Radiomic analysis using contrast-enhanced CT: predict treatment response to pulsed low dose rate radiotherapy in gastric carcinoma with abdominal cavity metastasis

Radiomics from Cardiovascular MR Cine Images for Identifying Patients with Hypertrophic Cardiomyopathy at High Risk for Heart Failure

Purpose To develop a model integrating radiomics features from cardiac MR cine images with clinical and standard cardiac MRI predictors to identify patients with hypertrophic cardiomyopathy (HCM) at high risk for heart failure (HF). Materials and Methods In this retrospective study, 516 patients with HCM (median age, 51 years [IQR: 40-62]; 367 [71.1%] men) who underwent cardiac MRI from January 2015 to June 2021 were divided into training and validation sets (7:3 ratio). Radiomics features were extracted from cardiac cine images, and radiomics scores were calculated based on reproducible features using the least absolute shrinkage and selection operator Cox regression. Radiomics scores and clinical and standard cardiac MRI predictors that were significantly associated with HF events in univariable Cox regression analysis were incorporated into a multivariable analysis to construct a combined prediction model. Model performance was validated using time-dependent area under the receiver operating characteristic curve (AUC), and the optimal cutoff value of the combined model was determined for patient risk stratification. Results The radiomics score was the strongest predictor for HF events in both univariable (hazard ratio, 10.37; P < .001) and multivariable (hazard ratio, 10.25; P < .001) analyses. The combined model yielded the highest 1- and 3-year AUCs of 0.81 and 0.80, respectively, in the training set and 0.82 and 0.77 in the validation set. Patients stratified as high risk had more than sixfold increased risk of HF events compared with patients at low risk. Conclusion The combined model with radiomics features and clinical and standard cardiac MRI parameters accurately identified patients with HCM at high risk for HF. Keywords: Cardiomyopathies, Outcomes Analysis, Cardiovascular MRI, Hypertrophic Cardiomyopathy, Radiomics, Heart Failure Supplemental material is available for this article. © RSNA, 2024.

Development and validation of CT-based radiomics nomogram for the classification of benign parotid gland tumors

PURPOSE

Accurate preoperative diagnosis of parotid tumor is essential for the formulation of optimal individualized surgical plans. The study aims to investigate the diagnostic performance of radiomics nomogram based on contrast-enhanced computed tomography (CT) images in the differentiation of the two most common benign parotid gland tumors.

METHODS

One hundred and ten patients with parotid gland tumors including 76 with pleomorphic adenoma (PA) and 34 with adenolymphoma (AL) confirmed by histopathology were included in this study. Radiomics features were extracted from contrast-enhanced CT images of venous phase. A radiomics model was established and a radiomics score (Rad-score) was calculated. Clinical factors including clinical data and CT features were assessed to build a clinical factor model. Finally, a nomogram incorporating the Rad-score and independent clinical factors was constructed. Receiver operator characteristics (ROC) curve was generated and the area under the ROC curve (AUC) was calculated to quantify the discriminative performance of each model on both the training and validation cohorts. Decision curve analysis (DCA) was conducted to evaluate the clinical usefulness of each model.

RESULTS

The radiomics model showed good discrimination in the training cohort [AUC, 0.89; 95% confidence interval (CI), 0.80-0.98] and validation cohort (AUC, 0.89; 95% CI, 0.77-1.00). The radiomics nomogram showed excellent discrimination in the training cohort (AUC, 0.98; 95% CI, 0.96-1.00) and validation cohort (AUC, 0.95; 95% CI, 0.88-1.00) and displayed better discrimination efficacy compared with the clinical factor model (AUC, 0.93; 95% CI, 0.88-0.99) in the training cohort (p < 0.05). The DCA demonstrated that the combined radiomics nomogram provided superior clinical usefulness than clinical factor model and radiomics model.

CONCLUSIONS

The CT-based radiomics nomogram combining Rad-score and clinical factors exhibits excellent predictive capability for differentiating parotid PA from AL, which might hold promise in assisting radiologists and clinicians in the exact differential diagnosis and formulation of appropriate treatment strategy.

Impact of Wavelet Kernels on Predictive Capability of Radiomic Features: A Case Study on COVID-19 Chest X-ray Images

Radiomic analysis allows for the detection of imaging biomarkers supporting decision-making processes in clinical environments, from diagnosis to prognosis. Frequently, the original set of radiomic features is augmented by considering high-level features, such as wavelet transforms. However, several wavelets families (so called kernels) are able to generate different multi-resolution representations of the original image, and which of them produces more salient images is not yet clear. In this study, an in-depth analysis is performed by comparing different wavelet kernels and by evaluating their impact on predictive capabilities of radiomic models. A dataset composed of 1589 chest X-ray images was used for COVID-19 prognosis prediction as a case study. Random forest, support vector machine, and XGBoost were trained (on a subset of 1103 images) after a rigorous feature selection strategy to build-up the predictive models. Next, to evaluate the models generalization capability on unseen data, a test phase was performed (on a subset of 486 images). The experimental findings showed that Bior1.5, Coif1, Haar, and Sym2 kernels guarantee better and similar performance for all three machine learning models considered. Support vector machine and random forest showed comparable performance, and they were better than XGBoost. Additionally, random forest proved to be the most stable model, ensuring an appropriate balance between sensitivity and specificity.

Integration of Clinical and CT-Based Radiomic Features for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Systemic Therapy in Breast Cancer

The purpose of the present study was to examine the potential of a machine learning model with integrated clinical and CT-based radiomics features in predicting pathologic complete response (pCR) to neoadjuvant systemic therapy (NST) in breast cancer. Contrast-enhanced CT was performed in 329 patients with breast tumors (n = 331) before NST. Pyradiomics was used for feature extraction, and 107 features of seven classes were extracted. Feature selection was performed on the basis of the intraclass correlation coefficient (ICC), and six ICC thresholds (0.7−0.95) were examined to identify the feature set resulting in optimal model performance. Clinical factors, such as age, clinical stage, cancer cell type, and cell surface receptors, were used for prediction. We tried six machine learning algorithms, and clinical, radiomics, and clinical−radiomics models were trained for each algorithm. Radiomics and clinical−radiomics models with gray level co-occurrence matrix (GLCM) features only were also built for comparison. The linear support vector machine (SVM) regression model trained with radiomics features of ICC ≥0.85 in combination with clinical factors performed the best (AUC = 0.87). The performance of the clinical and radiomics linear SVM models showed statistically significant difference after correction for multiple comparisons (AUC = 0.69 vs. 0.78; p < 0.001). The AUC of the radiomics model trained with GLCM features was significantly lower than that of the radiomics model trained with all seven classes of radiomics features (AUC = 0.85 vs. 0.87; p = 0.011). Integration of clinical and CT-based radiomics features was helpful in the pretreatment prediction of pCR to NST in breast cancer.

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.

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.

A Comparative and Summative Study of Radiomics-based Overall Survival Prediction in Glioblastoma Patients

PURPOSE

This study aimed to assess different machine learning models based on radiomic features, Visually Accessible Rembrandt Images features and clinical characteristics in overall survival prediction of glioblastoma and to identify the reproducible features.

MATERIALS AND METHODS

Patients with preoperative magnetic resonance scans were allocated into 3 data sets. The Least Absolute Shrinkage and Selection Operator was used for feature selection. The prediction models were built by random survival forest (RSF) and Cox regression. C-index and integrated Brier scores were calculated to compare model performances.

RESULTS

Patients with cortical involvement had shorter survival times in the training set (P = 0.006). Random survival forest showed higher C-index than Cox, and the RSF model based on the radiomic features was the best one (testing set: C-index = 0.935 ± 0.023). Ten reproducible radiomic features were summarized.

CONCLUSIONS

The RSF model based on radiomic features had promising potential in predicting overall survival of glioblastoma. Ten reproducible features were identified.

A Bounding Box-Based Radiomics Model for Detecting Occult Peritoneal Metastasis in Advanced Gastric Cancer: A Multicenter Study

Purpose

To develop a bounding box (BBOX)-based radiomics model for the preoperative diagnosis of occult peritoneal metastasis (OPM) in advanced gastric cancer (AGC) patients.

Materials and Methods

599 AGC patients from 3 centers were retrospectively enrolled and were divided into training, validation, and testing cohorts. The minimum circumscribed rectangle of the ROIs for the largest tumor area (R_BBOX), the nonoverlapping area between the tumor and R_BBOX (peritumoral area; PERI) and the smallest rectangle that could completely contain the tumor determined by a radiologist (M_BBOX) were used as inputs to extract radiomic features. Multivariate logistic regression was used to construct a radiomics model to estimate the preoperative probability of OPM in AGC patients.

Results

The M_BBOX model was not significantly different from R_BBOX in the validation cohort [AUC: M_BBOX model 0.871 (95% CI, 0.814–0.940) vs. R_BBOX model 0.873 (95% CI, 0.820–0.940); p = 0.937]. M_BBOX was selected as the final radiomics model because of its extremely low annotation cost and superior OPM discrimination performance (sensitivity of 85.7% and specificity of 82.8%) over the clinical model, and this radiomics model showed comparable diagnostic efficacy in the testing cohort.

Conclusions

The BBOX-based radiomics could serve as a simpler reliable and powerful tool for the preoperative diagnosis of OPM in AGC patients. And M_BBOX-based radiomics is simpler and less time consuming.

Diagnostic Performance of Artificial Intelligence-Centred Systems in the Diagnosis and Postoperative Surveillance of Upper Gastrointestinal Malignancies Using Computed Tomography Imaging: A Systematic Review and Meta-Analysis of Diagnostic Accuracy

Background

Upper gastrointestinal cancers are aggressive malignancies with poor prognosis, even following multimodality therapy. As such, they require timely and accurate diagnostic and surveillance strategies; however, such radiological workflows necessitate considerable expertise and resource to maintain. In order to lessen the workload upon already stretched health systems, there has been increasing focus on the development and use of artificial intelligence (AI)-centred diagnostic systems. This systematic review summarizes the clinical applicability and diagnostic performance of AI-centred systems in the diagnosis and surveillance of esophagogastric cancers.

Methods

A systematic review was performed using the MEDLINE, EMBASE, Cochrane Review, and Scopus databases. Articles on the use of AI and radiomics for the diagnosis and surveillance of patients with esophageal cancer were evaluated, and quality assessment of studies was performed using the QUADAS-2 tool. A meta-analysis was performed to assess the diagnostic accuracy of sequencing methodologies.

Results

Thirty-six studies that described the use of AI were included in the qualitative synthesis and six studies involving 1352 patients were included in the quantitative analysis. Of these six studies, four studies assessed the utility of AI in gastric cancer diagnosis, one study assessed its utility for diagnosing esophageal cancer, and one study assessed its utility for surveillance. The pooled sensitivity and specificity were 73.4% (64.6–80.7) and 89.7% (82.7–94.1), respectively.

Conclusions

AI systems have shown promise in diagnosing and monitoring esophageal and gastric cancer, particularly when combined with existing diagnostic methods. Further work is needed to further develop systems of greater accuracy and greater consideration of the clinical workflows that they aim to integrate within.

Impact of radiogenomics in esophageal cancer on clinical outcomes: A pilot study

BACKGROUND

Esophageal cancer (ESCA) is the sixth most common malignancy in the world, and its incidence is rapidly increasing. Recently, several microRNAs (miRNAs) and messenger RNA (mRNA) targets were evaluated as potential biomarkers and regulators of epigenetic mechanisms involved in early diagnosis. In addition, computed tomography (CT) radiomic studies on ESCA improved the early stage identification and the prediction of response to treatment. Radiogenomics provides clinically useful prognostic predictions by linking molecular characteristics such as gene mutations and gene expression patterns of malignant tumors with medical images and could provide more opportunities in the management of patients with ESCA.

AIM

To explore the combination of CT radiomic features and molecular targets associated with clinical outcomes for characterization of ESCA patients.

METHODS

Of 15 patients with diagnosed ESCA were included in this study and their CT imaging and transcriptomic data were extracted from The Cancer Imaging Archive and gene expression data from The Cancer Genome Atlas, respectively. Cancer stage, history of significant alcohol consumption and body mass index (BMI) were considered as clinical outcomes. Radiomic analysis was performed on CT images acquired after injection of contrast medium. In total, 1302 radiomics features were extracted from three-dimensional regions of interest by using PyRadiomics. Feature selection was performed using a correlation filter based on Spearman’s correlation (ρ) and Wilcoxon-rank sum test respect to clinical outcomes. Radiogenomic analysis involved ρ analysis between radiomic features associated with clinical outcomes and transcriptomic signatures consisting of eight N6-methyladenosine RNA methylation regulators and five up-regulated miRNA. The significance level was set at P < 0.05.

RESULTS

Of 25, five and 29 radiomic features survived after feature selection, considering stage, alcohol history and BMI as clinical outcomes, respectively. Radiogenomic analysis with stage as clinical outcome revealed that six of the eight mRNA regulators and two of the five up-regulated miRNA were significantly correlated with ten and three of the 25 selected radiomic features, respectively (-0.61 < ρ < -0.60 and 0.53 < ρ < 0.69, P < 0.05). Assuming alcohol history as clinical outcome, no correlation was found between the five selected radiomic features and mRNA regulators, while a significant correlation was found between one radiomic feature and three up-regulated miRNAs (ρ = -0.56, ρ = -0.64 and ρ = 0.61, P < 0.05). Radiogenomic analysis with BMI as clinical outcome revealed that four mRNA regulators and one up-regulated miRNA were significantly correlated with 10 and two radiomic features, respectively (-0.67 < ρ < -0.54 and 0.53 < ρ < 0.71, P < 0.05).

CONCLUSION

Our study revealed interesting relationships between the expression of eight N6-methyladenosine RNA regulators, as well as five up-regulated miRNAs, and CT radiomic features associated with clinical outcomes of ESCA patients.

Artificial Intelligence in the Imaging of Gastric Cancer: Current Applications and Future Direction

Gastric cancer (GC) is one of the most common cancers and one of the leading causes of cancer-related death worldwide. Precise diagnosis and evaluation of GC, especially using noninvasive methods, are fundamental to optimal therapeutic decision-making. Despite the recent rapid advancements in technology, pretreatment diagnostic accuracy varies between modalities, and correlations between imaging and histological features are far from perfect. Artificial intelligence (AI) techniques, particularly hand-crafted radiomics and deep learning, have offered hope in addressing these issues. AI has been used widely in GC research, because of its ability to convert medical images into minable data and to detect invisible textures. In this article, we systematically reviewed the methodological processes (data acquisition, lesion segmentation, feature extraction, feature selection, and model construction) involved in AI. We also summarized the current clinical applications of AI in GC research, which include characterization, differential diagnosis, treatment response monitoring, and prognosis prediction. Challenges and opportunities in AI-based GC research are highlighted for consideration in future studies.

Role of artificial intelligence in multidisciplinary imaging diagnosis of gastrointestinal diseases

The use of artificial intelligence-based tools is regarded as a promising approach to increase clinical efficiency in diagnostic imaging, improve the interpretability of results, and support decision-making for the detection and prevention of diseases. Radiology, endoscopy and pathology images are suitable for deep-learning analysis, potentially changing the way care is delivered in gastroenterology. The aim of this review is to examine the key aspects of different neural network architectures used for the evaluation of gastrointestinal conditions, by discussing how different models behave in critical tasks, such as lesion detection or characterization (i.e. the distinction between benign and malignant lesions of the esophagus, the stomach and the colon). To this end, we provide an overview on recent achievements and future prospects in deep learning methods applied to the analysis of radiology, endoscopy and histologic whole-slide images of the gastrointestinal tract.

Status quo and future prospects of artificial neural network from the perspective of gastroenterologists

Artificial neural networks (ANNs) are one of the primary types of artificial intelligence and have been rapidly developed and used in many fields. In recent years, there has been a sharp increase in research concerning ANNs in gastrointestinal (GI) diseases. This state-of-the-art technique exhibits excellent performance in diagnosis, prognostic prediction, and treatment. Competitions between ANNs and GI experts suggest that efficiency and accuracy might be compatible in virtue of technique advancements. However, the shortcomings of ANNs are not negligible and may induce alterations in many aspects of medical practice. In this review, we introduce basic knowledge about ANNs and summarize the current achievements of ANNs in GI diseases from the perspective of gastroenterologists. Existing limitations and future directions are also proposed to optimize ANN’s clinical potential. In consideration of barriers to interdisciplinary knowledge, sophisticated concepts are discussed using plain words and metaphors to make this review more easily understood by medical practitioners and the general public.

Radiomics based on multisequence magnetic resonance imaging for the preoperative prediction of peritoneal metastasis in ovarian cancer

OBJECTIVES

To develop a radiomics signature based on multisequence magnetic resonance imaging (MRI) to preoperatively predict peritoneal metastasis (PM) in ovarian cancer (OC).

METHODS

Eighty-nine patients with OC were divided into a training cohort including patients (n = 54) with a single lesion and a validation cohort including patients (n = 35) with bilateral lesions. Radiomics features were extracted from the T2-weighted images (T2WIs), fat-suppressed T2WIs, multi-b-value diffusion-weighted images (DWIs), and corresponding parametric maps. A radiomics signature and nomogram incorporating the radiomics signature and clinical predictors were developed and validated on the training and validation cohorts, respectively.

RESULTS

The radiomics signature generated by 6 selected features showed a favorable discriminatory ability to predict PM in OC with an area under the curve (AUC) of 0.963 in the training cohort and an AUC of 0.928 in the validation cohort. The nomogram, comprising the radiomics signature, pelvic fluid, and CA-125 level, showed more favorable discrimination with an AUC of 0.969 in the training cohort and 0.944 in the validation cohort. Net reclassification index with values of 0.548 in the training cohort and 0.500 in the validation cohort.

CONCLUSION

Radiomics signature based on multisequence MRI serves as an effective quantitative approach to predict PM in OC patients. A nomogram of radiomics signature and clinical predictors could further improve the prediction ability of PM in patients with OC.

KEY POINTS

• Multisequence MRI-based radiomics showed a favorable discriminatory ability to predict PM in OC. • The nomogram incorporating the radiomics signature and clinical predictors was clinically useful to preoperatively predict PM in patients with OC.

Differentiation of small (≤ 3 cm) hepatocellular carcinomas from benign nodules in cirrhotic liver: the added additive value of MRI-based radiomics analysis to LI-RADS version 2018 algorithm

Background

Accurate characterization of small nodules in a cirrhotic liver is challenging. We aimed to determine the additive value of MRI-based radiomics analysis to Liver Imaging Reporting and Data System version 2018 (LI-RADS v 2018) algorithm in differentiating small (≤ 3 cm) hepatocellular carcinomas (HCCs) from benign nodules in cirrhotic liver.

Methods

In this retrospective study, 150 cirrhosis patients with histopathologically confirmed small liver nodules (HCC, 112; benign nodules, 44) were evaluated from January 2013 to October 2018. Based on the LI-RADS algorithm, a LI-RADS category was assigned for each lesion. A radiomics signature was generated based on texture features extracted from T1-weighted, T2W, and apparent diffusion coefficient (ADC) images by using the least absolute shrinkage and selection operator regression model. A nomogram model was developed for the combined diagnosis. Diagnostic performance was assessed using receiver operating characteristic curve (ROC) analysis.

Results

A radiomics signature consisting of eight features was significantly associated with the differentiation of HCCs from benign nodules. Both LI-RADS algorithm (area under ROC [A_z] = 0.898) and the MRI-Based radiomics signature (A_z = 0.917) demonstrated good discrimination, and the nomogram model showed a superior classification performance (A_z = 0.975). Compared with LI-RADS alone, the combined approach significantly improved the specificity (97.7% vs 81.8%, p = 0.030) and positive predictive value (99.1% vs 92.9%, p = 0.031) and afforded comparable sensitivity (97.3% vs 93.8%, p = 0.215) and negative predictive value (93.5% vs 83.7%, p = 0.188).

Conclusions

MRI-based radiomics analysis showed additive value to the LI-RADS v 2018 algorithm for differentiating small HCCs from benign nodules in the cirrhotic liver.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12876-021-01710-y.

Advanced analytics and artificial intelligence in gastrointestinal cancer: a systematic review of radiomics predicting response to treatment

Purpose

Advanced medical image analytics is increasingly used to predict clinical outcome in patients diagnosed with gastrointestinal tumors. This review provides an overview on the value of radiomics in predicting response to treatment in patients with gastrointestinal tumors.

Methods

A systematic review was conducted, according to PRISMA guidelines. The protocol was prospectively registered (PROSPERO: CRD42019128408). PubMed, Embase, and Cochrane databases were searched. Original studies reporting on the value of radiomics in predicting response to treatment in patients with a gastrointestinal tumor were included. A narrative synthesis of results was conducted. Results were stratified by tumor type. Quality assessment of included studies was performed, according to the radiomics quality score.

Results

The comprehensive literature search identified 1360 unique studies, of which 60 articles were included for analysis. In 37 studies, radiomics models and individual radiomic features showed good predictive performance for response to treatment (area under the curve or accuracy > 0.75). Various strategies to construct predictive models were used. Internal validation of predictive models was often performed, while the majority of studies lacked external validation. None of the studies reported predictive models implemented in clinical practice.

Conclusion

Radiomics is increasingly used to predict response to treatment in patients suffering from gastrointestinal cancer. This review demonstrates its great potential to help predict response to treatment and improve patient selection and early adjustment of treatment strategy in a non-invasive manner.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-020-05142-w.

Preoperative computed tomography-guided disease-free survival prediction in gastric cancer: a multicenter radiomics study

PURPOSE

Preoperative and noninvasive prognosis evaluation remains challenging for gastric cancer. Novel preoperative prognostic biomarkers should be investigated. This study aimed to develop multidetector-row computed tomography (MDCT)-guided prognostic models to direct follow-up strategy and improve prognosis.

METHODS

A retrospective dataset of 353 gastric cancer patients were enrolled from two centers and allocated to three cohorts: training cohort (n = 166), internal validation cohort (n = 83), and external validation cohort (n = 104). Quantitative radiomic features were extracted from MDCT images. The least absolute shrinkage and selection operator penalized Cox regression was adopted to construct a radiomic signature. A radiomic nomogram was established by integrating the radiomic signature and significant clinical risk factors. We also built a preoperative tumor-node-metastasis staging model for comparison. All models were evaluated considering the abilities of risk stratification, discrimination, calibration, and clinical use.

RESULTS

In the two validation cohorts, the established four-feature radiomic signature showed robust risk stratification power (P = 0.0260 and 0.0003, log-rank test). The radiomic nomogram incorporated radiomic signature, extramural vessel invasion, clinical T stage, and clinical N stage, outperforming all the other models (concordance index = 0.720 and 0.727) with good calibration and decision benefits. Also, the 2-yr disease-free survival (DFS) prediction was most effective (time-dependent area under curve = 0.771 and 0.765). Moreover, subgroup analysis indicated that the radiomic signature was more sensitive in risk stratifying patients with advanced clinical T/N stage.

CONCLUSIONS

The proposed MDCT-guided radiomic signature was verified as a prognostic factor for gastric cancer. The radiomic nomogram was a noninvasive auxiliary model for preoperative individualized DFS prediction, holding potential in promoting treatment strategy and clinical prognosis.

Machine learning techniques for computer-aided classification of active inflammatory sacroiliitis in magnetic resonance imaging

Background

Currently, magnetic resonance imaging (MRI) is used to evaluate active inflammatory sacroiliitis related to axial spondyloarthritis (axSpA). The qualitative and semiquantitative diagnosis performed by expert radiologists and rheumatologists remains subject to significant intrapersonal and interpersonal variation. This encouraged us to use machine-learning methods for this task.

Methods

In this retrospective study including 56 sacroiliac joint MRI exams, 24 patients had positive and 32 had negative findings for inflammatory sacroiliitis according to the ASAS group criteria. The dataset was randomly split with ~ 80% (46 samples, 20 positive and 26 negative) as training and ~ 20% as external test (10 samples, 4 positive and 6 negative). After manual segmentation of the images by a musculoskeletal radiologist, multiple features were extracted. The classifiers used were the Support Vector Machine, the Multilayer Perceptron (MLP), and the Instance-Based Algorithm, combined with the Relief and Wrapper methods for feature selection.

Results

Based on 10-fold cross-validation using the training dataset, the MLP classifier obtained the best performance with sensitivity = 100%, specificity = 95.6% and accuracy = 84.7%, using 6 features selected by the Wrapper method. Using the test dataset (external validation) the same MLP classifier obtained sensitivity = 100%, specificity = 66.7% and accuracy = 80%.

Conclusions

Our results show the potential of machine learning methods to identify SIJ subchondral bone marrow edema in axSpA patients and are promising to aid in the detection of active inflammatory sacroiliitis on MRI STIR sequences. Multilayer Perceptron (MLP) achieved the best results.

Grade Prediction of Bleeding Volume in Cesarean Section of Patients With Pernicious Placenta Previa Based on Deep Learning

In order to predict the amount of bleeding in the cesarean section of the patients with Pernicious Placenta Previa (PPP), this study proposed an automatic blood loss prediction method based on Magnetic Resonance Imaging (MRI) uterus image. Firstly, the DeepLab-V3 + network was used to segment the original MRI abdominal image to obtain the uterine region image. Then, the uterine region image and the corresponding blood loss data were trained by Visual Geometry Group Network-16 (VGGNet-16) network. The classification model of blood loss level was obtained. Using a dataset of 82 positive samples and 128 negative samples, the proposed method achieved accuracy, sensitivity and specificity of 75.61, 73.75, and 77.46% respectively. The experimental results showed that this method can not only automatically identify the uterine region of pregnant women, but also objectively determine the level of intraoperative bleeding. Therefore, this method has the potential to reduce the workload of the attending physician and improve the accuracy of experts' judgment on the level of bleeding during cesarean section, so as to select the corresponding hemostasis measures.

Development and assessment of an individualized nomogram to predict colorectal cancer liver metastases

Background

This article aims to develop and assess the radiomics paradigm for predicting colorectal cancer liver metastasis (CRLM) from the primary tumor.

Methods

This retrospective study included 100 patients from the First Hospital of Jilin University from June 2017 to December 2017. The 100 patients comprised 50 patients with and 50 without CRLM. The maximum-level enhanced computed tomography (CT) image of primary cancer in the portal venous phase of each patient was selected as the original image data. To automatically implement radiomics-related paradigms, we developed a toolkit called Radiomics Intelligent Analysis Toolkit (RIAT).

Results

With RIAT, the model based on logistic regression (LR) using both the radiomics and clinical information signatures showed the maximum net benefit. The area under the curve (AUC) value was 0.90±0.02 (sensitivity =0.85±0.02, specificity =0.79±0.04) for the training set, 0.86±0.11 (sensitivity =0.85±0.09, specificity =0.75±0.19) for the verification set, 0.906 (95% CI, 0.840-0.971; sensitivity =0.81, specificity =0.84) for the cross-validation set, and 0.899 (95% CI, 0.761-1.000; sensitivity =0.78, specificity =0.91) for the test set.

Conclusions

The radiomics nomogram-based LR with clinical risk and radiomics features allows for a more accurate classification of CRLM using CT images with RIAT.

A Delta-radiomics model for preoperative evaluation of Neoadjuvant chemotherapy response in high-grade osteosarcoma

Background

The difficulty of assessment of neoadjuvant chemotherapeutic response preoperatively may hinder personalized-medicine strategies that depend on the results from pathological examination.

Methods

A total of 191 patients with high-grade osteosarcoma (HOS) were enrolled retrospectively from November 2013 to November 2017 and received neoadjuvant chemotherapy (NCT). A cutoff time of November 2016 was used to divide the training set and validation set. All patients underwent diagnostic CTs before and after chemotherapy. By quantifying the tumor regions on the CT images before and after NCT, 540 delta-radiomic features were calculated. The interclass correlation coefficients for segmentations of inter/intra-observers and feature pair-wise correlation coefficients (Pearson) were used for robust feature selection. A delta-radiomics signature was constructed using the lasso algorithm based on the training set. Radiomics signatures built from single-phase CT were constructed for comparison purpose. A radiomics nomogram was then developed from the multivariate logistic regression model by combining independent clinical factors and the delta-radiomics signature. The prediction performance was assessed using area under the ROC curve (AUC), calibration curves and decision curve analysis (DCA).

Results

The delta-radiomics signature showed higher AUC than single-CT based radiomics signatures in both training and validation cohorts. The delta-radiomics signature, consisting of 8 selected features, showed significant differences between the pathologic good response (pGR) (necrosis fraction ≥90%) group and the non-pGR (necrosis fraction < 90%) group (P < 0.0001, in both training and validation sets). The delta-radiomics nomogram, which consisted of the delta-radiomics signature and new pulmonary metastasis during chemotherapy showed good calibration and great discrimination capacity with AUC 0.871 (95% CI, 0.804 to 0.923) in the training cohort, and 0.843 (95% CI, 0.718 to 0.927) in the validation cohort. The DCA confirmed the clinical utility of the radiomics model.

Conclusion

The delta-radiomics nomogram incorporating the radiomics signature and clinical factors in this study could be used for individualized pathologic response evaluation after chemotherapy preoperatively and help tailor appropriate chemotherapy and further treatment plans.

Radiomics approaches in gastric cancer: a frontier in clinical decision making

Objective:

To review the application of radiomics in gastric cancer and its challenges as well as future prospects.

Data sources:

A research for relevant studies were performed in PubMed with the terms of “radiomics,” “texture analysis,” and “gastric cancer.” The search was updated until February 28^th, 2019.

Study selection:

All original articles regarding the investigation of texture analysis or radiomics in gastric cancer were retrieved. Only papers written in English were included.

Results:

A total of 17 original articles were selected in final. It is shown that radiomics has yielded moderate to excellent performance in a spectrum of respects including differential diagnosis, assessment of histological differential degree, evaluation of tumor stage, prediction of response to therapy, and prognosis in gastric cancer. Yet, a number of challenges are facing both radiomics itself and its application in gastric cancer.

Conclusions:

Radiomics holds great potential in facilitating decision-making in gastric cancer. With the standardization of work-flow and advancement of machine learning methods, radiomics is expected to make great breakthroughs in precision medicine of gastric cancer.

An investigation of the classification accuracy of a deep learning framework-based computer-aided diagnosis system in different pathological types of breast lesions

Background

Deep learning-based computer-aided diagnosis (CAD) is an important method in aiding diagnosis for radiologists. We investigated the accuracy of a deep learning-based CAD in classifying breast lesions with different histological types.

Methods

A total of 448 breast lesions were detected on ultrasound (US) and classified by an experienced radiologist, a resident and deep learning-based CAD respectively. The pathological results of the lesions were chosen as the golden standard. The diagnostic performances of the three raters in different pathological types were analyzed.

Results

For the overall diagnostic performance, deep learning-based CAD presented a significantly higher specificity (76.96%) compared with the two radiologists. The area under ROC of CAD was almost equal with the experienced radiologist (0.81 vs. 0.81), while significantly higher than the resident (0.81 vs. 0.70, P<0.0001). In the benign lesions, deep learning-based CAD had a higher accuracy than both the two radiologists, which correctly classified as benign lesions in 119/135 of fibroadenomas (88.1%), 25/35 of adenosis (71.4%), 14/27 of intraductal papillary tumors (51.9%), 5/10 of inflammation (50%), and 4/8 of sclerosing adenosis (50%). But only the differences between CAD and the two radiologists in fibroadenomas had statistical significance (P=0.0011 and P=0.0313), and the differences between CAD and the resident in adenosis had statistical significance (P=0.012). In the malignant lesions, 151/168 of invasive ductal carcinomas (89.9%), 21/29 of ductal carcinoma in situ (DCIS) (72.4%) and 6/7 of invasive lobular carcinomas (85.7%) were diagnosed as malignancies by deep learning-based CAD, with no significant differences between CAD and the two radiologists.

Conclusions

In the diagnosis of these common types of breast lesions, deep learning-based CAD had a satisfying performance. Deep learning-based CAD had a better performance in the breast benign lesions, especially in fibroadenomas and adenosis. Therefore, deep learning-based CAD is a promising supplemental tool to US to increase the specificity and avoid unnecessary benign biopsies.

CT radiomics nomogram for the preoperative prediction of lymph node metastasis in gastric cancer

PURPOSE

To investigate the role of computed tomography (CT) radiomics for the preoperative prediction of lymph node (LN) metastasis in gastric cancer.

MATERIALS AND METHODS

This retrospective study included 247 consecutive patients (training cohort, 197 patients; test cohort, 50 patients) with surgically proven gastric cancer. Dedicated radiomics prototype software was used to segment lesions on preoperative arterial phase (AP) CT images and extract features. A radiomics model was constructed to predict the LN metastasis by using a random forest (RF) algorithm. Finally, a nomogram was built incorporating the radiomics scores and selected clinical predictors. Receiver operating characteristic (ROC) curves were used to validate the capability of the radiomics model and nomogram on both the training and test cohorts.

RESULTS

The radiomics model showed a favorable discriminatory ability in the training cohort with an area under the curve (AUC) of 0.844 (95% CI, 0.759 to 0.909), which was confirmed in the test cohort with an AUC of 0.837 (95% CI, 0.705 to 0.926). The nomogram consisted of radiomics scores and the CT-reported LN status showed excellent discrimination in the training and test cohorts with AUCs of 0.886 (95% CI, 0.808 to 0.941) and 0.881 (95% CI, 0.759 to 0.956), respectively.

CONCLUSIONS

The CT-based radiomics nomogram holds promise for use as a noninvasive tool in the individual prediction of LN metastasis in gastric cancer.

KEY POINTS

• CT radiomics showed a favorable performance for the prediction of LN metastasis in gastric cancer. • Radiomics model outperformed the routine CT in predicting LN metastasis in gastric cancer. • The radiomics nomogram holds potential in the individualized prediction of LN metastasis in gastric cancer.

Treatment response prediction of rehabilitation program in children with cerebral palsy using radiomics strategy: protocol for a multicenter prospective cohort study in west China

Background

Cerebral palsy (CP) is a major cause of chronic childhood disability worldwide, causing activity limitation as well as impairments in sensation, cognition, and communication. Leveraging biomarkers to establish individualized predictions of future treatment responses will be of great value. We aim to develop and validate a model that can be used to predict the individualized treatment response in Children with CP.

Methods

A multicenter prospective cohort study will be conducted in 4 hospitals in west China. One hundred and thirty children with CP will be recruited and undergo clinical assessment using the Peabody Developmental Motor Scales, Manual Ability Classification System (MACS), Hand Assessment for Infants (HAI), Assisting Hand Assessment (AHA), and Gross Motor Function Classification System (GMFCS). The data collected will include MRI image, clinical status, and socioeconomic status. The clinical information and MRI features extracted using radiomics strategy will be combined for exploratory analysis. The accuracy, sensitivity, and specificity of the model will be assessed using multiple modeling methodologies. Internal and external validation will be used to evaluate the performance of the radiomics model.

Discussion

We hypothesized that the findings from this study could provide a critical step towards the prediction of treatment response in children with CP, which could also complement other biomarkers in the development of precision medicine approaches for this severe disorder.

Trial registration

The study was registered with clinicaltrials.gov (NCT02979743).

Reproducibility and non-redundancy of radiomic features extracted from arterial phase CT scans in hepatocellular carcinoma patients: impact of tumor segmentation variability

Background

The reproducibility and non-redundancy of radiomic features are challenges in accelerating the clinical translation of radiomics. In this study, we focused on the robustness and non-redundancy of radiomic features extracted from computed tomography (CT) scans in hepatocellular carcinoma (HCC) patients with respect to different tumor segmentation methods.

Methods

Arterial enhanced CT images were retrospectively randomly obtained from 106 patients. As a training data set, 26 HCC patients were used to calculate the features' reproducibility and redundancy. Another data set (55 HCC patients and 25 healthy volunteers) was used for classification. The GrowCut and GraphCut semiautomatic segmentation methods were implemented in 3D Slicer software by two independent observers, and manual delineation was performed by five abdominal radiation oncologists to acquire the gross tumor volume (GTV). Seventy-one radiomic features were extracted from GTVs using Imaging Biomarker Explorer (IBEX) software, including 17 tumor intensity statistical features, 16 shape features and 38 textural features. For each radiomic feature, intraclass correlation coefficient (ICC) and hierarchical clustering were used to quantify its reproducibility and redundancy. Features with ICC values greater than 0.75 were considered reproducible. To generate the number of non-redundancy feature subgroups, the R² statistic method was used. Then, a classification model was built using a support vector machine (SVM) algorithm with 10-fold cross validation, and area under ROC curve (AUC) was used to evaluate the utility of non-redundant feature extraction by hierarchical clustering.

Results

The percentages of excellent reproducible features in the manual delineation group, GraphCut and GrowCut segmentation group were 69% [49], 73% [52] and 79% [56], respectively. Sixty-five percent [46] of the features showed strong robustness for all segmentation methods. The optimal number of cluster subgroup were 9, 13 and 11 for manual delineation, GraphCut and GrowCut segmentation, respectively. The optimal cluster subgroup number was 6 for all groups when the collectively high reproducibility features were selected for clustering. The receiver operating characteristic (ROC) analysis of radiomics classification model with and without feature reduction for healthy liver and HCC had an AUC value of 0.857 and 0.721 respectively.

Conclusions

Our study demonstrates that variations exist in the reproducibility of quantitative imaging features extracted from tumor regions segmented using different methods. The reproducibility and non-redundancy of the radiomic features rely greatly on the tumor segmentation in HCC CT images. We recommend that the most reliable and uniform radiomic features should be selected in the clinical use of radiomics. Classification experiments with feature reduction showed that radiomic features were effective in identifying healthy liver and HCC.

Discrimination of smoking status by MRI based on deep learning method

Background

This study aimed to assess the feasibility of deep learning-based magnetic resonance imaging (MRI) in the prediction of smoking status.

Methods

The head MRI 3D-T1WI images of 127 subjects (61 smokers and 66 non-smokers) were collected, and 176 image slices obtained for each subject. These subjects were 23-45 years old, and the smokers had at least 5 years of smoking experience. Approximate 25% of the subjects were randomly selected as the test set (15 smokers and 16 non-smokers), and the remaining subjects as the training set. Two deep learning models were developed: deep 3D convolutional neural network (Conv3D) and convolution neural network plus a recurrent neural network (RNN) with long short-term memory architecture (ConvLSTM).

Results

In the prediction of smoking status, Conv3D model achieved an accuracy of 80.6% (25/31), a sensitivity of 80.0% and a specificity of 81.3%, and ConvLSTM model achieved an accuracy of 93.5% (29/31), a sensitivity of 93.33% and a specificity of 93.75%. The accuracy obtained by these methods was significantly higher than that (<70%) obtained with support vector machine (SVM) methods.

Conclusions

The deep learning-based MRI can accurately predict smoking status. Studies with large sample size are needed to improve the accuracy and to predict the level of nicotine dependence.

CT texture analysis as predictive factor in metastatic lung adenocarcinoma treated with tyrosine kinase inhibitors (TKIs)

PURPOSE

To assess the predictive and prognostic value of pre-treatment CT texture features in lung adenocarcinoma treated with tyrosine kinase inhibitors (TKI).

MATERIALS AND METHODS

Texture analysis was performed using commercially available software (TexRAD Ltd, Cambridge, UK) on pre-treatment contrast-enhanced CT studies from 50 patients with metastatic lung adenocarcinoma treated by TKI. Texture features were quantified on a 5-mm-thick central slice of the primary tumor and were correlated with progression-free and overall survival (PFS and OS) using an internally cross-validated machine learning approach then validated on a bootstrapped sample.

RESULTS

Median PFS and OS were 10.5 and 20.7 months, respectively. A noninvasive signature based on five texture parameters predicted 6-month progression with Area Under the Curve (AUC) of 0.8 (95% CI) and 1-year progression with AUC of 0.76. A high-risk group had hazard ratios for progression of 4.63 and 5.78 when divided by median and best cut-off points, respectively. Texture signature did not correlate with OS. Available clinical variables did not correlate with PFS or with OS.

CONCLUSION

Texture features seem to be associated with PFS in lung adenocarcinoma treated with TKI.