Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma

Machine Learning-Based Diagnostic Prediction Model Using T1-Weighted Striatal Magnetic Resonance Imaging for Early-Stage Parkinson's Disease Detection

RATIONALE AND OBJECTIVES

Diagnosing Parkinson's disease (PD) typically relies on clinical evaluations, often detecting it in advanced stages. Recently, artificial intelligence has increasingly been applied to imaging for neurodegenerative disorders. This study aims to develop a diagnostic prediction model using T1-weighted magnetic resonance imaging (T1-MRI) data from the caudate and putamen in individuals with early-stage PD.

MATERIALS AND METHODS

This retrospective case-control study included 69 early-stage PD patients and 22 controls, recruited through the Parkinson's Progression Markers Initiative. T1-MRI scans were acquired using a 3-tesla system. 432 radiomic features were extracted from images of the segmented caudate and putâmen in an automated way. Feature selection was performed using Pearson's correlation and recursive feature elimination to identify the most relevant variables. Three machine learning algorithms-random forest (RF), support vector machine and logistic regression-were evaluated for diagnostic prediction effectiveness using a cross-validation method. The Shapley Additive Explanations technique identified the most significant features distinguishing between the groups. The metrics used to evaluate the performance were discrimination, expressed in area under the ROC curve (AUC), sensitivity and specificity; and calibration, expressed as accuracy.

RESULTS

The RF algorithm showed superior performance with an average accuracy of 92.85%, precision of 100.00%, sensitivity of 86.66%, specificity of 96.65% and AUC of 0.93. The three most influential features were contrast, elongation, and gray-level non-uniformity, all from the putamen.

CONCLUSION

Machine learning-based models can differentiate early-stage PD from controls using T1-weighted MRI radiomic features.

Human-in-the-loop machine learning-based quantitative assessment of hemifacial spasm based on volumetric interpolated breath-hold examination MR

OBJECTIVES

The purpose of this study was to assess the severity of hemifacial spasm (HFS) through quantitative measures that associated it with neurovascular contact (NVC).

METHODS

We enrolled 108 HFS patients (63 severe and 45 mild cases) and implemented a human-in-the-loop approach to develop a quantitative NVC feature package. This process involved using interactive segmentation on 3D volumetric interpolated breath-hold examination (VIBE) MR images to delineate vascular and nerve structures. From these segmentations, we extracted quantitative NVC features, forming an NVC feature package, and applied a support vector machine model to assess HFS severity.

RESULTS

Our interactive segmentation technique achieved high accuracy (Dice similarity coefficients of 0.905 ± 0.030 for vascular structures and 0.922 ± 0.086 for nerves). The NVC feature package, comprising distance between vascular structures and nerves, vascular diameter, their ratio, and clinical characteristics, enabled our model to assess HFS severity with an AUC of 0.823 (95% CI: 0.714-0.932, P < .001).

CONCLUSIONS

This study introduced a quantitative approach in understanding the relationship between HFS severity and NVC, using VIBE MR imaging. Our model offers a promising tool for enhancing clinical decision-making and offers deeper insights into the impact of NVCon HFS, aiming to improve patient outcomes.

ADVANCES IN KNOWLEDGE

Microvascular decompression is well-established as a safe and effective treatment for HFS. However, there is a gap assessing the severity of HFS using quantitative measures that directly link it to NVC. Our method introduced a quantitative and objective alternative for assessing the severity of HFS to addressing this gap.

Early prediction of progression-free survival of patients with locally advanced nasopharyngeal carcinoma using multi-parametric MRI radiomics

PURPOSE

Prognostic prediction plays a pivotal role in guiding personalized treatment for patients with locoregionally advanced nasopharyngeal carcinoma (LANPC). However, few studies have investigated the incremental value of functional MRI to the conventional MRI-based radiomic models. Here, we aimed to develop a radiomic model including functional MRI to predict the prognosis of LANPC patients.

METHODS

One hundred and twenty-six patients (training dataset, n = 88; validation dataset, n = 38) with LANPC were retrospectively included. Radiomic features were extracted from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), contrast-enhanced T1WI (cT1WI), and diffusion-weighted imaging (DWI). Pearson correlation analysis and recursive feature elimination or Relief were used for identifying features associated with progression-free survival (PFS). Five machine learning algorithms with cross-validation were compared to develop the optimal single-layer and fusion radiomic models. Clinical and combined models were developed via multivariate Cox regression model.

RESULTS

The clinical model based on TNM stage achieved a C-index of 0.544 in the validation dataset. The fusion radiomic model, incorporating DWI-, T1WI-, and cT1WI-derived imaging features, yielded the highest C-index of 0.788, outperforming DWI-based (C-index = 0.739), T1WI-based (C-index = 0.734), cT1WI-based (C-index = 0.722), and T1WI plus cT1WI-based models (C-index = 0.747) in predicting PFS. The fusion radiomic model yielded the C-index of 0.786 and 0.690 in predicting distant metastasis-free survival and overall survival, respectively. However, the addition of TNM stage to the fusion radiomic model could not improve the predictive power.

CONCLUSION

The fusion radiomic model demonstrates favorable performance in predicting survival outcomes in LANPC patients, surpassing TNM staging alone. Integration of DWI-derived features into conventional MRI radiomic models could enhance predictive accuracy.

Exploring the influence of age on the causes of death in advanced nasopharyngeal carcinoma patients undergoing chemoradiotherapy using machine learning methods

The present study analyzed the impact of age on the causes of death (CODs) in patients with nasopharyngeal carcinoma (NPC) undergoing chemoradiotherapy (CRT) using machine learning approaches. A total of 2841 patients (1037 classified as older, ≥ 60 years and 1804 as younger, < 60 years) were enrolled. Variations in the CODs between the two age groups were analyzed before and after applying inverse probability of treatment weighting (IPTW). Additionally, seven different machine learning models were employed as predictive tools to identify key variables and assess the therapeutic outcomes in NPC patients receiving CRT. The younger group exhibited a significantly longer overall survival (OS) than the older group, both before the IPTW adjustment (140 vs. 50 months, P < 0.001) and after the adjustment (137 vs. 53 months, P < 0.001). After IPTW, the older group was associated with worse 5-, 10-, and 15-year cumulative incidences in terms of NPC-related deaths (30, 34, and 38% vs. 21, 27, and 30%; P < 0.001), cardiovascular disease (CVD; 4.1, 7.2, and 8.8% vs. 0.5, 1.8, and 3.0%; P < 0.001), and other causes (8.3, 17, and 24% vs. 4.1, 8.7, and 12%; P < 0.001). However, cumulative incidences of secondary malignant neoplasms were comparable between the two groups (P = 0.100). The random forest (RF) model demonstrated the highest concordance index of 0.701 among all models. Time-dependent variable importance plots indicated that age was the most influential factor affecting 3-, 5-, and 10-year survival, followed by metastasis and tumor stage. Younger patients had significantly longer OS than their older counterparts. Older patients had a higher likelihood of dying from non-NPC-related causes, particularly CVDs. The RF model showed the best predictive accuracy, identifying age as the most critical factor influencing OS in NPC patients undergoing CRT.

Prediction of Persistent Tumor Status in Nasopharyngeal Carcinoma Post-Radiotherapy-Related Treatment: A Machine Learning Approach

Background/Objectives: The duration of the response to radiotherapy-related treatment is a critical prognostic indicator for patients with nasopharyngeal carcinoma (NPC). Persistent tumor status, including residual tumor presence and early recurrence, is associated with poorer survival outcomes. To address this, we developed a prediction model to identify patients at a high risk of persistent tumor status prior to initiating treatment. Methods: This retrospective study included 104 patients with NPC receiving radiotherapy-related treatment who had completed a 3-year follow-up period; 29 were classified into the persistent tumor status group and 75 into the disease-free group. Radiomic features were extracted from pretreatment positron emission tomography (PET) images and used to construct a prediction model by employing machine learning algorithms. The model's diagnostic performance was assessed using the area under the receiver operating characteristic curve (AUC), whereas SHapley Additive exPlanations (SHAP) analysis was conducted to determine the contribution of individual features to the model. Results: The prediction model developed using the AdaBoost algorithm and validated through five-fold cross-validation achieved the highest AUC of 0.934. Its sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 89.66%, 86.67%, 72.22%, 95.59%, and 87.5%, respectively. SHAP analysis revealed that the feature of high dependence low metabolic uptake emphasis50 had the greatest impact on model predictions. Furthermore, patients classified as disease-free exhibited markedly higher overall survival rates compared with those with persistent tumor status. Conclusions: In conclusion, the proposed prediction model efficiently identified patients with NPC at a high risk of persistent tumor status by using radiomic features extracted from pretreatment PET images.

Artificial Intelligence in Head and Neck Surgery

This article explores artificial intelligence's (AI's) role in otolaryngology for head and neck cancer diagnosis and management. It highlights AI's potential in pattern recognition for early cancer detection, prognostication, and treatment planning, primarily through image analysis using clinical, endoscopic, and histopathologic images. Radiomics is also discussed at length, as well as the many ways that radiologic image analysis can be utilized, including for diagnosis, lymph node metastasis prediction, and evaluation of treatment response. The study highlights AI's promise and limitations, underlining the need for clinician-data scientist collaboration to enhance head and neck cancer care.

Artificial intelligence methods available for cancer research

Cancer is a heterogeneous and multifaceted disease with a significant global footprint. Despite substantial technological advancements for battling cancer, early diagnosis and selection of effective treatment remains a challenge. With the convenience of large-scale datasets including multiple levels of data, new bioinformatic tools are needed to transform this wealth of information into clinically useful decision-support tools. In this field, artificial intelligence (AI) technologies with their highly diverse applications are rapidly gaining ground. Machine learning methods, such as Bayesian networks, support vector machines, decision trees, random forests, gradient boosting, and K-nearest neighbors, including neural network models like deep learning, have proven valuable in predictive, prognostic, and diagnostic studies. Researchers have recently employed large language models to tackle new dimensions of problems. However, leveraging the opportunity to utilize AI in clinical settings will require surpassing significant obstacles-a major issue is the lack of use of the available reporting guidelines obstructing the reproducibility of published studies. In this review, we discuss the applications of AI methods and explore their benefits and limitations. We summarize the available guidelines for AI in healthcare and highlight the potential role and impact of AI models on future directions in cancer research.

Metabolism score and machine learning models for the prediction of esophageal squamous cell carcinoma progression

The incomplete prediction of prognosis in esophageal squamous cell carcinoma (ESCC) patients is attributed to various therapeutic interventions and complex prognostic factors. Consequently, there is a pressing demand for enhanced predictive biomarkers that can facilitate clinical management and treatment decisions. This study recruited 491 ESCC patients who underwent surgical treatment at Huashan Hospital, Fudan University. We incorporated 14 blood metabolic indicators and identified independent prognostic indicators for overall survival through univariate and multivariate analyses. Subsequently, a metabolism score formula was established based on the biochemical markers. We constructed a nomogram and machine learning models utilizing the metabolism score and clinically significant prognostic features, followed by an evaluation of their predictive accuracy and performance. We identified alkaline phosphatase, free fatty acids, homocysteine, lactate dehydrogenase, and triglycerides as independent prognostic indicators for ESCC. Subsequently, based on these five indicators, we established a metabolism score that serves as an independent prognostic factor in ESCC patients. By utilizing this metabolism score in conjunction with clinical features, a nomogram can precisely predict the prognosis of ESCC patients, achieving an area under the curve (AUC) of 0.89. The random forest (RF) model showed superior predictive ability (AUC = 0.90, accuracy = 86%, Matthews correlation coefficient = 0.55). Finally, we used an RF model with optimal performance to establish an online predictive tool. The metabolism score developed in this study serves as an independent prognostic indicator for ESCC patients.

Predicting progression-free survival in patients with epithelial ovarian cancer using an interpretable random forest model

Prognostic models play a crucial role in providing personalised risk assessment, guiding treatment decisions, and facilitating the counselling of patients with cancer. However, previous imaging-based artificial intelligence models of epithelial ovarian cancer lacked interpretability. In this study, we aimed to develop an interpretable machine-learning model to predict progression-free survival in patients with epithelial ovarian cancer using clinical variables and radiomics features. A total of 102 patients with epithelial ovarian cancer who underwent contrast-enhanced computed tomography scans were enrolled in this retrospective study. Pre-surgery clinical data, including age, performance status, body mass index, tumour stage, venous blood cancer antigen-125 (CA125) level, white blood cell count, neutrophil count, red blood cell count, haemoglobin level, and platelet count, were obtained from medical records. The volume of interest for each tumour was manually delineated slice-by-slice along the boundary. A total of 2074 radiomic features were extracted from the pre- and post-contrast computed tomography images. Optimal radiomic features were selected using the Least Absolute Shrinkage and Selection Operator logistic regression. Multivariate Cox analysis was performed to identify independent predictors of three-year progression-free survival. The random forest algorithm developed radiomic and combined models using four-fold cross-validation. Finally, the Shapley additive explanation algorithm was applied to interpret the predictions of the combined model. Multivariate Cox analysis identified CA-125 levels (P = 0.015), tumour stage (P = 0.019), and Radscore (P < 0.001) as independent predictors of progression-free survival. The combined model based on these factors achieved an area under the curve of 0.812 (95 % confidence interval: 0.802-0.822) in the training cohort and 0.772 (95 % confidence interval: 0.727-0.817) in the validation cohort. The most impactful features on the model output were Radscore, followed by tumour stage and CA-125. In conclusion, the Shapley additive explanation-based interpretation of the prognostic model enables clinicians to understand the reasoning behind predictions better.

Artificial Intelligence-Driven Radiomics in Head and Neck Cancer: Current Status and Future Prospects

BACKGROUND

Radiomics is a rapidly growing field used to leverage medical radiological images by extracting quantitative features. These are supposed to characterize a patient's phenotype, and when combined with artificial intelligence techniques, to improve the accuracy of diagnostic models and clinical outcome prediction.

OBJECTIVES

This review aims at examining the application areas of artificial intelligence-based radiomics (AI-based radiomics) for the management of head and neck cancer (HNC). It further explores the workflow of AI-based radiomics for personalized and precision oncology in HNC. Finally, it examines the current challenges of AI-based radiomics in daily clinical oncology and offers possible solutions to these challenges.

METHODS

Comprehensive electronic databases (PubMed, Medline via Ovid, Scopus, Web of Science, CINAHL, and Cochrane Library) were searched following the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines. The quality of included studies and their risk of biases were evaluated using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD)and Prediction Model Risk of Bias Assessment Tool (PROBAST).

RESULTS

Out of the 659 search hits retrieved, 45 fulfilled the inclusion criteria. Our review revealed that the application of AI-based radiomics model as an ancillary tool for improved decision-making in HNC management includes radiomics-based cancer diagnosis and radiomics-based cancer prognosis. The radiomics-based cancer diagnosis includes tumor staging, tumor grading, and classification of malignant and benign tumors. Similarly, radiomics-based cancer prognosis includes prediction for treatment response, recurrence, metastasis, and survival. In addition, the challenges in the implementation of these models for clinical evaluations include data imbalance, feature engineering (extraction and selection), model generalizability, multi-modal fusion, and model interpretability.

CONCLUSION

Considering the highly subjective and interobserver variability that is peculiar to the interpretation of medical images by expert clinicians, AI-based radiomics seeks to offer potentially useful quantitative information, which is not visible to the human eye or unintentionally often remain ignored during clinical imaging practice. By enabling the extraction of this type of information, AI-based radiomics has the potential to revolutionize HNC oncology, providing a platform for more personalized, higher quality, and cost-effective care for HNC patients.

Functional network reorganization after endovascular thrombectomy in patients with anterior circulation stroke

BACKGROUND

Endovascular thrombectomy has been confirmed to be an effective therapy for acute ischemic stroke (AIS). However, how functional brain networks reorganize after restoration of blood supply in AIS patients, and whether the degree of reperfusion associates with functional network changes remains unclear.

METHODS

Resting-state fMRI data were collected from 43 AIS patients with anterior circulation occlusion after thrombectomy and 37 healthy controls (HCs). Both static and dynamic functional connectivity (FC) within four advanced functional networks including dorsal attention network (DAN), ventral attention network (VAN), executive control network (ECN) and default mode network (DMN), were calculated and compared between post-thrombectomy patients and HCs, and between two subgroups of post-thrombectomy patients with different reperfusion conditions.

RESULTS

As compared to HCs, patients showed significant differences in static FC of four functional networks, and in dynamic FC of DAN, ECN and DMN. Furthermore, patients with better reperfusion conditions exhibited increased static FC with precuneus, and altered dynamic FC within precuneus. Moreover, these alterations were associated with clinical assessments of stroke severity and functional recovery in post-thrombectomy patients.

CONCLUSIONS

Collectively, these findings may provide the potential imaging markers for assessment of thrombectomy efficacy and help establish the specific rehabilitation treatments for post-thrombectomy patients.

Deciphering the Prognostic Efficacy of MRI Radiomics in Nasopharyngeal Carcinoma: A Comprehensive Meta-Analysis

This meta-analysis investigates the prognostic value of MRI-based radiomics in nasopharyngeal carcinoma treatment outcomes, specifically focusing on overall survival (OS) variability. The study protocol was registered with INPLASY (INPLASY202420101). Initially, a systematic review identified 15 relevant studies involving 6243 patients through a comprehensive search across PubMed, Embase, and Web of Science, adhering to PRISMA guidelines. The methodological quality was assessed using the Quality in Prognosis Studies (QUIPS) tool and the Radiomics Quality Score (RQS), highlighting a low risk of bias in most domains. Our analysis revealed a significant average concordance index (c-index) of 72% across studies, indicating the potential of radiomics in clinical prognostication. However, moderate heterogeneity was observed, particularly in OS predictions. Subgroup analyses and meta-regression identified validation methods and radiomics software as significant heterogeneity moderators. Notably, the number of features in the prognosis model correlated positively with its performance. These findings suggest radiomics' promising role in enhancing cancer treatment strategies, though the observed heterogeneity and potential biases call for cautious interpretation and standardization in future research.

Development of a joint prediction model based on both the radiomics and clinical factors for preoperative prediction of circumferential resection margin in middle-low rectal cancer using T2WI images

OBJECTIVES

A circumferential resection margin (CRM) is an independent risk factor for local recurrence, distant metastasis, and poor overall survival of rectal cancer. In this study, we developed and validated a radiomics prediction model to predict perioperative surgical margins in patients with middle and low rectal cancer following neoadjuvant treatment and for decisions about treatment plans for patients.

METHODS

This study retrospectively analyzed 275 patients from center 1(training cohort) and 120 patients from center 2(verification cohort) with rectal cancer diagnosed at two centers from July 2020 to July 2022 who underwent neoadjuvant therapy and had their CRM status confirmed by preoperative high-resolution magnetic resonance imaging (MRI) scans. Radiomics signatures were extracted and screened from MRI images and a radiomics signature was built by the least absolute shrinkage and selection operator (LASSO) logistic regression model, which was combined with clinical signatures to construct a nomogram. The receiver operating characteristic (ROC) curve and area under the curve (AUC) value, sensitivity, specificity, positive predictive value, negative predictive value, and calibration curve were used to evaluate the predictive performance of the model.

RESULTS

In our research, the combined model has the best performance. In the training group, the radiomics model based on high-spatial-resolution T2-weighted imaging (HR-T2WI), clinical model and combined model demonstrated an AUC of 0.819 (0.802-0.833), 0.843 (0.822-0.861), and 0.910 (0.880-0.940), respectively. In the validation group, they demonstrated an AUC of 0.745 (0.715-0.788), 0.827 (0.798-0.850), and 0.848 (0.779-0.917), respectively. The calibration curve confirmed the clinical applicability of the model.

CONCLUSIONS

The individualized prediction model established by combining radiomics signatures and clinical signatures can efficiently and objectively predict perioperative margin invasion in patients with middle and low rectal cancer.

Using machine learning algorithms to predict the prognosis of advanced nasopharyngeal carcinoma after intensity-modulated radiotherapy

BACKGROUND

The prognosis of advanced nasopharyngeal carcinoma (NPC) patients after intensity-modulated radiotherapy (IMRT) has not been well studied. We aimed to construct prognostic models for advanced NPC patients with stage III-IV after their first treatment with IMRT by using machine learning algorithms and to identify the most important predictors.

METHODS

A total of 427 patients treated in Meizhou People's Hospital in Guangdong province, China from January 1, 2013 to December 12, 2018 were enrolled in this study, with an average follow-up period of 7.16 years from July 2020 to March 2021. Candidate predictors were selected from demographics, clinical features, medical examinations and test results. Three machine learning algorithms were applied to construct advanced NPC prognostic models: logistic regression (LR), decision tree (DT), and random forest (RF). Area under the receiver operating characteristic curve (AUC) was used to evaluate the model performance. The important predictors of the optimal model for unfavourable prognosis were identified and ranked.

RESULTS

There were 50 (11.7%) NPC-related deaths observed in this study. The mean age of all participants was 49.39±11.29 years, of whom 299 (70.0%) were males. In general, RF showed the best predictive performance with the highest AUC (0.753, 95% CI: 0.609, 0.896), compared to LR (0.736, 95% confidence interval (CI): 0.590, 0.881), and DT (0.720, 95% CI: 0.520, 0.921). The six most important predictors identified by RF were Epstein-Barr virus deoxyribonucleic acid, aspartate aminotransferase, body mass index, age, blood glucose level, and alanine aminotransferase.

CONCLUSIONS

We proposed RF as a simple and accurate tool for the evaluation of the prognosis of advanced NPC patients after the treatment with IMRT in clinical settings.

Preoperative CT-based deep learning radiomics model to predict lymph node metastasis and patient prognosis in bladder cancer: a two-center study

OBJECTIVE

To establish a model for predicting lymph node metastasis in bladder cancer (BCa) patients.

METHODS

We retroactively enrolled 239 patients who underwent three-phase CT and resection for BCa in two centers (training set, n = 185; external test set, n = 54). We reviewed the clinical characteristics and CT features to identify significant predictors to construct a clinical model. We extracted the hand-crafted radiomics features and deep learning features of the lesions. We used the Minimum Redundancy Maximum Relevance algorithm and the least absolute shrinkage and selection operator logistic regression algorithm to screen features. We used nine classifiers to establish the radiomics machine learning signatures. To compensate for the uneven distribution of the data, we used the synthetic minority over-sampling technique to retrain each machine-learning classifier. We constructed the combined model using the top-performing radiomics signature and clinical model, and finally presented as a nomogram. We evaluated the combined model's performance using the area under the receiver operating characteristic, accuracy, calibration curves, and decision curve analysis. We used the Kaplan-Meier survival curve to analyze the prognosis of BCa patients.

RESULTS

The combined model incorporating radiomics signature and clinical model achieved an area under the receiver operating characteristic of 0.834 (95% CI: 0.659-1.000) for the external test set. The calibration curves and decision curve analysis demonstrated exceptional calibration and promising clinical use. The combined model showed good risk stratification performance for progression-free survival.

CONCLUSION

The proposed CT-based combined model is effective and reliable for predicting lymph node status of BCa patients preoperatively.

CRITICAL RELEVANCE STATEMENT

Bladder cancer is a type of urogenital cancer that has a high morbidity and mortality rate. Lymph node metastasis is an independent risk factor for death in bladder cancer patients. This study aimed to investigate the performance of a deep learning radiomics model for preoperatively predicting lymph node metastasis in bladder cancer patients.

KEY POINTS

• Conventional imaging is not sufficiently accurate to determine lymph node status. • Deep learning radiomics model accurately predicted bladder cancer lymph node metastasis. • The proposed method showed satisfactory patient risk stratification for progression-free survival.

Five machine learning-based radiomics models for preoperative prediction of histological grade in hepatocellular carcinoma

PURPOSE

To compare the efficacy of radiomics models via five machine learning algorithms in predicting the histological grade of hepatocellular carcinoma (HCC) before surgery and to develop the most stable model to classify high-risk HCC patients.

METHODS

Contrast-enhanced computed tomography (CECT) images of 175 HCC patients before surgery were analysed, and radiomics features were extracted from CECT images (including arterial and portal phases). Five machine learning models, including Bayes, random forest (RF), k-nearest neighbors (KNN), logistic regression (LR), and support vector machine (SVM), were applied to establish the model. The stability of the five models was weighed by the relative standard deviation (RSD), and the lowest RSD value was chosen as the most stable model to predict the histological grade of HCC. The area under the curve (AUC) and Delong tests were devoted to assessing the predictive efficacy of the models.

RESULTS

High-grade HCC accounted for 28.57% (50/175) of the 175 patients. The RSD value of AUC via the RF machine learning model was the lowest (2.3%), followed by Bayes (3.2%), KNN (6.4%), SVM (8.7%) and LR (31.3%). In addition, the RF model (AUC = 0.995) was better than the other four models in the training set (p < 0.05), as well as obtained good predictive performance in the test set (AUC = 0.837).

CONCLUSION

Among the five machine learning models, the RF-based radiomics model was the most stable and performed excellently in identifying high histological grade of HCC.

A deep learning MRI-based signature may provide risk-stratification strategies for nasopharyngeal carcinoma

OBJECTIVE

As the prognosis of nasopharyngeal carcinoma (NPC) is influenced by various factors, making it difficult for clinical physicians to predict the outcome, the objective of this study was to develop a deep learning-based signature for risk stratification in NPC patients.

METHODS

A total of 293 patients were enrolled in the study and divided into training, validation, and testing groups with a ratio of 7:1:2. MRI scans and corresponding clinical information were collected, and the 3-year disease-free survival (DFS) was chosen as the endpoint. The Res-Net18 algorithm was used to develop two deep learning (DL) models and another solely based on clinical characteristics developed by multivariate cox analysis. The performance of both models was evaluated using the area under the curve (AUC) and the concordance index (C-index). Discriminative performance was assessed using Kaplan-Meier survival analysis.

RESULTS

The deep learning approach identified DL prognostic models. The MRI-based DL model showed significantly better performance compared to the traditional model solely based on clinical characteristics (AUC: 0.8861 vs 0.745, p = 0.04 and C-index: 0.865 vs 0.727, p = 0.03). The survival analysis showed significant survival differences between the risk groups identified by the MRI-based model.

CONCLUSION

Our study highlights the potential of MRI in predicting the prognosis of NPC through DL algorithm. This approach has the potential to become a novel tool for prognosis prediction and can help physicians to develop more valid treatment strategies in the future.

Comparison of Dynamic Contrast-Enhanced MRI and Non-Mono-Exponential Model-Based Diffusion-Weighted Imaging for the Prediction of Prognostic Biomarkers and Molecular Subtypes of Breast Cancer Based on Radiomics

BACKGROUND

Dynamic contrast-enhanced (DCE) MRI and non-mono-exponential model-based diffusion-weighted imaging (NME-DWI) that does not require contrast agent can both characterize breast cancer. However, which technique is superior remains unclear.

PURPOSE

To compare the performances of DCE-MRI, NME-DWI and their combination as multiparametric MRI (MP-MRI) in the prediction of breast cancer prognostic biomarkers and molecular subtypes based on radiomics.

STUDY TYPE

Prospective.

POPULATION

A total of 477 female patients with 483 breast cancers (5-fold cross-validation: training/validation, 80%/20%).

FIELD STRENGTH/SEQUENCE

A 3.0 T/DCE-MRI (6 dynamic frames) and NME-DWI (13 b values).

ASSESSMENT

After data preprocessing, high-throughput features were extracted from each tumor volume of interest, and optimal features were selected using recursive feature elimination method. To identify ER+ vs. ER-, PR+ vs. PR-, HER2+ vs. HER2-, Ki-67+ vs. Ki-67-, luminal A/B vs. nonluminal A/B, and triple negative (TN) vs. non-TN, the following models were implemented: random forest, adaptive boosting, support vector machine, linear discriminant analysis, and logistic regression.

STATISTICAL TESTS

Student's t, chi-square, and Fisher's exact tests were applied on clinical characteristics to confirm whether significant differences exist between different statuses (±) of prognostic biomarkers or molecular subtypes. The model performances were compared between the DCE-MRI, NME-DWI, and MP-MRI datasets using the area under the receiver-operating characteristic curve (AUC) and the DeLong test. P < 0.05 was considered significant.

RESULTS

With few exceptions, no significant differences (P = 0.062-0.984) were observed in the AUCs of models for six classification tasks between the DCE-MRI (AUC = 0.62-0.87) and NME-DWI (AUC = 0.62-0.91) datasets, while the model performances on the two imaging datasets were significantly poorer than on the MP-MRI dataset (AUC = 0.68-0.93). Additionally, the random forest and adaptive boosting models (AUC = 0.62-0.93) outperformed other three models (AUC = 0.62-0.90).

DATA CONCLUSION

NME-DWI was comparable with DCE-MRI in predictive performance and could be used as an alternative technique. Besides, MP-MRI demonstrated significantly higher AUCs than either DCE-MRI or NME-DWI.

EVIDENCE LEVEL

2.

TECHNICAL EFFICACY

Stage 2.

Machine learning-aided metallomic profiling in serum and urine of thyroid cancer patients and its environmental implications

The incidence rate of thyroid cancer has been growing worldwide. Thyroid health is closely related with multiple trace metals, and the nutrients are essential in maintaining thyroid function while the contaminants can disturb thyroid morphology and homeostasis. In this study, we conducted metallomic analysis in thyroid cancer patients (n = 40) and control subjects (n = 40) recruited in Shenzhen, China with a high incidence of thyroid cancer. We found significant alterations in serumal and urinary metallomic profiling (including Cr, Mn, Fe, Co, Ni, Cu, Zn, As, Sr, Cd, I, Ba, Tl, and Pb) and elemental correlative patterns between thyroid cancer patients and controls. Additionally, we also measured the serum Cu isotopic composition and found a multifaceted disturbance in Cu metabolism in thyroid disease patients. Based on the metallome variations, we built and assessed the thyroid cancer-predictive performance of seven machine learning algorithms. Among them, the Random Forest model performed the best with the accuracy of 1.000, 0.858, and 0.813 on the training, 5-fold cross-validation, and test set, respectively. The high performance of machine learning has demonstrated the great promise of metallomic analysis in the identification of thyroid cancer. Then, the Shapley Additive exPlanations approach was used to further interpret the variable contributions of the model and it showed that serum Pb contributed the most in the identification process. To the best of our knowledge, this is the first study that combines machine learning and metallome data for cancer identification, and it supports the indication of environmental heavy metal-related thyroid cancer etiology.

Adjuvant chemotherapy or no adjuvant chemotherapy? A prediction model for the risk stratification of recurrence or metastasis of nasopharyngeal carcinoma combining MRI radiomics with clinical factors

BACKGROUND

Dose adjuvant chemotherapy (AC) should be offered in nasopharyngeal carcinoma (NPC) patients? Different guidelines provided the different recommendations.

METHODS

In this retrospective study, a total of 140 patients were enrolled and followed for 3 years, with 24 clinical features being collected. The imaging features on the enhanced-MRI sequence were extracted by using PyRadiomics platform. The pearson correlation coefficient and the random forest was used to filter the features associated with recurrence or metastasis. A clinical-radiomics model (CRM) was constructed by the Cox multivariable analysis in training cohort, and was validated in validation cohort. All patients were divided into high- and low-risk groups through the median Rad-score of the model. The Kaplan-Meier survival curves were used to compare the 3-year recurrence or metastasis free rate (RMFR) of patients with or without AC in high- and low-groups.

RESULTS

In total, 960 imaging features were extracted. A CRM was constructed from nine features (seven imaging features and two clinical factors). In the training cohort, the area under curve (AUC) of CRM for 3-year RMFR was 0.872 (P <0.001), and the sensitivity and specificity were 0.935 and 0.672, respectively; In the validation cohort, the AUC was 0.864 (P <0.001), and the sensitivity and specificity were 1.00 and 0.75, respectively. Kaplan-Meier curve showed that the 3-year RMFR and 3-year cancer specific survival (CSS) rate in the high-risk group were significantly lower than those in the low-risk group (P <0.001). In the high-risk group, patients who received AC had greater 3-year RMFR than those who did not receive AC (78.6% vs. 48.1%) (p = 0.03).

CONCLUSION

Considering increasing RMFR, a prediction model for NPC based on two clinical factors and seven imaging features suggested the AC needs to be added to patients in the high-risk group and not in the low-risk group.

Radiomics-based Machine Learning Methods for Volume Doubling Time Prediction of Pulmonary Ground-glass Nodules With Baseline Chest Computed Tomography

PURPOSE

Reliable prediction of volume doubling time (VDT) is essential for the personalized management of pulmonary ground-glass nodules (GGNs). We aimed to determine the optimal VDT prediction method by comparing different machine learning methods only based on the baseline chest computed tomography (CT) images.

MATERIALS AND METHODS

Seven classical machine learning methods were evaluated in terms of their stability and performance for VDT prediction. The VDT, calculated by the preoperative and baseline CT, was divided into 2 groups with a cutoff value of 400 days. A total of 90 GGNs from 3 hospitals constituted the training set, and 86 GGNs from the fourth hospital served as the external validation set. The training set was used for feature selection and model training, and the validation set was used to evaluate the predictive performance of the model independently.

RESULTS

The eXtreme Gradient Boosting showed the highest predictive performance (accuracy: 0.890±0.128 and area under the ROC curve (AUC): 0.896±0.134), followed by the neural network (NNet) (accuracy: 0.865±0.103 and AUC: 0.886±0.097). While regarding stability, the NNet showed the highest robustness against data perturbation (relative SDs [%] of mean AUC: 10.9%). Therefore, the NNet was chosen as the final model, achieving high accuracy of 0.756 in the external validation set.

CONCLUSION

The NNet is a promising machine learning method to predict the VDT of GGNs, which would assist in the personalized follow-up and treatment strategies for GGNs reducing unnecessary follow-up and radiation dose.

Combining ultrasound radiomics, complete blood count, and serum biochemical biomarkers for diagnosing intestinal disorders in cats using machine learning

This retrospective analytical observational cohort study aimed to model and predict the classification of feline intestinal diseases from segmentations of a transverse section from small intestine ultrasound (US) image, complete blood count (CBC), and serum biochemical profile data using a variety of machine-learning approaches. In 149 cats from three institutions, images were obtained from cats with biopsy-confirmed small cell epitheliotropic lymphoma (lymphoma), inflammatory bowel disease (IBD), no pathology ("healthy"), and other conditions (warrant a biopsy for further diagnosis). CBC, blood serum chemistry, small intestinal ultrasound, and small intestinal biopsy were obtained within a 2-week interval. CBC and serum biomarkers and radiomic features were combined for modeling. Four classification schemes were investigated: (1) normal versus abnormal; (2) warranting or not warranting a biopsy; (3) lymphoma, IBD, healthy, or other conditions; and (4) lymphoma, IBD, or other conditions. Two feature selection methods were used to identify the top 3, 5, 10, and 20 features, and six machine learning models were trained. The average (95% CI) performance of models for all combinations of features, numbers of features, and types of classifiers was 0.886 (0.871-0.912) for Model 1 (normal vs. abnormal), 0.751 (0.735-0.818) for Model 2 (biopsy vs. no biopsy), 0.504 (0.450-0.556) for Model 3 (lymphoma, IBD, healthy, or other), and 0.531 (0.426-0.589), for Model 4 (lymphoma, IBD, or other). Our findings suggest model accuracies above 0.85 can be achieved in Model 1 and 2, and that including CBC and biochemistry data with US radiomics data did not significantly improve accuracy in our models.

18F-FDG-PET Radiomics Based on White Matter Predicts The Progression of Mild Cognitive Impairment to Alzheimer Disease: A Machine Learning Study

RATIONALE AND OBJECTIVES

To build a model using white-matter radiomics features on positron-emission tomography (PET) and machine learning methods to predict progression from mild cognitive impairment (MCI) to Alzheimer disease (AD).

MATERIALS AND METHODS

We analyzed the data of 341 MCI patients from the Alzheimer's Disease Neuroimaging Initiative, of whom 102 progressed to AD during an 8-year follow-up. The patients were divided into the training (238 patients) and test groups (103 patients). PET-based radiomics features were extracted from the white matter in the training group, and dimensionally reduced to construct a psychoradiomics signature (PS), which was combined with multimodal data using machine learning methods to construct an integrated model. Model performance was evaluated using receiver operating characteristic curves in the test group.

RESULTS

Clinical Dementia Rating (CDR) scores, Alzheimer's Disease Assessment Scale (ADAS) scores, and PS independently predicted MCI progression to AD on multivariate logistic regression. The areas under the curve (AUCs) of the CDR, ADAS and PS in the training and test groups were 0.683, 0.755, 0.747 and 0.737, 0.743, 0.719 respectively, and were combined using a support vector machine to construct an integrated model. The AUC of the integrated model in the training and test groups was 0.868 and 0.865, respectively (sensitivity, 0.873 and 0.839, respectively; specificity, 0.784 and 0.806, respectively). The AUCs of the integrated model significantly differed from those of other predictors in both groups (p < 0.05, Delong test).

CONCLUSION

Our psych radiomics signature based on white-matter PET data predicted MCI progression to AD. The integrated model built using multimodal data and machine learning identified MCI patients at a high risk of progression to AD.

MRI-based radiomics model for distinguishing Stage I endometrial carcinoma from endometrial polyp: a multicenter study

BACKGROUND

Patients with early endometrial carcinoma (EC) have a good prognosis, but it is difficult to distinguish from endometrial polyps (EPs).

PURPOSE

To develop and assess magnetic resonance imaging (MRI)-based radiomics models for discriminating Stage I EC from EP in a multicenter setting.

MATERIAL AND METHODS

Patients with Stage I EC (n = 202) and EP (n = 99) who underwent preoperative MRI scans were collected in three centers (seven devices). The images from devices 1-3 were utilized for training and validation, and the images from devices 4-7 were utilized for testing, leading to three models. They were evaluated by the area under the receiver operating characteristic curve (AUC) and metrics including accuracy, sensitivity, and specificity. Two radiologists evaluated the endometrial lesions and compared them with the three models.

RESULTS

The AUCs of device 1, 2_ada, device 1, 3_ada, and device 2, 3_ada for discriminating Stage I EC from EP were 0.951, 0.912, and 0.896 for the training set, 0.755, 0.928, and 1.000 for the validation set, and 0.883, 0.956, and 0.878 for the external validation set, respectively. The specificity of the three models was higher, but the accuracy and sensitivity were lower than those of radiologists.

CONCLUSION

Our MRI-based models showed good potential in differentiating Stage I EC from EP and had been validated in multiple centers. Their specificity was higher than that of radiologists and may be used for computer-aided diagnosis in the future to assist clinical diagnosis.

Emerging role of quantitative imaging (radiomics) and artificial intelligence in precision oncology

Cancer is a fatal disease and the second most cause of death worldwide. Treatment of cancer is a complex process and requires a multi-modality-based approach. Cancer detection and treatment starts with screening/diagnosis and continues till the patient is alive. Screening/diagnosis of the disease is the beginning of cancer management and continued with the staging of the disease, planning and delivery of treatment, treatment monitoring, and ongoing monitoring and follow-up. Imaging plays an important role in all stages of cancer management. Conventional oncology practice considers that all patients are similar in a disease type, whereas biomarkers subgroup the patients in a disease type which leads to the development of precision oncology. The utilization of the radiomic process has facilitated the advancement of diverse imaging biomarkers that find application in precision oncology. The role of imaging biomarkers and artificial intelligence (AI) in oncology has been investigated by many researchers in the past. The existing literature is suggestive of the increasing role of imaging biomarkers and AI in oncology. However, the stability of radiomic features has also been questioned. The radiomic community has recognized that the instability of radiomic features poses a danger to the global generalization of radiomic-based prediction models. In order to establish radiomic-based imaging biomarkers in oncology, the robustness of radiomic features needs to be established on a priority basis. This is because radiomic models developed in one institution frequently perform poorly in other institutions, most likely due to radiomic feature instability. To generalize radiomic-based prediction models in oncology, a number of initiatives, including Quantitative Imaging Network (QIN), Quantitative Imaging Biomarkers Alliance (QIBA), and Image Biomarker Standardisation Initiative (IBSI), have been launched to stabilize the radiomic features.

A preliminary attempt to use radiomic features in the diagnosis of extra-articular long head biceps tendinitis

BACKGROUND

This study aims to present a radiomic application in diagnosing the long head of biceps (LHB) tendinitis. Moreover, we evaluated whether machine learning-derived radiomic features recognize LHB tendinitis.

PATIENTS AND METHODS

A total of 170 patients were reviewed. All LHB tendinitis patients were diagnosed under arthroscopy. Radiomic features were extracted from preoperative magnetic resonance imaging (MRI), and the input dataset was divided into a training set and a test set. For feature selection, the t test and least absolute shrinkage and selection operator (LASSO) methods were used, and random forest (RF) and support vector machine (SVM) were used as machine learning classifiers. The sensitivity, specificity, accuracy, and area under the curve (AUC) of each model's receiver operating characteristic (ROC) curves were calculated to evaluate model performance.

RESULTS

In total, 851 radiomic features were extracted, with 109 radiomic features extracted using a t test and 20 radiomic features extracted using the LASSO method. The random forest classifier shows the highest sensitivity, specificity, accuracy, and AUC (0.52, 0.92, 0.73, and 0.72).

CONCLUSION

The classifier contract by 20 radiomic features demonstrated a good ability to predict extra-articular LHB tendinitis.However because of poor segmentation reliability, the value of Radiomic in LHB tendinitis still needs to be further explored.

A machine learning approach for prediction of auditory brain stem response in patients after head-and-neck radiation therapy

Objective

The present study aimed to assess machine learning (ML) models according to radiomic features to predict ototoxicity using auditory brain stem responses (ABRs) in patients with radiation therapy (RT) for head-and-neck cancers.

Materials and Methods

The ABR test was performed on 50 patients having head-and-neck RT. Radiomic features were extracted from the brain stem in computed tomography images to generate a radiomic signature. Moreover, accuracy, sensitivity, specificity, the area under the curve, and mean cross-validation were used to evaluate six different ML models.

Results

Out of 50 patients, 21 participants experienced ototoxicity. Furthermore, 140 radiomic features were extracted from the segmented area. Among the six ML models, the Random Forest method with 77% accuracy provided the best result.

Conclusion

According to the ML approach, we showed the relatively high prediction power of the radiomic features in radiation-induced ototoxicity. To better predict the outcomes, future studies on a larger number of participants are recommended.

Blood Inflammatory Biomarkers Differentiate Inpatient and Outpatient Coronavirus Disease 2019 From Influenza

Background

The ongoing circulation of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) poses a diagnostic challenge because symptoms of coronavirus disease 2019 (COVID-19) are difficult to distinguish from other respiratory diseases. Our goal was to use statistical analyses and machine learning to identify biomarkers that distinguish patients with COVID-19 from patients with influenza.

Methods

Cytokine levels were analyzed in plasma and serum samples from patients with influenza and COVID-19, which were collected as part of the Centers for Disease Control and Prevention's Hospitalized Adult Influenza Vaccine Effectiveness Network (inpatient network) and the US Flu Vaccine Effectiveness (outpatient network).

Results

We determined that interleukin (IL)-10 family cytokines are significantly different between COVID-19 and influenza patients. The results suggest that the IL-10 family cytokines are a potential diagnostic biomarker to distinguish COVID-19 and influenza infection, especially for inpatients. We also demonstrate that cytokine combinations, consisting of up to 3 cytokines, can distinguish SARS-CoV-2 and influenza infection with high accuracy in both inpatient (area under the receiver operating characteristics curve [AUC] = 0.84) and outpatient (AUC = 0.81) groups, revealing another potential screening tool for SARS-CoV-2 infection.

Conclusions

This study not only reveals prospective screening tools for COVID-19 infections that are independent of polymerase chain reaction testing or clinical condition, but it also emphasizes potential pathways involved in disease pathogenesis that act as potential targets for future mechanistic studies.

Machine Learning Analysis of Postkeratoplasty Endothelial Cell Images for the Prediction of Future Graft Rejection

Purpose

This study developed machine learning (ML) classifiers of postoperative corneal endothelial cell images to identify postkeratoplasty patients at risk for allograft rejection within 1 to 24 months of treatment.

Methods

Central corneal endothelium specular microscopic images were obtained from 44 patients after Descemet membrane endothelial keratoplasty (DMEK), half of whom had experienced graft rejection. After deep learning segmentation of images from all patients' last and second-to-last imaging, time points prior to rejection were analyzed (175 and 168, respectively), and 432 quantitative features were extracted assessing cellular spatial arrangements and cell intensity values. Random forest (RF) and logistic regression (LR) models were trained on novel-to-this-application features from single time points, delta-radiomics, and traditional morphometrics (endothelial cell density, coefficient of variation, hexagonality) via 10 iterations of threefold cross-validation. Final assessments were evaluated on a held-out test set.

Results

ML classifiers trained on novel-to-this-application features outperformed those trained on traditional morphometrics for predicting future graft rejection. RF and LR models predicted post-DMEK patients' allograft rejection in the held-out test set with >0.80 accuracy. RF models trained on novel features from second-to-last time points and delta-radiomics predicted post-DMEK patients' rejection with >0.70 accuracy. Cell-graph spatial arrangement, intensity, and shape features were most indicative of graft rejection.

Conclusions

ML classifiers successfully predicted future graft rejections 1 to 24 months prior to clinically apparent rejection. This technology could aid clinicians to identify patients at risk for graft rejection and guide treatment plans accordingly.

Translational Relevance

Our software applies ML techniques to clinical images and enhances patient care by detecting preclinical keratoplasty rejection.

Use of Longitudinal Serum Analysis and Machine Learning to Develop a Classifier for Cancer Early Detection

Early detection of solid tumors through a simple screening process, such as the proteomic analysis of biofluids, has the potential to significantly alter the management and outcomes of cancers. The application of advanced targeted proteomics measurements and data analysis strategies to uniformly collected serum or plasma samples would enable longitudinal studies of cancer risk, progression, and response to therapy that have the potential to significantly reduce cancer burden in general. In this article, we describe a generalizable workflow combining robust, multiplexed targeted proteomics measurements applied to longitudinal samples from the Department of Defense Serum Repository with a Random Forest machine learning method for developing and initially evaluating the performance of candidate biomarker panels for early detection of cancers. The effectiveness of this approach was demonstrated in a cohort of 175 head and neck squamous cell carcinoma patients. The outlined protocols include methods for sample preparation, instrument analysis, and data analysis and interpretation using this workflow.

Predicting prognosis of nasopharyngeal carcinoma based on deep learning: peritumoral region should be valued

BACKGROUND

The purpose of this study was to explore whether incorporating the peritumoral region to train deep neural networks could improve the performance of the models for predicting the prognosis of NPC.

METHODS

A total of 381 NPC patients who were divided into high- and low-risk groups according to progression-free survival were retrospectively included. Deeplab v3 and U-Net were trained to build segmentation models for the automatic segmentation of the tumor and suspicious lymph nodes. Five datasets were constructed by expanding 5, 10, 20, 40, and 60 pixels outward from the edge of the automatically segmented region. Inception-Resnet-V2, ECA-ResNet50t, EfficientNet-B3, and EfficientNet-B0 were trained with the original, segmented, and the five new constructed datasets to establish the classification models. The receiver operating characteristic curve was used to evaluate the performance of each model.

RESULTS

The Dice coefficients of Deeplab v3 and U-Net were 0.741(95%CI:0.722-0.760) and 0.737(95%CI:0.720-0.754), respectively. The average areas under the curve (aAUCs) of deep learning models for classification trained with the original and segmented images and with images expanded by 5, 10, 20, 40, and 60 pixels were 0.717 ± 0.043, 0.739 ± 0.016, 0.760 ± 0.010, 0.768 ± 0.018, 0.802 ± 0.013, 0.782 ± 0.039, and 0.753 ± 0.014, respectively. The models trained with the images expanded by 20 pixels obtained the best performance.

CONCLUSIONS

The peritumoral region NPC contains information related to prognosis, and the incorporation of this region could improve the performance of deep learning models for prognosis prediction.

Development and validation of a clinical-radiomics model to predict recurrence for patients with hepatocellular carcinoma after curative resection

PURPOSE

Recurrence is the leading cause of death in hepatocellular carcinoma (HCC) patients with curative resection. In this study, we aimed to develop a preoperative predictive model based on high-throughput radiomics features and clinical factors for prediction of long- and short-term recurrence for these patients.

METHODS

A total of 270 patients with HCC who were followed up for at least 5 years after curative hepatectomy between June 2014 and December 2017 were enrolled in this retrospective study. Regions of interest were manually delineated in preoperative T2-weighted images using ITK-SNAP software on each HCC tumor slice. A total of 1197 radiomics features were extracted, and the recursive feature elimination method based on logistic regression was used for radiomics signature building. Tenfold cross-validation was applied for model development. Nomograms were constructed and assessed by calibration plot, which compares nomogram-predicated probability with observed outcome. Receiver-operating characteristic was then generated to evaluate the predictive performance of the model in the development and test cohorts.

RESULTS

The 10 most recurrence-free survival-related radiomics features were selected for the radiomics signatures. A multiparametric clinical-radiomics model combining albumin and radiomics score for recurrence prediction was further established. The integrated model demonstrated good calibration and satisfactory discrimination, with the area under the curve (AUC) of 0.864, 95% CI 0.842-0.903, sensitivity of 0.889, and specificity of 0.644 in the test set. Calibration curve showed good agreement concerning 5-year recurrence risk predicted by the nomogram. In addition, the AUC of 1-, 2-, 3-, and 4-year recurrence was 0.935 (95% CI 0.836-1.000), 0.861 (95% CI 0.723-0.999), 0.878 (95% CI 0.762-0.994), and 0.878 (95% CI 0.762-0.994) in the test set, respectively.

CONCLUSIONS

The clinical-radiomics model integrating radiomics features and clinical factors can improve recurrence predictions beyond predictions made using clinical factors or radiomics features alone. Our clinical-radiomics model is a valid method to predict recurrence that should improve preoperative prognostic performance and allow more individualized treatment decisions.

Integrative Scoring System for Survival Prediction in Patients With Locally Advanced Nasopharyngeal Carcinoma: A Retrospective Multicenter Study

PURPOSE

Tumor stage is crucial for prognostic evaluation and therapeutic decisions in locally advanced nasopharyngeal carcinoma (NPC) but is imprecise. We aimed to propose a new prognostic system by integrating quantitative imaging features and clinical factors.

MATERIALS AND METHODS

This retrospective study included 1,319 patients with stage III-IVa NPC between April 1, 2010, and July 31, 2019, who underwent pretherapy magnetic resonance imaging (MRI) and received concurrent chemoradiotherapy with or without induction chemotherapy. The hand-crafted and deep-learned features were extracted from MRI for each patient. After feature selection, the clinical score, radiomic score, deep score, and integrative scores were constructed via Cox regression analysis. The scores were validated in two external cohorts. The predictive accuracy and discrimination were measured by the area under the curve (AUC) and risk group stratification. The end points were progression-free survival (PFS), overall survival (OS), and distant metastasis-free survival (DMFS).

RESULTS

Both radiomics and deep learning were complementary to clinical variables (age, T stage, and N stage; all P < .05). The clinical-deep score was superior or equivalent to clinical-radiomic score, whereas it was noninferior to clinical-radiomic-deep score (all P > .05). These findings were also verified in the evaluation of OS and DMFS. The clinical-deep score yielded an AUC of 0.713 (95% CI, 0.697 to 0.729) and 0.712 (95% CI, 0.693 to 0.731) in the two external validation cohorts for predicting PFS with good calibration. This scoring system could stratify patients into high- and low-risk groups with distinct survivals (all P < .05).

CONCLUSION

We established and validated a prognostic system integrating clinical data and deep learning to provide an individual prediction of survival for patients with locally advanced NPC, which might inform clinicians in treatment decision making.

A CT-based radiomics approach to predict immediate response of radiofrequency ablation in colorectal cancer lung metastases

Objectives

To objectively and accurately assess the immediate efficacy of radiofrequency ablation (RFA) on colorectal cancer (CRC) lung metastases, the novel multimodal data fusion model based on radiomics features and clinical variables was developed.

Methods

This case-control single-center retrospective study included 479 lung metastases treated with RFA in 198 CRC patients. Clinical and radiological data before and intraoperative computed tomography (CT) scans were retrieved. The relative radiomics features were extracted from pre- and immediate post-RFA CT scans by maximum relevance and minimum redundancy algorithm (MRMRA). The Gaussian mixture model (GMM) was used to divide the data of the training dataset and testing dataset. In the process of modeling in the training set, radiomics model, clinical model and fusion model were built based on a random forest classifier. Finally, verification was carried out on an independent test dataset. The receiver operating characteristic curves (ROC) were drawn based on the obtained predicted scores, and the corresponding area under ROC curve (AUC), accuracy, sensitivity, and specificity were calculated and compared.

Results

Among the 479 pulmonary metastases, 379 had complete response (CR) ablation and 100 had incomplete response ablation. Three hundred eighty-six lesions were selected to construct a training dataset and 93 lesions to construct a testing dataset. The multivariate logistic regression analysis revealed cancer antigen 19-9 (CA19-9, p<0.001) and the location of the metastases (p< 0.05) as independent risk factors. Significant correlations were observed between complete ablation and 9 radiomics features. The best prediction performance was achieved with the proposed multimodal data fusion model integrating radiomic features and clinical variables with the highest accuracy (82.6%), AUC value (0.921), sensitivity (80.3%), and specificity (81.4%).

Conclusion

This novel multimodal data fusion model was demonstrated efficient for immediate efficacy evaluation after RFA for CRC lung metastases, which could benefit necessary complementary treatment.

The Effect of Magnetic Resonance Imaging Based Radiomics Models in Discriminating stage I-II and III-IVa Nasopharyngeal Carcinoma

BACKGROUND

Nasopharyngeal carcinoma (NPC) is a common tumor in China. Accurate stages of NPC are crucial for treatment. We therefore aim to develop radiomics models for discriminating early-stage (I-II) and advanced-stage (III-IVa) NPC based on MR images.

METHODS

329 NPC patients were enrolled and randomly divided into a training cohort (n = 229) and a validation cohort (n = 100). Features were extracted based on axial contrast-enhanced T1-weighted images (CE-T1WI), T1WI, and T2-weighted images (T2WI). Least absolute shrinkage and selection operator (LASSO) was used to build radiomics signatures. Seven radiomics models were constructed with logistic regression. The AUC value was used to assess classification performance. The DeLong test was used to compare the AUCs of different radiomics models and visual assessment.

RESULTS

Models A, B, C, D, E, F, and G were constructed with 13, 9, 7, 9, 10, 7, and 6 features, respectively. All radiomics models showed better classification performance than that of visual assessment. Model A (CE-T1WI + T1WI + T2WI) showed the best classification performance (AUC: 0.847) in the training cohort. CE-T1WI showed the greatest significance for staging NPC.

CONCLUSION

Radiomics models can effectively distinguish early-stage from advanced-stage NPC patients, and Model A (CE-T1WI + T1WI + T2WI) showed the best classification performance.

Radiation-Free Microwave Technology for Breast Lesion Detection Using Supervised Machine Learning Model

Mammography is the gold standard technology for breast screening, which has been demonstrated through different randomized controlled trials to reduce breast cancer mortality. However, mammography has limitations and potential harms, such as the use of ionizing radiation. To overcome the ionizing radiation exposure issues, a novel device (i.e. MammoWave) based on low-power radio-frequency signals has been developed for breast lesion detection. The MammoWave is a microwave device and is under clinical validation phase in several hospitals across Europe. The device transmits non-invasive microwave signals through the breast and accumulates the backscattered (returned) signatures, commonly denoted as the S21 signals in engineering terminology. Backscattered (complex) S21 signals exploit the contrast in dielectric properties of breasts with and without lesions. The proposed research is aimed to automatically segregate these two types of signal responses by applying appropriate supervised machine learning (ML) algorithm for the data emerging from this research. The support vector machine with radial basis function has been employed here. The proposed algorithm has been trained and tested using microwave breast response data collected at one of the clinical validation centres. Statistical evaluation indicates that the proposed ML model can recognise the MammoWave breasts signal with no radiological finding (NF) and with radiological findings (WF), i.e., may be the presence of benign or malignant lesions. A sensitivity of 84.40% and a specificity of 95.50% have been achieved in NF/WF recognition using the proposed ML model.

Levels of Autonomous Radiology

Radiology, being one of the younger disciplines of medicine with a history of just over a century, has witnessed tremendous technological advancements and has revolutionized the way we practice medicine today. In the last few decades, medical imaging modalities have generated seismic amounts of medical data. The development and adoption of artificial intelligence applications using this data will lead to the next phase of evolution in radiology. It will include automating laborious manual tasks such as annotations, report generation, etc, along with the initial radiological assessment of patients and imaging features to aid radiologists in their diagnostic and treatment planning workflow. We propose a level-wise classification for the progression of automation in radiology, explaining artificial intelligence assistance at each level with the corresponding challenges and solutions. We hope that such discussions can help us address challenges in a structured way and take the necessary steps to ensure the smooth adoption of new technologies in radiology.

Identification of biomarkers in nonalcoholic fatty liver disease: A machine learning method and experimental study

Nonalcoholic fatty liver disease (NAFLD) has become the most common chronic liver disease. However, the early diagnosis of NAFLD is challenging. Thus, the purpose of this study was to identify diagnostic biomarkers of NAFLD using machine learning algorithms. Differentially expressed genes between NAFLD and normal samples were identified separately from the GEO database. The key DEGs were selected through a protein‒protein interaction network, and their biological functions were analysed. Next, three machine learning algorithms were selected to construct models of NAFLD separately, and the model with the smallest sample residual was determined to be the best model. Then, logistic regression analysis was used to judge the accuracy of the five genes in predicting the risk of NAFLD. A single-sample gene set enrichment analysis algorithm was used to evaluate the immune cell infiltration of NAFLD, and the correlation between diagnostic biomarkers and immune cell infiltration was analysed. Finally, 10 pairs of peripheral blood samples from NAFLD patients and normal controls were collected for RNA isolation and quantitative real-time polymerase chain reaction for validation. Taken together, CEBPD, H4C11, CEBPB, GATA3, and KLF4 were identified as diagnostic biomarkers of NAFLD by machine learning algorithms and were related to immune cell infiltration in NAFLD. These key genes provide novel insights into the mechanisms and treatment of patients with NAFLD.

Prognostic value of PET/CT and MR-based baseline radiomics among patients with non-metastatic nasopharyngeal carcinoma

PURPOSE

Radiomics is an emerging imaging assessment technique that has shown promise in predicting survival among nasopharyngeal carcinoma (NPC) patients. Studies so far have focused on PET or MR-based radiomics independently. The aim of our study was to evaluate the prognostic value of clinical and radiomic parameters derived from both PET/CT and MR.

METHODS

Retrospective evaluation of 124 NPC patients with PET/CT and radiotherapy planning MR (RP-MR). Primary tumors were segmented using dedicated software (LIFEx version 6.1) from PET, CT, contrast-enhanced T1-weighted (T1-w), and T2-weighted (T2-w) MR sequences with 376 radiomic features extracted. Summary statistics describe patient, disease, and treatment characteristics. The Kaplan-Meier (KM) method estimates overall survival (OS) and progression-free survival (PFS). Clinical factors selected based on univariable analysis and the multivariable Cox model were subsequently constructed with radiomic features added.

RESULTS

The final models comparing clinical, clinical + RP-MR, clinical + PET/CT and clinical + RP-MR + PET/CT for OS and PFS demonstrated that combined radiomic signatures were significantly associated with improved survival prognostication (AUC 0.62 vs 0.81 vs 0.75 vs 0.86 at 21 months for PFS and 0.56 vs 0.85 vs 0.79 vs 0.96 at 24 months for OS). Clinical + RP-MR features initially outperform clinical + PET/CT for both OS and PFS (<18 months), and later in the clinical course for PFS (>42 months).

CONCLUSION

Our study demonstrated that PET/CT-based radiomic features may improve survival prognostication among NPC patients when combined with baseline clinical and MR-based radiomic features.

Deep Convolutional Neural Network for Nasopharyngeal Carcinoma Discrimination on MRI by Comparison of Hierarchical and Simple Layered Convolutional Neural Networks

Nasopharyngeal carcinoma (NPC) is one of the most common head and neck cancers. Early diagnosis plays a critical role in the treatment of NPC. To aid diagnosis, deep learning methods can provide interpretable clues for identifying NPC from magnetic resonance images (MRI). To identify the optimal models, we compared the discrimination performance of hierarchical and simple layered convolutional neural networks (CNN). Retrospectively, we collected the MRI images of patients and manually built the tailored NPC image dataset. We examined the performance of the representative CNN models including shallow CNN, ResNet50, ResNet101, and EfficientNet-B7. By fine-tuning, shallow CNN, ResNet50, ResNet101, and EfficientNet-B7 achieved the precision of 72.2%, 94.4%, 92.6%, and 88.4%, displaying the superiority of deep hierarchical neural networks. Among the examined models, ResNet50 with pre-trained weights demonstrated the best classification performance over other types of CNN with accuracy, precision, and an F1-score of 0.93, 0.94, and 0.93, respectively. The fine-tuned ResNet50 achieved the highest prediction performance and can be used as a potential tool for aiding the diagnosis of NPC tumors.

Silveira S, Brommonschenkel SH, Fontes EPB. RLPredictiOme, a Machine Learning-Derived Method for High-Throughput Prediction of Plant Receptor-like Proteins, Reveals Novel Classes of Transmembrane Receptors

Cell surface receptors play essential roles in perceiving and processing external and internal signals at the cell surface of plants and animals. The receptor-like protein kinases (RLK) and receptor-like proteins (RLPs), two major classes of proteins with membrane receptor configuration, play a crucial role in plant development and disease defense. Although RLPs and RLKs share a similar single-pass transmembrane configuration, RLPs harbor short divergent C-terminal regions instead of the conserved kinase domain of RLKs. This RLP receptor structural design precludes sequence comparison algorithms from being used for high-throughput predictions of the RLP family in plant genomes, as has been extensively performed for RLK superfamily predictions. Here, we developed the RLPredictiOme, implemented with machine learning models in combination with Bayesian inference, capable of predicting RLP subfamilies in plant genomes. The ML models were simultaneously trained using six types of features, along with three stages to distinguish RLPs from non-RLPs (NRLPs), RLPs from RLKs, and classify new subfamilies of RLPs in plants. The ML models achieved high accuracy, precision, sensitivity, and specificity for predicting RLPs with relatively high probability ranging from 0.79 to 0.99. The prediction of the method was assessed with three datasets, two of which contained leucine-rich repeats (LRR)-RLPs from Arabidopsis and rice, and the last one consisted of the complete set of previously described Arabidopsis RLPs. In these validation tests, more than 90% of known RLPs were correctly predicted via RLPredictiOme. In addition to predicting previously characterized RLPs, RLPredictiOme uncovered new RLP subfamilies in the Arabidopsis genome. These include probable lipid transfer (PLT)-RLP, plastocyanin-like-RLP, ring finger-RLP, glycosyl-hydrolase-RLP, and glycerophosphoryldiester phosphodiesterase (GDPD, GDPDL)-RLP subfamilies, yet to be characterized. Compared to the only Arabidopsis GDPDL-RLK, molecular evolution studies confirmed that the ectodomain of GDPDL-RLPs might have undergone a purifying selection with a predominance of synonymous substitutions. Expression analyses revealed that predicted GDPGL-RLPs display a basal expression level and respond to developmental and biotic signals. The results of these biological assays indicate that these subfamily members have maintained functional domains during evolution and may play relevant roles in development and plant defense. Therefore, RLPredictiOme provides a framework for genome-wide surveys of the RLP superfamily as a foundation to rationalize functional studies of surface receptors and their relationships with different biological processes.

MRI radiomics-based machine learning model integrated with clinic-radiological features for preoperative differentiation of sinonasal inverted papilloma and malignant sinonasal tumors

Objective

To explore the best MRI radiomics-based machine learning model for differentiation of sinonasal inverted papilloma (SNIP) and malignant sinonasal tumor (MST), and investigate whether the combination of radiomics features and clinic–radiological features can produce a superior diagnostic performance.

Methods

The database of 247 patients with SNIP (n=106) or MST (n=141) were analyzed. Dataset from scanner A were randomly divided into training set (n=135) and test set 1 (n=58) in a ratio of 7:3, and dataset from scanner B and C were used as an additional independent test set 2 (n=54). Fourteen clinic-radiological features were analyzed by using univariate analysis, and those with significant differences were applied to construct clinical model. Based on the radiomics features extracted from single sequence (T2WI or CE-T1WI) and combined sequence, four commonly used classifiers (logistic regression (LR), support vector machine (SVM), decision tree (DT) and k-nearest neighbor (KNN)) were employed to constitute twelve different machine learning models, and the best-performing one was confirmed as the optimal radiomics model. Furthermore, a combined model incorporated best radiomics feature subsets and clinic-radiological features was developed. The diagnostic performances of these models were assessed by the area under the receiver operating characteristic (ROC) curve (AUC) and the calibration curves.

Results

Five clinic-radiological features (age, convoluted cerebriform pattern sign, heterogeneity, adjacent bone involvement and infiltration of surrounding tissue) were considered to be significantly different between the tumor groups (P < 0.05). Among the twelve machine learning models, the T2WI-SVM model exhibited optimal predictive efficacy for classification tasks on the two test sets, with the AUC of 0.878 and 0.914, respectively. For three types of diagnostic models, the combined model achieved highest AUC of 0.912 (95%CI: 0.807-0.970) and 0.927 (95%CI: 0.823-0.980) for differentiation of SNIP and MST in test 1 and test 2 sets, which performed prominently better than clinical model (P=0.011, 0.005), but not significantly different from the optimal radiomics model (P=0.100, 0.452).

Conclusion

The machine learning model based on T2WI sequence and SVM classifier achieved best performance in differentiation of SNIP and MST, and the combination of radiomics features and clinic-radiological features significantly improved the diagnostic capability of the model.

Invasive ductal breast cancer molecular subtype prediction by MRI radiomic and clinical features based on machine learning

Background

Most studies of molecular subtype prediction in breast cancer were mainly based on two-dimensional MRI images, the predictive value of three-dimensional volumetric features from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for predicting breast cancer molecular subtypes has not been thoroughly investigated. This study aimed to look into the role of features derived from DCE-MRI and how they could be combined with clinical data to predict invasive ductal breast cancer molecular subtypes.

Methods

From January 2019 to December 2021, 190 Chinese women with invasive ductal breast cancer were studied (32 triple-negative, 59 HER2-enriched, and 99 luminal lesions) in this institutional review board-approved retrospective cohort study. The image processing software extracted 1130 quantitative radiomic features from the segmented lesion area, including shape-based, first-order statistical, texture, and wavelet features. Three binary classifications of the subtypes were performed: triple-negative vs. non-triple-negative, HER2-overexpressed vs. non-HER2-overexpressed, and luminal (A + B) vs. non-luminal. For the classification, five machine learning methods (random forest, logistic regression, support vector machine, naïve Bayes, and eXtreme Gradient Boosting) were employed. The classifiers were chosen using the least absolute shrinkage and selection operator method. The area evaluated classification performance under the receiver operating characteristic curve, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean.

Results

EXtreme Gradient Boosting model showed the best performance in luminal and non-luminal groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.8282, 0.7524, 0.6542, 0.6964, 0.6086, 0.3458, 0.8524 and 0.7016, respectively. Meanwhile, the random forest model showed the best performance in HER2-overexpressed and non-HER2-overexpressed groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.8054, 0.2941, 0.9744, 0.7679, 0.4348, 0.0256, 0.8333 and 0.5353, respectively. Furthermore, eXtreme Gradient Boosting model showed the best performance in the triple-negative and non-triple-negative groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.9031, 0.9362, 0.4444, 0.8571, 0.9167, 0.5556, 0.8980 and 0.6450.

Conclusion

Clinical data and three-dimension imaging features from DCE-MRI were identified as potential biomarkers for distinguishing between three molecular subtypes of invasive ductal carcinomas breast cancer. In the future, more extensive studies will be required to evaluate the findings.

AI-assisted biparametric MRI surveillance of prostate cancer: feasibility study

OBJECTIVES

To evaluate the feasibility of automatic longitudinal analysis of consecutive biparametric MRI (bpMRI) scans to detect clinically significant (cs) prostate cancer (PCa).

METHODS

This retrospective study included a multi-center dataset of 1513 patients who underwent bpMRI (T2 + DWI) between 2014 and 2020, of whom 73 patients underwent at least two consecutive bpMRI scans and repeat biopsies. A deep learning PCa detection model was developed to produce a heatmap of all PIRADS ≥ 2 lesions across prior and current studies. The heatmaps for each patient's prior and current examination were used to extract differential volumetric and likelihood features reflecting explainable changes between examinations. A machine learning classifier was trained to predict from these features csPCa (ISUP > 1) at the current examination according to biopsy. A classifier trained on the current study only was developed for comparison. An extended classifier was developed to incorporate clinical parameters (PSA, PSA density, and age). The cross-validated diagnostic accuracies were compared using ROC analysis. The diagnostic performance of the best model was compared to the radiologist scores.

RESULTS

The model including prior and current study (AUC 0.81, CI: 0.69, 0.91) resulted in a higher (p = 0.04) diagnostic accuracy than the current only model (AUC 0.73, CI: 0.61, 0.84). Adding clinical variables further improved diagnostic performance (AUC 0.86, CI: 0.77, 0.93). The diagnostic performance of the surveillance AI model was significantly better (p = 0.02) than of radiologists (AUC 0.69, CI: 0.54, 0.81).

CONCLUSIONS

Our proposed AI-assisted surveillance of prostate MRI can pick up explainable, diagnostically relevant changes with promising diagnostic accuracy.

KEY POINTS

• Sequential prostate MRI scans can be automatically evaluated using a hybrid deep learning and machine learning approach. • The diagnostic accuracy of our csPCa detection AI model improved by including clinical parameters.

Prediction of 5-year progression-free survival in advanced nasopharyngeal carcinoma with pretreatment PET/CT using multi-modality deep learning-based radiomics

Objective

Deep learning-based radiomics (DLR) has achieved great success in medical image analysis and has been considered a replacement for conventional radiomics that relies on handcrafted features. In this study, we aimed to explore the capability of DLR for the prediction of 5-year progression-free survival (PFS) in advanced nasopharyngeal carcinoma (NPC) using pretreatment PET/CT images.

Methods

A total of 257 patients (170/87 patients in internal/external cohorts) with advanced NPC (TNM stage III or IVa) were enrolled. We developed an end-to-end multi-modality DLR model, in which a 3D convolutional neural network was optimized to extract deep features from pretreatment PET/CT images and predict the probability of 5-year PFS. The TNM stage, as a high-level clinical feature, could be integrated into our DLR model to further improve the prognostic performance. For a comparison between conventional radiomics and DLR, 1,456 handcrafted features were extracted, and optimal conventional radiomics methods were selected from 54 cross-combinations of six feature selection methods and nine classification methods. In addition, risk group stratification was performed with clinical signature, conventional radiomics signature, and DLR signature.

Results

Our multi-modality DLR model using both PET and CT achieved higher prognostic performance (area under the receiver operating characteristic curve (AUC) = 0.842 ± 0.034 and 0.823 ± 0.012 for the internal and external cohorts) than the optimal conventional radiomics method (AUC = 0.796 ± 0.033 and 0.782 ± 0.012). Furthermore, the multi-modality DLR model outperformed single-modality DLR models using only PET (AUC = 0.818 ± 0.029 and 0.796 ± 0.009) or only CT (AUC = 0.657 ± 0.055 and 0.645 ± 0.021). For risk group stratification, the conventional radiomics signature and DLR signature enabled significant difference between the high- and low-risk patient groups in both the internal and external cohorts (p < 0.001), while the clinical signature failed in the external cohort (p = 0.177).

Conclusion

Our study identified potential prognostic tools for survival prediction in advanced NPC, which suggests that DLR could provide complementary values to the current TNM staging.

miR-212-5p inhibits nasopharyngeal carcinoma progression by targeting METTL3

This study was conducted to investigate the effect of microRNA-212-5p (miR-212-5p) on the proliferation and apoptosis of nasopharyngeal carcinoma (NPC) cells. Microarray datasets (EXP00394 and EXP00660) were downloaded from the dbDEMC database, and the differentially expressed microRNAs between high-grade and low-grade NPC were analyzed. miR-212-5p and methyltransferase like 3 (METTL3) expression levels in NPC tissues and cells were determined by the quantitative real-time polymerase chain reaction and Western blot. Besides, the relationship between miR-212-5p expression and clinicopathological characteristics of patients was analyzed by the Chi-square test. Cell counting kit-8 assay, 5-ethynyl-2-deoxyuridine (EdU) assay, and flow cytometry were adopted to detect the effect of miR-212-5p on the cell proliferation and apoptosis. Kyoto Encyclopedia of Genes and Genomes and Gene Ontology analysis were performed to explore the potential biological functions and the signal pathways related to the target genes of miR-212-5p. Bioinformatics prediction and dual luciferase reporter gene assay were used to verify the relationship between miR-212-5p and METTL3 3' untranslated region. Besides, western blot was adopted to detect the expression of METTL3. Gene set enrichment analysis was performed to analyze the downstream pathways in which METTL3 was enriched. It was found that miR-212-5p was downregulated in NPC tissues, and the low miR-212-5p expression was associated with lymph node metastasis and poor differentiation. miR-212-5p overexpression inhibited the growth and promoted apoptosis of NPC cells; miR-212-5p inhibition functioned oppositely. Mechanistically, miR-212-5p inhibited the proliferation and promoted apoptosis of NPC cells via suppressing METTL3 expression. miR-212-5p/METTL3 was associated with processes of RNA transport and cell cycle. In conclusion, miR-212-5p inhibits the progression of NPC by targeting METTL3.

MRI-based random survival Forest model improves prediction of progression-free survival to induction chemotherapy plus concurrent Chemoradiotherapy in Locoregionally Advanced nasopharyngeal carcinoma

Background

The present study aimed to explore the application value of random survival forest (RSF) model and Cox model in predicting the progression-free survival (PFS) among patients with locoregionally advanced nasopharyngeal carcinoma (LANPC) after induction chemotherapy plus concurrent chemoradiotherapy (IC + CCRT).

Methods

Eligible LANPC patients underwent magnetic resonance imaging (MRI) scan before treatment were subjected to radiomics feature extraction. Radiomics and clinical features of patients in the training cohort were subjected to RSF analysis to predict PFS and were tested in the testing cohort. The performance of an RSF model with clinical and radiologic predictors was assessed with the area under the receiver operating characteristic (ROC) curve (AUC) and Delong test and compared with Cox models based on clinical and radiologic parameters. Further, the Kaplan-Meier method was used for risk stratification of patients.

Results

A total of 294 LANPC patients (206 in the training cohort; 88 in the testing cohort) were enrolled and underwent magnetic resonance imaging (MRI) scans before treatment. The AUC value of the clinical Cox model, radiomics Cox model, clinical + radiomics Cox model, and clinical + radiomics RSF model in predicting 3- and 5-year PFS for LANPC patients was [0.545 vs 0.648 vs 0.648 vs 0.899 (training cohort), and 0.566 vs 0.736 vs 0.730 vs 0.861 (testing cohort); 0.556 vs 0.604 vs 0.611 vs 0.897 (training cohort), and 0.591 vs 0.661 vs 0.676 vs 0.847 (testing cohort), respectively]. Delong test showed that the RSF model and the other three Cox models were statistically significant, and the RSF model markedly improved prediction performance (P < 0.001). Additionally, the PFS of the high-risk group was lower than that of the low-risk group in the RSF model (P < 0.001), while comparable in the Cox model (P > 0.05).

Conclusion

The RSF model may be a potential tool for prognostic prediction and risk stratification of LANPC patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-022-09832-6.

Analysis of Cross-Combinations of Feature Selection and Machine-Learning Classification Methods Based on [18F]F-FDG PET/CT Radiomic Features for Metabolic Response Prediction of Metastatic Breast Cancer Lesions

BACKGROUND

This study aimed to identify optimal combinations between feature selection methods and machine-learning classifiers for predicting the metabolic response of individual metastatic breast cancer lesions, based on clinical variables and radiomic features extracted from pretreatment [18F]F-FDG PET/CT images.

METHODS

A total of 48 patients with confirmed metastatic breast cancer, who received different treatments, were included. All patients had an [18F]F-FDG PET/CT scan before and after the treatment. From 228 metastatic lesions identified, 127 were categorized as responders (complete or partial metabolic response) and 101 as non-responders (stable or progressive metabolic response), by using the percentage changes in SULpeak (peak standardized uptake values normalized for body lean body mass). The lesion pool was divided into training (n = 182) and testing cohorts (n = 46); for each lesion, 101 image features from both PET and CT were extracted (202 features per lesion). These features, along with clinical and pathological information, allowed the prediction model's construction by using seven popular feature selection methods in cross-combination with another seven machine-learning (ML) classifiers. The performance of the different models was investigated with the receiver-operating characteristic curve (ROC) analysis, using the area under the curve (AUC) and accuracy (ACC) metrics.

RESULTS

The combinations, least absolute shrinkage and selection operator (Lasso) + support vector machines (SVM), or random forest (RF) had the highest AUC in the cross-validation, with 0.93 ± 0.06 and 0.92 ± 0.03, respectively, whereas Lasso + neural network (NN) or SVM, and mutual information (MI) + RF, had the higher AUC and ACC in the validation cohort, with 0.90/0.72, 0.86/0.76, and 87/85, respectively. On average, the models with Lasso and models with SVM had the best mean performance for both AUC and ACC in both training and validation cohorts.

CONCLUSIONS

Image features obtained from a pretreatment [18F]F-FDG PET/CT along with clinical vaiables could predict the metabolic response of metastatic breast cancer lesions, by their incorporation into predictive models, whose performance depends on the selected combination between feature selection and ML classifier methods.