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

Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma

Objectives

Combination therapy of lenvatinib and immune checkpoint inhibitors (CLICI) has emerged as a promising approach for managing unresectable hepatocellular carcinoma (HCC). However, the response to such treatment is observed in only a subset of patients, underscoring the pressing need for reliable methods to identify potential responders.

Materials & methods

This was a retrospective analysis involving 120 patients with unresectable HCC. They were divided into training (n = 72) and validation (n = 48) cohorts. We developed an interpretable deep learning model using multiphase computed tomography (CT) images to predict whether patients will respond or not to CLICI treatment, based on the Response Evaluation Criteria in Solid Tumors, version 1.1 (RECIST v1.1). We evaluated the models' performance and analyzed the impact of each CT phase. Critical regions influencing predictions were identified and visualized through heatmaps.

Results

The multiphase model outperformed the best biphase and uniphase models, achieving an area under the curve (AUC) of 0.802 (95% CI = 0.780-0.824). The portal phase images were found to significantly enhance the model's predictive accuracy. Heatmaps identified six critical features influencing treatment response, offering valuable insights to clinicians. Additionally, we have made this model accessible via a web server at http://uhccnet.com/ for ease of use.

Conclusions

The integration of multiphase CT images with deep learning-generated heatmaps for predicting treatment response provides a robust and practical tool for guiding CLICI therapy in patients with unresectable HCC.

Predicting survival in patients with myelodysplastic/myeloproliferative neoplasms with SF3B1 mutation and thrombocytosis

We investigated data from 180 consecutive patients with myelodysplastic/myeloproliferative neoplasms with SF3B1 mutation and thrombocytosis (MDS/MPN-SF3B1-T) who were diagnosed according to the 2022 World Health Organization (WHO) classification of myeloid neoplasms to identify covariates associated with survival. At a median follow-up of 48 months (95% confidence interval [CI] 35-61 months), the median survival was 69 months (95% CI 59-79 months). Patients with bone marrow ring sideroblasts (RS) < 15% had shorter median overall survival (OS) than did those with bone marrow RS ≥ 15% (41 months [95% CI 32-50 months] versus 76 months [95% CI 59-93 months]; P < 0.001). According to the univariable analyses of OS, age ≥ 65 years (P < 0.001), hemoglobin concentration (Hb) < 80 g/L (P = 0.090), platelet count (PLT) ≥ 800 × 10E + 9/L (P = 0.087), bone marrow RS < 15% (P < 0.001), the Revised International Prognostic Scoring System (IPSS-R) cytogenetic category intermediate/poor/very poor (P = 0.005), SETBP1 mutation (P = 0.061) and SRSF2 mutation (P < 0.001) were associated with poor survival. Based on variables selected from univariable analyses, two separate survival prediction models, a clinical survival model, and a clinical-molecular survival model, were developed using multivariable analyses with the minimum value of the Akaike information criterion (AIC) to specifically predict outcomes in patients with MDS/MPN-SF3B1-T according to the 2022 WHO classification.

Detecting Adverse Pathology of Prostate Cancer With a Deep Learning Approach Based on a 3D Swin-Transformer Model and Biparametric MRI: A Multicenter Retrospective Study

BACKGROUND

Accurately detecting adverse pathology (AP) presence in prostate cancer patients is important for personalized clinical decision-making. Radiologists' assessment based on clinical characteristics showed poor performance for detecting AP presence.

PURPOSE

To develop deep learning models for detecting AP presence, and to compare the performance of these models with those of a clinical model (CM) and radiologists' interpretation (RI).

STUDY TYPE

Retrospective.

POPULATION

Totally, 616 men from six institutions who underwent radical prostatectomy, were divided into a training cohort (508 patients from five institutions) and an external validation cohort (108 patients from one institution).

FIELD STRENGTH/SEQUENCES

T2-weighted imaging with a turbo spin echo sequence and diffusion-weighted imaging with a single-shot echo plane-imaging sequence at 3.0 T.

ASSESSMENT

The reference standard for AP was histopathological extracapsular extension, seminal vesicle invasion, or positive surgical margins. A deep learning model based on the Swin-Transformer network (TransNet) was developed for detecting AP. An integrated model was also developed, which combined TransNet signature with clinical characteristics (TransCL). The clinical characteristics included biopsy Gleason grade group, Prostate Imaging Reporting and Data System scores, prostate-specific antigen, ADC value, and the lesion maximum cross-sectional diameter.

STATISTICAL TESTS

Model and radiologists' performance were assessed using area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. The Delong test was used to evaluate difference in AUC. P < 0.05 was considered significant.

RESULTS

The AUC of TransCL for detecting AP presence was 0.813 (95% CI, 0.726-0.882), which was higher than that of TransNet (0.791 [95% CI, 0.702-0.863], P = 0.429), and significantly higher than those of CM (0.749 [95% CI, 0.656-0.827]) and RI (0.664 [95% CI, 0.566-0.752]).

DATA CONCLUSION

TransNet and TransCL have potential to aid in detecting the presence of AP and some single adverse pathologic features.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: Stage 4.

Deep learning nomogram for predicting neoadjuvant chemotherapy response in locally advanced gastric cancer patients

PURPOSE

Developed and validated a deep learning radiomics nomogram using multi-phase contrast-enhanced computed tomography (CECT) images to predict neoadjuvant chemotherapy (NAC) response in locally advanced gastric cancer (LAGC) patients.

METHODS

This multi-center study retrospectively included 322 patients diagnosed with gastric cancer from January 2013 to June 2023 at two hospitals. Handcrafted radiomics technique and the EfficientNet V2 neural network were applied to arterial, portal venous, and delayed phase CT images to extract two-dimensional handcrafted and deep learning features. A nomogram model was built by integrating the handcrafted signature, the deep learning signature, with clinical features. Discriminative ability was assessed using the receiver operating characteristics (ROC) curve and the precision-recall (P-R) curve. Model fitting was evaluated using calibration curves, and clinical utility was assessed through decision curve analysis (DCA).

RESULTS

The nomogram exhibited excellent performance. The area under the ROC curve (AUC) was 0.848 [95% confidence interval (CI), 0.793-0.893)], 0.802 (95% CI 0.688-0.889), and 0.751 (95% CI 0.652-0.833) for the training, internal validation, and external validation sets, respectively. The AUCs of the P-R curves were 0.838 (95% CI 0.756-0.895), 0.541 (95% CI 0.329-0.740), and 0.556 (95% CI 0.376-0.722) for the corresponding sets. The nomogram outperformed the clinical model and handcrafted signature across all sets (all P < 0.05). The nomogram model demonstrated good calibration and provided greater net benefit within the relevant threshold range compared to other models.

CONCLUSION

This study created a deep learning nomogram using CECT images and clinical data to predict NAC response in LAGC patients undergoing surgical resection, offering personalized treatment insights.

Role of radiomics as a predictor of disease recurrence in ovarian cancer: a systematic review

Ovarian cancer is associated with high cancer-related mortality rate attributed to late-stage diagnosis, limited treatment options, and frequent disease recurrence. As a result, careful patient selection is important especially in setting of radical surgery. Radiomics is an emerging field in medical imaging, which may help provide vital prognostic evaluation and help patient selection for radical treatment strategies. This systematic review aims to assess the role of radiomics as a predictor of disease recurrence in ovarian cancer. A systematic search was conducted in Medline, EMBASE, and Web of Science databases. Studies meeting inclusion criteria investigating the use of radiomics to predict post-operative recurrence in ovarian cancer were included in our qualitative analysis. Study quality was assessed using the QUADAS-2 and Radiomics Quality Score tools. Six retrospective studies met the inclusion criteria, involving a total of 952 participants. Radiomic-based signatures demonstrated consistent performance in predicting disease recurrence, as evidenced by satisfactory area under the receiver operating characteristic curve values (AUC range 0.77-0.89). Radiomic-based signatures appear to good prognosticators of disease recurrence in ovarian cancer as estimated by AUC. The reviewed studies consistently reported the potential of radiomic features to enhance risk stratification and personalise treatment decisions in this complex cohort of patients. Further research is warranted to address limitations related to feature reliability, workflow heterogeneity, and the need for prospective validation studies.

Identifying the risk factors of ICU-acquired fungal infections: clinical evidence from using machine learning

Background

Fungal infections are associated with high morbidity and mortality in the intensive care unit (ICU), but their diagnosis is difficult. In this study, machine learning was applied to design and define the predictive model of ICU-acquired fungi (ICU-AF) in the early stage of fungal infections using Random Forest.

Objectives

This study aimed to provide evidence for the early warning and management of fungal infections.

Methods

We analyzed the data of patients with culture-positive fungi during their admission to seven ICUs of the First Affiliated Hospital of Chongqing Medical University from January 1, 2015, to December 31, 2019. Patients whose first culture was positive for fungi longer than 48 h after ICU admission were included in the ICU-AF cohort. A predictive model of ICU-AF was obtained using the Least Absolute Shrinkage and Selection Operator and machine learning, and the relationship between the features within the model and the disease severity and mortality of patients was analyzed. Finally, the relationships between the ICU-AF model, antifungal therapy and empirical antifungal therapy were analyzed.

Results

A total of 1,434 cases were included finally. We used lasso dimensionality reduction for all features and selected six features with importance ≥0.05 in the optimal model, namely, times of arterial catheter, enteral nutrition, corticosteroids, broadspectrum antibiotics, urinary catheter, and invasive mechanical ventilation. The area under the curve of the model for predicting ICU-AF was 0.981 in the test set, with a sensitivity of 0.960 and specificity of 0.990. The times of arterial catheter (p = 0.011, OR = 1.057, 95% CI = 1.053-1.104) and invasive mechanical ventilation (p = 0.007, OR = 1.056, 95%CI = 1.015-1.098) were independent risk factors for antifungal therapy in ICU-AF. The times of arterial catheter (p = 0.004, OR = 1.098, 95%CI = 0.855-0.970) were an independent risk factor for empirical antifungal therapy.

Conclusion

The most important risk factors for ICU-AF are the six time-related features of clinical parameters (arterial catheter, enteral nutrition, corticosteroids, broadspectrum antibiotics, urinary catheter, and invasive mechanical ventilation), which provide early warning for the occurrence of fungal infection. Furthermore, this model can help ICU physicians to assess whether empiric antifungal therapy should be administered to ICU patients who are susceptible to fungal infections.

Pathomics Signature for Prognosis and Chemotherapy Benefits in Stage III Colon Cancer

Importance

The current TNM staging system may not provide adequate information for prognostic purposes and to assess the potential benefits of chemotherapy for patients with stage III colon cancer.

Objective

To develop and validate a pathomics signature to estimate prognosis and benefit from chemotherapy using hematoxylin-eosin (H-E)-stained slides.

Design, Setting, and Participants

This retrospective prognostic study used data from consecutive patients with histologically confirmed stage III colon cancer at 2 medical centers between January 2012 and December 2015. A total of 114 pathomics features were extracted from digital H-E-stained images from Nanfang Hospital of Southern Medical University, Guangzhou, China, and a pathomics signature was constructed using a least absolute shrinkage and selection operator Cox regression model in the training cohort. The associations of the pathomics signature with disease-free survival (DFS) and overall survival (OS) were evaluated. Patients at the Sixth Affiliated Hospital, Sun Yat-sen University, Guangzhou, China, formed the validation cohort. Data analysis was conducted from September 2022 to March 2023.

Main Outcomes and Measures

The prognostic accuracy of the pathomics signature as well as its association with chemotherapy response were evaluated.

Results

This study included 785 patients (mean [SD] age, 62.7 [11.1] years; 437 [55.7%] male). A pathomics signature was constructed based on 4 features. Multivariable analysis revealed that the pathomics signature was an independent factor associated with DFS (hazard ratio [HR], 2.46 [95% CI, 2.89-4.13]; P < .001) and OS (HR, 2.78 [95% CI, 2.34-3.31]; P < .001) in the training cohort. Incorporating the pathomics signature into pathomics nomograms resulted in better performance for the estimation of prognosis than the traditional model in a concordance index comparison in the training cohort (DFS: HR, 0.88 [95% CI, 0.86-0.89] vs HR, 0.73 [95% CI, 0.71-0.75]; P < .001; OS: HR, 0.85 [95% CI, 0.84-0.86] vs HR, 0.74 [95% CI, 0.72-0.76]; P < .001) and validation cohort (DFS: HR, 0.83 [95% CI, 0.82-0.85] vs HR, 0.70 [95% CI, 0.67-0.72]; P < .001; OS: HR, 0.80 [95% CI, 0.78-0.82] vs HR, 0.69 [0.67-0.72]; P < .001). Further analysis revealed that patients with a low pathomics signature were more likely to benefit from chemotherapy (eg, combined cohort: DFS: HR, 0.44 [95% CI, 0.28-0.69]; P = .001; OS: HR, 0.43 [95% CI, 0.29-0.64]; P < .001).

Conclusions and Relevance

These findings suggest that a pathomics signature could help identify patients most likely to benefit from chemotherapy in stage III colon cancer.

Diagnostic accuracy of radiomics-based machine learning for neoadjuvant chemotherapy response and survival prediction in gastric cancer patients: A systematic review and meta-analysis

BACKGROUND

In recent years, researchers have explored the use of radiomics to predict neoadjuvant chemotherapy outcomes in gastric cancer (GC). Yet, a lingering debate persists regarding the accuracy of these predictions. Against this backdrop, this study was conducted to examine the accuracy of radiomics in predicting the response to neoadjuvant chemotherapy in GC patients.

METHODS

An exhaustive search of relevant studies was conducted in PubMed, Cochrane, Embase, and Web of Science databases up to February 21, 2023. The radiomics quality scoring (RQS) tool was employed to assess study quality. Tumor response to neoadjuvant chemotherapy and survival outcomes were examined as outcome measures.

RESULTS

Fourteen studies involving 3,373 GC patients who had received neoadjuvant chemotherapy were incorporated in our meta-analysis. The mean RQS score across all studies was 36.3%, ranging between 0 and 63.9%. On the validation cohort, when the modeling variables were restricted to radiomic features alone, the predictive performance was characterized by a c-index of 0.750 (95% CI: 0.710-0.790), with a sensitivity of 0.67 (95% CI: 0.58-0.75) and a specificity of 0.77 (95% CI: 0.69-0.84) for the prediction of neoadjuvant chemotherapy response. When clinical data was integrated with radiomic features as modeling variables, the predictive performance improved, yielding a c-index of 0.814 (95% CI: 0.780-0.847), a sensitivity of 0.78 [95% CI: 0.70-0.84], and a specificity of 0.73 [95% CI: 0.67-0.79].

CONCLUSIONS

Radiomics holds promise to noninvasively predict neoadjuvant chemotherapy response and survival outcomes among patients with locally advanced GC. Additionally, we underscore the need for future multicenter studies and the development of imaging-sourced tools for risk stratification in this patient population.

Predicting pathologic response to neoadjuvant chemotherapy in locally advanced gastric cancer: The establishment of a spectral CT-based nomogram from prospective datasets

BACKGROUND

To establish a spectral CT-based nomogram for predicting early neoadjuvant chemotherapy (NAC) response for locally advanced gastric cancer (LAGC).

METHODS

This study prospectively recruited 222 cases (177 male and 45 female patients, 9.59 ± 9.54 years) receiving NAC and radical gastrectomy. Triple enhanced spectral CT scans were performed before NAC initiation. According to post-operative tumor regression grade (TRG), patients were classified into responders (TRG = 0 + 1) or non-responders (TRG = 2 + 3), and split into a primary (156) and validation (66) dataset at 7:3 ratio chronologically. We compared clinicopathological data, follow-up information, iodine concentration (IC), normalized ICs (nICs) in arterial/venous/delayed phases (AP/VP/DP) between responders and non-responders. Independent risk factors of response were screened by multivariable logistic regression and adopted for model construction. Model was visualized by nomograms and its capability was determined through receiver operating characteristic (ROC) curves. Log-rank survival analysis was conducted to explore associations between TRG, nomogram and patients' survival.

RESULTS

This work identified Borrmann classification, ICDP, and nICDP were independent risk factors of response outcomes. A spectral CT-based nomogram was built accordingly and achieved an area under the curve (AUC) of 0.797 (0.692-0.879) and 0.741(0.661-0.811) for the primary and validation dataset, respectively, higher than AUC of individual parameters alone. The nomogram was related to disease-free survival in the validation dataset (Hazard ratio (HR): 5.19 [1.18-12.93], P = 0.02).

CONCLUSIONS

The spectral CT-based nomogram provides an efficient tool for predicting the pathologic response outcomes of GC after NAC and disease-free survival risk stratification.

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

Background

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

Objective

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

Methods

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

Results

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

Conclusion

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

Systematic review registration

PROSPERO, CRD42022377030.

Addressing the Contrast Media Recognition Challenge: A Fully Automated Machine Learning Approach for Predicting Contrast Phases in CT Imaging

OBJECTIVES

Accurately acquiring and assigning different contrast-enhanced phases in computed tomography (CT) is relevant for clinicians and for artificial intelligence orchestration to select the most appropriate series for analysis. However, this information is commonly extracted from the CT metadata, which is often wrong. This study aimed at developing an automatic pipeline for classifying intravenous (IV) contrast phases and additionally for identifying contrast media in the gastrointestinal tract (GIT).

MATERIALS AND METHODS

This retrospective study used 1200 CT scans collected at the investigating institution between January 4, 2016 and September 12, 2022, and 240 CT scans from multiple centers from The Cancer Imaging Archive for external validation. The open-source segmentation algorithm TotalSegmentator was used to identify regions of interest (pulmonary artery, aorta, stomach, portal/splenic vein, liver, portal vein/hepatic veins, inferior vena cava, duodenum, small bowel, colon, left/right kidney, urinary bladder), and machine learning classifiers were trained with 5-fold cross-validation to classify IV contrast phases (noncontrast, pulmonary arterial, arterial, venous, and urographic) and GIT contrast enhancement. The performance of the ensembles was evaluated using the receiver operating characteristic area under the curve (AUC) and 95% confidence intervals (CIs).

RESULTS

For the IV phase classification task, the following AUC scores were obtained for the internal test set: 99.59% [95% CI, 99.58-99.63] for the noncontrast phase, 99.50% [95% CI, 99.49-99.52] for the pulmonary-arterial phase, 99.13% [95% CI, 99.10-99.15] for the arterial phase, 99.8% [95% CI, 99.79-99.81] for the venous phase, and 99.7% [95% CI, 99.68-99.7] for the urographic phase. For the external dataset, a mean AUC of 97.33% [95% CI, 97.27-97.35] and 97.38% [95% CI, 97.34-97.41] was achieved for all contrast phases for the first and second annotators, respectively. Contrast media in the GIT could be identified with an AUC of 99.90% [95% CI, 99.89-99.9] in the internal dataset, whereas in the external dataset, an AUC of 99.73% [95% CI, 99.71-99.73] and 99.31% [95% CI, 99.27-99.33] was achieved with the first and second annotator, respectively.

CONCLUSIONS

The integration of open-source segmentation networks and classifiers effectively classified contrast phases and identified GIT contrast enhancement using anatomical landmarks.

Nomogram for predicting pathological response to neoadjuvant treatment in patients with locally advanced gastric cancer: Data from a phase III clinical trial

PURPOSE

This study aimed to establish a nomogram using routinely available clinicopathological parameters to predict the pathological response in patients with locally advanced gastric cancer (LAGC) undergoing neoadjuvant treatment.

MATERIALS AND METHODS

We conducted this study based on the ongoing Neo-CRAG trial, a prospective study focused on preoperative treatment in patients with LAGC. A total of 221 patients who underwent surgery following neoadjuvant chemotherapy (nCT) or neoadjuvant chemoradiotherapy (nCRT) at Sun Yat-sen University Cancer Center between June 2013 and July 2022 were included in the analysis. We defined complete or near-complete pathological regression and ypN0 as good response (GR), and determined the prognostic value of GR by Kaplan-Meier survival analysis. Eventually, a nomogram for predicting GR was developed based on statistically identified predictors through multivariate logistic regression analysis and internally validated by the bootstrap method.

RESULTS

GR was confirmed in 54 patients (54/221, 24.4%). Patients who achieved GR had a longer progression-free survival and overall survival. Then, five independent factors, including pretreatment tumor differentiation, clinical T stage, monocyte count, CA724 level, and the use of nCRT, were identified. Based on these predictors, the nomogram was established with an area under the curve (AUC) of 0.777 (95% CI, 0.705-0.850) and a bias-corrected AUC of 0.752.

CONCLUSION

A good pathological response after neoadjuvant treatment was associated with an improved prognosis in LAGC patients. The nomogram we established exhibits a high predictive capability for GR, offering potential value in devising personalized and precise treatment strategies for LAGC patients.

Prediction by a multiparametric magnetic resonance imaging-based radiomics signature model of disease-free survival in patients with rectal cancer treated by surgery

Objective

The aim of this study was to assess the ability of a multiparametric magnetic resonance imaging (MRI)-based radiomics signature model to predict disease-free survival (DFS) in patients with rectal cancer treated by surgery.

Materials and methods

We evaluated data of 194 patients with rectal cancer who had undergone radical surgery between April 2016 and September 2021. The mean age of all patients was 62.6 ± 9.7 years (range: 37-86 years). The study endpoint was DFS and 1132 radiomic features were extracted from preoperative MRIs, including contrast-enhanced T1- and T2-weighted imaging and apparent diffusion coefficient values. The study patients were randomly allocated to training (n=97) and validation cohorts (n=97) in a ratio of 5:5. A multivariable Cox regression model was used to generate a radiomics signature (rad score). The associations of rad score with DFS were evaluated using Kaplan-Meier analysis. Three models, namely a radiomics nomogram, radiomics signature, and clinical model, were compared using the Akaike information criterion.

Result

The rad score, which was composed of four MRI features, stratified rectal cancer patients into low- and high-risk groups and was associated with DFS in both the training (p = 0.0026) and validation sets (p = 0.036). Moreover, a radiomics nomogram model that combined rad score and independent clinical risk factors performed better (Harrell concordance index [C-index] =0.77) than a purely radiomics signature (C-index=0.73) or clinical model (C-index=0.70).

Conclusion

An MRI radiomics model that incorporates a radiomics signature and clinicopathological factors more accurately predicts DFS than does a clinical model in patients with rectal cancer.

A bibliometric insight into neoadjuvant chemotherapy in bladder cancer: trends, collaborations, and future avenues

Background

Neoadjuvant chemotherapy (NAC) followed by radical cystectomy (RC) remains the cornerstone of treatment for muscle-invasive bladder cancer (MIBC). While platinum-based regimens have demonstrated benefits in tumor downstaging and improved long-term survival for selected patients, they may pose risks for those who are ineligible or unresponsive to chemotherapy.

Objective

We undertook a bibliometric analysis to elucidate the breadth of literature on NAC in bladder cancer, discern research trajectories, and underscore emerging avenues of investigation.

Methods

A systematic search of the Web of Science Core Collection (WoSCC) was conducted to identify articles pertaining to NAC in bladder cancer from 1999 to 2022. Advanced bibliometric tools, such as VOSviewer, CiteSpace, and SCImago Graphica, facilitated the examination and depicted the publication trends, geographic contributions, institutional affiliations, journal prominence, author collaborations, and salient keywords, emphasizing the top 25 citation bursts.

Results

Our analysis included 1836 publications spanning 1999 to 2022, indicating a growing trend in both annual publications and citations related to NAC in bladder cancer. The United States emerged as the predominant contributor in terms of publications, citations, and international collaborations. The University of Texas was the leading institution in publication output. "Urologic Oncology Seminars and Original Investigations" was the primary publishing journal, while "European Urology" boasted the highest impact factor. Shariat, Shahrokh F., and Grossman, H.B., were identified as the most prolific and co-cited authors, respectively. Keyword analysis revealed both frequency of occurrence and citation bursts, highlighting areas of concentrated study. Notably, the integration of immunochemotherapy is projected to experience substantial growth in forthcoming research.

Conclusions

Our bibliometric assessment provides a panoramic view of the research milieu surrounding neoadjuvant chemotherapy for bladder cancer, encapsulating the present state, evolving trends, and potential future directions, with a particular emphasis on the promise of immunochemotherapy.

Risk factors, prognostic factors, and nomograms for distant metastases in patients with gastroenteropancreatic neuroendocrine tumors: a population-based study

Background

Patients with gastroenteropancreatic neuroendocrine tumors (GEP-NETs) have a poor prognosis for distant metastasis. Currently, there are no studies on predictive models for the risk of distant metastasis in GEP-NETs.

Methods

In this study, risk factors associated with metastasis in patients with GEP-NETs in the Surveillance, Epidemiology, and End Results (SEER) database were analyzed by univariate and multivariate logistic regression, and a nomogram model for metastasis risk prediction was constructed. Prognostic factors associated with distant metastasis in patients with GEP-NETs were analyzed by univariate and multivariate Cox, and a nomogram model for prognostic prediction was constructed. Finally, the performance of the nomogram model predictions is validated by internal validation set and external validation set.

Results

A total of 9145 patients with GEP-NETs were enrolled in this study. Univariate and multivariate logistic analysis demonstrated that T stage, N stage, tumor size, primary site, and histologic types independent risk factors associated with distant metastasis in GEP-NETs patients (p value < 0.05). Univariate and multivariate Cox analyses demonstrated that age, histologic type, tumor size, N stage, and primary site surgery were independent factors associated with the prognosis of patients with GEP-NETs (p value < 0.05). The nomogram model constructed based on metastasis risk factors and prognostic factors can predict the occurrence of metastasis and patient prognosis of GEP-NETs very effectively in the internal training and validation sets as well as in the external validation set.

Conclusion

In conclusion, we constructed a new distant metastasis risk nomogram model and a new prognostic nomogram model for GEP-NETs patients, which provides a decision-making reference for individualized treatment of clinical patients.

Total versus proximal gastrectomy for proximal gastric cancer after neoadjuvant chemotherapy: a multicenter retrospective propensity score-matched cohort study

BACKGROUND

This study aimed to analyze and compare the short-term and long-term outcomes of proximal gastrectomy (PG) and total gastrectomy (TG) in patients with locally advanced proximal gastric cancer (GC) following neoadjuvant chemotherapy (NACT).

METHOD

A multicenter retrospective cohort study and propensity score matching (PSM) were employed. The authors examined 367 patients with proximal GC who received NACT followed by PG ( n =164) or TG ( n =203) at two Chinese medical institutions between December 2009 and December 2022. Clinical and pathological parameters, postoperative complications, and 5-year overall survival (OS) and recurrence-free survival (RFS) were compared between the two groups. The dissection status and metastasis rate of each lymph node station were assessed.

RESULTS

After PSM, 80 patients were enrolled in both TG and PG group, and baseline characteristics were comparable between the groups (all P >0.05). The TG group had a higher total number of lymph nodes retrieved ( P <0.001) and longer operative time ( P =0.007) compared to the PG group. The incidence of Clavien-Dindo grade II or higher postoperative complications was similar between the TG group (21.3%, 17/80) and the PG group (17.5%, 14/80) ( P =0.689). The 5-year OS rates were 68.4 for the PG group and 66.0% for the TG group ( P =0.881), while the 5-year RFS rates were 64.8 and 61.9%, respectively ( P =0.571), with no statistically significant differences. Metastasis rates at lymph node stations #4d, #5, #6, and #12a were notably low in the TG group, with values of 2.74, 0.67, 1.33, and 1.74%, respectively.

CONCLUSION

For proximal GC patients following NACT, PG maintains comparable curative potential and oncological efficacy to TG, making it a safe option.

Peritumoral Radiomics for Identification of Telomerase Reverse Transcriptase Promoter Mutation in Patients With Glioblastoma Based on Preoperative MRI

Purpose: To evaluate the value of intra- and peritumoral deep learning (DL) features based on multi-parametric magnetic resonance imaging (MRI) for identifying telomerase reverse transcriptase (TERT) promoter mutation in glioblastoma (GBM). Methods: In this study, we included 229 patients with GBM who underwent preoperative MRI in two hospitals between November 2016 and September 2022. We used four 2D Convolutional Neural Networks (GoogLeNet, DenseNet121, VGG16, and MobileNetV3-Large) to extract intra- and peritumoral DL features. The Mann-Whitney U test, Pearson correlation analysis, least absolute shrinkage and selection operator, and logistic regression analysis were used for feature selection and construction of DL radiomics (DLR) signatures in different regions. These multi-parametric and multi-region signatures were combined to identify TERT promoter mutation. The area under the receiver operating characteristic curve (AUC) was used to evaluate the effects of the signatures. Results: The signatures based on the DL features from the peritumoral regions with expansion distances of 2 mm, 8 mm, and 10 mm using the GoogLeNet architecture correlated with the optimal AUC values (test set: .823, .753, and .768) in the T2-weighted, T1-weighted contrast-enhanced, and T1-weighted images. Using the stacking fusion method, DLR with multi-parameter and multi-region fusion achieved the best discrimination with AUC values of .948 and .902 in the training and test sets, respectively. Conclusions: The radiomics model based on the fusion of multi-parameter MRI intra- and peritumoral DLR signatures may help to identify TERT promoter mutation in patients with GBM.

Development and validation of a CT-based deep learning radiomics nomogram to predict muscle invasion in bladder cancer

Objective

This study aimed to develop a nomogram combining CT-based handcrafted radiomics and deep learning (DL) features to preoperatively predict muscle invasion in bladder cancer (BCa) with multi-center validation.

Methods

In this retrospective study, 323 patients underwent radical cystectomy with pathologically confirmed BCa were enrolled and randomly divided into the training cohort (n = 226) and internal validation cohort (n = 97). And fifty-two patients from another independent medical center were enrolled as an independent external validation cohort. Handcrafted radiomics and DL features were constructed from preoperative nephrographic phase CT images. Least absolute shrinkage and selection operator (LASSO) regression was used to identify the most discriminative features in train cohort. Multivariate logistic regression was used to develop the predictive model and a deep learning radiomics nomogram (DLRN) was constructed. The predictive performance of models was evaluated by area under the curves (AUC) in the three cohorts. The calibration and clinical usefulness of DLRN were estimated by calibration curve and decision curve analysis.

Results

The nomogram that incorporated radiomics signature and DL signature demonstrated satisfactory predictive performance for differentiating non-muscle invasive bladder cancer (NMIBC) from muscle invasive bladder cancer (MIBC), with an AUC of 0.884 (95 % CI: 0.813-0.953) in internal validation cohort and 0.862 (95 % CI: 0.756-0.968) in external validation cohort, respectively. Decision curve analysis confirmed the clinical usefulness of the nomogram.

Conclusions

A CT-based deep learning radiomics nomogram exhibited a promising performance for preoperative prediction of muscle invasion in bladder cancer, and may be helpful in the clinical decision-making process.

Intratumoral and peritumoral radiomics predict pathological response after neoadjuvant chemotherapy against advanced gastric cancer

BACKGROUND

To investigate whether intratumoral and peritumoral radiomics may predict pathological responses after neoadjuvant chemotherapy against advanced gastric cancer.

METHODS

Clinical, pathological, and CT data from 231 patients with advanced gastric cancer who underwent neoadjuvant chemotherapy at our hospital between July 2014 and February 2022 were retrospectively collected. Patients were randomly divided into a training group (n = 161) and a validation group (n = 70). The support vector machine classifier was used to establish radiomics models. A clinical model was established based on the selected clinical indicators. Finally, the radiomics and clinical models were combined to generate a radiomics-clinical model. ROC analyses were used to evaluate the prediction efficiency for each model. Calibration curves and decision curves were used to evaluate the optimal model.

RESULTS

A total of 91 cases were recorded with good response and 140 with poor response. The radiomics model demonstrated that the AUC was higher in the combined model than in the intratumoral and peritumoral models (training group: 0.949, 0.943, and 0.846, respectively; validation group: 0.815, 0.778, and 0.701, respectively). Age, Borrmann classification, and Lauren classification were used to construct the clinical model. Among the radiomics-clinical models, the combined-clinical model showed the highest AUC (training group: 0.960; validation group: 0.843), which significantly improved prediction efficiency.

CONCLUSION

The peritumoral model provided additional value in the evaluation of pathological response after neoadjuvant chemotherapy against advanced gastric cancer, and the combined-clinical model showed the highest predictive efficiency.

CRITICAL RELEVANCE STATEMENT

Intratumoral and peritumoral radiomics can noninvasively predict the pathological response against advanced gastric cancer after neoadjuvant chemotherapy to guide early treatment decision and provide individual treatment for patients.

KEY POINTS

1. Radiomics can predict pathological responses after neoadjuvant chemotherapy against advanced gastric cancer. 2. Peritumoral radiomics has additional predictive value. 3. Radiomics-clinical models can guide early treatment decisions and improve patient prognosis.

Exploring non-invasive precision treatment in non-small cell lung cancer patients through deep learning radiomics across imaging features and molecular phenotypes

BACKGROUND

Accurate prediction of tumor molecular alterations is vital for optimizing cancer treatment. Traditional tissue-based approaches encounter limitations due to invasiveness, heterogeneity, and molecular dynamic changes. We aim to develop and validate a deep learning radiomics framework to obtain imaging features that reflect various molecular changes, aiding first-line treatment decisions for cancer patients.

METHODS

We conducted a retrospective study involving 508 NSCLC patients from three institutions, incorporating CT images and clinicopathologic data. Two radiomic scores and a deep network feature were constructed on three data sources in the 3D tumor region. Using these features, we developed and validated the 'Deep-RadScore,' a deep learning radiomics model to predict prognostic factors, gene mutations, and immune molecule expression levels.

FINDINGS

The Deep-RadScore exhibits strong discrimination for tumor molecular features. In the independent test cohort, it achieved impressive AUCs: 0.889 for lymphovascular invasion, 0.903 for pleural invasion, 0.894 for T staging; 0.884 for EGFR and ALK, 0.896 for KRAS and PIK3CA, 0.889 for TP53, 0.895 for ROS1; and 0.893 for PD-1/PD-L1. Fusing features yielded optimal predictive power, surpassing any single imaging feature. Correlation and interpretability analyses confirmed the effectiveness of customized deep network features in capturing additional imaging phenotypes beyond known radiomic features.

INTERPRETATION

This proof-of-concept framework demonstrates that new biomarkers across imaging features and molecular phenotypes can be provided by fusing radiomic features and deep network features from multiple data sources. This holds the potential to offer valuable insights for radiological phenotyping in characterizing diverse tumor molecular alterations, thereby advancing the pursuit of non-invasive personalized treatment for NSCLC patients.

Development and validation of a nomogram model based on pretreatment ultrasound and contrast-enhanced ultrasound to predict the efficacy of neoadjuvant chemotherapy in patients with borderline resectable or locally advanced pancreatic cancer

OBJECTIVES

To develop a nomogram using pretreatment ultrasound (US) and contrast-enhanced ultrasound (CEUS) to predict the clinical response of neoadjuvant chemotherapy (NAC) in patients with borderline resectable pancreatic cancer (BRPC) or locally advanced pancreatic cancer (LAPC).

METHODS

A total of 111 patients with pancreatic ductal adenocarcinoma (PDAC) treated with NAC between October 2017 and February 2022 were retrospectively enrolled. The patients were randomly divided (7:3) into training and validation cohorts. The pretreatment US and CEUS features were reviewed. Univariate and multivariate logistic regression analyses were used to determine the independent predictors of clinical response in the training cohort. Then a prediction nomogram model based on the independent predictors was constructed. The area under the curve (AUC), calibration plot, C-index and decision curve analysis (DCA) were used to assess the nomogram's performance, calibration, discrimination and clinical benefit.

RESULTS

The multivariate logistic regression analysis showed that the taller-than-wide shape in the longitudinal plane (odds ratio [OR]:0.20, p = 0.01), time from injection of contrast agent to peak enhancement (OR:3.64; p = 0.05) and Peaktumor/ Peaknormal (OR:1.51; p = 0.03) were independent predictors of clinical response to NAC. The predictive nomogram developed based on the above imaging features showed AUCs were 0.852 and 0.854 in the primary and validation cohorts, respectively. Good calibration was achieved in the training datasets, with C-index of 0.852. DCA verified the clinical usefulness of the nomogram.

CONCLUSIONS

The nomogram based on pretreatment US and CEUS can effectively predict the clinical response of NAC in patients with BRPC and LAPC; it may help guide personalized treatment.

CT-based deep learning radiomics and hematological biomarkers in the assessment of pathological complete response to neoadjuvant chemoradiotherapy in patients with esophageal squamous cell carcinoma: A two-center study

PURPOSE

To evaluate and validate CT-based models using pre- and posttreatment deep learning radiomics features and hematological biomarkers for assessing esophageal squamous cell carcinoma (ESCC) pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT).

MATERIAL AND METHODS

This retrospective study recruited patients with biopsy-proven ESCC who underwent nCRT from two Chinese hospitals between May 2017 and May 2022, divided into a training set (hospital I, 111 cases), an internal validation set (hospital I, 47 cases), and an external validation set (hospital II, 33 cases). We used minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) as feature selection methods and three classifiers as model construction methods. The assessment of models was performed using area under the receiver operating characteristic (ROC) curve (AUC) and decision curve analysis (DCA).

RESULTS

A total 190 patients were included in our study (60.8 ± 7.08 years, 133 men), and seventy-seven of them (40.5 %) achieved pCR. The logistic regression (LR)-based combined model incorporating neutrophil to lymphocyte ratio, lymphocyte to monocyte ratio, albumin, and radscores performed well both in the internal and external validation sets with AUCs of 0.875 and 0.857 (95 % CI, 0.776-0.964; 0.731-0.984, P <0.05), respectively. DCA demonstrated that nomogram was useful for pCR prediction and produced clinical net benefits.

CONCLUSION

The incorporation of radscores and hematological biomarkers into LR-based model improved pCR prediction after nCRT in ESCC. Enhanced pCR predictability may improve patients selection before surgery, providing clinical application value for the use of active surveillance.

Prediction of recurrence risk factors in patients with early-stage cervical cancers by nomogram based on MRI handcrafted radiomics features and deep learning features: a dual-center study

PURPOSE

To establish and validate a deep learning radiomics nomogram (DLRN) based on intratumoral and peritumoral regions of MR images and clinical characteristics to predict recurrence risk factors in early-stage cervical cancer and to clarify whether DLRN could be applied for risk stratification.

METHODS

Two hundred and twenty five pathologically confirmed early-stage cervical cancers were enrolled and made up the training cohort and internal validation cohort, and 40 patients from another center were enrolled into the external validation cohort. On the basis of region of interest (ROI) of intratumoral and different peritumoral regions, two sets of features representing deep learning and handcrafted radiomics features were created using combined images of T2-weighted MRI (T2WI) and diffusion-weighted imaging (DWI). The signature subset with the best discriminant features was chosen, and deep learning and handcrafted signatures were created using logistic regression. Integrated with independent clinical factors, a DLRN was built. The discrimination and calibration of DLNR were applied to assess its therapeutic utility.

RESULTS

The DLRN demonstrated satisfactory performance for predicting recurrence risk factors, with AUCs of 0.944 (95% confidence interval 0.896-0.992) and 0.885 (95% confidence interval 0.834-0.937) in the internal and external validation cohorts. Furthermore, decision curve analysis revealed that the DLRN outperformed the clinical model, deep learning signature, and radiomics signature in terms of net benefit.

CONCLUSION

A DLRN based on intratumoral and peritumoral regions had the potential to predict and stratify recurrence risk factors for early-stage cervical cancers and enhance the value of individualized precision treatment.

Fusion Radiomics-Based Prediction of Response to Neoadjuvant Chemotherapy for Osteosarcoma

RATIONALE AND OBJECTIVES

Neoadjuvant chemotherapy (NAC) is the most crucial prognostic factor for osteosarcoma (OS), it significantly prolongs progression-free survival and improves the quality of life. This study aims to develop a deep learning radiomics (DLR) model to accurately predict the response to NAC in patients diagnosed with OS using preoperative MR images.

METHODS

We reviewed axial T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted (T1CE) of 106 patients pathologically confirmed as OS. First, the Auto3DSeg framework was utilized for automated OS segmentation. Second, using three feature extraction methods, nine risk classification models were constructed based on three classifiers. The area under the receiver operating curve (AUC), sensitivity, specificity, accuracy, negative predictive value and positive predictive value were calculated for performance evaluation. Additionally, we developed a deep learning radiomics nomogram with clinical indicators.

RESULTS

The model for OS automatic segmentation achieved a Dice coefficient of 0.868 across datasets. To predict the response to NAC, the DLR model achieved the highest prediction performance with an accuracy of 93.8% and an AUC of 0.961 in the test sets. We used calibration curves to assess the predictive ability of the models and performed decision curve analysis to evaluate the clinical net benefit of the DLR model.

CONCLUSION

The DLR model can serve as a pragmatic prediction tool, capable of identifying patients with poor response to NAC, providing information for risk counseling, and assisting in making clinical treatment decisions. Poor responders are better advised to undergo immunotherapy and receive the best supportive care.

Imaging advances in efficacy assessment of gastric cancer neoadjuvant chemotherapy

Effective neoadjuvant chemotherapy (NAC) can improve the survival of patients with locally progressive gastric cancer, but chemotherapeutics do not always exhibit good efficacy in all patients. Therefore, accurate preoperative evaluation of the effect of neoadjuvant therapy and the appropriate selection of surgery time to minimize toxicity and complications while prolonging patient survival are key issues that need to be addressed. This paper reviews the role of three imaging methods, morphological, functional, radiomics, and artificial intelligence (AI)-based imaging, in evaluating NAC pathological reactions for gastric cancer. In addition, the advantages and disadvantages of each method and the future application prospects are discussed.

Development and external validation of the multichannel deep learning model based on unenhanced CT for differentiating fat-poor angiomyolipoma from renal cell carcinoma: a two-center retrospective study

PURPOSE

There are undetectable levels of fat in fat-poor angiomyolipoma. Thus, it is often misdiagnosed as renal cell carcinoma. We aimed to develop and evaluate a multichannel deep learning model for differentiating fat-poor angiomyolipoma (fp-AML) from renal cell carcinoma (RCC).

METHODS

This two-center retrospective study included 320 patients from the First Affiliated Hospital of Sun Yat-Sen University (FAHSYSU) and 132 patients from the Sun Yat-Sen University Cancer Center (SYSUCC). Data from patients at FAHSYSU were divided into a development dataset (n = 267) and a hold-out dataset (n = 53). The development dataset was used to obtain the optimal combination of CT modality and input channel. The hold-out dataset and SYSUCC dataset were used for independent internal and external validation, respectively.

RESULTS

In the development phase, models trained on unenhanced CT images performed significantly better than those trained on enhanced CT images based on the fivefold cross-validation. The best patient-level performance, with an average area under the receiver operating characteristic curve (AUC) of 0.951 ± 0.026 (mean ± SD), was achieved using the "unenhanced CT and 7-channel" model, which was finally selected as the optimal model. In the independent internal and external validation, AUCs of 0.966 (95% CI 0.919-1.000) and 0.898 (95% CI 0.824-0.972), respectively, were obtained using the optimal model. In addition, the performance of this model was better on large tumors (≥ 40 mm) in both internal and external validation.

CONCLUSION

The promising results suggest that our multichannel deep learning classifier based on unenhanced whole-tumor CT images is a highly useful tool for differentiating fp-AML from RCC.

Development and validation of CT-based radiomics deep learning signatures to predict lymph node metastasis in non-functional pancreatic neuroendocrine tumors: a multicohort study

Background

Lymph node status is an important factor for the patients with non-functional pancreatic neuroendocrine tumors (NF-PanNETs) with respect to the surgical methods, prognosis, recurrence. Our aim is to develop and validate a combination model based on contrast-enhanced CT images to predict the lymph node metastasis (LNM) in NF-PanNETs.

Methods

Retrospective data were gathered for 320 patients with NF-PanNETs who underwent curative pancreatic resection and CT imaging at two institutions (Center 1, n = 236 and Center 2, n = 84) between January 2010 and March 2022. RDPs (Radiomics deep learning signature) were developed based on ten machine-learning techniques. These signatures were integrated with the clinicopathological factors into a nomogram for clinical applications. The evaluation of the model's performance was conducted through the metrics of the area under the curve (AUC).

Findings

The RDPs showed excellent performance in both centers with a high AUC for predicting LNM and disease-free survival (DFS) in Center 1 (AUC, 0.88; 95% CI: 0.84-0.92; DFS, p < 0.05) and Center 2 (AUC, 0.91; 95% CI: 0.85-0.97; DFS, p < 0.05). The clinical factors of vascular invasion, perineural invasion, and tumor grade were associated with LNM (p < 0.05). The combination nomogram showed better prediction capability for LNM (AUC, 0.93; 95% CI: 0.89-0.96). Notably, our model maintained a satisfactory predictive ability for tumors at the 2-cm threshold, demonstrating its effectiveness across different tumor sizes in Center 1 (≤2 cm: AUC, 0.90 and >2 cm: AUC, 0.86) and Center 2 (≤2 cm: AUC, 0.93 and >2 cm: AUC, 0.91).

Interpretation

Our RDPs may have the potential to preoperatively predict LNM in NF-PanNETs, address the insufficiency of clinical guidelines concerning the 2-cm threshold for tumor lymph node dissection, and provide precise therapeutic strategies.

Funding

This work was supported by JSPS KAKENHI Grant Number JP22K20814; the Rare Tumor Research Special Project of the National Natural Science Foundation of China (82141104) and Clinical Research Special Project of Shanghai Municipal Health Commission (202340123).

Development of a novel combined nomogram model integrating deep learning radiomics to diagnose IgA nephropathy clinically

This study aimed to develop and validate a combined nomogram model based on superb microvascular imaging (SMI)-based deep learning (DL), radiomics characteristics, and clinical factors for noninvasive differentiation between immunoglobulin A nephropathy (IgAN) and non-IgAN.We prospectively enrolled patients with chronic kidney disease who underwent renal biopsy from May 2022 to December 2022 and performed an ultrasound and SMI the day before renal biopsy. The selected patients were randomly divided into training and testing cohorts in a 7:3 ratio. We extracted DL and radiometric features from the two-dimensional ultrasound and SMI images. A combined nomograph model was developed by combining the predictive probability of DL with clinical factors using multivariate logistic regression analysis. The proposed model's utility was evaluated using receiver operating characteristics, calibration, and decision curve analysis. In this study, 120 patients with primary glomerular disease were included, including 84 in the training and 36 in the test cohorts. In the testing cohort, the ROC of the radiomics model was 0.816 (95% CI:0.663-0.968), and the ROC of the DL model was 0.844 (95% CI:0.717-0.971). The nomogram model combined with independent clinical risk factors (IgA and hematuria) showed strong discrimination, with an ROC of 0.884 (95% CI:0.773-0.996) in the testing cohort. Decision curve analysis verified the clinical practicability of the combined nomogram. The combined nomogram model based on SMI can accurately and noninvasively distinguish IgAN from non-IgAN and help physicians make clearer patient treatment plans.

Development of a deep learning model for early gastric cancer diagnosis using preoperative computed tomography images

Background

Gastric cancer is a highly prevalent and fatal disease. Accurate differentiation between early gastric cancer (EGC) and advanced gastric cancer (AGC) is essential for personalized treatment. Currently, the diagnostic accuracy of computerized tomography (CT) for gastric cancer staging is insufficient to meet clinical requirements. Many studies rely on manual marking of lesion areas, which is not suitable for clinical diagnosis.

Methods

In this study, we retrospectively collected data from 341 patients with gastric cancer at the First Affiliated Hospital of Wenzhou Medical University. The dataset was randomly divided into a training set (n=273) and a validation set (n=68) using an 8:2 ratio. We developed a two-stage deep learning model that enables fully automated EGC screening based on CT images. In the first stage, an unsupervised domain adaptive segmentation model was employed to automatically segment the stomach on unlabeled portal phase CT images. Subsequently, based on the results of the stomach segmentation model, the image was cropped out of the stomach area and scaled to a uniform size, and then the EGC and AGC classification models were built based on these images. The segmentation accuracy of the model was evaluated using the dice index, while the classification performance was assessed using metrics such as the area under the curve (AUC) of the receiver operating characteristic (ROC), accuracy, sensitivity, specificity, and F1 score.

Results

The segmentation model achieved an average dice accuracy of 0.94 on the hand-segmented validation set. On the training set, the EGC screening model demonstrated an AUC, accuracy, sensitivity, specificity, and F1 score of 0.98, 0.93, 0.92, 0.92, and 0.93, respectively. On the validation set, these metrics were 0.96, 0.92, 0.90, 0.89, and 0.93, respectively. After three rounds of data regrouping, the model consistently achieved an AUC above 0.9 on both the validation set and the validation set.

Conclusion

The results of this study demonstrate that the proposed method can effectively screen for EGC in portal venous CT images. Furthermore, the model exhibits stability and holds promise for future clinical applications.

An MRI-based machine learning radiomics can predict short-term response to neoadjuvant chemotherapy in patients with cervical squamous cell carcinoma: A multicenter study

BACKGROUND AND PURPOSE

Neoadjuvant chemotherapy (NACT) has become an essential component of the comprehensive treatment of cervical squamous cell carcinoma (CSCC). However, not all patients respond to chemotherapy due to individual differences in sensitivity and tolerance to chemotherapy drugs. Therefore, accurately predicting the sensitivity of CSCC patients to NACT was vital for individual chemotherapy. This study aims to construct a machine learning radiomics model based on magnetic resonance imaging (MRI) to assess its efficacy in predicting NACT susceptibility among CSCC patients.

METHODS

This study included 234 patients with CSCC from two hospitals, who were divided into a training set (n = 180), a testing set (n = 20), and an external validation set (n = 34). Manual radiomic features were extracted from transverse section MRI images, and feature selection was performed using the recursive feature elimination (RFE) method. A prediction model was then generated using three machine learning algorithms, namely logistic regression, random forest, and support vector machines (SVM), for predicting NACT susceptibility. The model's performance was assessed based on the area under the receiver operating characteristic curve (AUC), accuracy, and sensitivity.

RESULTS

The SVM approach achieves the highest scores on both the testing set and the external validation set. In the testing set and external validation set, the AUC of the model was 0.88 and 0.764, and the accuracy was 0.90 and 0.853, the sensitivity was 0.93 and 0.962, respectively.

CONCLUSIONS

Machine learning radiomics models based on MRI images have achieved satisfactory performance in predicting the sensitivity of NACT in CSCC patients with high accuracy and robustness, which has great significance for the treatment and personalized medicine of CSCC patients.

Artificial intelligence-based radiomics in bone tumors: Technical advances and clinical application

Radiomics is the extraction of predefined mathematic features from medical images for predicting variables of clinical interest. Recent research has demonstrated that radiomics can be processed by artificial intelligence algorithms to reveal complex patterns and trends for diagnosis, and prediction of prognosis and response to treatment modalities in various types of cancer. Artificial intelligence tools can utilize radiological images to solve next-generation issues in clinical decision making. Bone tumors can be classified as primary and secondary (metastatic) tumors. Osteosarcoma, Ewing sarcoma, and chondrosarcoma are the dominating primary tumors of bone. The development of bone tumor model systems and relevant research, and the assessment of novel treatment methods are ongoing to improve clinical outcomes, notably for patients with metastases. Artificial intelligence and radiomics have been utilized in almost full spectrum of clinical care of bone tumors. Radiomics models have achieved excellent performance in the diagnosis and grading of bone tumors. Furthermore, the models enable to predict overall survival, metastases, and recurrence. Radiomics features have exhibited promise in assisting therapeutic planning and evaluation, especially neoadjuvant chemotherapy. This review provides an overview of the evolution and opportunities for artificial intelligence in imaging, with a focus on hand-crafted features and deep learning-based radiomics approaches. We summarize the current application of artificial intelligence-based radiomics both in primary and metastatic bone tumors, and discuss the limitations and future opportunities of artificial intelligence-based radiomics in this field. In the era of personalized medicine, our in-depth understanding of emerging artificial intelligence-based radiomics approaches will bring innovative solutions to bone tumors and achieve clinical application.

Preoperative CT-based radiomics combined with tumour spread through air spaces can accurately predict early recurrence of stage I lung adenocarcinoma: a multicentre retrospective cohort study

OBJECTIVE

To develop and validate a prediction model for early recurrence of stage I lung adenocarcinoma (LUAD) that combines radiomics features based on preoperative CT with tumour spread through air spaces (STAS).

MATERIALS AND METHODS

The most recent preoperative thin-section chest CT scans and postoperative pathological haematoxylin and eosin-stained sections were retrospectively collected from patients with a postoperative pathological diagnosis of stage I LUAD. Regions of interest were manually segmented, and radiomics features were extracted from the tumour and peritumoral regions extended by 3 voxel units, 6 voxel units, and 12 voxel units, and 2D and 3D deep learning image features were extracted by convolutional neural networks. Then, the RAdiomics Integrated with STAS model (RAISm) was constructed. The performance of RAISm was then evaluated in a development cohort and validation cohort.

RESULTS

A total of 226 patients from two medical centres from January 2015 to December 2018 were retrospectively included as the development cohort for the model and were randomly split into a training set (72.6%, n = 164) and a test set (27.4%, n = 62). From June 2019 to December 2019, 51 patients were included in the validation cohort. RAISm had excellent discrimination in predicting the early recurrence of stage I LUAD in the training cohort (AUC = 0.847, 95% CI 0.762-0.932) and validation cohort (AUC = 0.817, 95% CI 0.625-1.000). RAISm outperformed single modality signatures and other combinations of signatures in terms of discrimination and clinical net benefits.

CONCLUSION

We pioneered combining preoperative CT-based radiomics with STAS to predict stage I LUAD recurrence postoperatively and confirmed the superior effect of the model in validation cohorts, showing its potential to assist in postoperative treatment strategies.

Contrast-Enhanced CT Imaging Features Combined with Clinical Factors to Predict the Efficacy and Prognosis for Transarterial Chemoembolization of Hepatocellular Carcinoma

RATIONALE AND OBJECTIVES

Accurate prediction of treatment response to transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC) is critical for precision treatment. This study aimed to develop a comprehensive model (DLRC) that incorporates contrast-enhanced computed tomography (CECT) images and clinical factors to predict the response to TACE in patients with HCC.

MATERIALS AND METHODS

A total of 399 patients with intermediate-stage HCC were included in this retrospective study. Deep learning and radiomic signatures were established based on arterial phase CECT images, Correlation analysis and the least absolute shrinkage and selection (LASSO) regression analysis were applied for features selection. The DLRC model incorporating deep learning radiomic signatures and clinical factors was developed using multivariate logistic regression. The area under the receiver operating characteristic curve (AUC), calibration curve and decision curve analysis (DCA) were used to evaluate the performance of the models. Kaplan-Meier survival curves based on the DLRC were plotted to assess overall survival in the follow-up cohort (n = 261).

RESULTS

The DLRC model was developed using 19 quantitative radiomic features, 10 deep learning features, and 3 clinical factors. The AUC of the DLRC model was 0.937 (95% confidence interval [CI], 0.912-0.962) and 0.909 (95% CI, 0.850-0.968) in the training and validation cohorts, respectively, outperforming models established with two signatures or a single signature (p < 0.05). Stratified analysis showed that the DLRC was not statistically different between subgroups (p > 0.05), and the DCA confirmed the greater net clinical benefit. In addition, multivariable cox regression revealed that DLRC model outputs were independent risk factors for the overall survival (hazard ratios: 1.20, 95% CI: 1.03-1.40; p = 0.019).

CONCLUSION

The DLRC model exhibited a remarkable accuracy in predicting response to TACE, and it can be utilized as a potent tool for precision treatment.

Comparison of MRI and CT-Based Radiomics and Their Combination for Early Identification of Pathological Response to Neoadjuvant Chemotherapy in Locally Advanced Gastric Cancer

BACKGROUND

Current radiomics for treatment response assessment in gastric cancer (GC) have focused solely on Computed tomography (CT). The importance of multi-parametric magnetic resonance imaging (mp-MRI) radiomics in GC is less clear.

PURPOSE

To compare and combine CT and mp-MRI radiomics for pretreatment identification of pathological response to neoadjuvant chemotherapy in GC.

STUDY TYPE

Retrospective.

POPULATION

Two hundred twenty-five GC patients were recruited and split into training (157) and validation dataset (68) in the ratio of 7:3 randomly.

FIELD/SEQUENCE

T2-weighted fast spin echo (fat suppressed T2-weighted imaging [fs-T2WI]), diffusion weighted echo planar imaging (DWI), and fast gradient echo (dynamic contrast enhanced [DCE]) sequences at 3.0T.

ASSESSMENT

Apparent diffusion coefficient (ADC) maps were generated from DWI. CT, fs-T2WI, ADC, DCE, and mp-MRI Radiomics score (Radscores) were compared between responders and non-responders. A multimodal nomogram combining CT and mp-MRI Radscores was developed. Patients were followed up for 3-65 months (median 19) after surgery, the overall survival (OS) and progression free survival (PFS) were calculated.

STATISTICAL TESTS

A logistic regression classifier was applied to construct the five models. Each model's performance was evaluated using a receiver operating characteristic curve. The association of the nomogram with OS/PFS was evaluated by Kaplan-Meier survival analysis and C-index. A P value <0.05 was considered statistically significant.

RESULTS

CT Radscore, mp-MRI Radscore and nomogram were significantly associated with tumor regression grading. The nomogram achieved the highest area under the curves (AUCs) of 0.893 (0.834-0.937) and 0.871 (0.767-0.940) in training and validation datasets, respectively. The C-index was 0.589 for OS and 0.601 for PFS. The AUCs of the mp-MRI model were not significantly different to that of the CT model in training (0.831 vs. 0.770, P = 0.267) and validation dataset (0.797 vs. 0.746, P = 0.137).

DATA CONCLUSIONS

mp-MRI radiomics provides similar results to CT radiomics for early identification of pathologic response to neoadjuvant chemotherapy. The multimodal radiomics nomogram further improved the capability.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: 2.

Application of artificial intelligence for improving early detection and prediction of therapeutic outcomes for gastric cancer in the era of precision oncology

Gastric cancer is a leading contributor to cancer incidence and mortality globally. Recently, artificial intelligence approaches, particularly machine learning and deep learning, are rapidly reshaping the full spectrum of clinical management for gastric cancer. Machine learning is formed from computers running repeated iterative models for progressively improving performance on a particular task. Deep learning is a subtype of machine learning on the basis of multilayered neural networks inspired by the human brain. This review summarizes the application of artificial intelligence algorithms to multi-dimensional data including clinical and follow-up information, conventional images (endoscope, histopathology, and computed tomography (CT)), molecular biomarkers, etc. to improve the risk surveillance of gastric cancer with established risk factors; the accuracy of diagnosis, and survival prediction among established gastric cancer patients; and the prediction of treatment outcomes for assisting clinical decision making. Therefore, artificial intelligence makes a profound impact on almost all aspects of gastric cancer from improving diagnosis to precision medicine. Despite this, most established artificial intelligence-based models are in a research-based format and often have limited value in real-world clinical practice. With the increasing adoption of artificial intelligence in clinical use, we anticipate the arrival of artificial intelligence-powered gastric cancer care.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

What benefit can be obtained from magnetic resonance imaging diagnosis with artificial intelligence in prostate cancer compared with clinical assessments?

The present study aimed to explore the potential of artificial intelligence (AI) methodology based on magnetic resonance (MR) images to aid in the management of prostate cancer (PCa). To this end, we reviewed and summarized the studies comparing the diagnostic and predictive performance for PCa between AI and common clinical assessment methods based on MR images and/or clinical characteristics, thereby investigating whether AI methods are generally superior to common clinical assessment methods for the diagnosis and prediction fields of PCa. First, we found that, in the included studies of the present study, AI methods were generally equal to or better than the clinical assessment methods for the risk assessment of PCa, such as risk stratification of prostate lesions and the prediction of therapeutic outcomes or PCa progression. In particular, for the diagnosis of clinically significant PCa, the AI methods achieved a higher summary receiver operator characteristic curve (SROC-AUC) than that of the clinical assessment methods (0.87 vs. 0.82). For the prediction of adverse pathology, the AI methods also achieved a higher SROC-AUC than that of the clinical assessment methods (0.86 vs. 0.75). Second, as revealed by the radiomics quality score (RQS), the studies included in the present study presented a relatively high total average RQS of 15.2 (11.0-20.0). Further, the scores of the individual RQS elements implied that the AI models in these studies were constructed with relatively perfect and standard radiomics processes, but the exact generalizability and clinical practicality of the AI models should be further validated using higher levels of evidence, such as prospective studies and open-testing datasets.

A virtual biopsy study of microsatellite instability in gastric cancer based on deep learning radiomics

OBJECTIVES

This study aims to develop and validate a virtual biopsy model to predict microsatellite instability (MSI) status in preoperative gastric cancer (GC) patients based on clinical information and the radiomics of deep learning algorithms.

METHODS

A total of 223 GC patients with MSI status detected by postoperative immunohistochemical staining (IHC) were retrospectively recruited and randomly assigned to the training (n = 167) and testing (n = 56) sets in a 3:1 ratio. In the training set, 982 high-throughput radiomic features were extracted from preoperative abdominal dynamic contrast-enhanced CT (CECT) and screened. According to the deep learning multilayer perceptron (MLP), 15 optimal features were optimized to establish the radiomic feature score (Rad-score), and LASSO regression was used to screen out clinically independent predictors. Based on logistic regression, the Rad-score and clinically independent predictors were integrated to build the clinical radiomics model and visualized as a nomogram and independently verified in the testing set. The performance and clinical applicability of hybrid model in identifying MSI status were evaluated by the area under the receiver operating characteristic (AUC) curve, calibration curve, and decision curve (DCA).

RESULTS

The AUCs of the clinical image model in training set and testing set were 0.883 [95% CI: 0.822-0.945] and 0.802 [95% CI: 0.666-0.937], respectively. This hybrid model showed good consistency in the calibration curve and clinical applicability in the DCA curve, respectively.

CONCLUSIONS

Using preoperative imaging and clinical information, we developed a deep-learning-based radiomics model for the non-invasive evaluation of MSI in GC patients. This model maybe can potentially support clinical treatment decision making for GC patients.

Multiparametric MRI-based radiomics nomogram for early prediction of pathological response to neoadjuvant chemotherapy in locally advanced gastric cancer

OBJECTIVES

To build and validate a multi-parametric MRI (mpMRI)-based radiomics nomogram for early prediction of treatment response to neoadjuvant chemotherapy (NAC) in locally advanced gastric cancer.

METHODS

Baseline MRI were retrospectively enrolled from 141 patients with gastric adenocarcinoma who received NAC followed by radical gastrectomy. According to pathologic response of tumor regression grading (TRG), patients were labeled as responders (TRG = 0 + 1) and non-responders (TRG = 2 + 3) and further divided into a training (n = 85) and validation dataset (n = 56). Radiomics score (Radscore) were built from T2WI, ADC, and venous phase of dynamic-contrasted-enhanced MR imaging. Clinical information, laboratory indicators, MRI parameters, and follow-up data were also recorded. According to multivariable regression analysis, an mpMRI radiomics nomogram was built and its predictive ability was evaluated by ROC analysis. Decision curve analysis was applied to evaluate the clinical usefulness. Kaplan-Meier survival curves based on the nomogram were used to estimate the progression-free survival (PFS) and overall survival (OS) in the validation dataset.

RESULTS

Both single sequence-based Radscores and mpMRI radiomics nomogram were associated with pathologic response (p < 0.001). The nomogram achieved the highest diagnostic ability with area under ROC curve of 0.844 (95% CI, 0.749-0.914) and 0.820 (95% CI, 0.695-0.910) in the training and validation datasets. The hazard ratio of the nomogram for PFS and OS prediction was 2.597 (95% CI: 1.046-6.451, log-rank p = 0.023) and 2.570 (95% CI: 1.166-5.666, log-rank p = 0.011).

CONCLUSIONS

The mpMRI-based radiomics nomogram showed preferable performance in predicting pathologic response to NAC in LAGC.

KEY POINTS

• This study investigated the value of multi-parametric MRI-based radiomics in predicting pathologic response to neoadjuvant chemotherapy in locally advanced gastric cancer. • The nomogram incorporating T2WI Radscore, ADC Radscore, and DCE Radscore as well as Borrmann classification outperformed the single sequence-based Radscore. • The nomogram also exhibited a promising prognostic ability for patient survival and enriched radiomics studies in gastric cancer.

A Deep Learning Radiomics Nomogram to Predict Response to Neoadjuvant Chemotherapy for Locally Advanced Cervical Cancer: A Two-Center Study

Purpose: This study aimed to establish a deep learning radiomics nomogram (DLRN) based on multiparametric MR images for predicting the response to neoadjuvant chemotherapy (NACT) in patients with locally advanced cervical cancer (LACC). Methods: Patients with LACC (FIGO stage IB-IIIB) who underwent preoperative NACT were enrolled from center 1 (220 cases) and center 2 (independent external validation dataset, 65 cases). Handcrafted and deep learning-based radiomics features were extracted from T2WI, DWI and contrast-enhanced (CE)-T1WI, and radiomics signatures were built based on the optimal features. Two types of radiomics signatures and clinical features were integrated into the DLRN for prediction. The AUC, calibration curve and decision curve analysis (DCA) were employed to illustrate the performance of these models and their clinical utility. In addition, disease-free survival (DFS) was assessed by Kaplan–Meier survival curves based on the DLRN. Results: The DLRN showed favorable predictive values in differentiating responders from nonresponders to NACT with AUCs of 0.963, 0.940 and 0.910 in the three datasets, with good calibration (all p > 0.05). Furthermore, the DLRN performed better than the clinical model and handcrafted radiomics signature in all datasets (all p < 0.05) and slightly higher than the DL-based radiomics signature in the internal validation dataset (p = 0.251). DCA indicated that the DLRN has potential in clinical applications. Furthermore, the DLRN was strongly correlated with the DFS of LACC patients (HR = 0.223; p = 0.004). Conclusion: The DLRN performed well in preoperatively predicting the therapeutic response in LACC and could provide valuable information for individualized treatment.

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.

Role of Machine Learning in Precision Oncology: Applications in Gastrointestinal Cancers

Gastrointestinal (GI) cancers, consisting of a wide spectrum of pathologies, have become a prominent health issue globally. Despite medical imaging playing a crucial role in the clinical workflow of cancers, standard evaluation of different imaging modalities may provide limited information. Accurate tumor detection, characterization, and monitoring remain a challenge. Progress in quantitative imaging analysis techniques resulted in "radiomics", a promising methodical tool that helps to personalize diagnosis and treatment optimization. Radiomics, a sub-field of computer vision analysis, is a bourgeoning area of interest, especially in this era of precision medicine. In the field of oncology, radiomics has been described as a tool to aid in the diagnosis, classification, and categorization of malignancies and to predict outcomes using various endpoints. In addition, machine learning is a technique for analyzing and predicting by learning from sample data, finding patterns in it, and applying it to new data. Machine learning has been increasingly applied in this field, where it is being studied in image diagnosis. This review assesses the current landscape of radiomics and methodological processes in GI cancers (including gastric, colorectal, liver, pancreatic, neuroendocrine, GI stromal, and rectal cancers). We explain in a stepwise fashion the process from data acquisition and curation to segmentation and feature extraction. Furthermore, the applications of radiomics for diagnosis, staging, assessment of tumor prognosis and treatment response according to different GI cancer types are explored. Finally, we discussed the existing challenges and limitations of radiomics in abdominal cancers and investigate future opportunities.

Deep learning based radiomics for gastrointestinal cancer diagnosis and treatment: A minireview

Gastrointestinal (GI) cancers are the major cause of cancer-related mortality globally. Medical imaging is an important auxiliary means for the diagnosis, assessment and prognostic prediction of GI cancers. Radiomics is an emerging and effective technology to decipher the encoded information within medical images, and traditional machine learning is the most commonly used tool. Recent advances in deep learning technology have further promoted the development of radiomics. In the field of GI cancer, although there are several surveys on radiomics, there is no specific review on the application of deep-learning-based radiomics (DLR). In this review, a search was conducted on Web of Science, PubMed, and Google Scholar with an emphasis on the application of DLR for GI cancers, including esophageal, gastric, liver, pancreatic, and colorectal cancers. Besides, the challenges and recommendations based on the findings of the review are comprehensively analyzed to advance DLR.

PET/CT Based EGFR Mutation Status Classification of NSCLC Using Deep Learning Features and Radiomics Features

Purpose: This study aimed to compare the performance of radiomics and deep learning in predicting EGFR mutation status in patients with lung cancer based on PET/CT images, and tried to explore a model with excellent prediction performance to accurately predict EGFR mutation status in patients with non-small cell lung cancer (NSCLC). Method: PET/CT images of 194 NSCLC patients from Xijing Hospital were collected and divided into a training set and a validation set according to the ratio of 7:3. Statistics were made on patients' clinical characteristics, and a large number of features were extracted based on their PET/CT images (4306 radiomics features and 2048 deep learning features per person) with the pyradiomics toolkit and 3D convolutional neural network. Then a radiomics model (RM), a deep learning model (DLM), and a hybrid model (HM) were established. The performance of the three models was compared by receiver operating characteristic (ROC) curves, sensitivity, specificity, accuracy, calibration curves, and decision curves. In addition, a nomogram based on a deep learning score (DS) and the most significant clinical characteristic was plotted. Result: In the training set composed of 138 patients (64 with EGFR mutation and 74 without EGFR mutation), the area under the ROC curve (AUC) of HM (0.91, 95% CI: 0.86-0.96) was higher than that of RM (0.82, 95% CI: 0.75-0.89) and DLM (0.90, 95% CI: 0.85-0.95). In the validation set composed of 57 patients (32 with EGFR mutation and 25 without EGFR mutation), the AUC of HM (0.85, 95% CI: 0.77-0.93) was also higher than that of RM (0.68, 95% CI: 0.52-0.84) and DLM (0.79, 95% CI: 0.67-0.91). In all, HM achieved better diagnostic performance in predicting EGFR mutation status in NSCLC patients than two other models. Conclusion: Our study showed that the deep learning model based on PET/CT images had better performance than radiomics model in diagnosing EGFR mutation status of NSCLC patients based on PET/CT images. Combined with the most statistically significant clinical characteristic (smoking) and deep learning features, our hybrid model had better performance in predicting EGFR mutation types of patients than two other models, which could enable NSCLC patients to choose more personalized treatment schemes.