Machine learning with multiparametric breast MRI for prediction of Ki-67 and histologic grade in early-stage luminal breast cancer

Multi-task learning for joint prediction of breast cancer histological indicators in dynamic contrast-enhanced magnetic resonance imaging

OBJECTIVES

Achieving efficient analysis of multiple pathological indicators has great significance for breast cancer prognosis and therapeutic decision-making. In this study, we aim to explore a deep multi-task learning (MTL) framework for collaborative prediction of histological grade and proliferation marker (Ki-67) status in breast cancer using multi-phase dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).

METHODS

In the novel design of hybrid multi-task architecture (HMT-Net), co-representative features are explicitly distilled using a feature extraction backbone. A customized prediction network is then introduced to perform soft-parameter sharing between two correlated tasks. Specifically, task-common and task-specific knowledge is transmitted into tower layers for informative interactions. Furthermore, low-level feature maps containing tumor edges and texture details are recaptured by a hard-parameter sharing branch, which are then incorporated into the tower layer for each subtask. Finally, the probabilities of two histological indicators, predicted in the multi-phase DCE-MRI, are separately fused using a decision-level fusion strategy.

RESULTS

Experimental results demonstrate that the proposed HMT-Net achieves optimal discriminative performance over other recent MTL architectures and deep models based on single image series, with the area under the receiver operating characteristic curve of 0.908 for tumor grade and 0.694 for Ki-67 status.

CONCLUSIONS

Benefiting from the innovative HMT-Net, our proposed method elucidates its strong robustness and flexibility in the collaborative prediction task of breast biomarkers. Multi-phase DCE-MRI is expected to contribute valuable dynamic information for breast cancer pathological assessment in a non-invasive manner.

Interpretable model based on MRI radiomics to predict the expression of Ki-67 in breast cancer

This study aimed to develop an interpretable machine learning model that accurately predicts Ki-67 expression in breast cancer (BC) patients using a combination of dynamic-contrast enhanced magnetic resonance imaging (DCE-MRI) radiomics and clinical-imaging features. A total of 195 BC patients, including 201 lesions, were enrolled retrospectively. These lesions were randomized into training and testing set (7:3). The correlation between clinical-imaging features and Ki-67 expression was analyzed via univariate analysis and binary logistic regression, leading to the development of a Clinical-imaging model. Radiomics features were extracted based on the early and delayed phases of DCE-MRI. These features were screened by Pearson correlation coefficient and recursive feature elimination (RFE). The logistic regression classifier was used to develop the Radiomics model. The clinical imaging and radiomics features were combined to form a Combined model. The Shapley Additive Explanation (SHAP) algorithm was employed to explain the optimal model, and the AUC was used to assess the model's performance. Ki-67 expression was markedly different from the internal enhancement pattern and necrosis among the imaging features. Compared to the Clinical-imaging model (AUC = 0.682), the AUCs of the Radiomics and the Combined models in the training set were 0.797 and 0.821, respectively. Clinical-imaging, Radiomics, and Combined models had AUCs of 0.666, 0.796, and 0.802 in the test set. Based on the IDI results, the combined model outperformed the Clinical-imaging and Radiomics models in the training set by 11.8% and 2.1%, respectively. They increased by 11% and 1.74% in the test set. SHAP analysis showed that ph2-original-shape-surface volume ratio was the most important feature of the model. Based on clinical-imaging features and DCE-MRI radiomics, the interpretable machine learning model can accurately predict the expression of Ki-67 in BC. Combining the SHAP algorithm with the model improves its interpretability, which may assist clinicians in formulating more accurate treatment strategies.

Application of DCE-MRI radiomics and heterogeneity analysis in predicting luminal and non-luminal subtypes of breast cancer

Purpose

The aim of this study was to explore the application value of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics and heterogeneity analysis in the differentiation of molecular subtypes of luminal and non-luminal breast cancer.

Methods

In this retrospective study, 388 female breast cancer patients (48.37 ± 9.41 years) with luminal (n = 190) and non-luminal (n = 198) molecular subtypes who received surgical treatment at Jilin Cancer Hospital were recruited from January 2019 to June 2023. All patients underwent breast MRI scan and DCE scan before surgery. The patients were then divided into a training set (n = 272) and a validation set (n = 116) in a 7:3 ratio. The three-dimensional texture feature parameters of the breast lesion areas were extracted. Four tumor heterogeneity parameters, including type I curve proportion, type II curve proportion, type III curve proportion and tumor heterogeneity values were calculated and normalized. Five machine learning (ML) models, including the logistic regression, naive Bayes algorithm (NB), k-nearest neighbor (KNN), decision tree algorithm (DT) and extreme gradient boosting (XGBoost) model were used to process the training data and were further validated. The best ML model was selected according to the performance in the validation set.

Results

In luminal subtype breast lesions, type III curve proportion and heterogeneity index were significantly lower than the corresponding parameters of the non-luminal subtype lesions both in the training set and validation set. Eight features together with four heterogeneity-related parameters with significant differences between luminal and non-luminal groups were retained as radiomics signatures for constructing the prediction model. The logistic regression ML model achieved the best performance in the validation set with the highest area under the curve value (0.93), highest accuracy (86.94%), sensitivity (87.55%) and specificity (86.25%).

Conclusion

The radiomics and heterogeneity analysis based on the DCE-MRI exhibit good application value in discriminating luminal and non-luminal subtype breast cancer. The logistic regression model demonstrates the best predictive performance among various machine learning models.

Dynamic contrast-enhanced magnetic resonance imaging parameters combined with diffusion-weighted imaging for discriminating malignant lesions, molecular subtypes, and pathological grades in invasive ductal carcinoma patients

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) parameters or diffusion-weighted imaging (DWI) findings provide prognostic information on breast cancer. However, the accuracy of a single MRI technique is unsatisfactory. This study intended to explore the combination of DWI and DCE-MRI parameters in discriminating molecular subtypes in invasive ductal carcinoma (IDC) patients. Eighty-two IDC patients who underwent breast DWI and DCE-MRI examinations were retrospectively analyzed. Eighty-six patients with benign masses were retrieved as benign controls. The combination of ADC value, Ktrans, Kep, Ve, and iAUC had a good ability to discriminate IDC patients (vs. benign controls) with an area under the curve (AUC) [95% confidence interval (CI)] of 0.961 (0.935-0.987). A nomogram-based prediction model with the above combination showed a good predictive value for IDC probability. The combination of ADC value, Ktrans, Kep, and iAUC also had a certain ability to discriminate pathological grade III (vs. I or II) [AUC (95% CI): 0.698 (0.572-0.825)] in IDC patients. Notably, ADC value (P=0.010) and Kep (P=0.043) differed in IDC patients with different molecular subtypes. Besides, ADC value was increased (P<0.001), but Ktrans (P=0.037) and Kep (P=0.004) were decreased in IDC patients with Lumina A (vs. other molecular subtypes). The combination of ADC value, Ktrans, Kep, had an acceptable ability to discriminate Luminal A (vs. other molecular subtypes) [AUC (95% CI): 0.845 (0.748-0.941)] in IDC patients. DWI combined with DCE-MRI parameters discriminates IDC from benign masses; it also identifies Luminal A and pathological grade III in IDC patients.

Machine learning-based models for prediction of survival in medulloblastoma: a systematic review and meta-analysis

BACKGROUND

Medulloblastoma (MB) is the pediatric population's most frequent malignant intracranial lesions. Prognostication plays a crucial role in optimizing treatment strategy in the MB setting. Several studies have developed ML-based models to predict survival outcomes in individuals with MB. In this systematic review and meta-analysis study, we aimed to evaluate the role of ML-based models in predicting survival in MB patients.

METHOD

Literature records were retrieved on May 14th, 2024, using the relevant key terms without filters in PubMed, Embase, Scopus, and Web of Science. Records were screened according to the eligibility criteria, and the data from the included studies were extracted. The quality assessment was performed using the QUADAS-2 tool. The meta-analysis and sensitivity analysis were conducted using R software.

RESULTS

Six studies were included, with 2771 patients ranging from 46 to 1759 individuals. A total of 23 ML and DL models were developed, 20 of which were ML and three DL. Random forest (RF) was the most frequent classifier, as it was utilized in nine models, followed by support vector machine (SVM). Eight models were included in the meta-analysis. Our meta-analysis revealed a pooled AUC of 0.77 (95% CI: 0.75-0.80). In addition, the radionics-based and genomics-based models had a pooled AUC of 0.77 (95% CI: 0.76-079) and 0.76 (0.63-0.88), respectively (P = 0.77).

CONCLUSION

Our results suggested that ML-based models, especially ML algorithms, could play a vital and efficient role in the prediction of survival of patients based on radiomics and genomics.

Application of Artificial Intelligence in Prediction of Ki-67 Index in Meningiomas: A Systematic Review and Meta-Analysis

BACKGROUND

The Ki-67 index is a histopathological marker that has been reported to be a crucial factor in the biological behavior and prognosis of meningiomas. Several studies have developed artificial intelligence (AI) models to predict the Ki-67 based on radiomics. In this study, we aimed to perform a systematic review and meta-analysis of AI models that predicted the Ki-67 index in meningioma.

METHODS

Literature records were retrieved on April 27, 2024, using the relevant key terms without filters in PubMed, Embase, Scopus, and Web of Science. Records were screened according to the eligibility criteria, and the data from included studies were extracted. The quality assessment was performed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. The meta-analysis, sensitivity analysis, and meta-regression were conducted using R software.

RESULTS

Our study included 6 studies. The mean Ki-67 ranged from 2.7 ± 2.97 to 4.8 ± 40.3. Of 6 studies, 5 utilized a machine learning method. The most used AI method was the least absolute shrinkage and selection operator. The area under the curve and accuracy ranged from 0.83 to 0.99 and 0.81 to 0.95, respectively. AI models demonstrated a pooled sensitivity of 87.5% (95% confidence interval [CI]: 75.2%, 94.2%), a specificity of 86.9% (95% CI: 75.8%, 93.4%), and a diagnostic odds ratio of 40.02 (95% CI: 13.5, 156.4). The summary receiver operating characteristic curve indicated an area under the curve of 0.931 for the prediction of Ki-67 index status in intracranial meningiomas.

CONCLUSIONS

AI models have demonstrated promising performance for predicting the Ki-67 index in meningiomas and can optimize the treatment strategy.

Machine learning models for differential diagnosing HER2-low breast cancer: A radiomics approach

To develop machine learning models based on preoperative dynamic enhanced magnetic resonance imaging (DCE-MRI) radiomics and to explore their potential prognostic value in the differential diagnosis of human epidermal growth factor receptor 2 (HER2)-low from HER2-positive breast cancer (BC). A total of 233 patients with pathologically confirmed invasive breast cancer admitted to our hospital between January 2018 and December 2022 were included in this retrospective analysis. Of these, 103 cases were diagnosed as HER2-positive and 130 cases were HER2 low-expression BC. The Synthetic Minority Oversampling Technique is employed to address the class imbalance problem. Patients were randomly split into a training set (163 cases) and a validation set (70 cases) in a 7:3 ratio. Radiomics features from DCE-MRI second-phase imaging were extracted. Z-score normalization was used to standardize the radiomics features, and Pearson's correlation coefficient and recursive feature elimination were used to explore the significant features. Prediction models were constructed using 6 machine learning algorithms: logistic regression, random forest, support vector machine, AdaBoost, decision tree, and auto-encoder. Receiver operating characteristic curves were constructed, and predictive models were evaluated according to the area under the curve (AUC), accuracy, sensitivity, and specificity. In the training set, the AUC, accuracy, sensitivity, and specificity of all models were 1.000. However, in the validation set, the auto-encoder model's AUC, accuracy, sensitivity, and specificity were 0.994, 0.976, 0.972, and 0.978, respectively. The remaining models' AUC, accuracy, sensitivity, and specificity were 1.000. The DeLong test showed no statistically significant differences between the machine learning models in the training and validation sets (Z = 0, P = 1). Our study investigated the feasibility of using DCE-MRI-based radiomics features to predict HER2-low BC. Certain radiomics features showed associations with HER2-low BC and may have predictive value. Machine learning prediction models developed using these radiomics features could be beneficial for distinguishing between HER2-low and HER2-positive BC. These noninvasive preoperative models have the potential to assist in clinical decision-making for HER2-low breast cancer, thereby advancing personalized clinical precision.

Performance evaluation of ML models for preoperative prediction of HER2-low BC based on CE-CBBCT radiomic features: A prospective study

To explore the value of machine learning (ML) models based on contrast-enhanced cone-beam breast computed tomography (CE-CBBCT) radiomics features for the preoperative prediction of human epidermal growth factor receptor 2 (HER2)-low expression breast cancer (BC). Fifty-six patients with HER2-negative invasive BC who underwent preoperative CE-CBBCT were prospectively analyzed. Patients were randomly divided into training and validation cohorts at approximately 7:3. A total of 1046 quantitative radiomic features were extracted from CE-CBBCT images and normalized using z-scores. The Pearson correlation coefficient and recursive feature elimination were used to identify the optimal features. Six ML models were constructed based on the selected features: linear discriminant analysis (LDA), random forest (RF), support vector machine (SVM), logistic regression (LR), AdaBoost (AB), and decision tree (DT). To evaluate the performance of these models, receiver operating characteristic curves and area under the curve (AUC) were used. Seven features were selected as the optimal features for constructing the ML models. In the training cohort, the AUC values for SVM, LDA, RF, LR, AB, and DT were 0.984, 0.981, 1.000, 0.970, 1.000, and 1.000, respectively. In the validation cohort, the AUC values for the SVM, LDA, RF, LR, AB, and DT were 0.859, 0.880, 0.781, 0.880, 0.750, and 0.713, respectively. Among all ML models, the LDA and LR models demonstrated the best performance. The DeLong test showed that there were no significant differences among the receiver operating characteristic curves in all ML models in the training cohort (P > .05); however, in the validation cohort, the DeLong test showed that the differences between the AUCs of LDA and RF, AB, and DT were statistically significant (P = .037, .003, .046). The AUCs of LR and RF, AB, and DT were statistically significant (P = .023, .005, .030). Nevertheless, no statistically significant differences were observed when compared to the other ML models. ML models based on CE-CBBCT radiomics features achieved excellent performance in the preoperative prediction of HER2-low BC and could potentially serve as an effective tool to assist in precise and personalized targeted therapy.

Histogram analysis comparison of readout-segmented and single-shot echo-planar imaging for differentiating luminal from non-luminal breast cancer

To compare diffusion-kurtosis imaging (DKI) and diffusion-weighted imaging (DWI) parameters of single-shot echo-planar imaging (ss-EPI) and readout-segmented echo-planar imaging (rs-EPI) in the differentiation of luminal vs. non-luminal breast cancer using histogram analysis. One hundred and sixty women with 111 luminal and 49 non-luminal breast lesions were enrolled in this study. All patients underwent ss-EPI and rs-EPI sequences on a 3.0T scanner. Histogram metrics were derived from mean kurtosis (MK), mean diffusion (MD) and the apparent diffusion coefficient (ADC) maps of two DWI sequences respectively. Student's t test or Mann-Whitney U test was performed for differentiating luminal subtype from non-luminal subtype. The ROC curves were plotted for evaluating the diagnostic performances of significant histogram metrics in differentiating luminal from non-luminal BC. The histogram metrics MKmean, MK50th, MK75th of luminal BC were significantly higher than those of non-luminal BC for both two DWI sequences (all P<0.05). Histogram metrics from rs-EPI sequence had better diagnostic performance in differentiating luminal from non-Luminal breast cancer compared to those from ss-EPI sequence. MK75th derived from rs-EPI sequence was the most valuable single metric (AUC, 0.891; sensitivity, 78.4%; specificity, 87.8%) for differentiating luminal from non-luminal BC among all the histogram metrics. Histogram metrics of MK derived from rs-EPI yielded better diagnostic performance for distinguishing luminal from non-luminal BC than that from ss-EPI. MK75th was the most valuable metric among all the histogram metrics.

The Impact of Artificial Intelligence on Microbial Diagnosis

Traditional microbial diagnostic methods face many obstacles such as sample handling, culture difficulties, misidentification, and delays in determining susceptibility. The advent of artificial intelligence (AI) has markedly transformed microbial diagnostics with rapid and precise analyses. Nonetheless, ethical considerations accompany AI adoption, necessitating measures to uphold patient privacy, mitigate biases, and ensure data integrity. This review examines conventional diagnostic hurdles, stressing the significance of standardized procedures in sample processing. It underscores AI's significant impact, particularly through machine learning (ML), in microbial diagnostics. Recent progressions in AI, particularly ML methodologies, are explored, showcasing their influence on microbial categorization, comprehension of microorganism interactions, and augmentation of microscopy capabilities. This review furnishes a comprehensive evaluation of AI's utility in microbial diagnostics, addressing both advantages and challenges. A few case studies including SARS-CoV-2, malaria, and mycobacteria serve to illustrate AI's potential for swift and precise diagnosis. Utilization of convolutional neural networks (CNNs) in digital pathology, automated bacterial classification, and colony counting further underscores AI's versatility. Additionally, AI improves antimicrobial susceptibility assessment and contributes to disease surveillance, outbreak forecasting, and real-time monitoring. Despite a few limitations, integration of AI in diagnostic microbiology presents robust solutions, user-friendly algorithms, and comprehensive training, promising paradigm-shifting advancements in healthcare.

Machine learning and new insights for breast cancer diagnosis

Breast cancer (BC) is the most prominent form of cancer among females all over the world. The current methods of BC detection include X-ray mammography, ultrasound, computed tomography, magnetic resonance imaging, positron emission tomography and breast thermographic techniques. More recently, machine learning (ML) tools have been increasingly employed in diagnostic medicine for its high efficiency in detection and intervention. The subsequent imaging features and mathematical analyses can then be used to generate ML models, which stratify, differentiate and detect benign and malignant breast lesions. Given its marked advantages, radiomics is a frequently used tool in recent research and clinics. Artificial neural networks and deep learning (DL) are novel forms of ML that evaluate data using computer simulation of the human brain. DL directly processes unstructured information, such as images, sounds and language, and performs precise clinical image stratification, medical record analyses and tumour diagnosis. Herein, this review thoroughly summarizes prior investigations on the application of medical images for the detection and intervention of BC using radiomics, namely DL and ML. The aim was to provide guidance to scientists regarding the use of artificial intelligence and ML in research and the clinic.

MRI-Based Radiomics Methods for Predicting Ki-67 Expression in Breast Cancer: A Systematic Review and Meta-analysis

RATIONALE AND OBJECTIVES

The purpose of this systematic review and meta-analysis was to assess the quality and diagnostic accuracy of MRI-based radiomics for predicting Ki-67 expression in breast cancer.

MATERIALS AND METHODS

A systematic literature search was performed to find relevant studies published in different databases, including PubMed, Web of Science, and Embase up until March 10, 2023. All papers were independently evaluated for eligibility by two reviewers. Studies that matched research questions and provided sufficient data for quantitative synthesis were included in the systematic review and meta-analysis, respectively. The quality of the articles was assessed using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) and Radiomics Quality Score (RQS) tools. The predictive value of MRI-based radiomics for Ki-67 antigen in patients with breast cancer was assessed using pooled sensitivity (SEN), specificity, and area under the curve (AUC). Meta-regression was performed to explore the cause of heterogeneity. Different covariates were used for subgroup analysis.

RESULTS

31 studies were included in the systematic review; among them, 21 reported sufficient data for meta-analysis. 20 training cohorts and five validation cohorts were pooled separately. The pooled sensitivity, specificity, and AUC of MRI-based radiomics for predicting Ki-67 expression in training cohorts were 0.80 [95% CI, 0.73-0.86], 0.82 [95% CI, 0.78-0.86], and 0.88 [95%CI, 0.85-0.91], respectively. The corresponding values for validation cohorts were 0.81 [95% CI, 0.72-0.87], 0.73 [95% CI, 0.62-0.82], and 0.84 [95%CI, 0.80-0.87], respectively. Based on QUADAS-2, some risks of bias were detected for reference standard and flow and timing domains. However, the quality of the included article was acceptable. The mean RQS score of the included articles was close to 6, corresponding to 16.6% of the maximum possible score. Significant heterogeneity was observed in pooled sensitivity and specificity of training cohorts (I2 > 75%). We found that using deep learning radiomic methods, magnetic field strength (3 T vs. 1.5 T), scanner manufacturer, region of interest structure (2D vs. 3D), route of tissue sampling, Ki-67 cut-off, logistic regression for model construction, and LASSO for feature reduction as well as PyRadiomics software for feature extraction had a great impact on heterogeneity according to our joint model analysis. Diagnostic performance in studies that used deep learning-based radiomics and multiple MRI sequences (e.g., DWI+DCE) was slightly higher. In addition, radiomic features derived from DWI sequences performed better than contrast-enhanced sequences in terms of specificity and sensitivity. No publication bias was found based on Deeks' funnel plot. Sensitivity analysis showed that eliminating every study one by one does not impact overall results.

CONCLUSION

This meta-analysis showed that MRI-based radiomics has a good diagnostic accuracy in differentiating breast cancer patients with high Ki-67 expression from low-expressing groups. However, the sensitivity and specificity of these methods still do not surpass 90%, restricting them from being used as a supplement to current pathological assessments (e.g., biopsy or surgery) to predict Ki-67 expression accurately.

HRadNet: A Hierarchical Radiomics-Based Network for Multicenter Breast Cancer Molecular Subtypes Prediction

Breast cancer is a heterogeneous disease, where molecular subtypes of breast cancer are closely related to the treatment and prognosis. Therefore, the goal of this work is to differentiate between luminal and non-luminal subtypes of breast cancer. The hierarchical radiomics network (HRadNet) is proposed for breast cancer molecular subtypes prediction based on dynamic contrast-enhanced magnetic resonance imaging. HRadNet fuses multilayer features with the metadata of images to take advantage of conventional radiomics methods and general convolutional neural networks. A two-stage training mechanism is adopted to improve the generalization capability of the network for multicenter breast cancer data. The ablation study shows the effectiveness of each component of HRadNet. Furthermore, the influence of features from different layers and metadata fusion are also analyzed. It reveals that selecting certain layers of features for a specified domain can make further performance improvements. Experimental results on three data sets from different devices demonstrate the effectiveness of the proposed network. HRadNet also has good performance when transferring to other domains without fine-tuning.

Artificial intelligence in breast imaging: potentials and challenges

Breast cancer, which is the most common type of malignant tumor among humans, is a leading cause of death in females. Standard treatment strategies, including neoadjuvant chemotherapy, surgery, postoperative chemotherapy, targeted therapy, endocrine therapy, and radiotherapy, are tailored for individual patients. Such personalized therapies have tremendously reduced the threat of breast cancer in females. Furthermore, early imaging screening plays an important role in reducing the treatment cycle and improving breast cancer prognosis. The recent innovative revolution in artificial intelligence (AI) has aided radiologists in the early and accurate diagnosis of breast cancer. In this review, we introduce the necessity of incorporating AI into breast imaging and the applications of AI in mammography, ultrasonography, magnetic resonance imaging, and positron emission tomography/computed tomography based on published articles since 1994. Moreover, the challenges of AI in breast imaging are discussed.

Silicon versus Superbug: Assessing Machine Learning's Role in the Fight against Antimicrobial Resistance

In his 1945 Nobel Prize acceptance speech, Sir Alexander Fleming warned of antimicrobial resistance (AMR) if the necessary precautions were not taken diligently. As the growing threat of AMR continues to loom over humanity, we must look forward to alternative diagnostic tools and preventive measures to thwart looming economic collapse and untold mortality worldwide. The integration of machine learning (ML) methodologies within the framework of such tools/pipelines presents a promising avenue, offering unprecedented insights into the underlying mechanisms of resistance and enabling the development of more targeted and effective treatments. This paper explores the applications of ML in predicting and understanding AMR, highlighting its potential in revolutionizing healthcare practices. From the utilization of supervised-learning approaches to analyze genetic signatures of antibiotic resistance to the development of tools and databases, such as the Comprehensive Antibiotic Resistance Database (CARD), ML is actively shaping the future of AMR research. However, the successful implementation of ML in this domain is not without challenges. The dependence on high-quality data, the risk of overfitting, model selection, and potential bias in training data are issues that must be systematically addressed. Despite these challenges, the synergy between ML and biomedical research shows great promise in combating the growing menace of antibiotic resistance.

Preoperative prediction of Ki-67 and p53 status in meningioma using a multiparametric MRI-based clinical-radiomic model

Purpose

To investigate the utility of preoperative multiparametric magnetic resonance imaging (mpMRI)-based clinical-radiomic analysis combined with machine learning (ML) algorithms in predicting the expression of the Ki-67 proliferative index and p53 tumor suppressor protein in patients with meningioma.

Methods

This multicenter retrospective study included 483 and 93 patients from two centers. The Ki-67 index was classified into high (Ki-67≥5%) and low (Ki-67<5%)-expressed groups, and the p53 index was classified into positive (p53≥5%) and negative (p53<5%)-expressed groups. Clinical and radiological features were analyzed using univariate and multivariate statistical analyses. Six ML models were performed with different types of classifiers to predict Ki-67 and p53 status.

Results

In the multivariate analysis, larger tumor volumes (p<0.001), irregular tumor margin (p<0.001), and unclear tumor-brain interface (p<0.001) were independently associated with a high Ki-67 status, whereas the presence of both necrosis (p=0.003) and the dural tail sign (p=0.026) were independently associated with a positive p53 status. A relatively better performance was yielded from the model constructed by combined clinical and radiological features. The area under the curve (AUC) and accuracy of high Ki-67 were 0.820 and 0.867 in the internal test, and 0.666 and 0.773 in the external test, respectively. Regarding p53 positivity, the AUC and accuracy were 0.858 and 0.857 in the internal test, and 0.684 and 0.718 in the external test.

Conclusion

The present study developed clinical-radiomic ML models to non-invasively predict Ki-67 and p53 expression in meningioma using mpMRI features, and provides a novel non-invasive strategy for assessing cell proliferation.

Nomogram based on MRI for preoperative prediction of Ki-67 expression in patients with intrahepatic mass cholangiocarcinoma

OBJECTIVES

To validate a new nomogram based on magnetic resonance imaging (MRI) for pre-operative prediction of Ki-67 expression in patients with intrahepatic mass cholangiocarcinoma (IMCC).

METHODS

A total of 78 patients with clinicopathologically confirmed IMCC who underwent pre-operative gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid enhanced MRI between 2016 and 2022 were enrolled in the training and validation group (53 patients and 25 patients, respectively). Images including qualitative, quantitative MRI features and clinical data were evaluated. Univariate analysis and multivariate logistic regression were used to select the independent predictors and establish different predictive models. The predictive performance was validated by operating characteristic curve (ROC) analysis, calibration curve, and decision curve analysis (DCA). The validation cohort was used to test the predictive performance of the optimal model. The nomogram was constructed with the optimal model.

RESULTS

In the training cohort, independent predictors obtained from the combined model were DWI (OR 1822.741; 95% CI 6.189, 536,781.805; P = 0.01) and HBP enhancement pattern (OR 14.270; 95% CI 1.044, 195.039; P = 0.046). The combined model showed the good performance (AUC 0.981; 95% CI 0.952, 1.000) for predicting Ki-67 expression. In the validation cohort, The combined model (AUC 0.909; 95% CI 0.787, 1.000)showed the best performance compared to the clinical model (AUC 0.448; 95% CI 0.196, 0.700) and MRI model (AUC 0.770; 95% CI 0.570, 0.970).

CONCLUSION

This new nomogram has a good performance in predicting Ki-67 expression in patients with IMCC, which could help the decision-making of the patients' therapy strategies.

Development and Validation of an MRI Radiomics-Based Signature to Predict Histological Grade in Patients with Invasive Breast Cancer

Background

Histological grade is an important factor in the overall prognosis of patients with invasive breast cancer. Therefore, the non-invasive assessment of histological grade in breast cancer patients is an increasing concern for clinicians. We aimed to establish an MRI-based radiomics model for preoperative prediction of invasive breast cancer histological grade.

Methods

We enrolled 901 patients with invasive breast cancer and pre-operative MRI. Patients were randomly divided into the training cohort (n=630) and validation cohort (n=271) with a ratio of 7:3. A radiomics signature was constructed by extracting radiomics features from MRI images and was developed according to multivariate logistic regression analysis. The diagnostic performance of the radiomics model was assessed using receiver operating characteristic (ROC) curve analysis.

Results

Of the 901 patients, 618 (68.6%) were histological grade 1 or 2 while 283 (31.4%) were histological grade 3. The area under the ROC curve (AUC) of the radiomics model for the prediction of the histological grade was 0.761 (95% CI 0.728–0.794) in the training cohort and 0.722 (95% CI 0.664–0.777) in the validation cohort. The decision curve analysis (DCA) demonstrated the radiomics model’s clinical application value.

Conclusion

This is a preliminary study suggesting that the development of an MRI-based radiomics model can predict the histological grade of invasive breast cancer.

Artificial intelligence in multi-parametric magnetic resonance imaging: A review

Multi-parametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for the diagnosis and treatment planning of various diseases. Machine learning-based artificial intelligence (AI) methods, especially those adopting the deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, and super-resolution. The current availability of increasing computational power and fast-improving AI algorithms have empowered numerous computer-based systems for applying mpMRI to disease diagnosis, imaging-guided radiotherapy, patient risk and overall survival time prediction, and the development of advanced quantitative imaging technology for magnetic resonance fingerprinting. However, the wide application of these developed systems in the clinic is still limited by a number of factors, including robustness, reliability, and interpretability. This survey aims to provide an overview for new researchers in the field as well as radiologists with the hope that they can understand the general concepts, main application scenarios, and remaining challenges of AI in mpMRI. This article is protected by copyright. All rights reserved.

Radiogenomics analysis reveals the associations of dynamic contrast-enhanced-MRI features with gene expression characteristics, PAM50 subtypes, and prognosis of breast cancer

BACKGROUND

To investigate reliable associations between dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) features and gene expression characteristics in breast cancer (BC) and to develop and validate classifiers for predicting PAM50 subtypes and prognosis from DCE-MRI non-invasively.

METHODS

Two radiogenomics cohorts with paired DCE-MRI and RNA-sequencing (RNA-seq) data were collected from local and public databases and divided into discovery (n = 174) and validation cohorts (n = 72). Six external datasets (n = 1,443) were used for prognostic validation. Spatial-temporal features of DCE-MRI were extracted, normalized properly, and associated with gene expression to identify the imaging features that can indicate subtypes and prognosis.

RESULTS

Expression of genes including RBP4, MYBL2, and LINC00993 correlated significantly with DCE-MRI features (q-value < 0.05). Importantly, genes in the cell cycle pathway exhibited a significant association with imaging features (p-value < 0.001). With eight imaging-associated genes (CHEK1, TTK, CDC45, BUB1B, PLK1, E2F1, CDC20, and CDC25A), we developed a radiogenomics prognostic signature that can distinguish BC outcomes in multiple datasets well. High expression of the signature indicated a poor prognosis (p-values < 0.01). Based on DCE-MRI features, we established classifiers to predict BC clinical receptors, PAM50 subtypes, and prognostic gene sets. The imaging-based machine learning classifiers performed well in the independent dataset (areas under the receiver operating characteristic curve (AUCs) of 0.8361, 0.809, 0.7742, and 0.7277 for estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2)-enriched, basal-like, and obtained radiogenomics signature). Furthermore, we developed a prognostic model directly using DCE-MRI features (p-value < 0.0001).

CONCLUSIONS

Our results identified the DCE-MRI features that are robust and associated with the gene expression in BC and displayed the possibility of using the features to predict clinical receptors and PAM50 subtypes and to indicate BC prognosis.

Multiparametric MRI-Based Radiomics Model for Predicting H3 K27M Mutant Status in Diffuse Midline Glioma: A Comparative Study Across Different Sequences and Machine Learning Techniques

Objectives

The performance of multiparametric MRI-based radiomics models for predicting H3 K27M mutant status in diffuse midline glioma (DMG) has not been thoroughly evaluated. The optimal combination of multiparametric MRI and machine learning techniques remains undetermined. We compared the performance of various radiomics models across different MRI sequences and different machine learning techniques.

Methods

A total of 102 patients with pathologically confirmed DMG were retrospectively enrolled (27 with H3 K27M-mutant and 75 with H3 K27M wild-type). Radiomics features were extracted from eight sequences, and 18 feature sets were conducted by independent combination. There were three feature matrix normalization algorithms, two dimensionality-reduction methods, four feature selectors, and seven classifiers, consisting of 168 machine learning pipelines. Radiomics models were established across different feature sets and machine learning pipelines. The performance of models was evaluated using receiver operating characteristic curves with area under the curve (AUC) and compared with DeLong’s test.

Results

The multiparametric MRI-based radiomics models could accurately predict the H3 K27M mutant status in DMG (highest AUC: 0.807–0.969, for different sequences or sequence combinations). However, the results varied significantly between different machine learning techniques. When suitable machine learning techniques were used, the conventional MRI-based radiomics models shared similar performance to advanced MRI-based models (highest AUC: 0.875–0.915 vs. 0.807–0.926; DeLong’s test, p > 0.05). Most models had a better performance when generated with a combination of MRI sequences. The optimal model in the present study used a combination of all sequences (AUC = 0.969).

Conclusions

The multiparametric MRI-based radiomics models could be useful for predicting H3 K27M mutant status in DMG, but the performance varied across different sequences and machine learning techniques.