Radiomics-based machine learning model to predict risk of death within 5-years in clear cell renal cell carcinoma patients

Clinical application of radiomics for the prediction of treatment outcome and survival in patients with renal cell carcinoma: a systematic review

PURPOSE

The management of renal cell carcinoma (RCC) relies on clinical and histopathological features for treatment decisions. Recently, radiomics, which involves the extraction and analysis of quantitative imaging features, has shown promise in improving RCC management. This review evaluates the current application and limitations of radiomics for predicting treatment and oncological outcomes in RCC.

METHODS

A systematic search was conducted in Medline, EMBASE, and Web of Science databases or studies that used radiomics to predict response to treatment and survival outcomes in patients with RCC. The study quality was assessed using the Radiomics Quality Score (RQS) tools.

RESULTS

The systematic review identified a total of 27 studies, examining 6,119 patients. The most used imaging modality was contrast-enhanced abdominal CT. The reviewed studies extracted between 19 and 3376 radiomics features, including Histogram, Texture, Filter, or transformation method. Radiomics-based risk stratification models provided valuable insights into treatment response and oncological outcomes. All developed signatures demonstrated at least modest accuracy (AUC range: 0.55-0.99). The studies included in this analysis reported heterogeneous results regarding radiomics methods. The range of Radiomics Quality Score (RQS) was from - 5 to 20, with a mean RQS total of 9.15 ± 7.95.

CONCLUSION

Radiomics has emerged as a promising tool in the management of RCC. It offers the potential for improved risk stratification and response assessment. However, future trials must demonstrate the generalizability of findings to prospective cohorts before progressing towards clinical translation.

Deep radiomics-based prognostic prediction of oral cancer using optical coherence tomography

BACKGROUND

This study aims to evaluate the integration of optical coherence tomography (OCT) and peripheral blood immune indicators for predicting oral cancer prognosis by artificial intelligence.

METHODS

In this study, we examined patients undergoing radical oral cancer resection and explored inherent relationships among clinical data, OCT images, and peripheral immune indicators for oral cancer prognosis. We firstly built a peripheral blood immune indicator-guided deep learning feature representation method for OCT images, and further integrated a multi-view prognostic radiomics model incorporating feature selection and logistic modeling. Thus, we can assess the prognostic impact of each indicator on oral cancer by quantifying OCT features.

RESULTS

We collected 289 oral mucosal samples from 68 patients, yielding 1,445 OCT images. Using our deep radiomics-based prognosis model, it achieved excellent discrimination for oral cancer prognosis with the area under the receiver operating characteristic curve (AUC) of 0.886, identifying systemic immune-inflammation index (SII) as the most informative feature for prognosis prediction. Additionally, the deep learning model also performed excellent results with 85.26% accuracy and 0.86 AUC in classifying the SII risk.

CONCLUSIONS

Our study effectively merged OCT imaging with peripheral blood immune indicators to create a deep learning-based model for inflammatory risk prediction in oral cancer. Additionally, we constructed a comprehensive multi-view radiomics model that utilizes deep learning features for accurate prognosis prediction. The study highlighted the significance of the SII as a crucial indicator for evaluating patient outcomes, corroborating our clinical statistical analyses. This integration underscores the potential of combining imaging and blood indicators in clinical decision-making.

TRIAL REGISTRATION

The clinical trial associated with this study was prospectively registered in the Chinese Clinical Trial Registry with the trial registration number (TRN) ChiCTR2200064861. The registration was completed on 2021.

Interpretable multiphasic CT-based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study

BACKGROUND

To develop and compare machine learning models based on triphasic contrast-enhanced CT (CECT) for distinguishing between benign and malignant renal tumors.

MATERIALS AND METHODS

In total, 427 patients were enrolled from two medical centers: Center 1 (serving as the training set) and Center 2 (serving as the external validation set). First, 1781 radiomic features were individually extracted from corticomedullary phase (CP), nephrographic phase (NP), and excretory phase (EP) CECT images, after which 10 features were selected by the minimum redundancy maximum relevance method. Second, random forest (RF) models were constructed from single-phase features (CP, NP, and EP) as well as from the combination of features from all three phases (TP). Third, the RF models were assessed in the training and external validation sets. Finally, the internal prediction mechanisms of the models were explained by the SHapley Additive exPlanations (SHAP) approach.

RESULTS

A total of 266 patients with renal tumors from Center 1 and 161 patients from Center 2 were included. In the training set, the AUCs of the RF models constructed from the CP, NP, EP, and TP features were 0.886, 0.912, 0.930, and 0.944, respectively. In the external validation set, the models achieved AUCs of 0.860, 0.821, 0.921, and 0.908, respectively. The "original_shape_Flatness" feature played the most important role in the prediction outcome for the RF model based on EP features according to the SHAP method.

CONCLUSIONS

The four RF models efficiently differentiated benign from malignant solid renal tumors, with the EP feature-based RF model displaying the best performance.

Impact of Preprocessing Parameters in Medical Imaging-Based Radiomic Studies: A Systematic Review

BACKGROUND

Lately, radiomic studies featuring the development of a signature to use in prediction models in diagnosis or prognosis outcomes have been increasingly published. While the results are shown to be promising, these studies still have many pitfalls and limitations. One of the main issues of these studies is that radiomic features depend on how the images are preprocessed before their computation. Since, in widely known and used software for radiomic features calculation, it is possible to set these preprocessing parameters before the calculation of the radiomic feature, there are ongoing studies assessing the stability and repeatability of radiomic features to find the most suitable preprocessing parameters for every used imaging modality.

MATERIALS AND METHODS

We performed a comprehensive literature search using four electronic databases: PubMed, Cochrane Library, Embase, and Scopus. Mesh terms and free text were modeled in search strategies for databases. The inclusion criteria were studies where preprocessing parameters' influence on feature values and model predictions was addressed. Records lacking information on image acquisition parameters were excluded, and any eligible studies with full-text versions were included in the review process, while conference proceedings and monographs were disregarded. We used the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2) tool to investigate the risk of bias. We synthesized our data in a table divided by the imaging modalities subgroups.

RESULTS

After applying the inclusion and exclusion criteria, we selected 43 works. This review examines the impact of preprocessing parameters on the reproducibility and reliability of radiomic features extracted from multimodality imaging (CT, MRI, CBCT, and PET/CT). Standardized preprocessing is crucial for consistent radiomic feature extraction. Key preprocessing steps include voxel resampling, normalization, and discretization, which influence feature robustness and reproducibility. In total, 44% of the included works studied the effects of an isotropic voxel resampling, and most studies opted to employ a discretization strategy. From 2021, several studies started selecting the best set of preprocessing parameters based on models' best performance. As for comparison metrics, ICC was the most used in MRI studies in 58% of the screened works.

CONCLUSIONS

From our work, we highlighted the need to harmonize the use of preprocessing parameters and their values, especially in light of future studies of prospective studies, which are still lacking in the current literature.

CT-Based Radiomics for the Preoperative Prediction of Occult Peritoneal Metastasis in Epithelial Ovarian Cancers

RATIONALE AND OBJECTIVES

The objective of this study was to develop a comprehensive combined model for predicting occult peritoneal metastasis (OPM) in epithelial ovarian cancers (EOCs) using radiomics features derived from computed tomography (CT) and clinical-radiological predictors.

MATERIALS AND METHODS

A total of 224 patients with EOCs were randomly divided into training dataset (N = 156) and test dataset (N = 86). Five clinical factors and seven radiological features were collected. The radiomics features were extracted from CT images of each patient. Multivariate logistic regression was employed to construct clinical and radiological models. The correlation analysis and least absolute shrinkage and selection operator algorithm were used to select radiomics features and build radiomics model. The important clinical, radiological factors, and radiomics features were integrated into a combined model by multivariate logistic regression. Receiver operating characteristics curve with area under the curve (AUC) were used to evaluate and compare predictive performance.

RESULTS

Carbohydrate antigen 125 (CA-125) and human epididymal protein 4 (HE-4) were independent clinical predictors. Laterality, thickened septa and margin were independent radiological predictors. In the training dataset, the AUCs for the clinical, radiological and radiomics models in evaluating OPM were 0.759, 0.819, and 0.830, respectively. In the test dataset, the AUCs for these models were 0.846, 0.835, and 0.779, respectively. The combined model outperformed other models in both the training and the test datasets with AUCs of 0.901 and 0.912, respectively. Decision curve analysis indicated that the combined model yielded a higher net benefit compared to the other models.

CONCLUSION

The combined model, integrating radiomics features with clinical and radiological predictors exhibited improved accuracy in predicting OPM in EOCs.

Radiomics Machine Learning Analysis of Clear Cell Renal Cell Carcinoma for Tumour Grade Prediction Based on Intra-Tumoural Sub-Region Heterogeneity

BACKGROUND

Renal cancers are among the top ten causes of cancer-specific mortality, of which the ccRCC subtype is responsible for most cases. The grading of ccRCC is important in determining tumour aggressiveness and clinical management.

OBJECTIVES

The objectives of this research were to predict the WHO/ISUP grade of ccRCC pre-operatively and characterise the heterogeneity of tumour sub-regions using radiomics and ML models, including comparison with pre-operative biopsy-determined grading in a sub-group.

METHODS

Data were obtained from multiple institutions across two countries, including 391 patients with pathologically proven ccRCC. For analysis, the data were separated into four cohorts. Cohorts 1 and 2 included data from the respective institutions from the two countries, cohort 3 was the combined data from both cohort 1 and 2, and cohort 4 was a subset of cohort 1, for which both the biopsy and subsequent histology from resection (partial or total nephrectomy) were available. 3D image segmentation was carried out to derive a voxel of interest (VOI) mask. Radiomics features were then extracted from the contrast-enhanced images, and the data were normalised. The Pearson correlation coefficient and the XGBoost model were used to reduce the dimensionality of the features. Thereafter, 11 ML algorithms were implemented for the purpose of predicting the ccRCC grade and characterising the heterogeneity of sub-regions in the tumours.

RESULTS

For cohort 1, the 50% tumour core and 25% tumour periphery exhibited the best performance, with an average AUC of 77.9% and 78.6%, respectively. The 50% tumour core presented the highest performance in cohorts 2 and 3, with average AUC values of 87.6% and 76.9%, respectively. With the 25% periphery, cohort 4 showed AUC values of 95.0% and 80.0% for grade prediction when using internal and external validation, respectively, while biopsy histology had an AUC of 31.0% for the classification with the final grade of resection histology as a reference standard. The CatBoost classifier was the best for each of the four cohorts with an average AUC of 80.0%, 86.5%, 77.0% and 90.3% for cohorts 1, 2, 3 and 4 respectively.

CONCLUSIONS

Radiomics signatures combined with ML have the potential to predict the WHO/ISUP grade of ccRCC with superior performance, when compared to pre-operative biopsy. Moreover, tumour sub-regions contain useful information that should be analysed independently when determining the tumour grade. Therefore, it is possible to distinguish the grade of ccRCC pre-operatively to improve patient care and management.

A distributed feature selection pipeline for survival analysis using radiomics in non-small cell lung cancer patients

Predictive modelling of cancer outcomes using radiomics faces dimensionality problems and data limitations, as radiomics features often number in the hundreds, and multi-institutional data sharing is ()often unfeasible. Federated learning (FL) and feature selection (FS) techniques combined can help overcome these issues, as one provides the means of training models without exchanging sensitive data, while the other identifies the most informative features, reduces overfitting, and improves model interpretability. Our proposed FS pipeline based on FL principles targets data-driven radiomics FS in a multivariate survival study of non-small cell lung cancer patients. The pipeline was run across datasets from three institutions without patient-level data exchange. It includes two FS techniques, Correlation-based Feature Selection and LASSO regularization, and Cox Proportional-Hazard regression with Overall Survival as endpoint. Trained and validated on 828 patients overall, our pipeline yielded a radiomic signature comprising "intensity-based energy" and "mean discretised intensity". Validation resulted in a mean Harrell C-index of 0.59, showcasing fair efficacy in risk stratification. In conclusion, we suggest a distributed radiomics approach that incorporates preliminary feature selection to systematically decrease the feature set based on data-driven considerations. This aims to address dimensionality challenges beyond those associated with data constraints and interpretability concerns.

Multimodal deep learning for personalized renal cell carcinoma prognosis: Integrating CT imaging and clinical data

BACKGROUND AND OBJECTIVE

Renal cell carcinoma represents a significant global health challenge with a low survival rate. The aim of this research was to devise a comprehensive deep-learning model capable of predicting survival probabilities in patients with renal cell carcinoma by integrating CT imaging and clinical data and addressing the limitations observed in prior studies. The aim is to facilitate the identification of patients requiring urgent treatment.

METHODS

The proposed framework comprises three modules: a 3D image feature extractor, clinical variable selection, and survival prediction. Based on the 3D CNN architecture, the feature extractor module predicts the ISUP grade of renal cell carcinoma tumors linked to mortality rates from CT images. Clinical variables are systematically selected using the Spearman score and random forest importance score as criteria. A deep learning-based network, trained with discrete LogisticHazard-based loss, performs the survival prediction. Nine distinct experiments are performed, with varying numbers of clinical variables determined by different thresholds of the Spearman and importance scores.

RESULTS

Our findings demonstrate that the proposed strategy surpasses the current literature on renal cancer prognosis based on CT scans and clinical factors. The best-performing experiment yielded a concordance index of 0.84 and an area under the curve value of 0.8 on the test cohort, which suggests strong predictive power.

CONCLUSIONS

The multimodal deep-learning approach developed in this study shows promising results in estimating survival probabilities for renal cell carcinoma patients using CT imaging and clinical data. This may have potential implications in identifying patients who require urgent treatment, potentially improving patient outcomes. The code created for this project is available for the public on: GitHub.

Non-invasive decision support for clinical treatment of non-small cell lung cancer using a multiscale radiomics approach

BACKGROUND

Selecting therapeutic strategies for cancer patients is typically based on key target-molecule biomarkers that play an important role in cancer onset, progression, and prognosis. Thus, there is a pressing need for novel biomarkers that can be utilized longitudinally to guide treatment selection.

METHODS

Using data from 508 non-small cell lung cancer (NSCLC) patients across three institutions, we developed and validated a comprehensive predictive biomarker that distinguishes six genotypes and infiltrative immune phenotypes. These features were analyzed to establish the association between radiological phenotypes and tumor genotypes/immune phenotypes and to create a radiological interpretation of molecular features. In addition, we assessed the sensitivity of the models by evaluating their performance at five different voxel intervals, resulting in improved generalizability of the proposed approach.

FINDINGS

The radiomics model we developed, which integrates clinical factors and multi-regional features, outperformed the conventional model that only uses clinical and intratumoral features. Our combined model showed significant performance for EGFR, KRAS, ALK, TP53, PIK3CA, and ROS1 mutation status with AUCs of 0.866, 0.874, 0.902, 0.850, 0.860, and 0.900, respectively. Additionally, the predictive performance for PD-1/PD-L1 was 0.852. Although the performance of all models decreased to different degrees at five different voxel space resolutions, the performance advantage of the combined model did not change.

CONCLUSIONS

We validated multiscale radiomic signatures across tumor genotypes and immunophenotypes in a multi-institutional cohort. This imaging-based biomarker offers a non-invasive approach to select patients with NSCLC who are sensitive to targeted therapies or immunotherapy, which is promising for developing personalized treatment strategies during therapy.

Several models combined with ultrasound techniques to predict breast muscle weight in broilers

The weight of breast muscle (WBM) is a highly monitored indicator in broiler breeding that can be obtained after slaughtering. Currently, due to the lack of accurate in vivo phenotypes for both genomic and phenotypic selection, genetic gains in WBM fall short of initial expectations. In this study, 1,006 market-age (42 d) broilers from 3 generations over 2 yr were randomly selected, and the breast width (BW), fossil bone length (FBL), breast muscle thickness (BMT), and live weight (LW) were measured exactly in vivo. Eight models, including multiple linear regression (MLR), ridge regression (RR), least absolute shrinkage and selection operator (LASSO), and elastic net (EN), were fitted to explore the best regression relationships between breast muscle weight and these indicators. Support vector machine (SVM) methods with both linear kernels and radial kernels were used to fit the models, while 2 decision tree-based machine learning algorithms, random forest (RF), and extreme gradient boosting (XGBoost), were used to establish the prediction model. The predictive effects of different combinations of independent variables were compared, leading to the conclusion that the EN model achieves the best predictive power when all 4 live features are used as inputs and is slightly better than the other models (R2 = 0.7696). This method could be applied in practical production and breeding work, leading to substantial cost savings and enhancements in the breeding process.

Radiomics under 2D regions, 3D regions, and peritumoral regions reveal tumor heterogeneity in non-small cell lung cancer: a multicenter study

PURPOSE

Lung cancer has significant genetic and phenotypic heterogeneity, leading to poor prognosis. Radiomic features have emerged as promising predictors of the tumor phenotype. However, the role of underlying information surrounding the cancer remains unclear.

MATERIALS AND METHODS

We conducted a retrospective study of 508 patients with NSCLC from three institutions. Radiomics models were built using features from six tumor regions and seven classifiers to predict three prognostically significant tumor phenotypes. The models were evaluated and interpreted by the mean area under the receiver operating characteristic curve (AUC) under nested cross-validation and Shapley values. The best-performing predictive models corresponding to six tumor regions and three tumor phenotypes were identified for further comparative analysis. In addition, we designed five experiments with different voxel spacing to assess the sensitivity of the experimental results to the spatial resolution of the voxels.

RESULTS

Our results demonstrated that models based on 2D, 3D, and peritumoral region features yielded mean AUCs and 95% confidence intervals of 0.759 and [0.747-0.771] for lymphovascular invasion, 0.889 and [0.882-0.896] for pleural invasion, and 0.839 and [0.829-0.849] for T-staging in the testing cohort, which was significantly higher than all other models. Similar results were obtained for the model combining the three regional features at five voxel spacings.

CONCLUSION

Our study revealed the predictive role of the developed methods with multi-regional features for the preoperative assessment of prognostic factors in NSCLC. The analysis of different voxel spacing and model interpretability strengthens the experimental findings and contributes to understanding the biological significance of the radiological phenotype.

Predicting the recurrence risk of renal cell carcinoma after nephrectomy: potential role of CT-radiomics for adjuvant treatment decisions

OBJECTIVES

Previous trial results suggest that only a small number of patients with non-metastatic renal cell carcinoma (RCC) benefit from adjuvant therapy. We assessed whether the addition of CT-based radiomics to established clinico-pathological biomarkers improves recurrence risk prediction for adjuvant treatment decisions.

METHODS

This retrospective study included 453 patients with non-metastatic RCC undergoing nephrectomy. Cox models were trained to predict disease-free survival (DFS) using post-operative biomarkers (age, stage, tumor size and grade) with and without radiomics selected on pre-operative CT. Models were assessed using C-statistic, calibration, and decision curve analyses (repeated tenfold cross-validation).

RESULTS

At multivariable analysis, one of four selected radiomic features (wavelet-HHL_glcm_ClusterShade) was prognostic for DFS with an adjusted hazard ratio (HR) of 0.44 (p = 0.02), along with American Joint Committee on Cancer (AJCC) stage group (III versus I, HR 2.90; p = 0.002), grade 4 (versus grade 1, HR 8.90; p = 0.001), age (per 10 years HR 1.29; p = 0.03), and tumor size (per cm HR 1.13; p = 0.003). The discriminatory ability of the combined clinical-radiomic model (C = 0.80) was superior to that of the clinical model (C = 0.78; p < 0.001). Decision curve analysis revealed a net benefit of the combined model when used for adjuvant treatment decisions. At an exemplary threshold probability of ≥ 25% for disease recurrence within 5 years, using the combined versus the clinical model was equivalent to treating 9 additional patients (per 1000 assessed) who would recur without treatment (i.e., true-positive predictions) with no increase in false-positive predictions.

CONCLUSION

Adding CT-based radiomic features to established prognostic biomarkers improved post-operative recurrence risk assessment in our internal validation study and may help guide decisions regarding adjuvant therapy.

KEY POINTS

In patients with non-metastatic renal cell carcinoma undergoing nephrectomy, CT-based radiomics combined with established clinical and pathological biomarkers improved recurrence risk assessment. Compared to a clinical base model, the combined risk model enabled superior clinical utility if used to guide decisions on adjuvant treatment.

The Present and Future of Artificial Intelligence in Urological Cancer

Artificial intelligence has drawn more and more attention for both research and application in the field of medicine. It has considerable potential for urological cancer detection, therapy, and prognosis prediction due to its ability to choose features in data to complete a particular task autonomously. Although the clinical application of AI is still immature and faces drawbacks such as insufficient data and a lack of prospective clinical trials, AI will play an essential role in individualization and the whole management of cancers as research progresses. In this review, we summarize the applications and studies of AI in major urological cancers, including tumor diagnosis, treatment, and prognosis prediction. Moreover, we discuss the current challenges and future applications of AI.

18F‑FDG PET/CT based radiomics features improve prediction of prognosis: multiple machine learning algorithms and multimodality applications for multiple myeloma

PURPOSE

Multiple myeloma (MM), the second most hematological malignancy, have been studied extensively in the prognosis of the clinical parameters, however there are only a few studies have discussed the role of dual modalities and multiple algorithms of ¹⁸F-FDG (¹⁸F-fluorodeoxyglucose) PET/CT based radiomics signatures for prognosis in MM patients. We hope to deeply mine the utility of raiomics data in the prognosis of MM.

METHODS

We extensively explored the predictive ability and clinical decision-making ability of different combination image data of PET, CT, clinical parameters and six machine learning algorithms, Cox proportional hazards model (Cox), linear gradient boosting models based on Cox's partial likelihood (GB-Cox), Cox model by likelihood based boosting (CoxBoost), generalized boosted regression modelling (GBM), random forests for survival model (RFS) and support vector regression for censored data model (SVCR). And the model evaluation methods include Harrell concordance index, time dependent receiver operating characteristic (ROC) curve, and decision curve analysis (DCA).

RESULTS

We finally confirmed 5 PET based features, and 4 CT based features, as well as 6 clinical derived features significantly related to progression free survival (PFS) and we included them in the model construction. In various modalities combinations, RSF and GBM algorithms significantly improved the accuracy and clinical net benefit of predicting prognosis compared with other algorithms. For all combinations of various modalities based models, single-modality PET based prognostic models' performance was outperformed baseline clinical parameters based models, while the performance of models of PET and CT combined with clinical parameters was significantly improved in various algorithms.

CONCLUSION

¹⁸F‑FDG PET/CT based radiomics models implemented with machine learning algorithms can significantly improve the clinical prediction of progress and increased clinical benefits providing prospects for clinical prognostic stratification for precision treatment as well as new research areas.

Comprehensive analysis of single-cell RNA-seq and bulk RNA-seq revealed the heterogeneity and convergence of the immune microenvironment in renal cell carcinoma

Substantial progress has been made in cancer biology and treatment in recent years, but the clinical outcome of patients with renal cell carcinoma (RCC) remains unsatisfactory. The tumor microenvironment (TME) is a potential target. By analyzing single-cell RNA sequencing (sc-RNAseq) data from six RCC tumor samples, this study identified 11 different cell types in the RCC cellular microenvironment, indicating a high degree of intratumoral heterogeneity. Through re-dimensionality reduction clustering of epithelial cells, neutrophils, macrophages, and T cells, we deeply reveal differences in the RCC tumor microenvironment. By analyzing differentially expressed genes in normal epithelial cells and malignant epithelial cells, we identify RNASET2 and GATM as potential prognostic biomarkers in RCC. In addition, by transcriptional factor analysis, we found significant differences in the expression of GZMK-CD8 T cell and B cell transcription factors between cancer tissues and normal tissues. By cell correlation analysis, we found significant correlations between neutrophils and macrophages and between IL7R-CD4 T cells and T regulatory (Treg) cells in RCC, which may be involved in the formation of immune TMEs. By cell developmental trajectory analysis, we showed that macrophages may be derived from neutrophils, whereas Treg cells may be derived from IL7R-CD4 T cells. By cell communication analysis, we found a clear interaction between macrophages and endothelial cells, neutrophils, and GZMK-CD8 T cells. In addition, we found that ADGRE5 signaling was mainly derived from mast cells and GZMK-CD8 T cells, and had a significant communication effect with neutrophils. The COLLAGEN signaling pathway is mainly derived from fibroblasts and has a significant communication effect with mast cells. Finally, we verified that RNASET2, which is highly expressed in epithelial cells, promotes proliferation and migration of RCC in vitro. RNASET2 is likely to be a potential target for renal cell carcinoma therapy. The results based on sc-RNAseq data analysis help to further elucidate the cellular microenvironment of RCC and provide help for cancer heterogeneity studies. This will help to provide more accurate personalized treatment for patients in clinical diagnosis.

Development and Validation of CT-Based Radiomics Signature for Overall Survival Prediction in Multi-organ Cancer

The malignant tumors in nature share some common morphological characteristics. Radiomics is not only images but also data; we think that a probability exists in a set of radiomics signatures extracted from CT scan images of one cancer tumor in one specific organ also be utilized for overall survival prediction in different types of cancers in different organs. The retrospective study enrolled four data sets of cancer patients in three different organs (420, 157, 137, and 191 patients for lung 1 training, lung 2 testing, and two external validation set: kidney and head and neck, respectively). In the training set, radiomics features were obtained from CT scan images, and essential features were chosen by LASSO algorithm. Univariable and multivariable analyses were then conducted to find a radiomics signature via Cox proportional hazard regression. The Kaplan-Meier curve was performed based on the risk score. The integrated time-dependent area under the ROC curve (iAUC) was calculated for each predictive model. In the training set, Kaplan-Meier curve classified patients as high or low-risk groups (p-value < 0.001; log-rank test). The risk score of radiomics signature was locked and independently evaluated in the testing set, and two external validation sets showed significant differences (p-value < 0.05; log-rank test). A combined model (radiomics + clinical) showed improved iAUC in lung 1, lung 2, head and neck, and kidney data set are 0.621 (95% CI 0.588, 0.654), 0.736 (95% CI 0.654, 0.819), 0.732 (95% CI 0.655, 0.809), and 0.834 (95% CI 0.722, 0.946), respectively. We believe that CT-based radiomics signatures for predicting overall survival in various cancer sites may exist.

An artificial neural network-based radiomics model for predicting the radiotherapy response of advanced esophageal squamous cell carcinoma patients: a multicenter study

Radiotherapy benefits patients with advanced esophageal squamous cell carcinoma (ESCC) in terms of symptom relief and long-term survival. In contrast, a substantial proportion of ESCC patients have not benefited from radiotherapy. This study aimed to establish and validate an artificial neural network-based radiomics model for the pretreatment prediction of the radiotherapy response of advanced ESCC by using integrated data combined with feasible baseline characteristics of computed tomography. A total of 248 patients with advanced ESCC who underwent baseline CT and received radiotherapy were enrolled in this study and were analyzed by two types of radiomics models, machine learning and deep learning. As a result, the Att. Resnet50 pretrained network model indicated superior performance, with AUCs of 0.876, 0.802 and 0.732 in the training, internal validation, and external validation cohorts, respectively. Similarly, our Att. Resnet50 pretrained network model showed excellent calibration and significant clinical benefit according to the C index and decision curve analysis. Herein, a novel pretreatment radiomics model was established based on deep learning methods and could be used for radiotherapy response prediction in advanced ESCC patients, thus providing reliable evidence for therapeutic decision-making.

Incremental value of radiomics with machine learning to the existing prognostic models for predicting outcome in renal cell carcinoma

Purpose

To systematically evaluate the potential of radiomics coupled with machine-learning algorithms to improve the predictive power for overall survival (OS) of renal cell carcinoma (RCC).

Methods

A total of 689 RCC patients (281 in the training cohort, 225 in the validation cohort 1 and 183 in the validation cohort 2) who underwent preoperative contrast-enhanced CT and surgical treatment were recruited from three independent databases and one institution. 851 radiomics features were screened using machine-learning algorithm, including Random Forest and Lasso-COX Regression, to establish radiomics signature. The clinical and radiomics nomogram were built by multivariate COX regression. The models were further assessed by Time-dependent receiver operator characteristic, concordance index, calibration curve, clinical impact curve and decision curve analysis.

Result

The radiomics signature comprised 11 prognosis-related features and was significantly correlated with OS in the training and two validation cohorts (Hazard Ratios: 2.718 (2.246,3.291)). Based on radiomics signature, WHOISUP, SSIGN, TNM Stage and clinical score, the radiomics nomogram has been developed. Compared with the existing prognostic models, the AUCs of 5 years OS prediction of the radiomics nomogram were superior to the TNM, WHOISUP and SSIGN model in the training cohort (0.841 vs 0.734, 0.707, 0.644) and validation cohort2 (0.917 vs 0.707, 0.773, 0.771). Stratification analysis suggested that the sensitivity of some drugs and pathways in cancer were observed different for RCC patients with high-and low-radiomics scores.

Conclusion

This study showed the application of contrast-enhanced CT-based radiomics in RCC patients, creating novel radiomics nomogram that could be used to predict OS. Radiomics provided incremental prognostic value to the existing models and significantly improved the predictive power. The radiomics nomogram might be helpful for clinicians to evaluate the benefit of surgery or adjuvant therapy and make individualized therapeutic regimens for patients with renal cell carcinoma.

A two-stage renal disease classification based on transfer learning with hyperparameters optimization

Renal diseases are common health problems that affect millions of people around the world. Among these diseases, kidney stones, which affect anywhere from 1 to 15% of the global population and thus; considered one of the leading causes of chronic kidney diseases (CKD). In addition to kidney stones, renal cancer is the tenth most prevalent type of cancer, accounting for 2.5% of all cancers. Artificial intelligence (AI) in medical systems can assist radiologists and other healthcare professionals in diagnosing different renal diseases (RD) with high reliability. This study proposes an AI-based transfer learning framework to detect RD at an early stage. The framework presented on CT scans and images from microscopic histopathological examinations will help automatically and accurately classify patients with RD using convolutional neural network (CNN), pre-trained models, and an optimization algorithm on images. This study used the pre-trained CNN models VGG16, VGG19, Xception, DenseNet201, MobileNet, MobileNetV2, MobileNetV3Large, and NASNetMobile. In addition, the Sparrow search algorithm (SpaSA) is used to enhance the pre-trained model's performance using the best configuration. Two datasets were used, the first dataset are four classes: cyst, normal, stone, and tumor. In case of the latter, there are five categories within the second dataset that relate to the severity of the tumor: Grade 0, Grade 1, Grade 2, Grade 3, and Grade 4. DenseNet201 and MobileNet pre-trained models are the best for the four-classes dataset compared to others. Besides, the SGD Nesterov parameters optimizer is recommended by three models, while two models only recommend AdaGrad and AdaMax. Among the pre-trained models for the five-class dataset, DenseNet201 and Xception are the best. Experimental results prove the superiority of the proposed framework over other state-of-the-art classification models. The proposed framework records an accuracy of 99.98% (four classes) and 100% (five classes).

Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomics

Objective

This study aims to establish a radiomics-based machine learning model that predicts the risk of transient ischemic attack in patients with mild carotid stenosis (30-50% North American Symptomatic Carotid Endarterectomy Trial) using extracted computed tomography radiomics features and clinical information.

Methods

A total of 179 patients underwent carotid computed tomography angiography (CTA), and 219 carotid arteries with a plaque at the carotid bifurcation or proximal to the internal carotid artery were selected. The patients were divided into two groups; patients with symptoms of transient ischemic attack after CTA and patients without symptoms of transient ischemic attack after CTA. Then we performed random sampling methods stratified by the predictive outcome to obtain the training set (N = 165) and testing set (N = 66). 3D Slicer was employed to select the site of plaque on the computed tomography image as the volume of interest. An open-source package PyRadiomics in Python was used to extract radiomics features from the volume of interests. The random forest and logistic regression models were used to screen feature variables, and five classification algorithms were used, including random forest, eXtreme Gradient Boosting, logistic regression, support vector machine, and k-nearest neighbors. Data on radiomic feature information, clinical information, and the combination of these pieces of information were used to generate the model that predicts the risk of transient ischemic attack in patients with mild carotid artery stenosis (30-50% North American Symptomatic Carotid Endarterectomy Trial).

Results

The random forest model that was built based on the radiomics and clinical feature information had the highest accuracy (area under curve = 0.879; 95% confidence interval, 0.787-0.979). The combined model outperformed the clinical model, whereas the combined model showed no significant difference from the radiomics model.

Conclusion

The random forest model constructed with both radiomics and clinical information can accurately predict and improve discriminative power of computed tomography angiography in identifying ischemic symptoms in patients with carotid atherosclerosis. This model can aid in guiding the follow-up treatment of patients at high risk.

A clinical prediction model for predicting the risk of liver metastasis from renal cell carcinoma based on machine learning

Background

Renal cell carcinoma (RCC) is a highly metastatic urological cancer. RCC with liver metastasis (LM) carries a dismal prognosis. The objective of this study is to develop a machine learning (ML) model that predicts the risk of RCC with LM, which is used to assist clinical treatment.

Methods

The retrospective study data of 42,547 patients with RCC were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. ML includes algorithmic methods and is a fast-rising field that has been widely used in the biomedical field. Logistic regression (LR), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGB), random forest (RF), decision tree (DT), and naive Bayesian model [Naive Bayes Classifier (NBC)] were applied to develop prediction models to predict the risk of RCC with LM. The six models were 10-fold cross-validated, and the best-performing model was selected based on the area under the curve (AUC) value. A web online calculator was constructed based on the best ML model.

Results

Bone metastasis, lung metastasis, grade, T stage, N stage, and tumor size were independent risk factors for the development of RCC with LM by multivariate regression analysis. In addition, the correlation of the relative proportions of the six clinical variables was shown by a heat map. In the prediction models of RCC with LM, the mean AUC of the XGB model among the six ML algorithms was 0.947. Based on the XGB model, the web calculator (https://share.streamlit.io/liuwencai4/renal_liver/main/renal_liver.py) was developed to evaluate the risk of RCC with LM.

Conclusions

This XGB model has the best predictive effect on RCC with LM. The web calculator constructed based on the XGB model has great potential for clinicians to make clinical decisions and improve the prognosis of RCC patients with LM.

Interpretable prediction of mortality in liver transplant recipients based on machine learning

BACKGROUND

Accurate prediction of the mortality of post-liver transplantation is an important but challenging task. It relates to optimizing organ allocation and estimating the risk of possible dysfunction. Existing risk scoring models, such as the Balance of Risk (BAR) score and the Survival Outcomes Following Liver Transplantation (SOFT) score, do not predict the mortality of post-liver transplantation with sufficient accuracy. In this study, we evaluate the performance of machine learning models and establish an explainable machine learning model for predicting mortality in liver transplant recipients.

METHOD

The optimal feature set for the prediction of the mortality was selected by a wrapper method based on binary particle swarm optimization (BPSO). With the selected optimal feature set, seven machine learning models were applied to predict mortality over different time windows. The best-performing model was used to predict mortality through a comprehensive comparison and evaluation. An interpretable approach based on machine learning and SHapley Additive exPlanations (SHAP) is used to explicitly explain the model's decision and make new discoveries.

RESULTS

With regard to predictive power, our results demonstrated that the feature set selected by BPSO outperformed both the feature set in the existing risk score model (BAR score, SOFT score) and the feature set processed by principal component analysis (PCA). The best-performing model, extreme gradient boosting (XGBoost), was found to improve the Area Under a Curve (AUC) values for mortality prediction by 6.7%, 11.6%, and 17.4% at 3 months, 3 years, and 10 years, respectively, compared to the SOFT score. The main predictors of mortality and their impact were discussed for different age groups and different follow-up periods.

CONCLUSIONS

Our analysis demonstrates that XGBoost can be an ideal method to assess the mortality risk in liver transplantation. In combination with the SHAP approach, the proposed framework provides a more intuitive and comprehensive interpretation of the predictive model, thereby allowing the clinician to better understand the decision-making process of the model and the impact of factors associated with mortality risk in liver transplantation.

Unsupervised Analysis Based on DCE-MRI Radiomics Features Revealed Three Novel Breast Cancer Subtypes with Distinct Clinical Outcomes and Biological Characteristics

Background: This study aimed to reveal the heterogeneity of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of breast cancer (BC) and identify its prognosis values and molecular characteristics. Methods: Two radiogenomics cohorts (n = 246) were collected and tumor regions were segmented semi-automatically. A total of 174 radiomics features were extracted, and the imaging subtypes were identified and validated by unsupervised analysis. A gene-profile-based classifier was developed to predict the imaging subtypes. The prognostic differences and the biological and microenvironment characteristics of subtypes were uncovered by bioinformatics analysis. Results: Three imaging subtypes were identified and showed high reproducibility. The subtypes differed remarkably in tumor sizes and enhancement patterns, exhibiting significantly different disease-free survival (DFS) or overall survival (OS) in the discovery cohort (p = 0.024) and prognosis datasets (p ranged from <0.0001 to 0.0071). Large sizes and rapidly enhanced tumors usually had the worst outcomes. Associations were found between imaging subtypes and the established subtypes or clinical stages (p ranged from <0.001 to 0.011). Imaging subtypes were distinct in cell cycle and extracellular matrix (ECM)-receptor interaction pathways (false discovery rate, FDR < 0.25) and different in cellular fractions, such as cancer-associated fibroblasts (p < 0.05). Conclusions: The imaging subtypes had different clinical outcomes and biological characteristics, which may serve as potential biomarkers.

The Impact of Image Acquisition Parameters and ComBat Harmonization on the Predictive Performance of Radiomics: A Renal Cell Carcinoma Model

Radiomics, one of the potential methods for developing clinical biomarker, is one of the exponentially growing research fields. In addition to its potential, several limitations have been identified in this field, and most importantly the effects of variations in imaging parameters on radiomic features (RFs). In this study, we investigate the potential of RFs to predict overall survival in patients with clear cell renal cell carcinoma, as well as the impact of ComBat harmonization on the performance of RF models. We assessed the robustness of the results by performing the analyses a thousand times. Publicly available CT scans of 179 patients were retrospectively collected and analyzed. The scans were acquired using different imaging vendors and parameters in different medical centers. The performance was calculated by averaging the metrics over all runs. On average, the clinical model significantly outperformed the radiomic models. The use of ComBat harmonization, on average, did not significantly improve the performance of radiomic models. Hence, the variability in image acquisition and reconstruction parameters significantly affect the performance of radiomic models. The development of radiomic specific harmonization techniques remain a necessity for the advancement of the field.

Machine learning based identification of hub genes in renal clear cell carcinoma using multi-omics data

Renal cell carcinoma is one of the most universal urinary system cancers in the world. The most common renal cell carcinoma subtype is renal clear cell carcinoma. It is usually associated with high rates of metastasis and mortality. Therefore, finding effective therapeutic targets and prognostic molecular markers is of great significance to improve the early diagnosis rate and prognostic accuracy of renal clear cell carcinoma. In this work, we successfully identified six hub genes that are closely related to the occurrence, development and prognosis of renal clear cell carcinoma and proposed three new potential prognostic markers, namely ATP4B, AC144831.1 and Tfcp2l1 through differentially expressed genes (DEGs) analysis, GO functional enrichment and KEGG pathway analysis, WGCNA analysis, and survival analysis. In addition, we established machine learning models to predict the occurrence of tumors through the gene expression data of patients. It is expected that the results of this study can provide reference value for the treatment of renal clear cell carcinoma.

Machine learning-based prognosis signature for survival prediction of patients with clear cell renal cell carcinoma

The sole clinicopathological characteristic is not enough for the prediction of survival of patients with clear cell renal cell carcinoma (ccRCC). However, the survival prediction model constructed by machine learning technology for patients with ccRCC using clinicopathological features is rarely reported yet. In this study, a total of 5878 patients diagnosed as ccRCC from four independent patient cohorts were recruited. The least absolute shrinkage and selection operator analysis was implemented to identify optimal clinicopathological characteristics and calculate each coefficient to construct the prognosis model. In addition, weighted gene co-expression network and gene enrichment analysis associated with risk score were also carried out. Three clinicopathologic features were selected for the construction of the prognosis risk score model as the prognostic factors of ccRCC, including tumor size, tumor grade, and tumor stage. In the CPTAC (Clinical Proteomic Tumor Analysis Consortium) cohort, the General cohort, the SEER (Surveillance, Epidemiology, and End Results) cohort, and the Huashan cohort, patients with high-risk score had worse clinical outcomes than patients with low-risk score (hazard ratio 5.15, 4.64, 3.96, and 5.15, respectively). Further functional enrichment analysis demonstrated that our machine learning-based risk score was significantly connected with some cell proliferation-related pathways, consisting of DNA repair, cell division, and cell cycle. In summary, we developed and validated a machine learning-based prognosis prediction model, which might contribute to clinical decision-making for patients with ccRCC.

Machine-learning-based contrast-enhanced computed tomography radiomic analysis for categorization of ovarian tumors

Objectives

This study aims to evaluate the diagnostic performance of machine-learning-based contrast-enhanced CT radiomic analysis for categorizing benign and malignant ovarian tumors.

Methods

A total of 1,329 patients with ovarian tumors were randomly divided into a training cohort (N=930) and a validation cohort (N=399). All tumors were resected, and pathological findings were confirmed. Radiomic features were extracted from the portal venous phase images of contrast-enhanced CT. The clinical predictors included age, CA-125, HE-4, ascites, and margin of tumor. Both radiomics model (including selected radiomic features) and mixed model (incorporating selected radiomic features and clinical predictors) were constructed respectively. Six classifiers [k-nearest neighbor (KNN), support vector machines (SVM), random forest (RF), logistic regression (LR), multi-layer perceptron (MLP), and eXtreme Gradient Boosting (XGBoost)] were used for each model. The mean relative standard deviation (RSD) and area under the receiver operating characteristic curve (AUC) were applied to evaluate and select the best classifiers. Then, the performances of the two models with selected classifiers were assessed in the validation cohort.

Results

The MLP classifier with the least RSD (1.21 and 0.53, respectively) was selected as the best classifier in both radiomics and mixed models. The two models with MLP classifier performed well in the validation cohort, with the AUCs of 0.91 and 0.96 and with accuracies (ACCs) of 0.83 and 0.87, respectively. The Delong test showed that the AUC of mixed model was statistically different from that of radiomics model (p&lt;0.001).

Conclusions

Machine-learning-based CT radiomic analysis could categorize ovarian tumors with good performance preoperatively. The mixed model with MLP classifier may be a potential tool in clinical applications.

An Investigation on Radiomics Feature Handling for HNSCC Staging Classification

The incidence of Head and Neck Squamous Cell Carcinoma (HNSCC) has been growing in the last few decades. Its diagnosis is usually performed through clinical evaluation and analyzing radiological images, then confirmed by histopathological examination, an invasive and time-consuming operation. The recent advances in the artificial intelligence field are leading to interesting results in the early diagnosis, personalized treatment and monitoring of HNSCC only by analyzing radiological images, without performing a tissue biopsy. The large amount of radiological images and the increasing interest in radiomics approaches can help to develop machine learning (ML) methods to support diagnosis. In this work, we propose an ML method based on the use of radiomics features, extracted from CT and PET images, to classify the disease in terms of pN-Stage, pT-Stage and Overall Stage. After the extraction of radiomics features, a selection step is performed to remove dataset redundancy. Finally, ML methods are employed to complete the classification task. Our pipeline is applied on the “Head-Neck-PET-CT” TCIA open-source dataset, considering a cohort of 201 patients from four different institutions. An AUC of 97%, 83% and 93% in terms of pN-Stage, pT-Stage and Overall Stage classification, respectively, is achieved. The obtained results are promising, showing the potential efficiency of the use of radiomics approaches in staging classification.

Comparison of Different Machine Models Based on Multi-Phase Computed Tomography Radiomic Analysis to Differentiate Parotid Basal Cell Adenoma From Pleomorphic Adenoma

Objective

This study explored the value of different radiomic models based on multiphase computed tomography in differentiating parotid pleomorphic adenoma (PA) and basal cell tumor (BCA) concerning the predominant phase and the optimal radiomic model.

Methods

This study enrolled 173 patients with pathologically confirmed parotid tumors (training cohort: n=121; testing cohort: n=52). Radiomic features were extracted from the nonenhanced, arterial, venous, and delayed phases CT images. After dimensionality reduction and screening, logistic regression (LR), K-nearest neighbor (KNN) and support vector machine (SVM) were applied to develop radiomic models. The optimal radiomic model was selected by using ROC curve analysis. Univariate and multivariable logistic regression was performed to analyze clinical-radiological characteristics and to identify variables for developing a clinical model. A combined model was constructed by integrating clinical and radiomic features. Model performances were assessed by ROC curve analysis.

Results

A total of 1036 radiomic features were extracted from each phase of CT images. Sixteen radiomic features were considered valuable by dimensionality reduction and screening. Among radiomic models, the SVM model of the arterial and delayed phases showed superior predictive efficiency and robustness (AUC, training cohort: 0.822, 0.838; testing cohort: 0.752, 0.751). The discriminatory capability of the combined model was the best (AUC, training cohort: 0.885; testing cohort: 0.834).

Conclusions

The diagnostic performance of the arterial and delayed phases contributed more than other phases. However, the combined model demonstrated excellent ability to distinguish BCA from PA, which may provide a non-invasive and efficient method for clinical decision-making.

Higher volume growth rate is associated with development of worrisome features in patients with branch duct-intraductal papillary mucinous neoplasms

BACKGROUND

Branch duct-intraductal papillary mucinous neoplasms (BD-IPMNs) are the most common pancreatic cystic tumours and have a low risk of malignant transformation. Current guidelines only evaluate cyst diameter as an important risk factor but it is not always easy to measure, especially when comparing different methods. On the other side, cyst volume is a new parameter with low inter-observer variability and is highly reproducible over time.

AIM

To assess both diameter and volume growth rate of BD-IPMNs and evaluate their correlation with the development of malignant characteristics.

METHODS

Computed tomography scans and magnetic resonance imaging exams were retrospectively reviewed. The diameter was measured on three planes, while the volume was calculated by segmentation: The volume of the entire cyst was determined by manually drawing a region of interest along the edge of the neoplasm on each consecutive slice covering the whole lesion; therefore, a three-dimensional volume of interest was finally obtained with the calculated value expressed in cm³. Changes in size over time were measured. The development of worrisome features was evaluated.

RESULTS

We evaluated exams of 98 patients across a 40.5-mo median follow-up time. Ten patients developed worrisome features. Cysts at baseline were significantly larger in patients who developed worrisome features (diameters P = 0.0035, P = 0.00652, P = 0.00424; volume P = 0.00222). Volume growth rate was significantly higher in patients who developed worrisome features (1.12 cm³/year vs 0 cm³/year, P = 0.0001); diameter growth rate was higher as well, but the difference did not always reach statistical significance. Volume but not diameter growth rate in the first year of follow-up was higher in patients who developed worrisome features (0.46 cm³/year vs 0 cm³/year, P = 0.00634).

CONCLUSION

The measurement of baseline volume and its variation over time is a reliable tool for the follow-up of BD-IPMNs. Volume measurement could be a better tool than diameter measurement to predict the development of worrisome features.

Artificial intelligence for renal cancer: From imaging to histology and beyond

Artificial intelligence (AI) has made considerable progress within the last decade and is the subject of contemporary literature. This trend is driven by improved computational abilities and increasing amounts of complex data that allow for new approaches in analysis and interpretation. Renal cell carcinoma (RCC) has a rising incidence since most tumors are now detected at an earlier stage due to improved imaging. This creates considerable challenges as approximately 10%–17% of kidney tumors are designated as benign in histopathological evaluation; however, certain co-morbid populations (the obese and elderly) have an increased peri-interventional risk. AI offers an alternative solution by helping to optimize precision and guidance for diagnostic and therapeutic decisions. The narrative review introduced basic principles and provide a comprehensive overview of current AI techniques for RCC. Currently, AI applications can be found in any aspect of RCC management including diagnostics, perioperative care, pathology, and follow-up. Most commonly applied models include neural networks, random forest, support vector machines, and regression. However, for implementation in daily practice, health care providers need to develop a basic understanding and establish interdisciplinary collaborations in order to standardize datasets, define meaningful endpoints, and unify interpretation.

Artificial Intelligence in Kidney Cancer

Artificial intelligence is rapidly expanding into nearly all facets of life, particularly within the field of medicine. The diagnosis, characterization, management, and treatment of kidney cancer is ripe with areas for improvement that may be met with the promises of artificial intelligence. Here, we explore the impact of current research work in artificial intelligence for clinicians caring for patients with renal cancer, with a focus on the perspectives of radiologists, pathologists, and urologists. Promising preliminary results indicate that artificial intelligence may assist in the diagnosis and risk stratification of newly discovered renal masses and help guide the clinical treatment of patients with kidney cancer. However, much of the work in this field is still in its early stages, limited in its broader applicability, and hampered by small datasets, the varied appearance and presentation of kidney cancers, and the intrinsic limitations of the rigidly structured tasks artificial intelligence algorithms are trained to complete. Nonetheless, the continued exploration of artificial intelligence holds promise toward improving the clinical care of patients with kidney cancer.

Non-contrast Cine Cardiac Magnetic Resonance image radiomics features and machine learning algorithms for myocardial infarction detection

OBJECTIVE

Robust differentiation between infarcted and normal tissue is important for clinical diagnosis and precision medicine. The aim of this work is to investigate the radiomic features and to develop a machine learning algorithm for the differentiation of myocardial infarction (MI) and viable tissues/normal cases in the left ventricular myocardium on non-contrast Cine Cardiac Magnetic Resonance (Cine-CMR) images.

METHODS

Seventy-two patients (52 with MI and 20 healthy control patients) were enrolled in this study. MR imaging was performed on a 1.5 T MRI using the following parameters: TR = 43.35 ms, TE = 1.22 ms, flip angle = 65°, temporal resolution of 30-40 ms. N4 bias field correction algorithm was applied to correct the inhomogeneity of images. All images were segmented and verified simultaneously by two cardiac imaging experts in consensus. Subsequently, features extraction was performed within the whole left ventricular myocardium (3D volume) in end-diastolic volume phase. Re-sampling to 1 × 1 × 1 mm³ voxels was performed for MR images. All intensities within the VOI of MR images were discretized to 64 bins. Radiomic features were normalized to obtain Z-scores, followed by Student's t-test statistical analysis for comparison. A p-value < 0.05 was used as a threshold for statistically significant differences and false discovery rate (FDR) correction performed to report q-value (FDR adjusted p-value). The extracted features were ranked using the MSVM-RFE algorithm, then Spearman correlation between features was performed to eliminate highly correlated features (R2 > 0.80). Ten different machine learning algorithms were used for classification and different metrics used for evaluation and various parameters used for models' evaluation.

RESULTS

In univariate analysis, the highest area under the curve (AUC) of receiver operating characteristic (ROC) value was achieved for the Maximum 2D diameter slice (M2DS) shape feature (AUC = 0.88, q-value = 1.02E-7), while the average of univariate AUCs was 0.62 ± 0.08. In multivariate analysis, Logistic Regression (AUC = 0.93 ± 0.03, Accuracy = 0.86 ± 0.05, Recall = 0.87 ± 0.1, Precision = 0.93 ± 0.03 and F1 Score = 0.90 ± 0.04) and SVM (AUC = 0.92 ± 0.05, Accuracy = 0.85 ± 0.04, Recall = 0.92 ± 0.01, Precision = 0.88 ± 0.04 and F1 Score = 0.90 ± 0.02) yielded optimal performance as the best machine learning algorithm for this radiomics analysis.

CONCLUSION

This study demonstrated that using radiomics analysis on non-contrast Cine-CMR images enables to accurately detect MI, which could potentially be used as an alternative diagnostic method for Late Gadolinium Enhancement Cardiac Magnetic Resonance (LGE-CMR).

MRI-based radiomics distinguish different pathological types of hepatocellular carcinoma

OBJECT

To distinguish combined hepatocellular cholangiocarcinoma (cHCC-CC), hepatocellular carcinoma (HCC) and cholangiocarcinoma (CC) before operation using MRI radiomics.

METHOD

This study retrospectively analyzed 196 liver cancers: 33 cHCC-CC, 88 HCC and 75 CC. They had confirmed by pathological analysis in the Affiliated Hospital of Hebei University. MRI lesions were manually segmented by a radiologist.1316 features were extracted from MRI lesions by Pyradiomics. Useful features were retained through two-level feature selection to establish a classification model. Receiver operating characteristic (ROC), area under curve (AUC) and F1-score were used to evaluate the performance of the model.

RESULTS

Compared with low-order image features, the performance of the model based on high-order features was improved by about 10%. The model showed better performance in identifying HCC tumors during the delay phase (AUC = 0.91, sensitivity = 0.88, specificity = 0.89, accuracy = 0.89, F1-Score = 0.88).

CONCLUSION

The classification ability of cHCC-CC, HCC and CC can be further improved by extracting MRI high-order features and using a two-level feature selection method.

The mathematics of erythema: Development of machine learning models for artificial intelligence assisted measurement and severity scoring of radiation induced dermatitis

Although significant advancements in computer-aided diagnostics using artificial intelligence (AI) have been made, to date, no viable method for radiation-induced skin reaction (RISR) analysis and classification is available. The objective of this single-center study was to develop machine learning and deep learning approaches using deep convolutional neural networks (CNNs) for automatic classification of RISRs according to the Common Terminology Criteria for Adverse Events (CTCAE) grading system. Scarletred^Ⓡ Vision, a novel and state-of-the-art digital skin imaging method capable of remote monitoring and objective assessment of acute RISRs was used to convert 2D digital skin images using the CIELAB color space and conduct SEV* measurements. A set of different machine learning and deep convolutional neural network-based algorithms has been explored for the automatic classification of RISRs. A total of 2263 distinct images from 209 patients were analyzed for training and testing the machine learning and CNN algorithms. For a 2-class problem of healthy skin (grade 0) versus erythema (grade ≥ 1), all machine learning models produced an accuracy of above 70%, and the sensitivity and specificity of erythema recognition were 67-72% and 72-83%, respectively. The CNN produced a test accuracy of 74%, sensitivity of 66%, and specificity of 83% for predicting healthy and erythema cases. For the severity grade prediction of a 3-class problem (grade 0 versus 1 versus 2), the overall test accuracy was 60-67%, and the sensitivities were 56-82%, 35-59%, and 65-72%, respectively. For estimating the severity grade of each class, the CNN obtained an accuracy of 73%, 66%, and 82%, respectively. Ensemble learning combines several individual predictions to obtain a better generalization performance. Furthermore, we exploited ensemble learning by deploying a CNN model as a meta-learner. The ensemble CNN based on bagging and majority voting shows an accuracy, sensitivity and specificity of 87%, 90%, and 82% for a 2-class problem, respectively. For a 3-class problem, the ensemble CNN shows an overall accuracy of 66%, while for each grade (0, 1, and 2) accuracies were 76%, 69%, and 87%, sensitivities were 70%, 57%, and 71%, and specificities were 78%, 75%, and 95%, respectively. This study is the first to focus on erythema in radiation-dermatitis and produces benchmark results using machine learning models. The outcome of this study validates that the proposed system can act as a pre-screening and decision support tool for oncologists or patients to provide fast, reliable, and efficient assessment of erythema grading.

Multi-level multi-modality (PET and CT) fusion radiomics: prognostic modeling for non-small cell lung carcinoma

We developed multi-modality radiomic models by integrating information extracted from¹⁸F-FDG PET and CT images using feature- and image-level fusions, toward improved prognosis for non-small cell lung carcinoma (NSCLC) patients. Two independent cohorts of NSCLC patients from two institutions (87 and 95 patients) were cycled as training and testing datasets. Fusion approaches were applied at two levels, namely feature- and image-levels. For feature-level fusion, radiomic features were extracted individually from CT and PET images and concatenated. Alternatively, radiomic features extracted separately from CT and PET images were averaged. For image-level fusion, wavelet fusion was utilized and tuned with two parameters, namely CT weight and Wavelet Band Pass Filtering Ratio. Clinical and combined clinical + radiomic models were developed. Gray level discretization was performed at 3 different levels (16, 32 and 64) and 225 radiomics features were extracted. Overall survival (OS) was considered as the endpoint. For feature reduction, correlated (redundant) features were excluded using Spearman's correlation, and best combination of top ten features with highest concordance-indices (via univariate Cox model) were selected in each model for further multivariate Cox model. Moreover, prognostic score's median, obtained from the training cohort, was used intact in the testing cohort as a threshold to classify patients into low- versus high-risk groups, and log-rank test was applied to assess differences between the Kaplan-Meier curves. Overall, while models based on feature-level fusion strategy showed limited superiority over single-modalities, image-level fusion strategy significantly outperformed both single-modality and feature-level fusion strategies. As such, the clinical model (C-index = 0.656) outperformed all models from single-modality and feature-level strategies, but was outperformed by certain models from image-level fusion strategy. Our findings indicated that image-level fusion multi-modality radiomics models outperformed single-modality, feature-level fusion, and clinical models for OS prediction of NSCLC patients.

Radiomics and Machine Learning Can Differentiate Transient Osteoporosis from Avascular Necrosis of the Hip

Differentiation between transient osteoporosis (TOH) and avascular necrosis (AVN) of the hip is a longstanding challenge in musculoskeletal radiology. The purpose of this study was to utilize MRI-based radiomics and machine learning (ML) for accurate differentiation between the two entities. A total of 109 hips with TOH and 104 hips with AVN were retrospectively included. Femoral heads and necks with segmented radiomics features were extracted. Three ML classifiers (XGboost, CatBoost and SVM) using 38 relevant radiomics features were trained on 70% and validated on 30% of the dataset. ML performance was compared to two musculoskeletal radiologists, a general radiologist and two radiology residents. XGboost achieved the best performance with an area under the curve (AUC) of 93.7% (95% CI from 87.7 to 99.8%) among ML models. MSK radiologists achieved an AUC of 90.6% (95% CI from 86.7% to 94.5%) and 88.3% (95% CI from 84% to 92.7%), respectively, similar to residents. The general radiologist achieved an AUC of 84.5% (95% CI from 80% to 89%), significantly lower than of XGboost (p = 0.017). In conclusion, radiomics-based ML achieved a performance similar to MSK radiologists and significantly higher compared to general radiologists in differentiating between TOH and AVN.

Machine learning-based CT radiomics model distinguishes COVID-19 from non-COVID-19 pneumonia

BACKGROUND

To develop a machine learning-based CT radiomics model is critical for the accurate diagnosis of the rapid spreading coronavirus disease 2019 (COVID-19).

METHODS

In this retrospective study, a total of 326 chest CT exams from 134 patients (63 confirmed COVID-19 patients and 71 non-COVID-19 patients) were collected from January 20 to February 8, 2020. A semi-automatic segmentation procedure was used to delineate the volume of interest (VOI), and radiomic features were extracted. The Support Vector Machine (SVM) model was built on the combination of 4 groups of features, including radiomic features, traditional radiological features, quantifying features, and clinical features. By repeating cross-validation procedure, the performance on the time-independent testing cohort was evaluated by the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.

RESULTS

For the SVM model built on the combination of 4 groups of features (integrated model), the per-exam AUC was 0.925 (95% CI 0.856 to 0.994) for differentiating COVID-19 on the testing cohort, and the sensitivity and specificity were 0.816 (95% CI 0.651 to 0.917) and 0.923 (95% CI 0.621 to 0.996), respectively. As for the SVM models built on radiomic features, radiological features, quantifying features, and clinical features, individually, the AUC on the testing cohort reached 0.765, 0.818, 0.607, and 0.739, respectively, significantly lower than the integrated model, except for the radiomic model.

CONCLUSION

The machine learning-based CT radiomics models may accurately classify COVID-19, helping clinicians and radiologists to identify COVID-19 positive cases.

Artificial intelligence-driven assessment of radiological images for COVID-19

Artificial Intelligence (AI) methods have significant potential for diagnosis and prognosis of COVID-19 infections. Rapid identification of COVID-19 and its severity in individual patients is expected to enable better control of the disease individually and at-large. There has been remarkable interest by the scientific community in using imaging biomarkers to improve detection and management of COVID-19. Exploratory tools such as AI-based models may help explain the complex biological mechanisms and provide better understanding of the underlying pathophysiological processes. The present review focuses on AI-based COVID-19 studies as applies to chest x-ray (CXR) and computed tomography (CT) imaging modalities, and the associated challenges. Explicit radiomics, deep learning methods, and hybrid methods that combine both deep learning and explicit radiomics have the potential to enhance the ability and usefulness of radiological images to assist clinicians in the current COVID-19 pandemic. The aims of this review are: first, to outline COVID-19 AI-analysis workflows, including acquisition of data, feature selection, segmentation methods, feature extraction, and multi-variate model development and validation as appropriate for AI-based COVID-19 studies. Secondly, existing limitations of AI-based COVID-19 analyses are discussed, highlighting potential improvements that can be made. Finally, the impact of AI and radiomics methods and the associated clinical outcomes are summarized. In this review, pipelines that include the key steps for AI-based COVID-19 signatures identification are elaborated. Sample size, non-standard imaging protocols, segmentation, availability of public COVID-19 databases, combination of imaging and clinical information and full clinical validation remain major limitations and challenges. We conclude that AI-based assessment of CXR and CT images has significant potential as a viable pathway for the diagnosis, follow-up and prognosis of COVID-19.

Overall Survival Prediction in Renal Cell Carcinoma Patients Using Computed Tomography Radiomic and Clinical Information

The aim of this work is to investigate the applicability of radiomic features alone and in combination with clinical information for the prediction of renal cell carcinoma (RCC) patients’ overall survival after partial or radical nephrectomy. Clinical studies of 210 RCC patients from The Cancer Imaging Archive (TCIA) who underwent either partial or radical nephrectomy were included in this study. Regions of interest (ROIs) were manually defined on CT images. A total of 225 radiomic features were extracted and analyzed along with the 59 clinical features. An elastic net penalized Cox regression was used for feature selection. Accelerated failure time (AFT) with the shared frailty model was used to determine the effects of the selected features on the overall survival time. Eleven radiomic and twelve clinical features were selected based on their non-zero coefficients. Tumor grade, tumor malignancy, and pathology t-stage were the most significant predictors of overall survival (OS) among the clinical features (p < 0.002, < 0.02, and < 0.018, respectively). The most significant predictors of OS among the selected radiomic features were flatness, area density, and median (p < 0.02, < 0.02, and < 0.05, respectively). Along with important clinical features, such as tumor heterogeneity and tumor grade, imaging biomarkers such as tumor flatness, area density, and median are significantly correlated with OS of RCC patients.

Non-small cell lung carcinoma histopathological subtype phenotyping using high-dimensional multinomial multiclass CT radiomics signature

OBJECTIVE

The aim of this study was to identify the most important features and assess their discriminative power in the classification of the subtypes of NSCLC.

METHODS

This study involved 354 pathologically proven NSCLC patients including 134 squamous cell carcinoma (SCC), 110 large cell carcinoma (LCC), 62 not other specified (NOS), and 48 adenocarcinoma (ADC). In total, 1433 radiomics features were extracted from 3D volumes of interest drawn on the malignant lesion identified on CT images. Wrapper algorithm and multivariate adaptive regression splines were implemented to identify the most relevant/discriminative features. A multivariable multinomial logistic regression was employed with 1000 bootstrapping samples based on the selected features to classify four main subtypes of NSCLC.

RESULTS

The results revealed that the texture features, specifically gray level size zone matrix features (GLSZM), were the significant indicators of NSCLC subtypes. The optimized classifier achieved an average precision, recall, F1-score, and accuracy of 0.710, 0.703, 0.706, and 0.865, respectively, based on the selected features by the wrapper algorithm.

CONCLUSIONS

Our CT radiomics approach demonstrated impressive potential for the classification of the four main histological subtypes of NSCLC, It is anticipated that CT radiomics could be useful in treatment planning and precision medicine.

Uncontrolled Confounders May Lead to False or Overvalued Radiomics Signature: A Proof of Concept Using Survival Analysis in a Multicenter Cohort of Kidney Cancer

Purpose

We aimed to explore potential confounders of prognostic radiomics signature predicting survival outcomes in clear cell renal cell carcinoma (ccRCC) patients and demonstrate how to control for them.

Materials and Methods

Preoperative contrast enhanced abdominal CT scan of ccRCC patients along with pathological grade/stage, gene mutation status, and survival outcomes were retrieved from The Cancer Imaging Archive (TCIA)/The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma (TCGA-KIRC) database, a publicly available dataset. A semi-automatic segmentation method was applied to segment ccRCC tumors, and 1,160 radiomics features were extracted from each segmented tumor on the CT images. Non-parametric principal component decomposition (PCD) and unsupervised hierarchical clustering were applied to build the radiomics signature models. The factors confounding the radiomics signature were investigated and controlled sequentially. Kaplan-Meier curves and Cox regression analyses were performed to test the association between radiomics signatures and survival outcomes.

Results

183 patients of TCGA-KIRC cohort with available imaging, pathological, and clinical outcomes were included in this study. All 1,160 radiomics features were included in the first radiomics signature. Three additional radiomics signatures were then modelled in successive steps removing redundant radiomics features first, removing radiomics features biased by CT slice thickness second, and removing radiomics features dependent on tumor size third. The final radiomics signature model was the most parsimonious, unbiased by CT slice thickness, and independent of tumor size. This final radiomics signature stratified the cohort into radiomics phenotypes that are different by cancer-specific and recurrence-free survival; HR (95% CI) = 3.0 (1.5-5.7), p <0.05 and HR (95% CI) = 6.6 (3.1-14.1), p <0.05, respectively.

Conclusion

Radiomics signature can be confounded by multiple factors, including feature redundancy, image acquisition parameters like slice thickness, and tumor size. Attention to and proper control for these potential confounders are necessary for a reliable and clinically valuable radiomics signature.

Treatment response prediction using MRI-based pre-, post-, and delta-radiomic features and machine learning algorithms in colorectal cancer

OBJECTIVES

We evaluate the feasibility of treatment response prediction using MRI-based pre-, post-, and delta-radiomic features for locally advanced rectal cancer (LARC) patients treated by neoadjuvant chemoradiation therapy (nCRT).

MATERIALS AND METHODS

This retrospective study included 53 LARC patients divided into a training set (Center#1, n = 36) and external validation set (Center#2, n = 17). T2-weighted (T2W) MRI was acquired for all patients, 2 weeks before and 4 weeks after nCRT. Ninety-six radiomic features, including intensity, morphological and second- and high-order texture features were extracted from segmented 3D volumes from T2W MRI. All features were harmonized using ComBat algorithm. Max-Relevance-Min-Redundancy (MRMR) algorithm was used as feature selector and k-nearest neighbors (KNN), Naïve Bayes (NB), Random forests (RF), and eXtreme Gradient Boosting (XGB) algorithms were used as classifiers. The evaluation was performed using the area under the receiver operator characteristic (ROC) curve (AUC), sensitivity, specificity and accuracy.

RESULTS

In univariate analysis, the highest AUC in pre-, post-, and delta-radiomic features were 0.78, 0.70, and 0.71, for GLCM_IMC1, shape (surface area and volume) and GLSZM_GLNU features, respectively. In multivariate analysis, RF and KNN achieved the highest AUC (0.85 ± 0.04 and 0.81 ± 0.14, respectively) among pre- and post-treatment features. The highest AUC was achieved for the delta-radiomic-based RF model (0.96 ± 0.01) followed by NB (0.96 ± 0.04). Overall. Delta-radiomics model, outperformed both pre- and post-treatment features (P-value <0.05).

CONCLUSION

Multivariate analysis of delta-radiomic T2W MRI features using machine learning algorithms could potentially be used for response prediction in LARC patients undergoing nCRT. We also observed that multivariate analysis of delta-radiomic features using RF classifiers can be used as powerful biomarkers for response prediction in LARC.

Radiomics-based neural network predicts recurrence patterns in glioblastoma using dynamic susceptibility contrast-enhanced MRI

Glioblastoma remains the most devastating brain tumor despite optimal treatment, because of the high rate of recurrence. Distant recurrence has distinct genomic alterations compared to local recurrence, which requires different treatment planning both in clinical practice and trials. To date, perfusion-weighted MRI has revealed that perfusional characteristics of tumor are associated with prognosis. However, not much research has focused on recurrence patterns in glioblastoma: namely, local and distant recurrence. Here, we propose two different neural network models to predict the recurrence patterns in glioblastoma that utilizes high-dimensional radiomic profiles based on perfusion MRI: area under the curve (AUC) (95% confidence interval), 0.969 (0.903-1.000) for local recurrence; 0.864 (0.726-0.976) for distant recurrence for each patient in the validation set. This creates an opportunity to provide personalized medicine in contrast to studies investigating only group differences. Moreover, interpretable deep learning identified that salient radiomic features for each recurrence pattern are related to perfusional intratumoral heterogeneity. We also demonstrated that the combined salient radiomic features, or "radiomic risk score", increased risk of recurrence/progression (hazard ratio, 1.61; p = 0.03) in multivariate Cox regression on progression-free survival.

Enhanced computed tomography radiomics-based machine-learning methods for predicting the Fuhrman grades of renal clear cell carcinoma

OBJECTIVE

To develop and test an optimal machine learning model based on the enhanced computed tomography (CT) to preoperatively predict pathological grade of clear cell renal cell carcinoma (ccRCC).

METHODS

A retrospective analysis of 53 pathologically confirmed cases of ccRCC was performed and 25 consecutive ccRCC cases were selected as a prospective testing set. All patients underwent routine preoperative abdominal CT plain and enhanced scans. Renal tumor lesions were segmented on arterial phase images and 396 radiomics features were extracted. In the training set, seven discrimination classifiers for high- and low-grade ccRCCs were constructed based on seven different machine learning models, respectively, and their performance and stability for predicting ccRCC grades were evaluated through receiver operating characteristic (ROC) analysis and cross-validation. Prediction accuracy and area under ROC curve were used as evaluation indices. Finally, the diagnostic efficacy of the optimal model was verified in the testing set.

RESULTS

The accuracies and AUC values achieved by support vector machine with radial basis function kernel (svmRadial), random forest and naïve Bayesian models were 0.860±0.158 and 0.919±0.118, 0.840±0.160 and 0.915±0.138, 0.839±0.147 and 0.921±0.133, respectively, which showed high predictive performance, whereas K-nearest neighborhood model yielded lower accuracy of 0.720±0.188 and lower AUC value of 0.810±0.150. Additionally, svmRadial had smallest relative standard deviation (RSD, 0.13 for AUC, 0.17 for accuracy), which indicates higher stability.

CONCLUSION

svmRadial performs best in predicting pathological grades of ccRCC using radiomics features computed from the preoperative CT images, and thus may have high clinical potential in guiding preoperative decision.