDA, and LR classifiers were 0.742, 0.706, and 0.690, respectively. The image models using AdaBoost, LDA, and LR classifiers achieved an AUC of 0.849, 0.778, and 0.810, respectively. The combined models showed improved performance than the image models and the clinical models, with the AUC values of AdaBoost, LDA, and LR classifier yielding 0.944, 0.929, and 0.921, respectively. The combined models also showed good calibration and clinical usefulness for LVI prediction.

CONCLUSION

ML-based models integrating PET/CT and enhanced CT radiomics features and clinical factors have good discrimination capability, which could serve as a noninvasive, preoperative tool for the prediction of LVI and assist surgical treatment decisions in patients with gastric cancer.

A CT-based deep learning radiomics nomogram for predicting the response to neoadjuvant chemotherapy in patients with locally advanced gastric cancer: A multicenter cohort study

BACKGROUND

Accurate prediction of treatment response to neoadjuvant chemotherapy (NACT) in individual patients with locally advanced gastric cancer (LAGC) is essential for personalized medicine. We aimed to develop and validate a deep learning radiomics nomogram (DLRN) based on pretreatment contrast-enhanced computed tomography (CT) images and clinical features to predict the response to NACT in patients with LAGC.

METHODS

719 patients with LAGC were retrospectively recruited from four Chinese hospitals between Dec 1st, 2014 and Nov 30th, 2020. The training cohort and internal validation cohort (IVC), comprising 243 and 103 patients, respectively, were randomly selected from center I; the external validation cohort1 (EVC1) comprised 207 patients from center II; and EVC2 comprised 166 patients from another two hospitals. Two imaging signatures, reflecting the phenotypes of the deep learning and handcrafted radiomics features, were constructed from the pretreatment portal venous-phase CT images. A four-step procedure, including reproducibility evaluation, the univariable analysis, the LASSO method, and the multivariable logistic regression analysis, was applied for feature selection and signature building. The integrated DLRN was then developed for the added value of the imaging signatures to independent clinicopathological factors for predicting the response to NACT. The prediction performance was assessed with respect to discrimination, calibration, and clinical usefulness. Kaplan-Meier survival curves based on the DLRN were used to estimate the disease-free survival (DFS) in the follow-up cohort (n = 300).

FINDINGS

The DLRN showed satisfactory discrimination of good response to NACT and yielded the areas under the receiver operating curve (AUCs) of 0.829 (95% CI, 0.739-0.920), 0.804 (95% CI, 0.732-0.877), and 0.827 (95% CI, 0.755-0.900) in the internal and two external validation cohorts, respectively, with good calibration in all cohorts (p > 0.05). Furthermore, the DLRN performed significantly better than the clinical model (p < 0.001). Decision curve analysis confirmed that the DLRN was clinically useful. Besides, DLRN was significantly associated with the DFS of patients with LAGC (p < 0.05).

INTERPRETATION

A deep learning-based radiomics nomogram exhibited a promising performance for predicting therapeutic response and clinical outcomes in patients with LAGC, which could provide valuable information for individualized treatment.

The radiomics-based tumor heterogeneity adds incremental value to the existing prognostic models for predicting outcome in localized clear cell renal cell carcinoma: a multicenter study

PURPOSE

Tumor heterogeneity, which is associated with poor outcomes, has not been exhibited in the University of California, Los Angeles, Integrated Staging System (UISS), and the Stage, Size, Grade and Necrosis (SSIGN) scores. Radiomics allows an in-depth characterization of heterogeneity across the tumor, but its incremental value to the existing prognostic models for clear cell renal cell carcinoma (ccRCC) outcome is unknown. The purpose of this study was to evaluate the association between the radiomics-based tumor heterogeneity and postoperative risk of recurrence in localized ccRCC, and to assess its incremental value to UISS and SSIGN.

METHODS

A multicenter 866 ccRCC patients derived from 12 Chinese hospitals were studied. The endpoint was recurrence-free survival (RFS). A CT-based radiomics signature (RS) was developed and assessed in the whole cohort and in the subgroups stratified by UISS and SSIGN. Two combined nomograms, the R-UISS (combining RS and UISS) and R-SSIGN (combining RS and SSIGN), were developed. The incremental value of RS to UISS and SSIGN in RFS prediction was evaluated. R statistical software was used for statistics.

RESULTS

Patients with low radiomics scores were 4.44 times more likely to experience recurrence than those with high radiomics scores (P<0.001). Stratified analysis suggested the association is significant among low- and intermediate-risk patients identified by UISS and SSIGN. The R-UISS and R-SSIGN showed better predictive capability than UISS and SSIGN did with higher C-indices (R-UISS vs. UISS, 0.74 vs. 0.64; R-SSIGN vs. SSIGN, 0.78 vs. 0.76) and higher clinical net benefit.

CONCLUSIONS

The radiomics-based tumor heterogeneity can predict outcome and add incremental value to the existing prognostic models in localized ccRCC patients. Incorporating radiomics-based tumor heterogeneity in ccRCC prognostic models may provide the opportunity to better surveillance and adjuvant clinical trial design.

CT-Based Radiomics Showing Generalization to Predict Tumor Regression Grade for Advanced Gastric Cancer Treated With Neoadjuvant Chemotherapy

Objective

The aim of this study was to develop and validate a radiomics model to predict treatment response in patients with advanced gastric cancer (AGC) sensitive to neoadjuvant therapies and verify its generalization among different regimens, including neoadjuvant chemotherapy (NAC) and molecular targeted therapy.

Materials and Methods

A total of 373 patients with AGC receiving neoadjuvant therapies were enrolled from five cohorts. Four cohorts of patients received different regimens of NAC, including three retrospective cohorts (training cohort and internal and external validation cohorts) and a prospective Dragon III cohort (NCT03636893). Another prospective SOXA (apatinib in combination with S-1 and oxaliplatin) cohort received neoadjuvant molecular targeted therapy (ChiCTR-OPC-16010061). All patients underwent computed tomography before treatment, and thereafter, tumor regression grade (TRG) was assessed. The primary tumor was delineated, and 2,452 radiomics features were extracted for each patient. Mutual information and random forest were used for dimensionality reduction and modeling. The performance of the radiomics model to predict TRG under different neoadjuvant therapies was evaluated.

Results

There were 28 radiomics features selected. The radiomics model showed generalization to predict TRG for AGC patients across different NAC regimens, with areas under the curve (AUCs) (95% interval confidence) of 0.82 (0.76~0.90), 0.77 (0.63~0.91), 0.78 (0.66~0.89), and 0.72 (0.66~0.89) in the four cohorts, with no statistical difference observed (all p > 0.05). However, the radiomics model showed poor predictive value on the SOXA cohort [AUC, 0.50 (0.27~0.73)], which was significantly worse than that in the training cohort (p = 0.010).

Conclusion

Radiomics is generalizable to predict TRG for AGC patients receiving NAC treatments, which is beneficial to transform appropriate treatment, especially for those insensitive to NAC.

Radiomics model based on preoperative 18F-fluorodeoxyglucose PET predicts N2-3b lymph node metastasis in gastric cancer patients

OBJECTIVE

The aim of the study was to construct and validate 18F-fluorodeoxyglucose (18F-FDG) PET-based radiomics nomogram and use it to predict N2-3b lymph node metastasis in Chinese patients with gastric cancer (GC).

METHODS

A total of 127 patients with pathologically confirmed GC who underwent preoperative 18F-FDG PET/CT imaging between January 2014 and September 2020 were enrolled as subjects in this study. We use the LIFEx software to extract PET radiomic features. A radiomics signature (Rad-score) was developed with the least absolute shrinkage and selection operator algorithm. Then a prediction model, which incorporated the Rad-score and independent clinical risk factors, was constructed and presented with a radiomics nomogram. Receiver operating characteristic (ROC) analysis was used to assess the performance of Rad-score and the nomogram. Finally, decision curve analysis (DCA) was applied to evaluate the clinical usefulness of the nomogram.

RESULTS

The PET Rad-score, which includes four selected features, was significantly related to pN2-3b (all P < 0.05). The prediction model, which comprised the Rad-score and carcinoembryonic antigen (CEA) level, showed good calibration and discrimination [area under the ROC curve: 0.81(95% confidence interval: 0.74-0.89), P < 0.001)]. The DCA also indicated that the prediction model was clinically useful.

CONCLUSION

This study presents a radiomics nomogram consisting of a radiomics signature based on PET images and CEA level that can be conveniently used for personalized prediction of high-risk N2-3b metastasis in Chinese GC patients.

Evaluation of the dependence of radiomic features on the machine learning model

BACKGROUND

In radiomic studies, several models are often trained with different combinations of feature selection methods and classifiers. The features of the best model are usually considered relevant to the problem, and they represent potential biomarkers. Features selected from statistically similarly performing models are generally not studied. To understand the degree to which the selected features of these statistically similar models differ, 14 publicly available datasets, 8 feature selection methods, and 8 classifiers were used in this retrospective study. For each combination of feature selection and classifier, a model was trained, and its performance was measured with AUC-ROC. The best-performing model was compared to other models using a DeLong test. Models that were statistically similar were compared in terms of their selected features.

RESULTS

Approximately 57% of all models analyzed were statistically similar to the best-performing model. Feature selection methods were, in general, relatively unstable (0.58; range 0.35-0.84). The features selected by different models varied largely (0.19; range 0.02-0.42), although the selected features themselves were highly correlated (0.71; range 0.4-0.92).

CONCLUSIONS

Feature relevance in radiomics strongly depends on the model used, and statistically similar models will generally identify different features as relevant. Considering features selected by a single model is misleading, and it is often not possible to directly determine whether such features are candidate biomarkers.

Radiomic analysis for predicting prognosis of colorectal cancer from preoperative 18F-FDG PET/CT

Background

To develop and validate a survival model with clinico-biological features and ¹⁸F- FDG PET/CT radiomic features via machine learning, and for predicting the prognosis from the primary tumor of colorectal cancer.

Methods

A total of 196 pathologically confirmed patients with colorectal cancer (stage I to stage IV) were included. Preoperative clinical factors, serum tumor markers, and PET/CT radiomic features were included for the recurrence-free survival analysis. For the modeling and validation, patients were randomly divided into the training (n = 137) and validation (n = 59) set, while the 78 stage III patients [training (n = 55), and validation (n = 23)] was divided for the further experiment. After selecting features by the log-rank test and variable-hunting methods, random survival forest (RSF) models were built on the training set to analyze the prognostic value of selected features. The performance of models was measured by C-index and was tested on the validation set with bootstrapping. Feature importance and the Pearson correlation were also analyzed.

Results

Radiomics signature (containing four PET/CT features and four clinical factors) achieved the best result for prognostic prediction of 196 patients (C-index 0.780, 95% CI 0.634–0.877). Moreover, four features (including two clinical features and two radiomics features) were selected for prognostic prediction of the 78 stage III patients (C-index was 0.820, 95% CI 0.676–0.900). K–M curves of both models significantly stratified low-risk and high-risk groups (P < 0.0001). Pearson correlation analysis demonstrated that selected radiomics features were correlated with tumor metabolic factors, such as SUVmean, SUVmax.

Conclusion

This study presents integrated clinico-biological-radiological models that can accurately predict the prognosis in colorectal cancer using the preoperative ¹⁸F-FDG PET/CT radiomics in colorectal cancer. It is of potential value in assisting the management and decision making for precision treatment in colorectal cancer.

Trial registration The retrospectively registered study was approved by the Ethics Committee of Fudan University Shanghai Cancer Center (No. 1909207-14-1910) and the data were analyzed anonymously.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12967-022-03262-5.

Benchmarking Feature Selection Methods in Radiomics

OBJECTIVES

A critical problem in radiomic studies is the high dimensionality of the datasets, which stems from small sample sizes and many generic features extracted from the volume of interest. Therefore, feature selection methods are used, which aim to remove redundant as well as irrelevant features. Because there are many feature selection algorithms, it is key to understand their performance in the context of radiomics.

MATERIALS AND METHODS

A total of 29 feature selection algorithms and 10 classifiers were evaluated on 10 publicly available radiomic datasets. Feature selection methods were compared for training times, for the stability of the selected features, and for ranking, which measures the pairwise similarity of the methods. In addition, the predictive performance of the algorithms was measured by utilizing the area under the receiver operating characteristic curve of the best-performing classifier.

RESULTS

Feature selections differed largely in training times as well as stability and similarity. No single method was able to outperform another one consistently in predictive performance.

CONCLUSION

Our results indicated that simpler methods are more stable than complex ones and do not perform worse in terms of area under the receiver operating characteristic curve. Analysis of variance, least absolute shrinkage and selection operator, and minimum redundancy, maximum relevance ensemble appear to be good choices for radiomic studies in terms of predictive performance, as they outperformed most other feature selection methods.