Radiomic analysis in T2W and SPAIR T2W MRI: predict treatment response to chemoradiotherapy in esophageal squamous cell carcinoma

Radiomics in Oesogastric Cancer: Staging and Prediction of Preoperative Treatment Response: A Narrative Review and the Results of Personal Experience

BACKGROUND

Oesophageal, gastroesophageal, and gastric malignancies are often diagnosed at locally advanced stage and multimodal therapy is recommended to increase the chances of survival. However, given the significant variation in treatment response, there is a clear imperative to refine patient stratification. The aim of this narrative review was to explore the existing evidence and the potential of radiomics to improve staging and prediction of treatment response of oesogastric cancers.

METHODS

The references for this review article were identified via MEDLINE (PubMed) and Scopus searches with the terms "radiomics", "texture analysis", "oesophageal cancer", "gastroesophageal junction cancer", "oesophagogastric junction cancer", "gastric cancer", "stomach cancer", "staging", and "treatment response" until May 2024.

RESULTS

Radiomics proved to be effective in improving disease staging and prediction of treatment response for both oesophageal and gastric cancer with all imaging modalities (TC, MRI, and 18F-FDG PET/CT). The literature data on the application of radiomics to gastroesophageal junction cancer are very scarce. Radiomics models perform better when integrating different imaging modalities compared to a single radiology method and when combining clinical to radiomics features compared to only a radiomics signature.

CONCLUSIONS

Radiomics shows potential in noninvasive staging and predicting response to preoperative therapy among patients with locally advanced oesogastric cancer. As a future perspective, the incorporation of molecular subgroup analysis to clinical and radiomic features may even increase the effectiveness of these predictive and prognostic models.

Integrating MR radiomics and dynamic hematological factors predicts pathological response to neoadjuvant chemoradiotherapy in esophageal cancer

Purpose

We aimed to integrate MR radiomics and dynamic hematological factors to build a model to predict pathological complete response (pCR) to neoadjuvant chemoradiotherapy (NCRT) in esophageal squamous cell carcinoma (ESCC).

Methods

Patients with ESCC receiving NCRT and esophagectomy between September 2014 and September 2022 were retrospectively included. All patients underwent pre-treatment T2-weighted imaging as well as pre-treatment and post-treatment blood tests. Patients were randomly divided to training set and testing set at a ratio of 7:3. Machine learning models were constructed based on MR radiomics and hematological factors to predict pCR, respectively. A nomogram model was developed to integrate MR radiomics and hematological factors. Model performances were evaluated by areas under curves (AUCs), sensitivity, specificity, positive predictive value and negative.

Results

A total of 82 patients were included, of whom 39 (47.6 %) achieved pCR. The hematological model built with four hematological factors had an AUC of 0.628 (95%CI 0.391-0.852) in the testing set. Two out of 1106 extracted features were selected to build the radiomics model with an AUC of 0.821 (95%CI 0.641-0.981). The nomogram model integrating hematological factors and MR radiomics had best predictive performance, with an AUC of 0.904 (95%CI 0.770-1.000) in the testing set.

Conclusion

An integrated model using dynamic hematological factors and MR radiomics is constructed to accurately predicted pCR to NCRT in ESCC, which may be potentially useful to assist individualized preservation treatment of the esophagus.

Radiomics and dosiomics for predicting complete response to definitive chemoradiotherapy patients with oesophageal squamous cell cancer using the hybrid institution model

OBJECTIVES

To develop a multi-institutional prediction model to estimate the local response to oesophageal squamous cell carcinoma (ESCC) treated with definitive radiotherapy based on radiomics and dosiomics features.

METHODS

The local responses were categorised into two groups (incomplete and complete). An external validation model and a hybrid model that the patients from two institutions were mixed randomly were proposed. The ESCC patients at stages I-IV who underwent chemoradiotherapy from 2012 to 2017 and had follow-up duration of more than 5 years were included. The patients who received palliative or pre-operable radiotherapy and had no FDG PET images were excluded. The segmentations included the GTV, CTV, and PTV which are used in treatment planning. In addition, shrinkage, expansion, and shell regions were created. Radiomic and dosiomic features were extracted from CT, FDG PET images, and dose distribution. Machine learning-based prediction models were developed using decision tree, support vector machine, k-nearest neighbour (kNN) algorithm, and neural network (NN) classifiers.

RESULTS

A total of 116 and 26 patients enrolled at Centre 1 and Centre 2, respectively. The external validation model exhibited the highest accuracy with 65.4% for CT-based radiomics, 77.9% for PET-based radiomics, and 72.1% for dosiomics based on the NN classifiers. The hybrid model exhibited the highest accuracy of 84.4% for CT-based radiomics based on the kNN classifier, 86.0% for PET-based radiomics, and 79.0% for dosiomics based on the NN classifiers.

CONCLUSION

The proposed hybrid model exhibited promising predictive performance for the local response to definitive radiotherapy in ESCC patients.

CLINICAL RELEVANCE STATEMENT

The prediction of the complete response for oesophageal cancer patients may contribute to improving overall survival. The hybrid model has the potential to improve prediction performance than the external validation model that was conventionally proposed.

KEY POINTS

• Radiomics and dosiomics used to predict response in patients with oesophageal cancer receiving definitive radiotherapy. • Hybrid model with neural network classifier of PET-based radiomics improved prediction accuracy by 8.1%. • The hybrid model has the potential to improve prediction performance.

Multi-omics approaches for biomarker discovery in predicting the response of esophageal cancer to neoadjuvant therapy: A multidimensional perspective

Neoadjuvant chemoradiotherapy (NCRT) followed by surgery has been established as the standard treatment strategy for operable locally advanced esophageal cancer (EC). However, achieving pathologic complete response (pCR) or near pCR to NCRT is significantly associated with a considerable improvement in survival outcomes, while pCR patients may help organ preservation for patients by active surveillance to avoid planned surgery. Thus, there is an urgent need for improved biomarkers to predict EC chemoradiation response in research and clinical settings. Advances in multiple high-throughput technologies such as next-generation sequencing have facilitated the discovery of novel predictive biomarkers, specifically based on multi-omics data, including genomic/transcriptomic sequencings and proteomic/metabolomic mass spectra. The application of multi-omics data has shown the benefits in improving the understanding of underlying mechanisms of NCRT sensitivity/resistance in EC. Particularly, the prominent development of artificial intelligence (AI) has introduced a new direction in cancer research. The integration of multi-omics data has significantly advanced our knowledge of the disease and enabled the identification of valuable biomarkers for predicting treatment response from diverse dimension levels, especially with rapid advances in biotechnological and AI methodologies. Herein, we summarize the current status of research on the use of multi-omics technologies in predicting NCRT response for EC patients. Current limitations, challenges, and future perspectives of these multi-omics platforms will be addressed to assist in experimental designs and clinical use for further integrated analysis.

MR radiomics predicts pathological complete response of esophageal squamous cell carcinoma after neoadjuvant chemoradiotherapy: a multicenter study

BACKGROUND

More than 40% of patients with resectable esophageal squamous cell cancer (ESCC) achieve pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT), who have favorable prognosis and may benefit from an organ-preservation strategy. Our study aims to develop and validate a machine learning model based on MR radiomics to accurately predict the pCR of ESCC patients after nCRT.

METHODS

In this retrospective multicenter study, eligible patients with ESCC who underwent baseline MR (T2-weighted imaging) and nCRT plus surgery were enrolled between September 2014 and September 2022 at institution 1 (training set) and between December 2017 and August 2021 at institution 2 (testing set). Models were constructed using machine learning algorithms based on clinical factors and MR radiomics to predict pCR after nCRT. The area under the curve (AUC) and cutoff analysis were used to evaluate model performance.

RESULTS

A total of 155 patients were enrolled in this study, 82 in the training set and 73 in the testing set. The radiomics model was constructed based on two radiomics features, achieving AUCs of 0.968 (95%CI 0.933-0.992) in the training set and 0.885 (95%CI 0.800-0.958) in the testing set. The cutoff analysis resulted in an accuracy of 82.2% (95%CI 72.6-90.4%), a sensitivity of 75.0% (95%CI 58.3-91.7%), and a specificity of 85.7% (95%CI 75.5-96.0%) in the testing set.

CONCLUSION

A machine learning model based on MR radiomics was developed and validated to accurately predict pCR after nCRT in patients with ESCC.

The MRI radiomics signature can predict the pathologic response to neoadjuvant chemotherapy in locally advanced esophageal squamous cell carcinoma

OBJECTIVES

To investigate the MRI radiomics signatures in predicting pathologic response among patients with locally advanced esophageal squamous cell carcinoma (ESCC), who received neoadjuvant chemotherapy (NACT).

METHODS

Patients who underwent NACT from March 2015 to October 2019 were prospectively included. Each patient underwent esophageal MR scanning within one week before NACT and within 2-3 weeks after completion of NACT, prior to surgery. Radiomics features extracted from T2-TSE-BLADE were randomly split into the training and validation sets at a ratio of 7:3. According to the progressive tumor regression grade (TRG), patients were stratified into two groups: good responders (GR, TRG 0 + 1) and poor responders (non-GR, TRG 2 + 3). We constructed the Pre/Post-NACT model (Pre/Post-model) and the Delta-NACT model (Delta-model). Kruskal-Wallis was used to select features, logistic regression was used to develop the final model.

RESULTS

A total of 108 ESCC patients were included, and 3/2/4 out of 107 radiomics features were selected for constructing the Pre/Post/Delta-model, respectively. The selected radiomics features were statistically different between GR and non-GR groups. The highest area under the curve (AUC) was for the Delta-model, which reached 0.851 in the training set and 0.831 in the validation set. Among the three models, Pre-model showed the poorest performance in the training and validation sets (AUC, 0.466 and 0.596), and the Post-model showed better performance than the Pre-model in the training and validation sets (AUC, 0.753 and 0.781).

CONCLUSIONS

MRI-based radiomics models can predict the pathological response after NACT in ESCC patients, with the Delta-model exhibiting optimal predictive efficacy.

CLINICAL RELEVANCE STATEMENT

MRI radiomics features could be used as a useful tool for predicting the efficacy of neoadjuvant chemotherapy in esophageal carcinoma patients, especially in selecting responders among those patients who may be candidates to benefit from neoadjuvant chemotherapy.

KEY POINTS

• The MRI radiomics features based on T2WI-TSE-BLADE could potentially predict the pathologic response to NACT among ESCC patients. • The Delta-model exhibited the best predictive ability for pathologic response, followed by the Post-model, which similarly had better predictive ability, while the Pre-model performed less well in predicting TRG.

A Radiotherapy Dose Map-Guided Deep Learning Method for Predicting Pathological Complete Response in Esophageal Cancer Patients after Neoadjuvant Chemoradiotherapy Followed by Surgery

Esophageal cancer is a deadly disease, and neoadjuvant chemoradiotherapy can improve patient survival, particularly for patients achieving a pathological complete response (ypCR). However, existing imaging methods struggle to accurately predict ypCR. This study explores computer-aided detection methods, considering both imaging data and radiotherapy dose variations to enhance prediction accuracy. It involved patients with node-positive esophageal squamous cell carcinoma undergoing neoadjuvant chemoradiotherapy and surgery, with data collected from 2014 to 2017, randomly split into five subsets for 5-fold cross-validation. The algorithm DCRNet, an advanced version of OCRNet, integrates RT dose distribution into dose contextual representations (DCR), combining dose and pixel representation with ten soft regions. Among the 80 enrolled patients (mean age 55.68 years, primarily male, with stage III disease and middle-part lesions), the ypCR rate was 28.75%, showing no significant demographic or disease differences between the ypCR and non-ypCR groups. Among the three summarization methods, the maximum value across the CTV method produced the best results with an AUC of 0.928. The HRNetV2p model with DCR performed the best among the four backbone models tested, with an AUC of 0.928 (95% CI, 0.884-0.972) based on 5-fold cross-validation, showing significant improvement compared to other models. This underscores DCR-equipped models' superior AUC outcomes. The study highlights the potential of dose-guided deep learning in ypCR prediction, necessitating larger, multicenter studies to validate the results.

The gap before real clinical application of imaging-based machine-learning and radiomic models for chemoradiation outcome prediction in esophageal cancer: a systematic review and meta-analysis

BACKGROUND

Due to tumoral heterogeneity and the lack of robust biomarkers, the prediction of chemoradiotherapy response and prognosis in patients with esophageal cancer (EC) is challenging. The goal of this study was to assess the study quality and clinical value of machine learning and radiomic-based quantitative imaging studies for predicting the outcomes of EC patients after chemoradiotherapy.

MATERIALS AND METHODS

PubMed, Embase, and Cochrane were searched for eligible articles. The methodological quality and risk of bias were evaluated using the Radiomics Quality Score (RQS), Image Biomarkers Standardization Initiative (IBSI) Guideline, and Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) statement, as well as the modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. A meta-analysis of the evidence focusing on predicting chemoradiotherapy response and outcome in EC patients was implemented.

RESULTS

Forty-six studies were eligible for qualitative synthesis. The mean RQS score was 9.07, with an adherence rate of 42.52%. The adherence rates of the TRIPOD and IBSI were 61.70 and 43.17%, respectively. Ultimately, 24 studies were included in the meta-analysis, of which 16 studies had a pooled sensitivity, specificity, and area under the curve (AUC) of 0.83 (0.76-0.89), 0.83 (0.79-0.86), and 0.84 (0.81-0.87) in neoadjuvant chemoradiotherapy datasets, as well as 0.84 (0.75-0.93), 0.89 (0.83-0.93), and 0.93 (0.90-0.95) in definitive chemoradiotherapy datasets, respectively. Moreover, radiomics could distinguish patients from the low-risk and high-risk groups with different disease-free survival (DFS) (pooled hazard ratio: 3.43, 95% CI 2.39-4.92) and overall survival (pooled hazard ratio: 2.49, 95% CI 1.91-3.25). The results of subgroup and regression analyses showed that some of the heterogeneity was explained by the combination with clinical factors, sample size, and usage of the deep learning (DL) signature.

CONCLUSIONS

Noninvasive radiomics offers promising potential for optimizing treatment decision-making in EC patients. However, it is necessary to make scientific advancements in EC radiomics regarding reproducibility, clinical usefulness analysis, and open science categories. Improved model reporting of study objectives, blind assessment, and image processing steps are required to help promote real clinical applications of radiomics in EC research.

Artificial intelligence-driven radiomics study in cancer: the role of feature engineering and modeling

Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients' anatomy. However, the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians. Moreover, some potentially useful quantitative information in medical images, especially that which is not visible to the naked eye, is often ignored during clinical practice. In contrast, radiomics performs high-throughput feature extraction from medical images, which enables quantitative analysis of medical images and prediction of various clinical endpoints. Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis, demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine. However, radiomics remains in a developmental phase as numerous technical challenges have yet to be solved, especially in feature engineering and statistical modeling. In this review, we introduce the current utility of radiomics by summarizing research on its application in the diagnosis, prognosis, and prediction of treatment responses in patients with cancer. We focus on machine learning approaches, for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling. Furthermore, we introduce the stability, reproducibility, and interpretability of features, and the generalizability and interpretability of models. Finally, we offer possible solutions to current challenges in radiomics research.

Predicting the efficacy of radiotherapy for esophageal squamous cell carcinoma based on enhanced computed tomography radiomics and combined models

Purpose

This study aimed to investigate the ability of enhanced computed tomography (CT)-based radiomics and dosimetric parameters in predicting response to radiotherapy for esophageal cancer.

Methods

A retrospective analysis of 147 patients diagnosed with esophageal cancer was performed, and the patients were divided into a training group (104 patients) and a validation group (43 patients). In total, 851 radiomics features were extracted from the primary lesions for analysis. Maximum correlation minimum redundancy and minimum least absolute shrinkage and selection operator were utilized for feature screening of radiomics features, and logistic regression was applied to construct a radiotherapy radiomics model for esophageal cancer. Finally, univariate and multivariate parameters were used to identify significant clinical and dosimetric characteristics for constructing combination models. The area evaluated the predictive performance under the receiver operating characteristics (AUC) curve and the accuracy, sensitivity, and specificity of the training and validation cohorts.

Results

Univariate logistic regression analysis revealed statistically significant differences in clinical parameters of sex (p=0.031) and esophageal cancer thickness (p=0.028) on treatment response, whereas dosimetric parameters did not differ significantly in response to treatment. The combined model demonstrated improved discrimination between the training and validation groups, with AUCs of 0.78 (95% confidence interval [CI], 0.69–0.87) and 0.79 (95% CI, 0.65–0.93) in the training and validation groups, respectively.

Conclusion

The combined model has potential application value in predicting the treatment response of patients with esophageal cancer after radiotherapy.

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 feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer

Radiomics is a promising technique for discovering image based biomarkers of therapy response in cancer. Reproducibility of radiomics features is a known issue that is addressed by the image biomarker standardisation initiative (IBSI), but it remains challenging to interpret previously published radiomics signatures. This study investigates the reproducibility of radiomics features calculated with two widely used radiomics software packages (IBEX, MaZda) in comparison to an IBSI compliant software package (PyRadiomics). Intensity histogram, shape and textural features were extracted from 334 diffusion weighted magnetic resonance images of 59 head and neck cancer (HNC) patients from the PREDICT-HN observational radiotherapy study. Based on name and linear correlation, PyRadiomics shares 83 features with IBEX and 49 features with MaZda, a sub-set of well correlated features are considered reproducible (IBEX: 15 features, MaZda: 18 features). We explore the impact of including non-reproducible radiomics features in a HNC radiotherapy response model. It is possible to classify equivalent patient groups using radiomic features from either software, but only when restricting the model to reliable features using a correlation threshold method. This is relevant for clinical biomarker validation trials as it provides a framework to assess the reproducibility of reported radiomic signatures from existing trials.

Imaging to assist fertility-sparing surgery

Cytological screening and human papilloma virus testing has led to diagnosis of cervical cancer in young women at an earlier stage. Defining the full extent of the disease within the cervix with imaging aids the decision on feasibility of fertility-sparing surgical options, such as extended cone biopsy or trachelectomy. High spatial resolution images with maximal contrast between tumour and surrounding background are achieved with T2-weighted and diffusion-weighted (DW) magnetic resonance imaging (MRI) obtained using an endovaginal receiver coil. Tumour size and volume demonstrated in this way correlates between observers and with histology and differences between MRI and histology estimates of normal endocervical canal length are not significant. For planning fertility-sparing surgery, this imaging technique facilitates the best oncological outcome while minimising subsequent obstetric risks. Parametrial invasion may be assessed on large field of view T2-weighted MRI. The fat content of the parametrium limits the utility of DW imaging in this context, because fat typically shows diffusion restriction. The use of contrast-enhanced MRI for assessing the parametrium does not provide additional benefits to the T2-weighted images and the need for an extrinsic contrast agent merely adds additional complexity and cost. For nodal assessment, 18fluorodeoxyglucose positron emission tomography-computerised tomography (18FDG PET-CT) remains the gold standard.

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.

3D Deep Learning Model for the Pretreatment Evaluation of Treatment Response in Esophageal Carcinoma: A Prospective Study (ChiCTR2000039279)

PURPOSE

To develop and validate a pretreatment computed tomography (CT)-based deep-learning (DL) model for predicting the treatment response to concurrent chemoradiation therapy (CCRT) among patients with locally advanced thoracic esophageal squamous cell carcinoma (TESCC).

METHODS AND MATERIALS

We conducted a prospective, multicenter study on the therapeutic efficacy of CCRT among TESCC patients across 9 hospitals in China (ChiCTR2000039279). A total of 306 patients with locally advanced TESCC diagnosed by histopathology from August 2015 to May 2020 were included in this study. A 3-dimensional DL radiomics model (3D-DLRM) was developed and validated based on pretreatment CT images to predict the response to CCRT. Furthermore, the prediction performance of the newly developed 3D-DLRM was analyzed according to 3 categories: radiation therapy plan, radiation field, and prescription dose used.

RESULTS

The 3D-DLRM achieved good prediction performance, with areas under the receiver operating characteristic curve of 0.897 (95% confidence interval, 0.840-0.959) for the training cohort and 0.833 (95% confidence interval, 0.654-1.000) for the validation cohort. Specifically, the 3D-DLRM accurately predicted patients who would not respond to CCRT, with a positive predictive value (PPV) of 100% for the validation cohort. Moreover, the 3D-DLRM performed well in all 3 categories, each with areas under the receiver operating characteristic curve of >0.8 and positive predictive values of approximately 100%.

CONCLUSION

The proposed pretreatment CT-based 3D-DLRM provides a potential tool for predicting the response to CCRT among patients with locally advanced TESCC. With the help of precise pretreatment prediction, we may guide the individualized treatment of patients and improve survival.

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.

Machine Learning and Radiomics Applications in Esophageal Cancers Using Non-Invasive Imaging Methods-A Critical Review of Literature

Esophageal cancer (EC) is of public health significance as one of the leading causes of cancer death worldwide. Accurate staging, treatment planning and prognostication in EC patients are of vital importance. Recent advances in machine learning (ML) techniques demonstrate their potential to provide novel quantitative imaging markers in medical imaging. Radiomics approaches that could quantify medical images into high-dimensional data have been shown to improve the imaging-based classification system in characterizing the heterogeneity of primary tumors and lymph nodes in EC patients. In this review, we aim to provide a comprehensive summary of the evidence of the most recent developments in ML application in imaging pertinent to EC patient care. According to the published results, ML models evaluating treatment response and lymph node metastasis achieve reliable predictions, ranging from acceptable to outstanding in their validation groups. Patients stratified by ML models in different risk groups have a significant or borderline significant difference in survival outcomes. Prospective large multi-center studies are suggested to improve the generalizability of ML techniques with standardized imaging protocols and harmonization between different centers.

A nomogram based on pretreatment CT radiomics features for predicting complete response to chemoradiotherapy in patients with esophageal squamous cell cancer

Purpose

To develop and validate a nomogram model to predict complete response (CR) after concurrent chemoradiotherapy (CCRT) in esophageal squamous cell carcinoma (ESCC) patients using pretreatment CT radiomic features.

Methods

Data of patients diagnosed as ESCC and treated with CCRT in Shantou Central Hospital during the period from January 2013 to December 2015 were retrospectively collected. Eligible patients were included in this study and randomize divided into a training set and a validation set after successive screening. The least absolute shrinkage and selection operator (LASSO) with logistic regression to select radiomics features calculating Rad-score in the training set. The logistic regression analysis was performed to identify the predictive clinical factors for developing a nomogram model. The area under the receiver operating characteristic curves (AUC) was used to assess the performance of the predictive nomogram model and decision curve was used to analyze the impact of the nomogram model on clinical treatment decisions.

Results

A total of 226 patients were included and randomly divided into two groups, 160 patients in training set and 66 patients in validation set. After LASSO analysis, seven radiomics features were screened out to develop a radiomics signature Rad-score. The AUC of Rad-score was 0.812 (95% CI 0.742–0.869, p < 0.001) in the training set and 0.744 (95% CI 0.632–0.851, p = 0.003) in the validation set. Multivariate analysis showed that Rad-score and clinical staging were independent predictors of CR status, with p values of 0.035 and 0.023, respectively. A nomogram model incorporating Rad-socre and clinical staging was developed and validated, with an AUC of 0.844 (95% CI 0.779–0.897) in the training set and 0.807 (95% CI 0.691–0.894) in the validation set. Delong test showed that the nomogram model was significantly superior to the clinical staging, with p < 0.001 in the training set and p = 0.026 in the validation set. The decision curve showed that the nomogram model was superior to the clinical staging when the risk threshold was greater than 25%.

Conclusion

We developed and validated a nomogram model for predicting CR status of ESCC patients after CCRT. The nomogram model was combined radiomics signature Rad-score and clinical staging. This model provided us with an economical and simple method for evaluating the response of chemoradiotherapy for patients with ESCC.

A radiomics model of liver CT to predict risk of hepatic encephalopathy secondary to hepatitis B related cirrhosis

PURPOSE

To build a radiomics model of liver contrast-enhanced computed tomography (CT) to predict hepatic encephalopathy secondary to Hepatitis B related cirrhosis.

MATERIALS AND METHODS

This study consisted of 304 consecutive patients with first-diagnosed hepatitis B related cirrhosis. 212 and 92 patients were randomly computer-generated into training and testing cohorts, among which 38 and 21 patients endured HE, respectively. 356 radiomics features of liver were extracted from portal venous-phase CT data, and 3 clinical features were collected from medical record. After data were standardized by Z-score, we used least absolute shrinkage and selection operator to choose useful radiomics features. Ultimately, three predictive models including a radiomics model, a clinical model and an integrated model of radiomics and clinical features were built by analysis of R-software. Predictive performance was tested by multivariable logistic regression, and evaluated by area under receiver-operating characteristic curve (AUC), and accuracy.

RESULTS

19 radiomics features of liver CT were selected. The selected radiomics features and 3 relevant clinical features were applied to develop a radiomics model, a clinical model, and an integrated model of both radiomics and clinical features. The integrated model showed better performance than the radiomics model or clinical model to predict HE (AUC = 0.94 vs. 0.91 or 0.76, and 0.87 vs. 0.86 or 0.73; accuracy = 0.93 vs. 0.89 or 0.83, and 0.83 vs. 0.84 or 0.77) in the training and testing cohorts, respectively.

CONCLUSION

The integrated model of radiomics and clinical features could well predict HE secondary to hepatitis B related cirrhosis.

Diagnostic advances of artificial intelligence and radiomics in gastroenterology

Traditional medical imaging, including ultrasound, computed tomography, magnetic resonance imaging, or positron emission tomography, remains widely used diagnostic modalities for gastrointestinal diseases at present. These modalities are used to assess changes in morphology, attenuation, signal intensity, and enhancement characteristics. Gastrointestinal tumors, especially malignant tumors, are commonly seen in clinical practice with an increasing number of deaths each year. Because the imaging manifestations of different diseases usually overlap, accurate early diagnosis of tumor lesions, noninvasive and effective evaluation of tumor staging, and prediction of prognosis remain challenging. Fortunately, traditional medical images contain a great deal of important information that cannot be recognized by human eyes but can be extracted by artificial intelligence (AI) technology, which can quantitatively assess the heterogeneity of lesions and provide valuable information, including therapeutic effects and patient prognosis. With the development of computer technology, the combination of medical imaging and AI technology is considered to represent a promising field in medical image analysis. This new emerging field is called “radiomics”, which makes big data mining and extraction from medical imagery possible and can help clinicians make effective decisions and develop personalized treatment plans. Recently, AI and radiomics have been gradually applied to lesion detection, qualitative and quantitative diagnosis, histopathological grading and staging of tumors, therapeutic efficacy assessment, and prognosis evaluation. In this minireview, we briefly introduce the basic principles and technology of radiomics. Then, we review the research and application of AI and radiomics in gastrointestinal diseases, especially diagnostic advancements of radiomics in the differential diagnosis, treatment option, assessment of therapeutic efficacy, and prognosis evaluation of esophageal, gastric, hepatic, pancreatic, and colorectal diseases.

Application of Texture Analysis Based on Sagittal Fat-Suppression and Oblique Axial T2-Weighted Magnetic Resonance Imaging to Identify Lymph Node Invasion Status of Rectal Cancer

Objective: To investigate the value of texture features derived from T2-weighted magnetic resonance imaging (T2WI) for predicting preoperative lymph node invasion (N stage) in rectal cancer.

Materials and Methods: One hundred and eighty-two patients with histopathologically confirmed rectal cancer and preoperative magnetic resonance imaging were retrospectively analyzed, who were divided into high (N1-2) and low N stage (N0). Texture features were calculated from histogram, gray-level co-occurrence matrix, and gray-level run-length matrix from sagittal fat-suppression and oblique axial T2WI. Independent sample t-test or Mann-Whitney U-test were used for statistical analysis. Multivariate logistic regression analysis was conducted to build the predictive models. Predictive performance was evaluated by receiver operating characteristic (ROC) analysis.

Results: Energy (ENE), entropy (ENT), information correlation (INC), long-run emphasis (LRE), and short-run low gray-level emphasis (SRLGLE) extracted from sagittal fat-suppression T2WI, and ENE, ENT, INC, low gray-level run emphasis (LGLRE), and SRLGLE from oblique axial T2WI were significantly different between stage N0 and stage N1-2 tumors. The multivariate analysis for features from sagittal fat-suppression T2WI showed that higher SRLGLE and lower ENE were independent predictors of lymph node invasion. The model reached an area under ROC curve (AUC) of 0.759. The analysis for features from oblique axial T2WI showed that higher INC and SRLGLE were independent predictors. The model achieved an AUC of 0.747. The analysis for all extracted features showed that lower ENE from sagittal fat-suppression T2WI and higher INC and SRLGLE from oblique axial T2WI were independent predictors. The model showed an AUC of 0.772.

Conclusions: Texture features derived from T2WI could provide valuable information for identifying the status of lymph node invasion in rectal cancer.

Development and validation of a radiomics signature on differentially expressed features of 18F-FDG PET to predict treatment response of concurrent chemoradiotherapy in thoracic esophagus squamous cell carcinoma

BACKGROUND AND PURPOSE

To investigate potential image markers for early prediction of treatment response on thoracic esophagus squamous cell carcinoma (ESCC) treated with concurrent chemoradiotherapy (CCRT).

MATERIALS AND METHODS

159 thoracic ESCC patients enrolled from two institutions were divided into training and validation sets. A total of 944 radiomics features were extracted from pretreatment ¹⁸F-FDG PET images. We first performed the inter-observer reproducibility test in 10 pairs of patients (responders vs. nonresponders), and the limma package was used to identify differentially expressed features (DEFs). Then the least absolute shrinkage and selection operator (LASSO) logistic regression model with 10-fold cross-validation was used to construct a treatment response related radiomics signature. Finally, the performance was assessed in both sets with receiver operating characteristic (ROC) curves and Kaplan-Meier analysis.

RESULTS

After the inter-observer test, 691 features were considered reproducible and been retained (ICC > 0.9). 61 DEFs were selected from limma and entered into the LASSO logistic regression model. The radiomics signature was significantly associated with treatment response in the training (p < 0.001) and validation set (p = 0.026), which achieved area under curve (AUC) values of 0.844 and 0.835, respectively. Delong test results of two ROCs showed no significant difference (p = 0.918). The cut-off value of the radiomics signature could successfully divide patients into high-risk and low-risk groups in both sets.

CONCLUSION

This study indicated that the proposed radiomics signature could be a useful image marker to predict the therapeutic response of thoracic ESCC patients treated with CCRT.

Radiomic features of cervical cancer on T2-and diffusion-weighted MRI: Prognostic value in low-volume tumors suitable for trachelectomy

BACKGROUND

Textural features extracted from MRI potentially provide prognostic information additional to volume for influencing surgical management of cervical cancer.

PURPOSE

To identify textural features that differ between cervical tumors above and below the volume threshold of eligibility for trachelectomy and determine their value in predicting recurrence in patients with low-volume tumors.

METHODS

Of 378 patients with Stage1-2 cervical cancer imaged prospectively (3T, endovaginal coil), 125 had well-defined, histologically-confirmed squamous or adenocarcinomas with >100 voxels (>0.07 cm3) suitable for radiomic analysis. Regions-of-interest outlined the whole tumor on T2-W images and apparent diffusion coefficient (ADC) maps. Textural features based on grey-level co-occurrence matrices were compared (Mann-Whitney test with Bonferroni correction) between tumors greater (n = 46) or less (n = 79) than 4.19 cm3. Clustering eliminated correlated variables. Significantly different features were used to predict recurrence (regression modelling) in surgically-treated patients with low-volume tumors and compared with a model using clinico-pathological features.

RESULTS

Textural features (Dissimilarity, Energy, ClusterProminence, ClusterShade, InverseVariance, Autocorrelation) in 6 of 10 clusters from T2-W and ADC data differed between high-volume (mean ± SD 15.3 ± 11.7 cm3) and low-volume (mean ± SD 1.3 ± 1.2 cm3) tumors. (p < 0.02). In low-volume tumors, predicting recurrence was indicated by: Dissimilarity, Energy (ADC-radiomics, AUC = 0.864); Dissimilarity, ClusterProminence, InverseVariance (T2-W-radiomics, AUC = 0.808); Volume, Depth of Invasion, LymphoVascular Space Invasion (clinico-pathological features, AUC = 0.794). Combining ADC-radiomic (but not T2-radiomic) and clinico-pathological features improved prediction of recurrence compared to the clinico-pathological model (AUC = 0.916, p = 0.006). Findings were supported by bootstrap re-sampling (n = 1000).

CONCLUSION

Textural features from ADC maps and T2-W images differ between high- and low-volume tumors and potentially predict recurrence in low-volume tumors.

Predicting gastro-oesophageal variceal bleeding in hepatitis B-related cirrhosis by CT radiomics signature

AIM

To develop liver a computed tomography (CT) radiomics model to predict gastro-oesophageal variceal bleeding (GVB) secondary to hepatitis B-related cirrhosis.

MATERIALS AND METHODS

Electronic medical records and image data of liver triple-phase contrast-enhanced CT examinations of 295 patients with hepatitis B-related cirrhosis were collected retrospectively from two hospitals. Two hundred and thirty-six and 59 patients were enrolled randomly into the training and validation cohorts, respectively; and 75 in the training cohort and 16 in the validation cohort endured GVB while the others did not during follow-up period. Radiomics features of the liver were extracted from the portal venous phase images, and clinical features came from medical records. The tree-based method and univariate feature selection were used to select useful features. The radiomics model, clinical model, and integration of radiomics and clinical models were built using the useful image features and/or clinical features. Predicting performance of three models was evaluated with the area under receiver-operating characteristic curve (AUC), accuracy, and F-1 score.

RESULTS

Twenty-one useful radiomics features and/or three clinical features were selected to build prediction models that correlated with GVB. AUC of integration of radiomics and clinical models was larger than of clinical or radiomics models for the training cohort (0.83±0.09 versus 0.64±0.08 or 0.82±0.10) and the validation cohort (0.64 versus 0.61 or 0.61). Integration of radiomics and clinical models obtained good performance in predicting GVB for both the training and validation cohorts (accuracy: 0.76±0.07 and 0.73, and F-1 score: 0.77±0.09 and 0.72, respectively).

CONCLUSION

Integration of the radiomics and clinical models may be a non-invasive method to predict GVB.

Towards clinical application of image mining: a systematic review on artificial intelligence and radiomics

PURPOSE

The aim of this systematic review was to analyse literature on artificial intelligence (AI) and radiomics, including all medical imaging modalities, for oncological and non-oncological applications, in order to assess how far the image mining research stands from routine medical application. To do this, we applied a trial phases classification inspired from the drug development process.

METHODS

Among the articles we considered for inclusion from PubMed were multimodality AI and radiomics investigations, with a validation analysis aimed at relevant clinical objectives. Quality assessment of selected papers was performed according to the QUADAS-2 criteria. We developed the phases classification criteria for image mining studies.

RESULTS

Overall 34,626 articles were retrieved, 300 were selected applying the inclusion/exclusion criteria, and 171 high-quality papers (QUADAS-2 ≥ 7) were identified and analysed. In 27/171 (16%), 141/171 (82%), and 3/171 (2%) studies the development of an AI-based algorithm, radiomics model, and a combined radiomics/AI approach, respectively, was described. A total of 26/27(96%) and 1/27 (4%) AI studies were classified as phase II and III, respectively. Consequently, 13/141 (9%), 10/141 (7%), 111/141 (79%), and 7/141 (5%) radiomics studies were classified as phase 0, I, II, and III, respectively. All three radiomics/AI studies were categorised as phase II trials.

CONCLUSIONS

The results of the studies are promising but still not mature enough for image mining tools to be implemented in the clinical setting and be widely used. The transfer learning from the well-known drug development process, with some specific adaptations to the image mining discipline could represent the most effective way for radiomics and AI algorithms to become the standard of care tools.

Imaging biomarkers in upper gastrointestinal cancers

In parallel with the increasingly widespread availability of high performance imaging platforms and recent progresses in pathobiological characterisation and treatment of gastrointestinal malignancies, imaging biomarkers have become a major research topic due to their potential to provide additional quantitative information to conventional imaging modalities that can improve accuracy at staging and follow-up, predict outcome, and guide treatment planning in an individualised manner. The aim of this review is to briefly examine the status of current knowledge about imaging biomarkers in the field of upper gastrointestinal cancers, highlighting their potential applications and future perspectives in patient management from diagnosis onwards.

MRI radiomics analysis for predicting preoperative synchronous distant metastasis in patients with rectal cancer

OBJECTIVES

To investigate the value of MRI radiomics based on T2-weighted (T2W) images in predicting preoperative synchronous distant metastasis (SDM) in patients with rectal cancer.

METHODS

This retrospective study enrolled 177 patients with histopathology-confirmed rectal adenocarcinoma (123 patients in the training cohort and 54 in the validation cohort). A total of 385 radiomics features were extracted from pretreatment T2W images. Five steps, including univariate statistical tests and a random forest algorithm, were performed to select the best preforming features for predicting SDM. Multivariate logistic regression analysis was conducted to build the clinical and clinical-radiomics combined models in the training cohort. The predictive performance was validated by receiver operating characteristics curve (ROC) analysis and clinical utility implementing a nomogram and decision curve analysis.

RESULTS

Fifty-nine patients (33.3%) were confirmed to have SDM. Six radiomics features and four clinical characteristics were selected for predicting SDM. The clinical-radiomics combined model performed better than the clinical model in both the training and validation datasets. A threshold of 0.44 yielded an area under the ROC (AUC) value of 0.827 (95% confidence interval (CI), 0.6963-0.9580), a sensitivity of 72.2%, a specificity of 94.4%, and an accuracy of 87.0% in the validation cohort for the combined model. A clinical-radiomics nomogram and decision curve analysis confirmed the clinical utility of the combined model.

CONCLUSIONS

Our proposed clinical-radiomics combined model could be utilized as a noninvasive biomarker for identifying patients at high risk of SDM, which could aid in tailoring treatment strategies.

KEY POINTS

• T2WI-based radiomics analysis helps predict synchronous distant metastasis (SDM) of rectal cancer. • The clinical-radiomics combined model could be utilized as a noninvasive biomarker for predicting SDM. • Personalized treatment can be carried out with greater confidence based on the risk stratification for SDM in rectal cancer.

Potentials of radiomics for cancer diagnosis and treatment in comparison with computer-aided diagnosis

Computer-aided diagnosis (CAD) is a field that is essentially based on pattern recognition that improves the accuracy of a diagnosis made by a physician who takes into account the computer's "opinion" derived from the quantitative analysis of radiological images. Radiomics is a field based on data science that massively and comprehensively analyzes a large number of medical images to extract a large number of phenotypic features reflecting disease traits, and explores the associations between the features and patients' prognoses for precision medicine. According to the definitions for both, you may think that radiomics is not a paraphrase of CAD, but you may also think that these definitions are "image manipulation". However, there are common and different features between the two fields. This review paper elaborates on these common and different features and introduces the potential of radiomics for cancer diagnosis and treatment by comparing it with CAD.

Identification of the most significant magnetic resonance imaging (MRI) radiomic features in oncological patients with vertebral bone marrow metastatic disease: a feasibility study

OBJECTIVES

Recently, radiomic analysis has gained attention as a valuable instrument for the management of oncological patients. The aim of the study is to isolate which features of magnetic resonance imaging (MRI)-based radiomic analysis have to be considered the most significant predictors of metastasis in oncological patients with spinal bone marrow metastatic disease.

MATERIALS AND METHODS

Eight oncological patients (3 lung cancer; 1 prostatic cancer; 1 esophageal cancer; 1 nasopharyngeal cancer; 1 hepatocarcinoma; 1 breast cancer) with pre-radiotherapy MR imaging for a total of 58 dorsal vertebral bodies, 29 metastatic and 29 non-metastatic were included. Each vertebral body was contoured in T1 and T2 weighted images at a radiotherapy delineation console. The obtained data were transferred to an automated data extraction system for morphological, statistical and textural analysis. Eighty-nine features for each lesion in both T1 and T2 images were computed as the median of by-slice values. A Wilcoxon test was applied to the 89 features and the most statistically significant of them underwent to a stepwise feature selection, to find the best performing predictors of metastasis in a logistic regression model. An internal cross-validation via bootstrap was conducted for estimating the model performance in terms of the area under the curve (AUC) of the receiver operating characteristic.

RESULTS

Of the 89 textural features tested, 16 were found to differ with statistical significance in the metastatic vs non-metastatic group. The best performing model was constituted by two predictors for T1 and T2 images, namely one morphological feature (center of mass shift) (p value < 0.01) for both datasets and one histogram feature minimum grey level (p value < 0.01) for T1 images and one textural feature (grey-level co-occurrence matrix joint variance (p value < 0.01) for T2 images. The internal cross-validation showed an AUC of 0.8141 (95% CI 0.6854-0.9427) in T1 images and 0.9116 (95% CI 0.8294-0.9937) in T2 images.

CONCLUSIONS

The results suggest that MRI-based radiomic analysis on oncological patients with bone marrow metastatic disease is able to differentiate between metastatic and non-metastatic vertebral bodies. The most significant predictors of metastasis were found to be based on T2 sequence and were one morphological and one textural feature.