Machine Learning methods for Quantitative Radiomic Biomarkers

CT-based radiomics model for predicting perineural invasion status in gastric cancer

PURPOSE

Perineural invasion (PNI) is an independent risk factor for poor prognosis in gastric cancer (GC) patients. This study aimed to develop and validate predictive models based on CT imaging and clinical features to predict PNI status in GC patients.

METHODS

This retrospective study included 291 GC patients (229 in the training cohort and 62 in the validation cohort) who underwent gastrectomy between January 2020 and August 2022. The clinical data and preoperative abdominal contrast-enhanced computed tomography (CECT) images were collected. Radiomics features were extracted from the venous phase of CECT images. The intraclass correlation coefficient (ICC), Pearson correlation coefficient, and t-test were applied for radiomics feature selection. The random forest algorithm was used to construct a radiomics signature and calculate the radiomics feature score (Rad-score). A hybrid model was built by aggregating the Rad-score and clinical predictors. The area under the receiver operating characteristic curve (ROC) and decision curve analysis (DCA) were used to evaluate the prediction performance of the radiomics, clinical, and hybrid models.

RESULTS

A total of 994 radiomics features were extracted from the venous phase images of each patient. Finally, 5 radiomics features were selected and used to construct a radiomics signature. The hybrid model demonstrated strong predictive ability for PNI, with AUCs of 0.833 (95% CI: 0.779-0.887) and 0.806 (95% CI: 0.628-0.983) in the training and validation cohorts, respectively. The DCA showed that the hybrid model had good clinical utility.

CONCLUSION

We established three models, and the hybrid model that combined the Rad-score and clinical predictors had a high potential for predicting PNI in GC patients.

Potential of AI and ML in oncology research including diagnosis, treatment and future directions: A comprehensive prospective

Artificial intelligence (AI) and machine learning (ML) have emerged as transformative tools in cancer research, offering the ability to process huge data rapidly and make precise therapeutic decisions. Over the last decade, AI, particularly deep learning (DL) and machine learning (ML), has significantly enhanced cancer prediction, diagnosis, and treatment by leveraging algorithms such as convolutional neural networks (CNNs) and multi-layer perceptrons (MLPs). These technologies provide reliable, efficient solutions for managing aggressive diseases like cancer, which have high recurrence and mortality rates. This review prospective highlights the applications of AI in oncology, a long with FDA-approved technologies like EFAI RTSuite CT HN-Segmentation System, Quantib Prostate, and Paige Prostate, and explore their role in advancing cancer detection, personalized care, and treatment. Furthermore, we also explored broader applications of AI in healthcare, addressing challenges, limitations, regulatory considerations, and ethical implications. By presenting these advancements, we underscore AI's potential to revolutionize cancer care, management and treatment.

Peroxisomal membrane protein PMP70 confers drug resistance in colorectal cancer

Metabolic reprogramming is a key contributor to cancer therapeutic resistance. Peroxisomes are highly metabolic organelles essential for lipid metabolism and reactive oxygen species (ROS) turnover. Recent studies pointed out that targeting peroxisomal genes could be a promising strategy for treating therapy-resistant cells. However, the role of peroxisomes in CRC chemoresistance remains largely unexplored. This study aimed to investigate the function of peroxisomes in CRC chemoresistance and uncover the underlying mechanisms. Our results showed that the protein level of peroxisome marker PMP70 was strongly correlated with oxaliplatin (LOHP)-treated tumor recurrence in CRC. LOHP was confirmed to induce pexophagy in CRC cells, whereas LOHP-resistant cells maintained stable peroxisome levels and resisted this selective autophagy. Moreover, depletion of PMP70 significantly reduced the viability of resistant CRC cells in response to LOHP, both in vitro and in vivo. Mechanistically, PMP70 acted as a potential protector against excessive lipid peroxidation (LPO) in PMP70High and LOHP-resistant CRC cells. Additionally, PMP70-depleted cells exhibited an altered metabolic profile, characterized by reduced neutral lipids, fewer lipid droplets (LDs), and cell cycle arrest, indicating that PMP70 downregulation resulted in metabolic impairment. In conclusion, our study unveiled the pivotal role of PMP70-mediated peroxisomal functions in conferring chemoresistance, particularly in the context of LOHP resistance in CRC.

Enhancing radiomics features via a large language model for classifying benign and malignant breast tumors in mammography

BACKGROUND AND OBJECTIVES

Radiomics is widely used to assist in clinical decision-making, disease diagnosis, and treatment planning for various target organs, including the breast. Recent advances in large language models (LLMs) have helped enhance radiomics analysis.

MATERIALS AND METHODS

Herein, we sought to improve radiomics analysis by incorporating LLM-learned clinical knowledge, to classify benign and malignant tumors in breast mammography. We extracted radiomics features from the mammograms based on the region of interest and retained the features related to the target task. Using prompt engineering, we devised an input sequence that reflected the selected features and the target task. The input sequence was fed to the chosen LLM (LLaMA variant), which was fine-tuned using low-rank adaptation to enhance radiomics features. This was then evaluated on two mammogram datasets (VinDr-Mammo and INbreast) against conventional baselines.

RESULTS

The enhanced radiomics-based method performed better than baselines using conventional radiomics features tested on two mammogram datasets, achieving accuracies of 0.671 for the VinDr-Mammo dataset and 0.839 for the INbreast dataset. Conventional radiomics models require retraining from scratch for an unseen dataset using a new set of features. In contrast, the model developed in this study effectively reused the common features between the training and unseen datasets by explicitly linking feature names with feature values, leading to extensible learning across datasets. Our method performed better than the baseline method in this retraining setting using an unseen dataset.

CONCLUSIONS

Our method, one of the first to incorporate LLM into radiomics, has the potential to improve radiomics analysis.

Multiparametric MRI-based Interpretable Machine Learning Radiomics Model for Distinguishing Between Luminal and Non-luminal Tumors in Breast Cancer: A Multicenter Study

RATIONALE AND OBJECTIVES

To construct and validate an interpretable machine learning (ML) radiomics model derived from multiparametric magnetic resonance imaging (MRI) images to differentiate between luminal and non-luminal breast cancer (BC) subtypes.

METHODS

This study enrolled 1098 BC participants from four medical centers, categorized into a training cohort (n = 580) and validation cohorts 1-3 (n = 252, 89, and 177, respectively). Multiparametric MRI-based radiomics features, including T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC), and dynamic contrast-enhanced (DCE) imaging, were extracted. Five ML algorithms were applied to develop various radiomics models, from which the best performing model was identified. A ML-based combined model including optimal radiomics features and clinical predictors was constructed, with performance assessed through receiver operating characteristic (ROC) analysis. The Shapley additive explanation (SHAP) method was utilized to assess model interpretability.

RESULTS

Tumor size and MR-reported lymph node status were chosen as significant clinical variables. Thirteen radiomics features were identified from multiparametric MRI images. The extreme gradient boosting (XGBoost) radiomics model performed the best, achieving area under the curves (AUCs) of 0.941, 0.903, 0.862, and 0.894 across training and validation cohorts 1-3, respectively. The XGBoost combined model showed favorable discriminative power, with AUCs of 0.956, 0.912, 0.894, and 0.906 in training and validation cohorts 1-3, respectively. The SHAP visualization facilitated global interpretation, identifying "ADC_wavelet-HLH_glszm_ZoneEntropy" and "DCE_wavelet-HLL_gldm_DependenceVariance" as the most significant features for the model's predictions.

CONCLUSION

The XGBoost combined model derived from multiparametric MRI may proficiently differentiate between luminal and non-luminal BC and aid in treatment decision-making.

CRITICAL RELEVANCE STATEMENT

An interpretable machine learning radiomics model can preoperatively predict luminal and non-luminal subtypes in breast cancer, thereby aiding therapeutic decision-making.

Mesothelin expression prediction in pancreatic cancer based on multimodal stochastic configuration networks

Predicting tumor biomarkers with high precision is essential for improving the diagnostic accuracy and developing more effective treatment strategies. This paper proposes a machine learning model that utilizes CT images and biopsy whole slide images (WSI) to classify mesothelin expression levels in pancreatic cancer. By combining multimodal learning and stochastic configuration networks, a radiopathomics mesothelin-prediction system named RPMSNet is developed. The system extracts radiomic and pathomic features from CT images and WSI, respectively, and sends them into stochastic configuration networks for the final prediction. Compared to traditional radiomics or pathomics, this system has the capability to capture more comprehensive image features, providing a multidimensional insight into tissue characteristics. The experiments and analyses demonstrate the accuracy and effectiveness of the system, with an area under the curve of 81.03%, an accuracy of 73.67%, a sensitivity of 71.54%, a precision of 76.78%, and a F1-score of 72.61%, surpassing both single-modality and dual-modality models. RPMSNet highlights its potential for early diagnosis and personalized treatment in precision medicine.

Radiomics analysis for prediction and classification of submucosal tumors based on gastrointestinal endoscopic ultrasonography

Objectives

To identify and classify submucosal tumors by building and validating a radiomics model with gastrointestinal endoscopic ultrasonography (EUS) images.

Methods

A total of 144 patients diagnosed with submucosal tumors through gastrointestinal EUS were collected between January 2019 and October 2020. There are 1952 radiomic features extracted from each patient's EUS images. The statistical test and the customized least absolute shrinkage and selection operator regression were used for feature selection. Subsequently, an extremely randomized trees algorithm was utilized to construct a robust radiomics classification model specifically tailored for gastrointestinal EUS images. The performance of the model was measured by evaluating the area under the receiver operating characteristic curve.

Results

The radiomics model comprised 30 selected features that showed good discrimination performance in the validation cohorts. During validation, the area under the receiver operating characteristic curve was calculated as 0.9203 and the mean value after 10-fold cross-validation was 0.9260, indicating excellent stability and calibration. These results confirm the clinical utility of the model.

Conclusions

Utilizing the dataset provided curated from gastrointestinal EUS examinations at our collaborating hospital, we have developed a well-performing radiomics model. It can be used for personalized and non-invasive prediction of the type of submucosal tumors, providing physicians with aid for early treatment and management of tumor progression.

Prognostic power of radiomics in head and neck cancers: Insights from a meta-analysis

BACKGROUND

Prognostic modeling in head and neck cancers (HNC) has advanced with the integration of clinical factors and radiomic data from CT and MRI scans. However, previous reviews have not systematically evaluated the predictive performance of these models across different oncological endpoints or assessed factors affecting their generalizability. This study aims to fill this gap by providing a comprehensive analysis of prognostic models in HNC.

METHODS

Our systematic review and meta-analysis sourced data from PubMed, Embase, and Web of Science until August 30, 2023, shortlisting 16 studies. We concentrated on studies detailing HNC prognosis prediction through radiomics, which transparently tabulated performance metrics of c-index and utilized external validation sets. We excluded studies employing imaging techniques other than CT or MRI. Study quality was assessed using the QUIPS and RQS tools. Our meta-analysis comprised the radiomics prognosis model on all validation datasets, overall survival prediction with radiomics on all validation datasets, and overall survival prediction integrating clinical and radiomics data on external validation sets. All assessments adopted a random effects model. The research has been registered under CRD42023459049.

RESULTS

When evaluating by distinct endpoints, marked differences were observed. Delving deeper into the complexities of overall survival prediction, variables such as incorporation of clinical features and an enlarged training set were identified as major enhancers of the model's performance. Evaluating exclusively on external validation cohorts, purely clinical models demonstrated a prognostic strength of pooled 0.69 c-index for overall survival, in contrast to the 0.68 pooled c-index achieved by models rooted in radiomics. Combining both approaches elevated the pooled c-index to 0.76. It was clear that a blend of an expanded training dataset and features selected, coupled with the diversity in CT and MRI equipment and model counts, are pivotal in fortifying the model's resilience.

CONCLUSION

This systematic review and meta-analysis demonstrate that combining clinical and radiomic features significantly improves the predictive performance of prognostic models for overall survival in HNC. By systematically evaluating various endpoints and identifying key factors influencing model generalizability, our study fills a critical gap in the literature. These findings provide valuable insights for developing more accurate and personalized prognostic tools in HNC, guiding future research and enhancing clinical decision-making.

In vivo spatiotemporal mapping of proliferation activity in gliomas via water-exchange dynamic contrast-enhanced MRI

Proliferation activity mapping is crucial for the guidance of first biopsy and treatment evaluation of gliomas due to the highly heterogenous nature of glioma tumor. Here we propose and demonstrate an ease-of-use way of in vivo spatiotemporal mapping of proliferation activity by simply tracking transmembrane water dynamics with magnetic resonance imaging (MRI). Specifically, we demonstrated that proliferation activity can accelerate the transmembrane water transport in glioma cells. Method: The transmembrane water-efflux rate (k io) measured by water-exchange dynamic contrast-enhanced (DCE) MRI. Immunofluorescence, immunohistochemistry, and immunocytochemistry staining were used to validate results obtained from the in vivo imaging studies. Results: In glioma cell cultures, k io precisely followed the dynamic changes of proliferation activity in growth cycles and response to temozolomide (TMZ) treatment. In both animal glioma model and human glioma, k io linearly and strongly correlated with the spatial heterogeneity of intra-tumoral proliferation activity. More importantly, proliferation activity predicted by the single MRI parameter k io is much more accurate than those predicted by state-of-the-art methods using multimodal standard MRIs and advanced machine learning. Upregulated aquaporin 4 (AQP4) expression were observed in most proliferating glioma cells and the knockout of AQP4 could largely slow down proliferation activity, suggesting AQP4 is the potential molecule connecting MRI-k io with proliferation activity. Conclusion: This study provides an ease-of-use, accurate, and non-invasive imaging method for the spatiotemporal monitoring of proliferation activity in glioma.

Model Based on Ultrasound Radiomics and Machine Learning to Preoperative Differentiation of Follicular Thyroid Neoplasm

OBJECTIVES

To evaluate the value of radiomics based on ultrasonography in differentiating follicular thyroid carcinoma (FTC) and follicular thyroid adenoma (FTA) and construct a tool for preoperative noninvasive predicting FTC and FTA.

METHODS

The clinical data and ultrasound images of 389 patients diagnosed with FTC or FTA postoperatively were retrospectively analyzed at 3 institutions from January 2017 to December 2023. Patients in our hospital were randomly assigned in a 7:3 ratio to training cohort and validation cohort. External test cohort consisted of data collected from other 2 hospitals. Radiomics features were used to develop models based on different machine learning classifiers. A combined model was developed combining radiomics features with clinical characteristics and a nomogram was depicted. The performance of the models was assessed by area under the receiver operating characteristic curve (AUC), calibration curve and decision curve.

RESULTS

Radiomics model based on random forest showed best performance in discriminating FTC and FTA, with AUCs 0.880 (95% confidence interval [CI]: 0.8290-0.9308), 0.871 (95% CI: 0.7690-0.9734), and 0.821 (95% CI: 0.7036-0.9389) in training, validation, and test cohort, respectively. The combined model presented better efficacy comparing with clinical model and radiomics model, with AUCs 0.883 (95% CI: 0.8359-0.9295), 0.874 (95% CI: 0.7873-0.9615), and 0.876 (0.7809-0.9714) in training, validation, and test cohort, respectively. The calibration curves suggested good consistency and decision curves showed the highest overall clinical benefit for the combined model.

CONCLUSIONS

Ultrasound radiomics model based on random forest is feasible to differentiate FTC and FTA, and the combined model is an intuitively noninvasive tool for FTC and FTA preoperative identification.

Comparative analysis of machine learning models for predicting pathological complete response to neoadjuvant chemotherapy in breast cancer: An MRI radiomics approach

PURPOSE

The aim of this work is to compare different machine learning models for predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer using radiomics features from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).

METHOD

The study included 55 patients with breast cancer, among whom 18 achieved pCR and 37 did not respond completely to NAC (non-pCR). After some pre-processing steps, 1446 features were extracted and corrected for batch effects using ComBat. Five machine learning algorithms, namely random forest (RF), decision tree (DT), logistic regression (LR), k-nearest neighbors (k-NN), and extreme gradient boosting (XGB), were evaluated using area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and F1 score as classification metrics. A Leave-Group-Out cross validation (LGOCV) was applied in the outer loop.

RESULTS

RF and DT models exhibited the highest performances compared to the other algorithms. DT achieved an accuracy of 0.96 ± 0.07, and RF achieved 0.95 ± 0.05. The AUC values for RF and DT were 0.98 ± 0.06 and 0.94 ± 0.07, respectively. LR and k-NN demonstrated lower performance across all metrics, while XGB showed competitive results but slightly lower than RF and DT.

CONCLUSIONS

This study demonstrates the potential of radiomics and machine learning for predicting pCR to NAC in breast cancer. RF and DT models proved to be the most effective in capturing underlying patterns in radiomics data. Further research is required to validate and strengthen the proposed approach and explore its applicability in diverse radiomics datasets and clinical scenarios.

Rib suppression-based radiomics for diagnosis of neonatal respiratory distress syndrome in chest X-rays

This study aims to refine a radiomics-based diagnostic approach for detecting neonatal respiratory distress syndrome (NRDS) and examines the influence of rib suppression on the diagnostic precision of radiomics models using neonatal chest X-ray (CXR) images. A total of 138 CXR images were collected in this study. The data was partitioned into training and validation subsets based on chronological order. We applied rib suppression to the CXR images and extracted and analyzed radiomic features from lung regions both before and after rib suppression. This approach was designed to identify NRDS, develop radiomics models, and assess the impact of rib suppression on model performance. To establish these radiomics models, six machine learning models were utilized in the study. The performance was evaluated using the area under the receiver operating characteristic curve (AUC). On the validation set, the models demonstrated significant improvements after rib suppression. Specifically, the Gradient Boosting Machine (GBM) achieved an AUC of 0.781 post-suppression compared to 0.556 pre-suppression. Notably, Linear Discriminant Analysis (LDA) and Logistic Regression (LR) performed particularly well when combining features from both scenarios, achieving AUCs of 0.762 and 0.756. The results indicate the feasibility of developing radiomics models for diagnosing NRDS and highlight the enhancement in model performance due to rib suppression. This study provides a promising new method for the imaging diagnosis and prognosis evaluation of neonatal respiratory distress syndrome, showcasing the potential of radiomics in pediatric imaging.

Ultrasound-based radiomics and clinical factors-based nomogram for early intracranial hypertension detection in patients with decompressive craniotomy

Objective

This study aims to develop and validate a nomogram that combines traditional ultrasound radiomics features with clinical parameters to assess early intracranial hypertension (IH) following primary decompressive craniectomy (DC) in patients with severe traumatic brain injury (TBI). The study incorporates the Shapley Additive Explanations (SHAP) method to interpret the radiomics model.

Methods

This study included 199 patients with severe TBI (training cohort: n = 159; testing cohort: n = 40). Postoperative ultrasound images of the optic nerve sheath (ONS) were obtained at 6 and 18 h after DC. Based on invasive intracranial pressure (ICPi) measurements, patients were grouped according to threshold values of 15 mmHg and 20 mmHg. Radiomics features were extracted from ONS images, and feature selection methods were applied to construct predictive models using logistic regression (LR), support vector machine (SVM), random forest (RF), and K-Nearest Neighbors (KNN). Clinical-ultrasound variables were incorporated into the model through univariate and multivariate logistic regression. A combined nomogram was developed by integrating radiomics features with clinical-ultrasound variables, and its diagnostic performance was evaluated using Receiver Operating Characteristic (ROC) curve analysis and decision curve analysis (DCA). The SHAP method was adopted to explain the prediction models.

Results

Among the machine learning models, the LR model demonstrated superior predictive efficiency and robustness at threshold values of 15 mmHg and 20 mmHg. At a threshold of 20 mmHg, the AUC values for the training and testing cohorts were 0.803 and 0.735 for the clinical model, 0.908 and 0.891 for the radiomics model, and 0.918 and 0.902 for the nomogram model, respectively. Similarly, at a threshold of 15 mmHg, the AUC values were consistent across models: 0.803 and 0.735 for the clinical model, 0.908 and 0.891 for the radiomics model, and 0.918 and 0.902 for the nomogram model. Notably, the nomogram model outperformed the clinical model. Decision curve analysis (DCA) further confirmed a higher net benefit for predicting intracranial hypertension across all models.

Conclusion

The nomogram model, which integrates both clinical-semantic and radiomics features, demonstrated strong performance in predicting intracranial hypertension across different threshold values. It shows promise for enhancing non-invasive ICP monitoring and supporting individualized therapeutic strategies.

Clinical impact of an explainable machine learning with amino acid PET imaging: application to the diagnosis of aggressive glioma

PURPOSE

Radiomics-based machine learning (ML) models of amino acid positron emission tomography (PET) images have shown efficiency in glioma prediction tasks. However, their clinical impact on physician interpretation remains limited. This study investigated whether an explainable radiomics model modifies nuclear physicians' assessment of glioma aggressiveness at diagnosis.

METHODS

Patients underwent dynamic 6-[18F]fluoro-L-DOPA PET acquisition. With a 75%/25% split for training (n = 63) and test sets (n = 22), an ensemble ML model was trained using radiomics features extracted from static/dynamic parametric PET images to classify lesion aggressiveness. Three explainable ML methods-Local Interpretable Model-agnostic Explanations (LIME), Anchor, and SHapley Additive exPlanations (SHAP)-generated patient-specific explanations. Eighteen physicians from eight institutions evaluated the test samples. During the first phase, physicians analyzed the 22 cases exclusively through magnetic resonance and static/dynamic PET images, acquired within a maximum interval of 30 days. In the second phase, the same physicians reevaluated the same cases (n = 22), using all available data, including the radiomics model predictions and explanations.

RESULTS

Eighty-five patients (54[39-62] years old, 41 women) were selected. In the second phase, physicians demonstrated a significant improvement in diagnostic accuracy compared to the first phase (0.775 [0.750-0.802] vs. 0.717 [0.694-0.737], p = 0.007). The explainable radiomics model augmented physician agreement, with a 22.72% increase in Fleiss's kappa, and significantly enhanced physician confidence (p < 0.001). Among all physicians, Anchor and SHAP showed efficacy in 75% and 72% of cases, respectively, outperforming LIME (p ≤ 0.001).

CONCLUSIONS

Our results highlight the potential of an explainable radiomics model using amino acid PET scans as a diagnostic support to assist physicians in identifying glioma aggressiveness.

Texture analysis combined with machine learning in radiographs of the knee joint: potential to identify tibial plateau occult fractures

Background

Missed or delayed diagnosis of occult fractures of tibial plateau may cause adverse effects on patients. The objective of this study was to evaluate the diagnostic performance of texture analysis (TA) of knee joint radiographs combined with machine learning (ML) in identifying patients at risk of tibial plateau occult fractures.

Methods

A total of 169 patients with negative fracture on knee X-ray films from 2018 to 2022 who were diagnosed with occult tibial plateau fractures or no fractures by subsequent magnetic resonance imaging (MRI) examination were retrospectively enrolled. The X-ray images of the patient's knee joint were used for texture feature extraction. A total of 9 ML feature selection methods (including 6 mainstream methods and 3 methods provided by MaZda software) combined with 3 classification methods were used to build the best diagnostic model. The performance of each model was evaluated by accuracy, F1-value, and area under the curve (AUC).

Results

The least absolute shrinkage and selection operator (LASSO) method had the best performance of the 6 mainstream methods, with an accuracy of 0.81, an F1 value of 0.80, and an AUC of 0.920, all of which were higher than those of the other five methods (accuracy range: 0.65-0.80, F1 score range: 0.61-0.79, AUC range: 0.722-0.895). Among the three feature selection models in MaZda software, the most ideal method for accuracy measurement was the MI method, reaching 0.77. In the measurement of the F1 value and AUC, MaZda's best method was Fisher, reaching 0.78 and 0.888, respectively. All indicators were lower than those of the LASSO method. The combination of LASSO and support vector machine (SVM) yielded the best classification performance, while the performance of the combination of LASSO and logistic regression was slightly inferior, but the difference was not statistically significant.

Conclusions

TA of knee joint radiography combined with ML has achieved high performance in identifying patients at risk of occult fractures of the tibial plateau. Considering both the model performance and computational complexity, the LASSO feature selection method combined with the logistic regression classifier yielded the best classification performance in this process.

From images to clinical insights: an educational review on radiomics in lung diseases

Radiological imaging is a cornerstone in the clinical workup of lung diseases. Radiomics represents a significant advancement in clinical lung imaging, offering a powerful tool to complement traditional qualitative image analysis. Radiomic features are quantitative and computationally describe shape, intensity, texture and wavelet characteristics from medical images that can uncover detailed and often subtle information that goes beyond the visual capabilities of radiological examiners. By extracting this quantitative information, radiomics can provide deep insights into the pathophysiology of lung diseases and support clinical decision-making as well as personalised medicine approaches. In this educational review, we provide a step-by-step guide to radiomics-based medical image analysis, discussing the technical challenges and pitfalls, and outline the potential clinical applications of radiomics in diagnosing, prognosticating and evaluating treatment responses in respiratory medicine.

Dual biomarkers CT-based deep learning model incorporating intrathoracic fat for discriminating benign and malignant pulmonary nodules in multi-center cohorts

BACKGROUND

Recent studies in the field of lung cancer have emphasized the important role of body composition, particularly fatty tissue, as a prognostic factor. However, there is still a lack of practice in combining fatty tissue to discriminate benign and malignant pulmonary nodules.

PURPOSE

This study proposes a deep learning (DL) approach to explore the potential predictive value of dual imaging markers, including intrathoracic fat (ITF), in patients with pulmonary nodules.

METHODS

We enrolled 1321 patients with pulmonary nodules from three centers. Image feature extraction was performed on computed tomography (CT) images of pulmonary nodules and ITF by DL, multimodal information was used to discriminate benign and malignant in patients with pulmonary nodules.

RESULTS

Here, the areas under the receiver operating characteristic curve (AUC) of the model for ITF combined with pulmonary nodules were 0.910(95 % confidence interval [CI]: 0.870-0.950, P = 0.016), 0.922(95 % CI: 0.883-0.960, P = 0.037) and 0.899(95 % CI: 0.849-0.949, P = 0.033) in the internal test cohort, external test cohort1 and external test cohort2, respectively, which were significantly better than the model for pulmonary nodules. Intrathoracic fat index (ITFI) emerged as an independent influencing factor for benign and malignant in patients with pulmonary nodules, correlating with a 9.4 % decrease in the risk of malignancy for each additional unit.

CONCLUSION

This study demonstrates the potential auxiliary predictive value of ITF as a noninvasive imaging biomarker in assessing pulmonary nodules.

US-based Radiomics Analysis of Different Machine Learning Models for Differentiating Benign and Malignant BI-RADS 4A Breast Lesions

RATIONALE AND OBJECTIVES

To investigate and authenticate the effectiveness of various radiomics models in distinguishing between benign and malignant BI-RADS 4A lesions.

METHODS

A total of 936 patients with pathologically confirmed 4A lesions were included in the study (training cohort: n = 655; test cohort: n = 281). Radiomic features were derived from greyscale US images. Following dimensionality reduction and feature selection, radiomics models were developed using logistic regression (LR), support vector machine (SVM), random forest (RF), eXtreme gradient boosting (XGBoost) and multilayer perceptron (MLP) algorithms. Univariate and multivariable logistic regression analyses were employed to investigate clinical-radiological characteristics and determine variables for creating a clinical model. Five combined models integrating radiomic and clinical parameters were constructed by using each algorithm, and comparison with radiologists' performance was performed. SHapley Additive exPlanations (SHAP) approach was used to elucidate the radiomic model by ranking the significance of features based on their contribution to the evaluation.

RESULTS

A total of 1561 radiomic features were extracted. Thirty-six features were deemed significant by dimensionality reduction and selection. The radiomic models showed good performance with AUCs of 0.829-0.945 in training cohort; and 0.805-0.857 in test cohort. The combined model developed by using LR showed the best performance (AUC, training cohort: 0.909; test cohort: 0.905), which is superior to radiologists' performance. Decision curve analysis (DCA) of this combined model indicated better clinical efficacy than clinical and radiomic models.

CONCLUSIONS

The combined model integrating radiomic and clinical features demonstrated excellent performance in differentiating between benign and malignant 4A lesions. It may offer a non-invasive and efficient approach to aid in clinical decision-making.

Developing a novel dosiomics model to predict treatment failures following lung stereotactic body radiation therapy

Purpose

The purpose of this study was to investigate the dosiomics features of the interplay between CT density and dose distribution in lung SBRT plans, and to develop a model to predict treatment failure following lung SBRT treatment.

Methods

A retrospective study was conducted involving 179 lung cancer patients treated with SBRT at the University of Nebraska Medical Center (UNMC) between October 2007 and June 2022. Features from the CT image, Biological Effective Dose (BED) and five interaction matrices between CT and BED were extracted using radiomics mathematics. Our in-house feature selection pipeline was utilized to evaluate and rank features based on their importance and redundancy, with only the selected non-redundant features being used for predictive modeling. We randomly selected 151 cases and 28 cases as training and test datasets. Four different models were trained utilizing the Balanced Random Forest framework on the same training dataset to differentiate between failure and non-failure cases. These four models utilized the same number of selected features extracted from CT-only, BED-only, a combination of CT and BED, and a composite of CT and BED including their interaction matrices, respectively.

Results

The cohort included 125 non-failure cases and 54 failure cases, with a median follow-up time of 34.4 months. We selected the top 17 important and non-redundant features (with the Pearsons's coefficient < 0.5) in each model. When evaluated on the same independent test set, the four models-CT features-only, BED features-only, a combination of CT and BED features, and a composite model including features from CT and BED that includes their interaction matrices-achieved AUC values of 0.56, 0.75, 0.73, and 0.82, respectively, with corresponding accuracies of 0.61, 0.79, 0.71, and 0.79. The composite model demonstrated the highest AUC and accuracy, indicating that incorporating interactions between CT and BED reveals more predictive capabilities in distinguishing between failure and non-failure cases.

Conclusion

The dosiomics model integrating the interaction between CT and Dose can effectively predict treatment failure following lung SBRT treatment and may serve as a useful tool to proactively evaluate and select lung SBRT treatment plans to reduce treatment failure in the future.

Radiomics based Machine Learning Models for Classification of Prostate Cancer Grade Groups from Multi Parametric MRI Images

Purpose

This study aimed to investigate the performance of multiparametric magnetic resonance imaging (mpMRI) radiomic feature-based machine learning (ML) models in classifying the Gleason grade group (GG) of prostate cancer.

Methods

In this retrospective study, a total of 203 patients with histopathologically confirmed prostate cancer who underwent mpMRI before prostate biopsy were included. After manual segmentation, radiomic features (RFs) were extracted from T2-weighted, apparent diffusion coefficient, and high b-value diffusion-weighted magnetic resonance imaging (DWMRI). Patients were split into training sets and testing sets according to a ratio of 8:2. A pipeline considering combinations of two feature selection (FS) methods and six ML classifiers was developed and evaluated. The performance of models was assessed using the accuracy, sensitivity, precision, F1-measure, and the area under curve (AUC).

Results

On high b-value DWMRI-derived features, a combination of FS method recursive feature elimination (RFE) and classifier random forest achieved the highest performance for classification of prostate cancer into five GGs, with 97.0% accuracy, 98.0% sensitivity, 98.0% precision, and 97.0% F1-measure. The method also achieved an average AUC for GG of 98%.

Conclusion

Preoperative mpMRI radiomic analysis based on ML, as a noninvasive approach, showed good performance for classification of prostate cancer into five GGs.

Advances in Knowledge

Herein, radiomic models based on preoperative mpMRI and ML were developed to classify prostate cancer into 5 GGs. Our study provides evidence that analysis of quantitative RFs extracted from high b-value DWMRI images based on a combination of FS method RFE and classifier random forest can be applied for multiclass grading of prostate cancer with an accuracy of 97.0%.

Comparison prediction models of bladder toxicity based on radiomic features of CT and MRI in patients with prostate cancer undergoing radiotherapy

PURPOSE

This study aimed to assess the radiomic features of computed tomography (CT) and magnetic resonance imaging (MRI) of the bladder wall before radiotherapy using machine learning (ML) methods to predict bladder radiotoxicity in patients with prostate cancer.

METHODS

This study enrolled 70 patients with pathologically confirmed prostate cancer who were candidates for radiation therapy (RT). CT and MRI of the bladder wall before radiotherapy were used to extract radiomic features. The least absolute shrinkage and selection operator (LASSO) was used for feature selection. Algorithms such as Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), and K-Nearest Neighbors (KNN) have been used to develop models based on radiomic, dosimetry, and clinical parameters. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve and accuracy were used to analyze the predictive power of all models.

RESULTS

The RF and LR models based on the radiomic features of MRI and clinical/dosimetry parameters with an AUC of 0.95 and 0.93, and an accuracy of 86% and 86%, respectively, had the highest performance in the prediction of bladder radiation toxicity.

CONCLUSIONS

This study showed that, firstly, CT and MRI radiomic features of the bladder wall before treatment could be used to predict bladder radiotoxicity. Second, MRI is better than CT in predicting bladder toxicity caused by radiation. And thirdly, the performance of the predictive models based on the combination of radiomic, clinical, and dosimetry characteristics was improved.

Breast MRI radiomics and machine learning-based predictions of response to neoadjuvant chemotherapy - How are they affected by variations in tumor delineation?

Manual delineation of volumes of interest (VOIs) by experts is considered the gold-standard method in radiomics analysis. However, it suffers from inter- and intra-operator variability. A quantitative assessment of the impact of variations in these delineations on the performance of the radiomics predictors is required to develop robust radiomics based prediction models. In this study, we developed radiomics models for the prediction of pathological complete response to neoadjuvant chemotherapy in patients with two different breast cancer subtypes based on contrast-enhanced magnetic resonance imaging acquired prior to treatment (baseline MRI scans). Different mathematical operations such as erosion, smoothing, dilation, randomization, and ellipse fitting were applied to the original VOIs delineated by experts to simulate variations of segmentation masks. The effects of such VOI modifications on various steps of the radiomics workflow, including feature extraction, feature selection, and prediction performance, were evaluated. Using manual tumor VOIs and radiomics features extracted from baseline MRI scans, an AUC of up to 0.96 and 0.89 was achieved for human epidermal growth receptor 2 positive and triple-negative breast cancer, respectively. For smoothing and erosion, VOIs yielded the highest number of robust features and the best prediction performance, while ellipse fitting and dilation lead to the lowest robustness and prediction performance for both breast cancer subtypes. At most 28% of the selected features were similar to manual VOIs when different VOI delineation data were used. Differences in VOI delineation affect different steps of radiomics analysis, and their quantification is therefore important for development of standardized radiomics research.

Lung nodule classification using radiomics model trained on degraded SDCT images

BACKGROUND AND OBJECTIVE

Low-dose computed tomography (LDCT) screening has shown promise in reducing lung cancer mortality; however, it suffers from high false positive rates and a scarcity of available annotated datasets. To overcome these challenges, we propose a novel approach using synthetic LDCT images generated from standard-dose CT (SDCT) scans from the LIDC-IDRI dataset. Our objective is to develop and validate an interpretable radiomics-based model for distinguishing likely benign from likely malignant pulmonary nodules.

METHODS

From a total of 1010 CT images (695 SDCTs and 315 LDCTs), we degraded SDCTs in the sinogram domain and obtained 1950 nodules as the training set. The 675 nodules from the LDCTs were stratified into 50%-50% partitions for validation and testing. Radiomic features were extracted from nodules, and three feature sets were assessed using: a) only shape and size (SS) features, b) all features but SS features, and c) all features. A systematic pipeline was developed to optimize the feature set and evaluate multiple machine learning models. Models were trained using degraded SDCT, validated and tested on the LDCT nodules.

RESULTS

Training a logistic regression model using three SS features yielded the most promising results, achieving on the test set mean balanced accuracy, sensitivity, specificity, and AUC-ROC scores of 0.81, 0.76, 0.85, and 0.87, respectively.

CONCLUSIONS

Our study demonstrates the feasibility and effectiveness of using synthetic LDCT images for developing a relatively accurate radiomics-based model in lung nodule classification. This approach addresses challenges associated with LDCT screening, offering potential implications for improving lung cancer detection and reducing false positives.

Computational analysis of variability and uncertainty in the clinical reference on magnetic resonance imaging radiomics: modelling and performance

To conduct a computational investigation to explore the influence of clinical reference uncertainty on magnetic resonance imaging (MRI) radiomics feature selection, modelling, and performance. This study used two sets of publicly available prostate cancer MRI = radiomics data (Dataset 1: n = 260; Dataset 2: n = 100) with Gleason score clinical references. Each dataset was divided into training and holdout testing datasets at a ratio of 7:3 and analysed independently. The clinical references of the training set were permuted at different levels (increments of 5%) and repeated 20 times. Four feature selection algorithms and two classifiers were used to construct the models. Cross-validation was employed for training, while a separate hold-out testing set was used for evaluation. The Jaccard similarity coefficient was used to evaluate feature selection, while the area under the curve (AUC) and accuracy were used to assess model performance. An analysis of variance test with Bonferroni correction was conducted to compare the metrics of each model. The consistency of the feature selection performance decreased substantially with the clinical reference permutation. AUCs of the trained models with permutation particularly after 20% were significantly lower (Dataset 1 (with ≥ 20% permutation): 0.67, and Dataset 2 (≥ 20% permutation): 0.74), compared to the AUC of models without permutation (Dataset 1: 0.94, Dataset 2: 0.97). The performances of the models were also associated with larger uncertainties and an increasing number of permuted clinical references. Clinical reference uncertainty can substantially influence MRI radiomic feature selection and modelling. The high accuracy of clinical references should be helpful in building reliable and robust radiomic models. Careful interpretation of the model performance is necessary, particularly for high-dimensional data.

Image biomarkers and explainable AI: handcrafted features versus deep learned features

Feature extraction and selection from medical data are the basis of radiomics and image biomarker discovery for various architectures, including convolutional neural networks (CNNs). We herein describe the typical radiomics steps and the components of a CNN for both deep feature extraction and end-to-end approaches. We discuss the curse of dimensionality, along with dimensionality reduction techniques. Despite the outstanding performance of deep learning (DL) approaches, the use of handcrafted features instead of deep learned features needs to be considered for each specific study. Dataset size is a key factor: large-scale datasets with low sample diversity could lead to overfitting; limited sample sizes can provide unstable models. The dataset must be representative of all the "facets" of the clinical phenomenon/disease investigated. The access to high-performance computational resources from graphics processing units is another key factor, especially for the training phase of deep architectures. The advantages of multi-institutional federated/collaborative learning are described. When large language models are used, high stability is needed to avoid catastrophic forgetting in complex domain-specific tasks. We highlight that non-DL approaches provide model explainability superior to that provided by DL approaches. To implement explainability, the need for explainable AI arises, also through post hoc mechanisms. RELEVANCE STATEMENT: This work aims to provide the key concepts for processing the imaging features to extract reliable and robust image biomarkers. KEY POINTS: The key concepts for processing the imaging features to extract reliable and robust image biomarkers are provided. The main differences between radiomics and representation learning approaches are highlighted. The advantages and disadvantages of handcrafted versus learned features are given without losing sight of the clinical purpose of artificial intelligence models.

Bibliometric and visual analysis of radiomics for evaluating lymph node status in oncology

Background

Radiomics, which involves the conversion of digital images into high-dimensional data, has been used in oncological studies since 2012. We analyzed the publications that had been conducted on this subject using bibliometric and visual methods to expound the hotpots and future trends regarding radiomics in evaluating lymph node status in oncology.

Methods

Documents published between 2012 and 2023, updated to August 1, 2024, were searched using the Scopus database. VOSviewer, R Package, and Microsoft Excel were used for visualization.

Results

A total of 898 original articles and reviews written in English and be related to radiomics for evaluating lymph node status in oncology, published between 2015 and 2023, were retrieved. A significant increase in the number of publications was observed, with an annual growth rate of 100.77%. The publications predominantly originated from three countries, with China leading in the number of publications and citations. Fudan University was the most contributing affiliation, followed by Sun Yat-sen University and Southern Medical University, all of which were from China. Tian J. from the Chinese Academy of Sciences contributed the most within 5885 authors. In addition, Frontiers in Oncology had the most publications and transcended other journals in recent 4 years. Moreover, the keywords co-occurrence suggested that the interplay of "radiomics" and "lymph node metastasis," as well as "major clinical study" were the predominant topics, furthermore, the focused topics shifted from revealing the diagnosis of cancers to exploring the deep learning-based prediction of lymph node metastasis, suggesting the combination of artificial intelligence research would develop in the future.

Conclusion

The present bibliometric and visual analysis described an approximately continuous trend of increasing publications related to radiomics in evaluating lymph node status in oncology and revealed that it could serve as an efficient tool for personalized diagnosis and treatment guidance in clinical patients, and combined artificial intelligence should be further considered in the future.

Adrenal indeterminate nodules: CT-based radiomics analysis of different machine learning models for predicting adrenal metastases in lung cancer patients

Objective

There is a paucity of research using different machine learning algorithms for distinguishing between adrenal metastases and benign tumors in lung cancer patients with adrenal indeterminate nodules based on plain and biphasic-enhanced CT radiomics.

Materials and Methods

This study retrospectively enrolled 292 lung cancer patients with adrenal indeterminate nodules (training dataset, 205 (benign, 96; metastases, 109); testing dataset, 87 (benign, 42; metastases, 45)). Radiomics features were extracted from the plain, arterial, and portal CT images, respectively. The independent risk radiomics features selected by least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression (LR) were used to construct the single-phase and combined-phase radiomics models, respectively, by support vector machine (SVM), decision tree (DT), random forest (RF), and LR. The independent clinical-pathological and radiological risk factors for predicting adrenal metastases selected by using univariate and multivariate LR were used to develop the traditional model. The optimal model was selected by ROC curve, and the models' clinical values were estimated by decision curve analysis (DCA).

Results

In the testing dataset, all SVM radiomics models showed the best robustness and efficiency, and then RF, LR, and DT models. The combined radiomics model had the best ability in predicting adrenal metastases (AUC=0.938), and then the plain (AUC=0.935), arterial (AUC=0.870), and portal radiomics model (AUC=0.851). Besides, compared to clinical-pathological-radiological model (AUC=0.870), the discriminatory capability of the plain and combined radiomics model were further improved. All radiomics models had good calibration curves and DCA showed the plain and combined radiomics models had more optimal clinical efficacy compared to other models, with the combined radiomics model having the largest net benefit.

Conclusions

The combined SVM radiomics model can non-invasively and efficiently predict adrenal metastatic nodules in lung cancer patients. In addition, the plain radiomics model with high predictive performance provides a convenient and accurate new method for patients with contraindications in enhanced CT.

Computed tomography enterography radiomics and machine learning for identification of Crohn's disease

BACKGROUND

Crohn's disease is a severe chronic and relapsing inflammatory bowel disease. Although contrast-enhanced computed tomography enterography is commonly used to evaluate crohn's disease, its imaging findings are often nonspecific and can overlap with other bowel diseases. Recent studies have explored the application of radiomics-based machine learning algorithms to aid in the diagnosis of medical images. This study aims to develop a non-invasive method for detecting bowel lesions associated with Crohn's disease using CT enterography radiomics and machine learning algorithms.

METHODS

A total of 139 patients with pathologically confirmed Crohn's disease were retrospectively enrolled in this study. Radiomics features were extracted from both arterial- and venous-phase CT enterography images, representing both bowel lesions with Crohn's disease and segments of normal bowel. A machine learning classification system was constructed by combining six selected radiomics features with eight classification algorithms. The models were trained using leave-one-out cross-validation and evaluated for accuracy.

RESULTS

The classification model demonstrated robust performance and high accuracy, with an area under the curve of 0.938 and 0.961 for the arterial- and venous-phase images, respectively. The model achieved an accuracy of 0.938 for arterial-phase images and 0.961 for venous-phase images.

CONCLUSIONS

This study successfully identified a radiomics machine learning method that effectively differentiates Crohn's disease bowel lesions from normal bowel segments. Further studies with larger sample sizes and external cohorts are needed to validate these findings.

Optimizing radiomics for prostate cancer diagnosis: feature selection strategies, machine learning classifiers, and MRI sequences

OBJECTIVES

Radiomics-based analyses encompass multiple steps, leading to ambiguity regarding the optimal approaches for enhancing model performance. This study compares the effect of several feature selection methods, machine learning (ML) classifiers, and sources of radiomic features, on models' performance for the diagnosis of clinically significant prostate cancer (csPCa) from bi-parametric MRI.

METHODS

Two multi-centric datasets, with 465 and 204 patients each, were used to extract 1246 radiomic features per patient and MRI sequence. Ten feature selection methods, such as Boruta, mRMRe, ReliefF, recursive feature elimination (RFE), random forest (RF) variable importance, L1-lasso, etc., four ML classifiers, namely SVM, RF, LASSO, and boosted generalized linear model (GLM), and three sets of radiomics features, derived from T2w images, ADC maps, and their combination, were used to develop predictive models of csPCa. Their performance was evaluated in a nested cross-validation and externally, using seven performance metrics.

RESULTS

In total, 480 models were developed. In nested cross-validation, the best model combined Boruta with Boosted GLM (AUC = 0.71, F1 = 0.76). In external validation, the best model combined L1-lasso with boosted GLM (AUC = 0.71, F1 = 0.47). Overall, Boruta, RFE, L1-lasso, and RF variable importance were the top-performing feature selection methods, while the choice of ML classifier didn't significantly affect the results. The ADC-derived features showed the highest discriminatory power with T2w-derived features being less informative, while their combination did not lead to improved performance.

CONCLUSION

The choice of feature selection method and the source of radiomic features have a profound effect on the models' performance for csPCa diagnosis.

CRITICAL RELEVANCE STATEMENT

This work may guide future radiomic research, paving the way for the development of more effective and reliable radiomic models; not only for advancing prostate cancer diagnostic strategies, but also for informing broader applications of radiomics in different medical contexts.

KEY POINTS

Radiomics is a growing field that can still be optimized. Feature selection method impacts radiomics models' performance more than ML algorithms. Best feature selection methods: RFE, LASSO, RF, and Boruta. ADC-derived radiomic features yield more robust models compared to T2w-derived radiomic features.

Radiomics for differentiation of somatic BAP1 mutation on CT scans of patients with pleural mesothelioma

Purpose

The BRCA1-associated protein 1 (BAP1) gene is of great interest because somatic (BAP1) mutations are the most common alteration associated with pleural mesothelioma (PM). Further, germline mutation of the BAP1 gene has been linked to the development of PM. This study aimed to explore the potential of radiomics on computed tomography scans to identify somatic BAP1 gene mutations and assess the feasibility of radiomics in future research in identifying germline mutations.

Approach

A cohort of 149 patients with PM and known somatic BAP1 mutation status was collected, and a previously published deep learning model was used to first automatically segment the tumor, followed by radiologist modifications. Image preprocessing was performed, and texture features were extracted from the segmented tumor regions. The top features were selected and used to train 18 separate machine learning models using leave-one-out cross-validation (LOOCV). The performance of the models in distinguishing between BAP1-mutated (BAP1+) and BAP1 wild-type (BAP1-) tumors was evaluated using the receiver operating characteristic area under the curve (ROC AUC).

Results

A decision tree classifier achieved the highest overall AUC value of 0.69 (95% confidence interval: 0.60 and 0.77). The features selected most frequently through the LOOCV were all second-order (gray-level co-occurrence or gray-level size zone matrices) and were extracted from images with an applied transformation.

Conclusions

This proof-of-concept work demonstrated the potential of radiomics to differentiate among BAP1+/- in patients with PM. Future work will extend these methods to the assessment of germline BAP1 mutation status through image analysis for improved patient prognostication.

Radiomics As Biomarkers for the Treatment of Non-small Cell Lung Cancer With Stereotactic Body Radiation Therapy: A Review of Concepts

Stereotactic body radiation therapy (SBRT) is currently the alternative for inoperable early-stage and oligometastatic non-small cell lung cancer (NSCLC) patients. While most patients are good responders among this specific group, some patients do not experience the benefits of this treatment. Even though physicians use clinical variables and semantic radiological features to make treatment decisions, medical images contain a wealth of personalized pathophysiological information that can be extracted and used for clinical decision support systems. In the form of radiomics features, details unique to each patient's medical scans can be utilized to create predictive models and to identify biomarking signatures. Then, these tools and indices can predict treatment outcomes and categorize patients to the most optimal treatment regimen. A conceptual review of relevant topics centered around the identification and development of radiomic-based biomarkers for SBRT-treated NSCLC was conducted. To begin with, an overview of the nature and management of non-small cell lung cancer was provided. To continue, biomarkers were defined in the context of cancer care. Then, the uses of stereotactic body radiation therapy in the treatment of NSCLC were further explained. Finally, the study of radiomics was discussed, and the uses and limitations of radiomic features and ML for SBRT-treated NSCLC were expanded upon. Radiomics-based biomarkers and predictive algorithmic models can potentially improve the SBRT treatment of early-stage and oligometastatic NSCLC by providing personalized support systems to healthcare professionals. While many institutions are attempting to optimize their biomarkers and AI-based tools for clinical use, additional prospective studies are needed to properly ensure their efficacy. As such, the improvements made in the field of personalized medicine are promising.

radMLBench: A dataset collection for benchmarking in radiomics

BACKGROUND

New machine learning methods and techniques are frequently introduced in radiomics, but they are often tested on a single dataset, which makes it challenging to assess their true benefit. Currently, there is a lack of a larger, publicly accessible dataset collection on which such assessments could be performed. In this study, a collection of radiomics datasets with binary outcomes in tabular form was curated to allow benchmarking of machine learning methods and techniques.

METHODS

A variety of journals and online sources were searched to identify tabular radiomics data with binary outcomes, which were then compiled into a homogeneous data collection that is easily accessible via Python. To illustrate the utility of the dataset collection, it was applied to investigate whether feature decorrelation prior to feature selection could improve predictive performance in a radiomics pipeline.

RESULTS

A total of 50 radiomic datasets were collected, with sample sizes ranging from 51 to 969 and 101 to 11165 features. Using this data, it was observed that decorrelating features did not yield any significant improvement on average.

CONCLUSIONS

A large collection of datasets, easily accessible via Python, suitable for benchmarking and evaluating new machine learning techniques and methods was curated. Its utility was exemplified by demonstrating that feature decorrelation prior to feature selection does not, on average, lead to significant performance gains and could be omitted, thereby increasing the robustness and reliability of the radiomics pipeline.

Radiomics approach for identifying radiation-induced normal tissue toxicity in the lung

The rapidly evolving field of radiomics has shown that radiomic features are able to capture characteristics of both tumor and normal tissue that can be used to make accurate and clinically relevant predictions. In the present study we sought to determine if radiomic features can characterize the adverse effects caused by normal tissue injury as well as identify if human embryonic stem cell (hESC) derived extracellular vesicle (EV) treatment can resolve certain adverse complications. A cohort of 72 mice (n = 12 per treatment group) were exposed to X-ray radiation to the whole lung (3 × 8 Gy) or to the apex of the right lung (3 × 12 Gy), immediately followed by retro-orbital injection of EVs. Cone-Beam Computed Tomography images were acquired before and 2 weeks after treatment. In total, 851 radiomic features were extracted from the whole lungs and < 20 features were selected to train and validate a series of random forest classification models trained to predict radiation status, EV status and treatment group. It was found that all three classification models achieved significantly high prediction accuracies on a validation subset of the dataset (AUCs of 0.91, 0.86 and 0.80 respectively). In the locally irradiated lung, a significant difference between irradiated and unirradiated groups as well as an EV sparing effect were observed in several radiomic features that were not seen in the unirradiated lung (including wavelet-LLH Kurtosis, wavelet HLL Large Area High Gray Level Emphasis, and Gray Level Non-Uniformity). Additionally, a radiation difference was not observed in a secondary comparison cohort, but there was no impact of imaging machine parameters on the radiomic signature of unirradiated mice. Our data demonstrate that radiomics has the potential to identify radiation-induced lung injury and could be applied to predict therapeutic efficacy at early timepoints.

A Hybrid CNN-Transformer Model for Predicting N Staging and Survival in Non-Small Cell Lung Cancer Patients Based on CT-Scan

Accurate assessment of N staging in patients with non-small cell lung cancer (NSCLC) is critical for the development of effective treatment plans, the optimization of therapeutic strategies, and the enhancement of patient survival rates. This study proposes a hybrid model based on 3D convolutional neural networks (CNNs) and transformers for predicting the N-staging and survival rates of NSCLC patients within the NSCLC radiogenomics and Nsclc-radiomics datasets. The model achieved accuracies of 0.805, 0.828, and 0.819 for the training, validation, and testing sets, respectively. By leveraging the strengths of CNNs in local feature extraction and the superior performance of transformers in global information modeling, the model significantly enhances predictive accuracy and efficacy. A comparative analysis with traditional CNN and transformer architectures demonstrates that the CNN-transformer hybrid model outperforms N-staging predictions. Furthermore, this study extracts the one-year survival rate as a feature and employs the Lasso-Cox model for survival predictions at various time intervals (1, 3, 5, and 7 years), with all survival prediction p-values being less than 0.05, illustrating the time-dependent nature of survival analysis. The application of time-dependent ROC curves further validates the model's accuracy and reliability for survival predictions. Overall, this research provides innovative methodologies and new insights for the early diagnosis and prognostic evaluation of NSCLC.

Radiomics in Diagnosis, Grading, and Treatment Response Assessment of Soft Tissue Sarcomas: A Systematic Review and Meta-analysis

RATIONALE AND OBJECTIVES

To evaluate radiomics in soft tissue sarcomas (STSs) for diagnostic accuracy, grading, and treatment response assessment, with a focus on clinical relevance.

METHODS

In this diagnostic accuracy study, radiomics was applied using multiple MRI sequences and AI classifiers, with histopathological diagnosis as the reference standard. Statistical analysis involved meta-analysis, random-effects model, and Deeks' funnel plot asymmetry test.

RESULTS

Among 579 unique titles and abstracts, 24 articles were included in the systematic review, with 21 used for meta-analysis. Radiomics demonstrated a pooled sensitivity of 84% (95% CI: 80-87) and specificity of 63% (95% CI: 56-70), AUC of 0.93 for diagnosis, sensitivity of 84% (95% CI: 82-87) and specificity of 73% (95% CI: 68-77), AUC of 0.91 for grading, and sensitivity of 83% (95% CI: 67-94) and specificity of 67% (95% CI: 59-74), AUC of 0.87 for treatment response assessment.

CONCLUSION

Radiomics exhibits potential for accurate diagnosis, grading, and treatment response assessment in STSs, emphasizing the need for standardization and prospective trials.

CLINICAL RELEVANCE STATEMENT

Radiomics offers precise tools for STS diagnosis, grading, and treatment response assessment, with implications for optimizing patient care and treatment strategies in this complex malignancy.

Radiomic Features at Contrast-Enhanced CT Predict Virus-Driven Liver Fibrosis: A Multi-Institutional Study

INTRODUCTION

Liver fibrosis is a major cause of morbidity and mortality among in patients with chronic hepatitis. Radiomics, particularly of the spleen, may improve diagnostic accuracy and treatment strategies. External validations are necessary to ensure reliability and generalizability.

METHODS

In this retrospective study, we developed 3 radiomics models using contrast-enhanced computed tomography scans from 167 patients with liver fibrosis (training group) between January 2020 and December 2021. Radiomic features were extracted from arterial venous, portal venous, and equilibrium phase images. Recursive feature selection random forest and the least absolute shrinkage and selection operator logistic regression were used for feature selection and dimensionality reduction. Performance was assessed by area under the curve, C-index, calibration plots, and decision curve analysis. External validation was performed on 114 patients from 2 institutions.

RESULTS

Twenty-five radiomic features were significantly associated with fibrosis stage, with 80% of the top 10 features originating from portal venous phase spleen images. The radiomics models showed good performance in the validation cohort (C-indices 0.723-0.808) and excellent calibration. Decision curve analysis indicated clinical benefits, with machine learning-based radiomics models (Random Forest score and support vector machine based radiomics score) providing more significant advantages.

DISCUSSION

Radiomic features offer significant benefits over existing serum indices for staging virus-driven liver fibrosis, underscoring the value of radiomics in enhancing diagnostic accuracy. Specifically, radiomics analysis of the spleen presents additional noninvasive options for assessing fibrosis, highlighting its potential in improving patient management and outcomes.

Computed tomography radiomics models of tumor differentiation in canine small intestinal tumors

Radiomics models have been widely exploited in oncology for the investigation of tumor classification, as well as for predicting tumor response to treatment and genomic sequence; however, their performance in veterinary gastrointestinal tumors remains unexplored. Here, we sought to investigate and compare the performance of radiomics models in various settings for differentiating among canine small intestinal adenocarcinoma, lymphoma, and spindle cell sarcoma. Forty-two small intestinal tumors were contoured using four different segmentation methods: pre- or post-contrast, each with or without the inclusion of intraluminal gas. The mesenteric lymph nodes of pre- and post-contrast images were also contoured. The bin settings included bin count and bin width of 16, 32, 64, 128, and 256. Multinomial logistic regression, random forest, and support vector machine models were used to construct radiomics models. Using features from both primary tumors and lymph nodes showed significantly better performance than modeling using only the radiomics features of primary tumors, which indicated that the inclusion of mesenteric lymph nodes aids model performance. The support vector machine model exhibited significantly superior performance compared with the multinomial logistic regression and random forest models. Combining radiologic findings with radiomics features improved performance compared to using only radiomics features, highlighting the importance of radiologic findings in model building. A support vector machine model consisting of radiologic findings, primary tumors, and lymph node radiomics features with bin count 16 in post-contrast images with the exclusion of intraluminal gas showed the best performance among the various models tested. In conclusion, this study suggests that mesenteric lymph node segmentation and radiological findings should be integrated to build a potent radiomics model capable of differentiating among small intestinal tumors.

AI-based strategies in breast mass ≤ 2 cm classification with mammography and tomosynthesis

PURPOSE

To evaluate the diagnosis performance of digital mammography (DM) and digital breast tomosynthesis (DBT), DM combined DBT with AI-based strategies for breast mass ≤ 2 cm.

MATERIALS AND METHODS

DM and DBT images in 483 patients including 512 breast masses were acquired from November 2018 to November 2019. Malignant and benign tumours were determined by biopsies using histological analysis and follow-up within 24 months. The radiomics and deep learning methods were employed to extract the breast mass features in images and finally for benign and malignant classification. The DM, DBT and DM combined DBT (DM + DBT) images were fed into radiomics and deep learning models to construct corresponding models, respectively. The area under the receiver operating characteristic curve (AUC) was employed to estimate model performance. An external dataset of 146 patients from March 2021 to December 2022 from another center was enrolled for external validation.

RESULTS

In the internal testing dataset, compared with the DM model and the DBT model, the DM + DBT models based on radiomics and deep learning both showed statistically significant higher AUCs [0.810 (RA-DM), 0.823 (RA-DBT) and 0.869 (RA-DM + DBT), P ≤ 0.001; 0.867 (DL-DM), 0.871 (DL-DBT) and 0.908 (DL-DM + DBT), P = 0.001]. The deep learning models present superior to the radiomics models in the experiments with only DM (0.867 vs 0.810, P = 0.001), only DBT (0.871 vs 0.823, P = 0.001) and DM + DBT (0.908 vs 0.869, P = 0.003).

CONCLUSIONS

DBT has a clear additional value for diagnosing breast mass less than 2 cm compared with only DM. AI-based methods, especially deep learning, can help achieve excellent performance.

Preoperative CT-based intra- and peri-tumoral radiomic models for differentiating benign and malignant tumors of the parotid gland: a two-center study

OBJECTIVE

To investigate the ability of intra- and peritumoral radiomics based on three-phase computed tomography (CT) to distinguish between malignant and benign parotid tumors.

METHODS

We conducted a retrospective analysis of data from 374 patients with parotid gland tumors, all confirmed by histopathology. A total of 321 patients from Center 1 (January 2014 to January 2023) were randomly divided into the training set and internal testing set at a ratio of 7:3, whereas 53 patients from Center 2 (January 2020 to June 2022) constituted the external testing set. CT images of both the tumor and surrounding areas (2 mm and 5 mm areas surrounding the tumor) were reviewed, and their radiomic features were extracted for the construction of different radiomic models. In addition, a combined clinical-radiomic model was developed using multivariate logistic regression analysis. The model's predictive performance was evaluated using decision curve analysis (DCA) and receiver operating characteristic (ROC) curves.

RESULTS

Among the models evaluated, Tumor + External2 model demonstrated superior predictive performance. The areas under the curve (AUCs) of this model were 0.986 in the training set, 0.827 in the internal test set, and 0.749 in the external test set. For the clinical model, independent predictive factors included symptoms, boundaries, and lymph node swelling. The combined clinical-radiomic model achieved AUCs of 0.981, 0.842, and 0.749 in the three cohorts, outperforming both the Tumor model and the clinical model individually.

CONCLUSION

The CT-based radiomic models incorporating intratumoral and peritumoral radiomic features can effectively distinguish malignant from benign parotid tumors, and the predictive accuracy is further improved by incorporating clinically independent predictors.

Systematic review and meta-analysis on the classification metrics of machine learning algorithm based radiomics in hepatocellular carcinoma diagnosis

The aim of this systematic review and meta-analysis is to evaluate the performance of classification metrics of machine learning-driven radiomics in diagnosing hepatocellular carcinoma (HCC). Following the PRISMA guidelines, a comprehensive search was conducted across three major scientific databases-PubMed, ScienceDirect, and Scopus-from 2018 to 2022. The search yielded a total of 436 articles pertinent to the application of machine learning and deep learning for HCC prediction. These studies collectively reflect the burgeoning interest and rapid advancements in employing artificial intelligence (AI)-driven radiomics for enhanced HCC diagnostic capabilities. After the screening process, 34 of these articles were chosen for the study. The area under curve (AUC), accuracy, specificity, and sensitivity of the proposed and basic models were assessed in each of the studies. Jamovi (version 1.1.9.0) was utilised to carry out a meta-analysis of 12 cohort studies to evaluate the classification accuracy rate. The risk of bias was estimated, and Logistic Regression was found to be the most suitable classifier for binary problems, with least absolute shrinkage and selection operator (LASSO) as the feature selector. The pooled proportion for HCC prediction classification was high for all performance metrics, with an AUC value of 0.86 (95 % CI: 0.83-0.88), accuracy of 0.83 (95 % CI: 0.78-0.88), sensitivity of 0.80 (95 % CI: 0.75-0.84) and specificity of 0.84 (95 % CI: 0.80-0.88). The performance of feature selectors, classifiers, and input features in detecting HCC and related factors was evaluated and it was observed that radiomics features extracted from medical images were adequate for AI to accurately distinguish the condition. HCC based radiomics has favourable predictive performance especially with addition of clinical features that may serve as tool that support clinical decision-making.

Data-driven rapid detection of Helicobacter pylori infection through machine learning with limited laboratory parameters in Chinese primary clinics

Background

Helicobacter pylori (H. pylori) is a significant global health concern, posing a high risk for gastric cancer. Conventional diagnostic and screening approaches are inaccessible, invasive, inaccurate, time-consuming, and expensive in primary clinics.

Objective

This study aims to apply machine learning (ML) models to detect H. pylori infection using limited laboratory parameters from routine blood tests and to investigate the association of these biomarkers with clinical outcomes in primary clinics.

Methods

A retrospective analysis with three ML and five ensemble models was conducted on 1409 adults from Hubei Provincial Hospital of Traditional Chinese Medicine. evaluating twenty-three blood test parameters and using theC 14 urea breath test as the gold standard for diagnosing H. pylori infection.

Results

In our comparative study employing three different feature selection strategies, Random Forest (RF) model exhibited superior performance over other ML and ensemble models. Multiple evaluation metrics underscored the optimal performance of the RF model (ROC = 0.951, sensitivity = 0.882, specificity = 0.906, F1 = 0.906, accuracy = 0.894, PPV = 0.908, NPV = 0.880) without feature selection. Key biomarkers identified through importance ranking and shapley additive Explanations (SHAP) analysis using the RF model without feature selection include White Blood Cell Count (WBC), Mean Platelet Volume (MPV), Hemoglobin (Hb), Red Blood Cell Count (RBC), Platelet Crit (PCT), and Platelet Count (PLC). These biomarkers were found to be significantly associated with the presence of H. pylori infection, reflecting the immune response and inflammation levels.

Conclusion

Abnormalities in key biomarkers could prompt clinical workers to consider H. pylori infection. The RF model effectively identifies H. pylori infection using routine blood tests, offering potential for clinical application in primary clinics. This ML approach can enhance diagnosis and screening, reducing medical burdens and reliance on invasive diagnostics.

Significance of MRI-based radiomics in predicting pathological complete response to neoadjuvant chemoradiotherapy of locally advanced rectal cancer: A narrative review

Neoadjuvant chemoradiotherapy is the standard treatment for patients with locally advanced rectal cancers owing to its ability to downstage primary tumours. Some patients can achieve pathological complete response after neoadjuvant therapy, and can adopt a "watch and wait" treatment strategy to avoid overtreatment. Therefore, it is essential to develop strategies for predicting responses to neoadjuvant therapy. Radiomics has shown great potential in extracting tumour features from high-throughput medical images for the construction of mathematics models for predicting the effects of anticancerous therapies. Herein, we explored MRI-based radiomics and found that it can predict responses of locally advanced rectal cancers to chemoradiation. Efficient radiomics model allow early-stage prediction of the effect of neoadjuvant chemoradiotherapy on locally advanced rectal cancers. It helps clinicians to make informed therapeutic decisions. In this review, we discuss the workflow of radiomics, and summarize the clinical application of MRI-based radiomics in predicting pathological complete response to neoadjuvant chemoradiotherapy of locally advanced rectal cancer.

Radiomics as a tool for prognostic prediction in transarterial chemoembolization for hepatocellular carcinoma: a systematic review and meta-analysis

INTRODUCTION

Transarterial chemoembolization (TACE) is one of the predominant locoregional therapeutic modalities for addressing hepatocellular carcinoma (HCC). However, achieving precise prognostic predictions and effective patient selection remains a challenging pursuit. The primary objective of this systematic review and meta-analysis is to evaluate the efficacy of radiomics in forecasting the prognosis associated with TACE treatment.

METHODS

A comprehensive exploration of pertinent original studies was undertaken, encompassing databases of PubMed, Web of Science and Embase. The studies' quality was meticulously evaluated employing the quality assessment of diagnostic accuracy studies 2 (QUADAS-2), the radiomics quality score (RQS) and the METhodological RadiomICs Score (METRICS). Pooled statistics, along with 95% confidence intervals (95% CI), were computed for sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR). Additionally, a summary receiver operating characteristic curve (sROC) was generated. To discern potential sources of heterogeneity, meta-regression and subgroup analyses were performed.

RESULTS

The systematic review incorporated 29 studies, comprising a total of 5483 patients, with 14 studies involving 2691 patients qualifying for inclusion in the meta-analysis. The assessed studies exhibited commendable quality with regard to bias risk, with mean RQS of 12.90 ± 5.13 (35.82% ± 14.25%) and mean METRICS of 62.98% ± 14.58%. The pooled sensitivity was 0.83 (95% CI: 0.78-0.87), specificity was 0.86 (95% CI: 0.79-0.92), PLR was 6.13 (95% CI: 3.79-9.90), and NLR was 0.20 (95% CI: 0.15-0.27). The area under the sROC was 0.90 (95% CI: 0.87-0.93). Significant heterogeneity within all the included studies was observed, while meta-regression and subgroup analyses revealed homogeneous and promising findings in subgroups where principal methodological variables such as modeling algorithms, imaging modalities, and imaging phases were specified.

CONCLUSION

Radiomics models have exhibited robust predictive capabilities concerning prognosis subsequent to TACE, thereby presenting promising prospects for clinical translation.

Cardiovascular Magnetic Resonance Radiomics to Identify Components of the Extracellular Matrix in Dilated Cardiomyopathy

BACKGROUND

Current cardiovascular magnetic resonance sequences cannot discriminate between different myocardial extracellular space (ECSs), including collagen, noncollagen, and inflammation. We sought to investigate whether cardiovascular magnetic resonance radiomics analysis can distinguish between noncollagen and inflammation from collagen in dilated cardiomyopathy.

METHODS

We identified data from 132 patients with dilated cardiomyopathy scheduled for an invasive septal biopsy who underwent cardiovascular magnetic resonance at 3 T. Cardiovascular magnetic resonance imaging protocol included native and postcontrast T1 mapping and late gadolinium enhancement (LGE). Radiomic features were computed from the midseptal myocardium, near the biopsy region, on native T1, extracellular volume (ECV) map, and LGE images. Principal component analysis was used to reduce the number of radiomic features to 5 principal radiomics. Moreover, a correlation analysis was conducted to identify radiomic features exhibiting a strong correlation (r>0.9) with the 5 principal radiomics. Biopsy samples were used to quantify ECS, myocardial fibrosis, and inflammation.

RESULTS

Four histopathological phenotypes were identified: low collagen (n=20), noncollagenous ECS expansion (n=49), mild to moderate collagenous ECS expansion (n=42), and severe collagenous ECS expansion (n=21). Noncollagenous expansion was associated with the highest risk of myocardial inflammation (65%). Although native T1 and ECV provided high diagnostic performance in differentiating severe fibrosis (C statistic, 0.90 and 0.90, respectively), their performance in differentiating between noncollagen and mild to moderate collagenous expansion decreased (C statistic: 0.59 and 0.55, respectively). Integration of ECV principal radiomics provided better discrimination and reclassification between noncollagen and mild to moderate collagen (C statistic, 0.79; net reclassification index, 0.83 [95% CI, 0.45-1.22]; P<0.001). There was a similar trend in the addition of native T1 principal radiomics (C statistic, 0.75; net reclassification index, 0.93 [95% CI, 0.56-1.29]; P<0.001) and LGE principal radiomics (C statistic, 0.74; net reclassification index, 0.59 [95% CI, 0.19-0.98]; P=0.004). Five radiomic features per sequence were identified with correlation analysis. They showed a similar improvement in performance for differentiating between noncollagen and mild to moderate collagen (native T1, ECV, LGE C statistic, 0.75, 0.77, and 0.71, respectively). These improvements remained significant when confined to a single radiomic feature (native T1, ECV, LGE C statistic, 0.71, 0.70, and 0.64, respectively).

CONCLUSIONS

Radiomic features extracted from native T1, ECV, and LGE provide incremental information that improves our capability to discriminate noncollagenous expansion from mild to moderate collagen and could be useful for detecting subtle chronic inflammation in patients with dilated cardiomyopathy.

Non-linear Logistic Regression applied to Radiomics

In the past decade, radiomics has gained huge popularity. This method has a significant potential in cancer detection, diagnostic or prediction of response to a treatment due to its capacity of reflecting tumor-phenotypic characteristics. Despite its qualities and the interest shown in it by the scientific community, radiomics is still not used for clinical care. Reliable Machine Learning (ML) approaches could promote the usage of radiomics by showing relevant results. In this context, we propose to improve the performance of the Logistic Regression (LR) which is the most used ML model in radiomics. We propose to represent the radiomics features with one-hot encoding. Then, we show that the resulting LR is non-linear and almost equivalent to the Naive Bayes classifier (NBC). Since our LR score function remains additive, the contribution of each feature to the decision can be easily measured. We illustrate the performance of the proposed non-linear LR with two radiomics datasets.

Predicting intraoperative blood loss during cesarean sections based on multi-modal information: a two-center study

PURPOSE

To develop and validate a nomogram model that combines radiomics features, clinical factors, and coagulation function indexes (CFI) to predict intraoperative blood loss (IBL) during cesarean sections, and to explore its application in optimizing perioperative management and reducing maternal morbidity.

METHODS

In this retrospective consecutive series study, a total of 346 patients who underwent magnetic resonance imaging (156 for training and 68 for internal test, center 1; 122 for external test, center 2) were included. IBL+ was defined as more than 1000 mL estimated blood loss during cesarean sections. The prediction models of IBL were developed based on machine-learning algorithms using CFI, radiomics features, and clinical factors. ROC analysis was performed to evaluate the performance for IBL diagnosis.

RESULTS

The support vector machine model incorporating all three modalities achieved an AUC of 0.873 (95% CI 0.769-0.941) and a sensitivity of 1.000 (95% CI 0.846-1.000) in the internal test set, with an AUC of 0.806 (95% CI 0.725-0.872) and a sensitivity of 0.873 (95% CI 0.799-0.922) in the external test set. It was also scored significantly higher than the CFI model (P = 0.035) on the internal test set, and both the CFI (P = 0.002) and radiomics-CFI models (P = 0.007) on the external test set. Additionally, the nomogram constructed based on three modalities achieved an internal testing set AUC of 0.960 (95% CI 0.806-0.999) and an external testing set AUC of 0.869 (95% CI 0.684-0.967) in the pregnant population without a pernicious placenta previa. It is noteworthy that the AUC of the proposed model did not show a statistically significant improvement compared to the Clinical-CFI model in both internal (P = 0.115) and external test sets (P = 0.533).

CONCLUSION

The proposed model demonstrated good performance in predicting intraoperative blood loss (IBL), exhibiting high sensitivity and robust generalizability, with potential applicability to other surgeries such as vaginal delivery and postpartum hysterectomy. However, the performance of the proposed model was not statistically significantly better than that of the Clinical-CFI model.

CT-Based Radiomics Analysis of Different Machine Learning Models for Discriminating the Risk Stratification of Pheochromocytoma and Paraganglioma: A Multicenter Study

RATIONALE AND OBJECTIVES

Using different machine learning models CT-based radiomics to integrate clinical radiological features to discriminating the risk stratification of pheochromocytoma/paragangliomas (PPGLs).

MATERIALS AND METHODS

The present study included 201 patients with PPGLs from three hospitals (training set: n = 125; external validation set: n = 45; external test set: n = 31). Patients were divided into low-risk and high-risk groups using a staging system for adrenal pheochromocytoma and paraganglioma (GAPP). We extracted and selected CT radiomics features, and built radiomics models using support vector machines (SVM), k-nearest neighbors, random forests, and multilayer perceptrons. Using receiver operating characteristic curve analysis to select the optimal radiomics model, a combined model was built using the output of the optimal radiomics model and clinical radiological features, and its accuracy and clinical applicability were evaluated using calibration curves and clinical decision curve analysis (DCA).

RESULTS

Finally, 13 radiomics features were selected to construct machine learning models. In the radiomics model, the SVM model demonstrated higher accuracy and stability, with an AUC value of 0.915 in the training set, 0.846 in external validation set, and 0.857 in external test set. Combining the outputs of SVM models with two clinical radiological features, a combined model constructed has demonstrated optimal risk stratification ability for PPGLs with an AUC of 0.926 for the training set, 0.883 for the external validation set, and 0.899 for the external test set. The calibration curve and DCA show good calibration accuracy and clinical effectiveness for the combined model.

CONCLUSION

Combined model that integrates radiomics and clinical radiological features can discriminate the risk stratification of PPGLs.

Robustness of radiomics features on 0.35 T magnetic resonance imaging for magnetic resonance-guided radiotherapy

Background and purpose

MR-guided radiotherapy adds the precision of magnetic resonance imaging (MRI) to the therapeutic benefits of a linear accelerator. Prior to each therapeutic session, an MRI generates a significant volume of imaging data ripe for analysis. Radiomics stands at the forefront of medical imaging and oncology research, dedicated to mining quantitative imaging attributes to forge predictive models. However, the robustness of these models is often challenged.

Materials and methods

To assess the robustness of feature extraction, we conducted reproducibility studies using a 0.35 T MR-linac system, employing both a specialized phantom and patient-derived images, focusing on cases of pancreatic cancer. We extracted shape-based, first-order and textural features from patient-derived images and only first-order and textural features from phantom-derived images. The impact of the delay between simulation and first fraction images was also assessed with an equivalence test.

Results

From 107 features evaluated, 58 (54 %) were considered as non-reproducible: 18 were uniformly inconsistent across both phantom and patient images, 9 were specific to phantom-based analysis, and 31 to patient-derived data.

Conclusion

Our findings show that a significant proportion of radiomic features extracted from this dual dataset were unreliable. It is essential to discard these non-reproducible elements to refine and enhance radiomic model development, particularly for MR-guided radiotherapy in pancreatic cancer.

Multiparametric MRI-based radiomic model for predicting lymph node metastasis after neoadjuvant chemoradiotherapy in locally advanced rectal cancer

OBJECTIVES

To construct and validate multiparametric MR-based radiomic models based on primary tumors for predicting lymph node metastasis (LNM) following neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC) patients.

METHODS

A total of 150 LARC patients from two independent centers were enrolled. The training cohort comprised 100 patients from center A. Fifty patients from center B were included in the external validation cohort. Radiomic features were extracted from the manually segmented volume of interests of the primary tumor before and after nCRT. Feature selection was performed using multivariate logistic regression analysis. The clinical risk factors were selected via the least absolute shrinkage and selection operator method. The radiologist's assessment of LNM was performed. Eight models were constructed using random forest classifiers, including four single-sequence models, three combined-sequence models, and a clinical model. The models' discriminative performance was assessed via receiver operating characteristic curve analysis quantified by the area under the curve (AUC).

RESULTS

The AUCs of the radiologist's assessment, the clinical model, and the single-sequence models ranged from 0.556 to 0.756 in the external validation cohort. Among the single-sequence models, modelpost_DWI exhibited superior predictive power, with an AUC of 0.756 in the external validation set. In combined-sequence models, modelpre_T2_DWI_post had the best diagnostic performance in predicting LNM after nCRT, with a significantly higher AUC (0.831) than those of the clinical model, modelpre_T2_DWI, and the single-sequence models (all p < 0.05).

CONCLUSIONS

A multiparametric model that incorporates MR radiomic features before and after nCRT is optimal for predicting LNM after nCRT in LARC.

CRITICAL RELEVANCE STATEMENT

This study enrolled 150 LARC patients from two independent centers and constructed multiparametric MR-based radiomic models based on primary tumors for predicting LNM following nCRT, which aims to guide therapeutic decisions and predict prognosis for LARC patients.

KEY POINTS

The biological characteristics of primary tumors and metastatic LNs are similar in rectal cancer. Radiomics features and clinical data before and after nCRT provide complementary tumor information. Preoperative prediction of LN status after nCRT contributes to clinical decision-making.

Enhancing Lung Cancer Survival Prediction: 3D CNN Analysis of CT Images Using Novel GTV1-SliceNum Feature and PEN-BCE Loss Function

Lung cancer is a prevalent malignancy associated with a high mortality rate, with a 5-year relative survival rate of 23%. Traditional survival analysis methods, reliant on clinician judgment, may lack accuracy due to their subjective nature. Consequently, there is growing interest in leveraging AI-based systems for survival analysis using clinical data and medical imaging. The purpose of this study is to improve survival classification for lung cancer patients by utilizing a 3D-CNN architecture (ResNet-34) applied to CT images from the NSCLC-Radiomics dataset. Through comprehensive ablation studies, we evaluate the effectiveness of different features and methodologies in classification performance. Key contributions include the introduction of a novel feature (GTV1-SliceNum), the proposal of a novel loss function (PEN-BCE) accounting for false negatives and false positives, and the showcasing of their efficacy in classification. Experimental work demonstrates results surpassing those of the existing literature, achieving a classification accuracy of 0.7434 and an ROC-AUC of 0.7768. The conclusions of this research indicate that the AI-driven approach significantly improves survival prediction for lung cancer patients, highlighting its potential for enhancing personalized treatment strategies and prognostic modeling.