Differentiation of glioblastoma from solitary brain metastases using radiomic machine-learning classifiers

Ensemble learning-based pretreatment MRI radiomic model for distinguishing intracranial extraventricular ependymoma from glioblastoma multiforme

This study aims to develop an ensemble learning (EL) method based on magnetic resonance (MR) radiomic features to preoperatively differentiate intracranial extraventricular ependymoma (IEE) from glioblastoma (GBM). This retrospective study enrolled patients with histopathologically confirmed IEE and GBM from June 2016 to June 2021. Radiomics features were extracted from T1-weighted imaging (T1WI) and T2-weighted imaging (T2WI) sequence images, and classification models were constructed using EL methods and logistic regression (LR). The efficiency of the models was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis. The combined EL model, based on clinical parameters and radiomic features from T1WI and T2WI images, demonstrated good discriminative ability, achieving an area under the receiver operating characteristics curve (AUC) of 0.96 (95% CI 0.94-0.98), a specificity of 0.84, an accuracy of 0.92, and a sensitivity of 0.95 in the training set, and an AUC of 0.89 (95% CI 0.83-0.94), a specificity of 0.83, an accuracy of 0.81, and a sensitivity of 0.74 in the validation set. The discriminative efficacy of the EL model was significantly higher than that of the LR model. Favorable calibration performance and clinical applicability for the EL model were observed. The EL model combining preoperative MR-based tumor radiomics and clinical data showed high accuracy and sensitivity in differentiating IEE from GBM preoperatively, which may potentially assist in clinical management of these brain tumors.

High-performance presurgical differentiation of glioblastoma and metastasis by means of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics

OBJECTIVES

To evaluate the performance of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics in distinguishing between glioblastoma (Gb) and solitary brain metastasis (SBM).

MATERIALS AND METHODS

In this retrospective study, NODDI images were curated from 109 patients with Gb (n = 57) or SBM (n = 52). Automatically segmented multiple volumes of interest (VOIs) encompassed the main tumor regions, including necrosis, solid tumor, and peritumoral edema. Radiomics features were extracted for each main tumor region, using three NODDI parameter maps. Radiomics models were developed based on these three NODDI parameter maps and their amalgamation to differentiate between Gb and SBM. Additionally, radiomics models were constructed based on morphological magnetic resonance imaging (MRI) and diffusion imaging (diffusion-weighted imaging [DWI]; diffusion tensor imaging [DTI]) for performance comparison.

RESULTS

The validation dataset results revealed that the performance of a single NODDI parameter map model was inferior to that of the combined NODDI model. In the necrotic regions, the combined NODDI radiomics model exhibited less than ideal discriminative capabilities (area under the receiver operating characteristic curve [AUC] = 0.701). For peritumoral edema regions, the combined NODDI radiomics model achieved a moderate level of discrimination (AUC = 0.820). Within the solid tumor regions, the combined NODDI radiomics model demonstrated superior performance (AUC = 0.904), surpassing the models of other VOIs. The comparison results demonstrated that the NODDI model was better than the DWI and DTI models, while those of the morphological MRI and NODDI models were similar.

CONCLUSION

The NODDI radiomics model showed promising performance for preoperative discrimination between Gb and SBM.

CLINICAL RELEVANCE STATEMENT

The NODDI radiomics model showed promising performance for preoperative discrimination between Gb and SBM, and radiomics features can be incorporated into the multidimensional phenotypic features that describe tumor heterogeneity.

KEY POINTS

• The neurite orientation dispersion and density imaging (NODDI) radiomics model showed promising performance for preoperative discrimination between glioblastoma and solitary brain metastasis. • Compared with other tumor volumes of interest, the NODDI radiomics model based on solid tumor regions performed best in distinguishing the two types of tumors. • The performance of the single-parameter NODDI model was inferior to that of the combined-parameter NODDI model.

Noninvasive radiomics approach predicts dopamine agonists treatment response in patients with prolactinoma: a multicenter study

RATIONALE AND OBJECTIVES

The first-line treatment for prolactinoma is drug therapy with dopamine agonists (DAs). However, some patients with resistance to DA treatment should prioritize surgical treatment. Therefore, it is crucial to accurately identify the drug treatment response of prolactinoma before treatment. The present study was performed to determine the DA treatment response of prolactinoma using a clinical radiomic model that incorporated radiomic and clinical features before treatment.

MATERIALS AND METHODS

In total, 255 patients diagnosed with prolactinoma were retrospectively divided to training and validation sets. An elastic net algorithm was used to screen the radiomic features, and a fusion radiomic model was established. A clinical radiomic model was then constructed to integrate the fusion radiomic model and the most important clinical features through multivariate logistic regression analysis for individual prediction. The calibration, discrimination, and clinical applicability of the established models were evaluated. 60 patients with prolactinoma from other centers were used to validate the performance of the constructed model.

RESULTS

The fusion radiomic model was constructed from three significant radiomic features, and the area under the curve in the training set and validation set was 0.930 and 0.910, respectively. The clinical radiomic model was constructed using the radiomic model and three clinical features. The model exhibited good recognition and calibration abilities as evidenced by its area under the curve of 0.96, 0.92, and 0.92 in the training, validation, and external multicenter validation set, respectively. Analysis of the decision curve showed that the fusion radiomic model and clinical radiomic model had good clinical application value for DA treatment response prediction in patients with prolactinoma.

CONCLUSION

Our clinical radiomic model demonstrated high sensitivity and excellent performance in predicting DA treatment response in prolactinoma. This model holds promise for the noninvasive development of individualized diagnosis and treatment strategies for patients with prolactinoma.

Combined CT-Based Radiomics and Clinic-Radiological Characteristics for Preoperative Differentiation of Solitary-Type Invasive Mucinous and Non-Mucinous Lung Adenocarcinoma

Purpose

The clinical, pathological, gene expression, and prognosis of invasive mucinous adenocarcinoma (IMA) differ from those of invasive non-mucinous adenocarcinoma (INMA), but it is not easy to distinguish these two. This study aims to explore the value of combining CT-based radiomics features with clinic-radiological characteristics for preoperative diagnosis of solitary-type IMA and to establish an optimal diagnostic model.

Methods

In this retrospective study, a total of 220 patients were enrolled and randomly assigned to a training cohort (n = 154; 73 IMA and 81 INMA) and a testing cohort (n = 66; 31 IMA and 35 INMA). Radiomics features and clinic-radiological characteristics were extracted from plain CT images. The radiomics models for predicting solitary-type IMA were developed by three classifiers: linear discriminant analysis (LDA), logistic regression-least absolute shrinkage and selection operator (LR-LASSO), and support vector machine (SVM). The combined model was constructed by integrating radiomics and clinic-radiological features with the best performing classifier. Receiver operating characteristic (ROC) curves were used to evaluate models' performance, and the area under the curve (AUC) were compared by the DeLong test. Decision curve analysis (DCA) was conducted to assess the clinical utility.

Results

Regarding CT characteristics, tumor lung interface, and pleural retraction were the independent risk factors of solitary-type IMA. The radiomics model using the SVM classifier outperformed the other two classifiers in the testing cohort, with an AUC of 0.776 (95% CI: 0.664-0.888). The combined model incorporating radiomics features and clinic-radiological factors was the optimal model, with AUCs of 0.843 (95% CI: 0.781-0.906) and 0.836 (95% CI: 0.732-0.940) in the training and testing cohorts, respectively.

Conclusion

The combined model showed good ability in predicting solitary-type IMA and can provide a non-invasive and efficient approach to clinical decision-making.

Glioblastoma and Solitary Brain Metastasis: Differentiation by Integrating Demographic-MRI and Deep-Learning Radiomics Signatures

BACKGROUND

Studies have shown that deep-learning radiomics (DLR) could help differentiate glioblastoma (GBM) from solitary brain metastasis (SBM), but whether integrating demographic-MRI and DLR features can more accurately distinguish GBM from SBM remains uncertain.

PURPOSE

To construct and validate a demographic-MRI deep-learning radiomics nomogram (DDLRN) integrating demographic-MRI and DLR signatures to differentiate GBM from SBM preoperatively.

STUDY TYPE

Retrospective.

POPULATION

Two hundred and thirty-five patients with GBM (N = 115) or SBM (N = 120), randomly divided into a training cohort (90 GBM and 98 SBM) and a validation cohort (25 GBM and 22 SBM).

FIELD STRENGTH/SEQUENCE

Axial T2-weighted fast spin-echo sequence (T2WI), T2-weighted fluid-attenuated inversion recovery sequence (T2-FLAIR), and contrast-enhanced T1-weighted spin-echo sequence (CE-T1WI) using 1.5-T and 3.0-T scanners.

ASSESSMENT

The demographic-MRI signature was constructed with seven imaging features ("pool sign," "irregular ring sign," "regular ring sign," "intratumoral vessel sign," the ratio of the area of peritumoral edema to the enhanced tumor, the ratio of the lesion area on T2-FLAIR to CE-T1WI, and the tumor location) and demographic factors (age and sex). Based on multiparametric MRI, radiomics and deep-learning (DL) models, DLR signature, and DDLRN were developed and validated.

STATISTICAL TESTS

The Mann-Whitney U test, Pearson test, least absolute shrinkage and selection operator, and support vector machine algorithm were applied for feature selection and construction of radiomics and DL models.

RESULTS

DDLRN showed the best performance in differentiating GBM from SBM with area under the curves (AUCs) of 0.999 and 0.947 in the training and validation cohorts, respectively. Additionally, the DLR signature (AUC = 0.938) outperformed the radiomics and DL models, and the demographic-MRI signature (AUC = 0.775) was comparable to the T2-FLAIR radiomics and DL models in the validation cohort (AUC = 0.762 and 0.749, respectively).

DATA CONCLUSION

DDLRN integrating demographic-MRI and DLR signatures showed excellent performance in differentiating GBM from SBM.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Integrated diagnosis of glioma based on magnetic resonance images with incomplete ground truth labels

BACKGROUND

Since the 2016 WHO guidelines, glioma diagnosis has entered an era of integrated diagnosis, combining tissue pathology and molecular pathology. The WHO has focused on promoting the application of molecular diagnosis in the classification of central nervous system tumors. Genetic information such as IDH1 and 1p/19q are important molecular markers, and pathological grading is also a key clinical indicator. However, obtaining genetic pathology labels is more costly than conventional MRI images, resulting in a large number of missing labels in realistic modeling.

METHOD

We propose a training strategy based on label encoding and a corresponding loss function to enable the model to effectively utilize data with missing labels. Additionally, we integrate a graph model with genes and pathology-related clinical prior knowledge into the ResNet backbone to further improve the efficacy of diagnosis. Ten-fold cross-validation experiments were conducted on a large dataset of 1072 patients.

RESULTS

The classification area under the curve (AUC) values are 0.93, 0.91, and 0.90 for IDH1, 1p/19q status, and grade (LGG/HGG), respectively. When the label miss rate reached 59.3 %, the method improved the AUC by 0.09, 0.10, and 0.04 for IDH1, 1p/19q, and pathological grade, respectively, compared to the same backbone without the missing label strategy.

CONCLUSIONS

Our method effectively utilizes data with missing labels and integrates clinical prior knowledge, resulting in improved diagnostic performance for glioma genetic and pathological markers, even with high rates of missing labels.

Multiparametric MRI-Based Machine Learning Models for the Characterization of Cystic Renal Masses Compared to the Bosniak Classification, Version 2019: A Multicenter Study

RATIONALE AND OBJECTIVE

Accurate differentiation between benign and malignant cystic renal masses (CRMs) is challenging in clinical practice. This study aimed to develop MRI-based machine learning models for differentiating between benign and malignant CRMs and compare the best-performing model with the Bosniak classification, version 2019 (BC, version 2019).

METHODS

Between 2009 and 2021, consecutive surgery-proven CRM patients with renal MRI were enrolled in this multicenter study. Models were constructed to differentiate between benign and malignant CRMs using logistic regression (LR), random forest (RF), and support vector machine (SVM) algorithms, respectively. Meanwhile, two radiologists classified CRMs into I-IV categories according to the BC, version 2019 in consensus in the test set. A subgroup analysis was conducted to investigate the performance of the best-performing model in complicated CRMs (II-IV lesions in the test set). The performances of models and BC, version 2019 were evaluated using the area under the receiver operating characteristic curve (AUC). Performance was statistically compared between the best-performing model and the BC, version 2019.

RESULTS

278 and 48 patients were assigned to the training and test sets, respectively. In the test set, the AUC and accuracy of the LR model, the RF model, the SVM model, and the BC, version 2019 were 0.884 and 75.0%, 0.907 and 83.3%, 0.814 and 72.9%, and 0.893 and 81.2%, respectively. Neither the AUC nor the accuracy of the RF model that performed best were significantly different from the BC, version 2019 (P = 0.780, P = 0.065). The RF model achieved an AUC and accuracy of 0.880 and 81.0% in complicated CRMs.

CONCLUSIONS

The MRI-based RF model can accurately differentiate between benign and malignant CRMs with comparable performance to the BC, version 2019, and has good performance in complicated CRMs, which may facilitate treatment decision-making and is less affected by interobserver disagreements.

Radiomics based on multiple machine learning methods for diagnosing early bone metastases not visible on CT images

OBJECTIVES

This study utilizes [99mTc]-methylene diphosphate (MDP) single photon emission computed tomography (SPECT) images as a reference standard to evaluate whether the integration of radiomics features from computed tomography (CT) and machine learning algorithms can identify microscopic early bone metastases. Additionally, we also determine the optimal machine learning approach.

MATERIALS AND METHODS

We retrospectively studied 63 patients with early bone metastasis from July 2020 to March 2023. The ITK-SNAP software was used to delineate early bone metastases and normal bone tissue in SPECT images of each patient, which were then registered onto CT images to outline the volume of interest (VOI). The VOI includes 63 early bone metastasis volumes and 63 normal bone tissue volumes. 126 VOIs were randomly distributed in a 7:3 ratio between the training and testing groups, and 944 radiomics features were extracted from every VOI. We established 20 machine learning models using 5 feature selection algorithms and 4 classification methods. Evaluate the performance of the model using the area under the receiver operating characteristic curve (AUC).

RESULTS

Most machine learning models demonstrated outstanding discriminative capacity, with AUCs higher than 0.70. Notably, the K-Nearest Neighbors (KNN) classifier exhibited significant performance improvement compared to the other four classifiers. Specifically, the model constructed utilizing eXtreme Gradient Boosting (XGBoost) feature selection method integrated with KNN classifier achieved the maximum AUC, which is 0.989 in the training set and 0.975 in the testing set.

CONCLUSIONS

Radiomics features integrated with machine learning methods can identify early bone metastases that are not visible on CT images. In our analysis, KNN is considered the optimal classification method.

Comprehensive quantitative radiogenomic evaluation reveals novel radiomic subtypes with distinct immune pattern in glioma

BACKGROUND

Accurate classification of gliomas is critical to the selection of immunotherapy, and MRI contains a large number of radiomic features that may suggest some prognostic relevant signals. We aim to predict new subtypes of gliomas using radiomic features and characterize their survival, immune, genomic profiles and drug response.

METHODS

We initially obtained 341 images of 36 patients from the CPTAC dataset for the development of deep learning models. Further 1812 images of 111 patients from TCGA_GBM and 152 images of 53 patients from TCGA_LGG were collected for testing and validation. A deep learning method based on Mask R-CNN was developed to identify new subtypes of glioma patients and compared the survival status, immune infiltration patterns, genomic signatures, specific drugs, and predictive models of different subtypes.

RESULTS

200 glioma patients (mean age, 33 years ± 19 [standard deviation]) were enrolled. The accuracy of the deep learning model for identifying tumor regions achieved 88.3 % (98/111) in the test set and 83 % (44/53) in the validation set. The sample was divided into two subtypes based on radiomic features showed different prognostic outcomes (hazard ratio, 2.70). According to the results of the immune infiltration analysis, the subtype with a poorer prognosis was defined as the immunosilencing radiomic (ISR) subtype (n = 43), and the other subtype was the immunoactivated radiomic (IAR) subtype (n = 53). Subtype-specific genomic signatures distinguished celllines into ISR celllines (n = 9) and control celllines (n = 13), and identified eight ISR-specific drugs, four of which were validated by the OCTAD database. Three machine learning-based classifiers showed that radiomic and genomic co-features better predicted the radiomic subtypes of gliomas.

CONCLUSIONS

These findings provide insights into how radiogenomic could identify specific subtypes that predict prognosis, immune and drug sensitivity in a non-invasive manner.

An MRI radiomics approach to discriminate haemorrhage-prone intracranial tumours before stereotactic biopsy

PURPOSE

To explore imaging biomarkers predictive of intratumoral haemorrhage for lesions intended for elective stereotactic biopsy.

METHOD

This study included a retrospective cohort of 143 patients with 175 intracranial lesions intended for stereotactic biopsy. All the lesions were randomly split into a training dataset ( n =121) and a test dataset ( n =54) at a ratio of 7:3. Thirty-four lesions were defined as "hemorrhage-prone tumors" as haemorrhage occurred between initial diagnostic MRI acquisition and the scheduled biopsy procedure. Radiomics features were extracted from the contrast-enhanced T1 Weighted Imaging and T2 Weighted Imaging images. Features informative of haemorrhage were then selected by the LASSO algorithm, and an Support Vector Machine model was built with selected features. The Support Vector Machine model was further simplified by discarding features with low importance and calculating them using a "permutation importance" method. The model's performance was evaluated with confusion matrix-derived metrics and area under curve (AUC) values on the independent test dataset.

RESULTS

Nine radiomics features were selected as haemorrhage-related features of intracranial tumours by the LASSO algorithm. The simplified model's sensitivity, specificity, accuracy, and AUC reached 0.909, 0.930, 0.926, and 0.949 (95% CI: 0.865-1.000) on the test dataset in the discrimination of "hemorrhage-prone tumors". The permutation method rated feature "T2_gradient_firstorder_10Percentile" as the most important, the absence of which decreased the model's accuracy by 10.9%.

CONCLUSION

Radiomics features extracted on contrast-enhanced T1 Weighted Imaging and T2 Weighted Imaging sequences were predictive of future haemorrhage of intracranial tumours with favourable accuracy. This model may assist in the arrangement of biopsy procedures and the selection of target lesions in patients with multiple lesions.

Uses of artificial intelligence in glioma: A systematic review

Glioma is the most prevalent type of primary brain tumor in adults. The use of artificial intelligence (AI) in glioma is increasing and has exhibited promising results. The present study performed a systematic review of the applications of AI in glioma as regards diagnosis, grading, prediction of genotype, progression and treatment response using different databases. The aim of the present study was to demonstrate the trends (main directions) of the recent applications of AI within the field of glioma, and to highlight emerging challenges in integrating AI within clinical practice. A search in four databases (Scopus, PubMed, Wiley and Google Scholar) yielded a total of 42 articles specifically using AI in glioma and glioblastoma. The articles were retrieved and reviewed, and the data were summarized and analyzed. The majority of the articles were from the USA (n=18) followed by China (n=11). The number of articles increased by year reaching the maximum number in 2022. The majority of the articles studied glioma as opposed to glioblastoma. In terms of grading, the majority of the articles were about both low-grade glioma (LGG) and high-grade glioma (HGG) (n=23), followed by HGG/glioblastoma (n=13). Additionally, three articles were about LGG only; two articles did not specify the grade. It was found that one article had the highest sample size among the other studies, reaching 897 samples. Despite the limitations and challenges that face AI, the use of AI in glioma has increased in recent years with promising results, with a variety of applications ranging from diagnosis, grading, prognosis prediction, and reaching to treatment and post-operative care.

Artificial Intelligence Applications for Thoracic Surgeons: "The Phenomenal Cosmic Powers of the Magic Lamp"

In the digital age, artificial intelligence (AI) is emerging as a transformative force in various sectors, including medicine. This article explores the potential of AI, which is akin to the magical genie of Aladdin's lamp, particularly within thoracic surgery and lung cancer management. It examines AI applications like machine learning and deep learning in achieving more precise diagnoses, preoperative risk assessment, and improved surgical outcomes. The challenges and advancements in AI integration, especially in computer vision and multi-modal models, are discussed alongside their impact on robotic surgery and operating room management. Despite its transformative potential, implementing AI in medicine faces challenges regarding data scarcity, interpretability issues, and ethical concerns. Collaboration between AI and medical communities is essential to address these challenges and unlock the full potential of AI in revolutionizing clinical practice. This article underscores the importance of further research and interdisciplinary collaboration to ensure the safe and effective deployment of AI in real-world clinical settings.

Application of Machine Learning for Classification of Brain Tumors: A Systematic Review and Meta-Analysis

BACKGROUND

Classifying brain tumors accurately is crucial for treatment and prognosis. Machine learning (ML) shows great promise in improving tumor classification accuracy. This study evaluates ML algorithms for differentiating various brain tumor types.

METHODS

A systematic review and meta-analysis were conducted, searching PubMed, Embase, and Web of Science up to March 14, 2023. Studies that only investigated image segmentation accuracy or brain tumor detection instead of classification were excluded. We extracted binary diagnostic accuracy data, constructing contingency tables to derive sensitivity and specificity.

RESULTS

Fifty-one studies were included. The pooled area under the curve for glioblastoma versus lymphoma and low-grade versus high-grade gliomas were 0.99 (95% confidence interval [CI]: 0.98-1.00) and 0.89, respectively. The pooled sensitivity and specificity for benign versus malignant tumors were 0.90 (95% CI: 0.85-0.93) and 0.93 (95% CI: 0.90-0.95), respectively. The pooled sensitivity and specificity for low-grade versus high-grade gliomas were 0.99 (95% CI: 0.97-1.00) and 0.94, (95% CI: 0.79-0.99), respectively. Primary versus metastatic tumor identification yields sensitivity and specificity of 0.89, (95% CI: 0.83-0.93) and 0.87 (95% CI: 0.82-0.91), correspondingly. The differentiation of gliomas from pituitary tumors yielded the highest results among primary brain tumor classifications: sensitivity of 0.99 (95% CI: 0.99-1.00) and specificity of 0.99 (95% CI: 0.98-1.00).

CONCLUSIONS

ML demonstrated excellent performance in classifying brain tumor images, with near-maximum area under the curves, sensitivity, and specificity.

Implementation of Artificial Intelligence in Personalized Prognostic Assessment of Lung Cancer: A Narrative Review

Artificial Intelligence (AI) has revolutionized the management of non-small-cell lung cancer (NSCLC) by enhancing different aspects, including staging, prognosis assessment, treatment prediction, response evaluation, recurrence/prognosis prediction, and personalized prognostic assessment. AI algorithms may accurately classify NSCLC stages using machine learning techniques and deep imaging data analysis. This could potentially improve precision and efficiency in staging, facilitating personalized treatment decisions. Furthermore, there are data suggesting the potential application of AI-based models in predicting prognosis in terms of survival rates and disease progression by integrating clinical, imaging and molecular data. In the present narrative review, we will analyze the preliminary studies reporting on how AI algorithms could predict responses to various treatment modalities, such as surgery, radiotherapy, chemotherapy, targeted therapy, and immunotherapy. There is robust evidence suggesting that AI also plays a crucial role in predicting the likelihood of tumor recurrence after surgery and the pattern of failure, which has significant implications for tailoring adjuvant treatments. The successful implementation of AI in personalized prognostic assessment requires the integration of different data sources, including clinical, molecular, and imaging data. Machine learning (ML) and deep learning (DL) techniques enable AI models to analyze these data and generate personalized prognostic predictions, allowing for a precise and individualized approach to patient care. However, challenges relating to data quality, interpretability, and the ability of AI models to generalize need to be addressed. Collaboration among clinicians, data scientists, and regulators is critical for the responsible implementation of AI and for maximizing its benefits in providing a more personalized prognostic assessment. Continued research, validation, and collaboration are essential to fully exploit the potential of AI in NSCLC management and improve patient outcomes. Herein, we have summarized the state of the art of applications of AI in lung cancer for predicting staging, prognosis, and pattern of recurrence after treatment in order to provide to the readers a large comprehensive overview of this challenging issue.

Differentiation Between Glioblastoma and Metastatic Disease on Conventional MRI Imaging Using 3D-Convolutional Neural Networks: Model Development and Validation

RATIONALE AND OBJECTIVES

Imaging-based differentiation between glioblastoma (GB) and brain metastases (BM) remains challenging. Our aim was to evaluate the performance of 3D-convolutional neural networks (CNN) to address this binary classification problem.

MATERIALS AND METHODS

T1-CE, T2WI, and FLAIR 3D-segmented masks of 307 patients (157 GB and 150 BM) were generated post resampling, co-registration normalization and semi-automated 3D-segmentation and used for internal model development. Subsequent external validation was performed on 59 cases (27 GB and 32 BM) from another institution. Four different mask-sequence combinations were evaluated using area under the curve (AUC), precision, recall and F1-scores. Diagnostic performance of a neuroradiologist and a general radiologist, both without and with the model output available, was also assessed.

RESULTS

3D-model using the T1-CE tumor mask (TM) showed the highest performance [AUC 0.93 (95% CI 0.858-0.995)] on the external test set, followed closely by the model using T1-CE TM and FLAIR mask of peri-tumoral region (PTR) [AUC of 0.91 (95% CI 0.834-0.986)]. Models using T2WI masks showed robust performance on the internal dataset but lower performance on the external set. Both neuroradiologist and general radiologist showed improved performance with model output provided [AUC increased from 0.89 to 0.968 (p = 0.06) and from 0.78 to 0.965 (p = 0.007) respectively], the latter being statistically significant.

CONCLUSION

3D-CNNs showed robust performance for differentiating GB from BMs, with T1-CE TM, either alone or combined with FLAIR-PTR masks. Availability of model output significantly improved the accuracy of the general radiologist.

Deep learning and radiomics-based approach to meningioma grading: exploring the potential value of peritumoral edema regions

Objective.To address the challenge of meningioma grading, this study aims to investigate the potential value of peritumoral edema (PTE) regions and proposes a unique approach that integrates radiomics and deep learning techniques.Approach.The primary focus is on developing a transfer learning-based meningioma feature extraction model (MFEM) that leverages both vision transformer (ViT) and convolutional neural network (CNN) architectures. Additionally, the study explores the significance of the PTE region in enhancing the grading process.Main results.The proposed method demonstrates excellent grading accuracy and robustness on a dataset of 98 meningioma patients. It achieves an accuracy of 92.86%, precision of 93.44%, sensitivity of 95%, and specificity of 89.47%.Significance.This study provides valuable insights into preoperative meningioma grading by introducing an innovative method that combines radiomics and deep learning techniques. The approach not only enhances accuracy but also reduces observer subjectivity, thereby contributing to improved clinical decision-making processes.

Radiomics signature for dynamic changes of tumor-infiltrating CD8+ T cells and macrophages in cervical cancer during chemoradiotherapy

BACKGROUND

Our previous study suggests that tumor CD8+ T cells and macrophages (defined as CD68+ cells) infiltration underwent dynamic and heterogeneous changes during concurrent chemoradiotherapy (CCRT) in cervical cancer patients, which correlated with their short-term tumor response. This study aims to develop a CT image-based radiomics signature for such dynamic changes.

METHODS

Thirty cervical squamous cell carcinoma patients, who were treated with CCRT followed by brachytherapy, were included in this study. Pre-therapeutic CT images were acquired. And tumor biopsies with immunohistochemistry at primary sites were performed at baseline (0 fraction (F)) and immediately after 10F. Radiomics features were extracted from the region of interest (ROI) of CT images using Matlab. The LASSO regression model with ten-fold cross-validation was utilized to select features and construct an immunomarker classifier and a radiomics signature. Their performance was evaluated by the area under the curve (AUC).

RESULTS

The changes of tumor-infiltrating CD8+T cells and macrophages after 10F radiotherapy as compared to those at baseline were used to generate the immunomarker classifier (AUC= 0.842, 95% CI:0.680-1.000). Additionally, a radiomics signature was developed using 4 key radiomics features to predict the immunomarker classifier (AUC=0.875, 95% CI:0.753-0.997). The patients stratified based on this signature exhibited significant differences in treatment response (p = 0.004).

CONCLUSION

The radiomics signature could be used as a potential predictor for the CCRT-induced dynamic alterations of CD8+ T cells and macrophages, which may provide a less invasive approach to appraise tumor immune status during CCRT in cervical cancer compared to tissue biopsy.

An accessible deep learning tool for voxel-wise classification of brain malignancies from perfusion MRI

Noninvasive differential diagnosis of brain tumors is currently based on the assessment of magnetic resonance imaging (MRI) coupled with dynamic susceptibility contrast (DSC). However, a definitive diagnosis often requires neurosurgical interventions that compromise patients' quality of life. We apply deep learning on DSC images from histology-confirmed patients with glioblastoma, metastasis, or lymphoma. The convolutional neural network trained on ∼50,000 voxels from 40 patients provides intratumor probability maps that yield clinical-grade diagnosis. Performance is tested in 400 additional cases and an external validation cohort of 128 patients. The tool reaches a three-way accuracy of 0.78, superior to the conventional MRI metrics cerebral blood volume (0.55) and percentage of signal recovery (0.59), showing high value as a support diagnostic tool. Our open-access software, Diagnosis In Susceptibility Contrast Enhancing Regions for Neuro-oncology (DISCERN), demonstrates its potential in aiding medical decisions for brain tumor diagnosis using standard-of-care MRI.

Classification of high-grade glioblastoma and single brain metastases using a new SCAT-inception model trained with MRI images

Background and objectives

Glioblastoma (GBM) and brain metastasis (MET) are the two most common intracranial tumors. However, the different pathogenesis of the two tumors leads to completely different treatment options. In terms of magnetic resonance imaging (MRI), GBM and MET are extremely similar, which makes differentiation by imaging extremely challenging. Therefore, this study explores an improved deep learning algorithm to assist in the differentiation of GBM and MET.

Materials and methods

For this study, axial contrast-enhanced T1 weight (ceT1W) MRI images from 321 cases of high-grade gliomas and solitary brain metastasis were collected. Among these, 251 out of 270 cases were selected for the experimental dataset (127 glioblastomas and 124 metastases), 207 cases were chosen as the training dataset, and 44 cases as the testing dataset. We designed a new deep learning algorithm called SCAT-inception (Spatial Convolutional Attention inception) and used five-fold cross-validation to verify the results.

Results

By employing the newly designed SCAT-inception model to predict glioblastomas and brain metastasis, the prediction accuracy reached 92.3%, and the sensitivity and specificity reached 93.5 and 91.1%, respectively. On the external testing dataset, our model achieved an accuracy of 91.5%, which surpasses other model performances such as VGG, UNet, and GoogLeNet.

Conclusion

This study demonstrated that the SCAT-inception architecture could extract more subtle features from ceT1W images, provide state-of-the-art performance in the differentiation of GBM and MET, and surpass most existing approaches.

Natural language processing deep learning models for the differential between high-grade gliomas and metastasis: what if the key is how we report them?

OBJECTIVES

The differential between high-grade glioma (HGG) and metastasis remains challenging in common radiological practice. We compare different natural language processing (NLP)-based deep learning models to assist radiologists based on data contained in radiology reports.

METHODS

This retrospective study included 185 MRI reports between 2010 and 2022 from two different institutions. A total of 117 reports were used for the training and 21 were reserved for the validation set, while the rest were used as a test set. A comparison of the performance of different deep learning models for HGG and metastasis classification has been carried out. Specifically, Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), a hybrid version of BiLSTM and CNN, and a radiology-specific Bidirectional Encoder Representations from Transformers (RadBERT) model were used.

RESULTS

For the classification of MRI reports, the CNN network provided the best results among all tested, showing a macro-avg precision of 87.32%, a sensitivity of 87.45%, and an F1 score of 87.23%. In addition, our NLP algorithm detected keywords such as tumor, temporal, and lobe to positively classify a radiological report as HGG or metastasis group.

CONCLUSIONS

A deep learning model based on CNN enables radiologists to discriminate between HGG and metastasis based on MRI reports with high-precision values. This approach should be considered an additional tool in diagnosing these central nervous system lesions.

CLINICAL RELEVANCE STATEMENT

The use of our NLP model enables radiologists to differentiate between patients with high-grade glioma and metastasis based on their MRI reports and can be used as an additional tool to the conventional image-based approach for this challenging task.

KEY POINTS

• Differential between high-grade glioma and metastasis is still challenging in common radiological practice. • Natural language processing (NLP)-based deep learning models can assist radiologists based on data contained in radiology reports. • We have developed and tested a natural language processing model for discriminating between high-grade glioma and metastasis based on MRI reports that show high precision for this task.

An integrated machine learning-based model for joint diagnosis of ovarian cancer with multiple test indicators

OBJECTIVE

To construct a machine learning diagnostic model integrating feature dimensionality reduction techniques and artificial neural network classifiers to develop the value of clinical routine blood indexes for the auxiliary diagnosis of ovarian cancer.

METHODS

Patients with ovarian cancer clearly diagnosed in our hospital were collected as a case group (n = 185), and three groups of patients with other malignant otolaryngology tumors (n = 138), patients with benign otolaryngology diseases (n = 339) and those with normal physical examination (n = 92) were used as an overall control group. In this paper, a fully automated segmentation network for magnetic resonance images of ovarian cancer is proposed to improve the reproducibility of tumor segmentation results while effectively reducing the burden on radiologists. A pre-trained Res Net50 is used to the three edge output modules are fused to obtain the final segmentation results. The segmentation results of the proposed network architecture are compared with the segmentation results of the U-net based network architecture and the effect of different loss functions and region of interest sizes on the segmentation performance of the proposed network is analyzed.

RESULTS

The average Dice similarity coefficient, average sensitivity, average specificity (specificity) and average hausdorff distance of the proposed network segmentation results reached 83.62%, 89.11%, 96.37% and 8.50, respectively, which were better than the U-net based segmentation method. For ROIs containing tumor tissue, the smaller the size, the better the segmentation effect. Several loss functions do not differ much. The area under the ROC curve of the machine learning diagnostic model reached 0.948, with a sensitivity of 91.9% and a specificity of 86.9%, and its diagnostic efficacy was significantly better than that of the traditional way of detecting CA125 alone. The model was able to accurately diagnose ovarian cancer of different disease stages and showed certain discriminative ability for ovarian cancer in all three control subgroups.

CONCLUSION

Using machine learning to integrate multiple conventional test indicators can effectively improve the diagnostic efficacy of ovarian cancer, which provides a new idea for the intelligent auxiliary diagnosis of ovarian cancer.

Incidence and imaging characteristics of difficult to detect retrospectively identified brain metastases in patients receiving repeat courses of stereotactic radiosurgery

PURPOSE

During stereotactic radiosurgery (SRS) planning for brain metastases (BM), brain MRIs are reviewed to select appropriate targets based on radiographic characteristics. Some BM are difficult to detect and/or definitively identify and may go untreated initially, only to become apparent on future imaging. We hypothesized that in patients receiving multiple courses of SRS, reviewing the initial planning MRI would reveal early evidence of lesions that developed into metastases requiring SRS.

METHODS

Patients undergoing two or more courses of SRS to BM within 6 months between 2016 and 2018 were included in this single-institution, retrospective study. Brain MRIs from the initial course were reviewed for lesions at the same location as subsequently treated metastases; if present, this lesion was classified as a "retrospectively identified metastasis" or RIM. RIMs were subcategorized as meeting or not meeting diagnostic imaging criteria for BM (+ DC or -DC, respectively).

RESULTS

Among 683 patients undergoing 923 SRS courses, 98 patients met inclusion criteria. There were 115 repeat courses of SRS, with 345 treated metastases in the subsequent course, 128 of which were associated with RIMs found in a prior MRI. 58% of RIMs were + DC. 17 (15%) of subsequent courses consisted solely of metastases associated with + DC RIMs.

CONCLUSION

Radiographic evidence of brain metastases requiring future treatment was occasionally present on brain MRIs from prior SRS treatments. Most RIMs were + DC, and some subsequent SRS courses treated only + DC RIMs. These findings suggest enhanced BM detection might enable earlier treatment and reduce the need for additional SRS.

Applications of Machine Learning (ML) and Mathematical Modeling (MM) in Healthcare with Special Focus on Cancer Prognosis and Anticancer Therapy: Current Status and Challenges

The use of data-driven high-throughput analytical techniques, which has given rise to computational oncology, is undisputed. The widespread use of machine learning (ML) and mathematical modeling (MM)-based techniques is widely acknowledged. These two approaches have fueled the advancement in cancer research and eventually led to the uptake of telemedicine in cancer care. For diagnostic, prognostic, and treatment purposes concerning different types of cancer research, vast databases of varied information with manifold dimensions are required, and indeed, all this information can only be managed by an automated system developed utilizing ML and MM. In addition, MM is being used to probe the relationship between the pharmacokinetics and pharmacodynamics (PK/PD interactions) of anti-cancer substances to improve cancer treatment, and also to refine the quality of existing treatment models by being incorporated at all steps of research and development related to cancer and in routine patient care. This review will serve as a consolidation of the advancement and benefits of ML and MM techniques with a special focus on the area of cancer prognosis and anticancer therapy, leading to the identification of challenges (data quantity, ethical consideration, and data privacy) which are yet to be fully addressed in current studies.

New Directions in Diagnostics for Aortic Aneurysms: Biomarkers and Machine Learning

This review article presents an appraisal of pioneering technologies poised to revolutionize the diagnosis and management of aortic aneurysm disease, with a primary focus on the thoracic aorta while encompassing insights into abdominal manifestations. Our comprehensive analysis is rooted in an exhaustive survey of contemporary and historical research, delving into the realms of machine learning (ML) and computer-assisted diagnostics. This overview draws heavily upon relevant studies, including Siemens' published field report and many peer-reviewed publications. At the core of our survey lies an in-depth examination of ML-driven diagnostic advancements, dissecting an array of algorithmic suites to unveil the foundational concepts anchoring computer-assisted diagnostics and medical image processing. Our review extends to a discussion of circulating biomarkers, synthesizing insights gleaned from our prior research endeavors alongside contemporary studies gathered from the PubMed Central database. We elucidate the prevalent challenges and envisage the potential fusion of AI-guided aortic measurements and sophisticated ML frameworks with the computational analyses of pertinent biomarkers. By framing current scientific insights, we contemplate the transformative prospect of translating fundamental research into practical diagnostic tools. This narrative not only illuminates present strides, but also forecasts promising trajectories in the clinical evaluation and therapeutic management of aortic aneurysm disease.

Advances in Neuro-Oncological Imaging: An Update on Diagnostic Approach to Brain Tumors

This study delineates the pivotal role of imaging within the field of neurology, emphasizing its significance in the diagnosis, prognostication, and evaluation of treatment responses for central nervous system (CNS) tumors. A comprehensive understanding of both the capabilities and limitations inherent in emerging imaging technologies is imperative for delivering a heightened level of personalized care to individuals with neuro-oncological conditions. Ongoing research in neuro-oncological imaging endeavors to rectify some limitations of radiological modalities, aiming to augment accuracy and efficacy in the management of brain tumors. This review is dedicated to the comparison and critical examination of the latest advancements in diverse imaging modalities employed in neuro-oncology. The objective is to investigate their respective impacts on diagnosis, cancer staging, prognosis, and post-treatment monitoring. By providing a comprehensive analysis of these modalities, this review aims to contribute to the collective knowledge in the field, fostering an informed approach to neuro-oncological care. In conclusion, the outlook for neuro-oncological imaging appears promising, and sustained exploration in this domain is anticipated to yield further breakthroughs, ultimately enhancing outcomes for individuals grappling with CNS tumors.

An [18F]FDG PET/3D-ultrashort echo time MRI-based radiomics model established by machine learning facilitates preoperative assessment of lymph node status in non-small cell lung cancer

OBJECTIVES

To develop an [18F]FDG PET/3D-UTE model based on clinical factors, three-dimensional ultrashort echo time (3D-UTE), and PET radiomics features via machine learning for the assessment of lymph node (LN) status in non-small cell lung cancer (NSCLC).

METHODS

A total of 145 NSCLC patients (training, 101 cases; test, 44 cases) underwent whole-body [18F]FDG PET/CT and chest [18F]FDG PET/MRI were enrolled. Preoperative clinical factors and 3D-UTE, CT, and PET radiomics features were analyzed. The Mann-Whitney U test, LASSO regression, and SelectKBest were used for feature extraction. Five machine learning algorithms were used to establish prediction models, which were evaluated by the area under receiver-operator characteristic (ROC), DeLong test, calibration curves, and decision curve analysis (DCA).

RESULTS

A prediction model based on random forest, consisting of four clinical factors, six 3D-UTE, and six PET radiomics features, was used as the final model for PET/3D-UTE. The AUCs of this model were 0.912 and 0.791 in the training and test sets, respectively, which not only showed different degrees of improvement over individual models such as clinical, 3D-UTE, and PET (AUC-training = 0.838, 0.834, and 0.828, AUC-test = 0.756, 0.745, and 0.768, respectively) but also achieved the similar diagnostic efficacy as the optimal PET/CT model (AUC-training = 0.890, AUC-test = 0.793). The calibration curves and DCA indicated good consistency (C-index, 0.912) and clinical utility of this model, respectively.

CONCLUSION

The [18F]FDG PET/3D-UTE model based on clinical factors, 3D-UTE, and PET radiomics features using machine learning methods could noninvasively assess the LN status of NSCLC.

CLINICAL RELEVANCE STATEMENT

A machine learning model of 18F-fluorodeoxyglucose positron emission tomography/ three-dimensional ultrashort echo time could noninvasively assess the lymph node status of non-small cell lung cancer, which provides a novel method with less radiation burden for clinical practice.

KEY POINTS

• The 3D-UTE radiomics model using the PLS-DA classifier was significantly associated with LN status in NSCLC and has similar diagnostic performance as the clinical, CT, and PET models. • The [18F]FDG PET/3D-UTE model based on clinical factors, 3D-UTE, and PET radiomics features using the RF classifier could noninvasively assess the LN status of NSCLC and showed improved diagnostic performance compared to the clinical, 3D-UTE, and PET models. • In the assessment of LN status in NSCLC, the [18F]FDG PET/3D-UTE model has similar diagnostic efficacy as the [18F]FDG PET/CT model that incorporates clinical factors and CT and PET radiomics features.

Differentiation between cerebral alveolar echinococcosis and brain metastases with radiomics combined machine learning approach

BACKGROUND

Cerebral alveolar echinococcosis (CAE) and brain metastases (BM) share similar in locations and imaging appearance. However, they require distinct treatment approaches, with CAE typically treated with chemotherapy and surgery, while BM is managed with radiotherapy and targeted therapy for the primary malignancy. Accurate diagnosis is crucial due to the divergent treatment strategies.

PURPOSE

This study aims to evaluate the effectiveness of radiomics and machine learning techniques based on magnetic resonance imaging (MRI) to differentiate between CAE and BM.

METHODS

We retrospectively analyzed MRI images of 130 patients (30 CAE and 100 BM) from Xinjiang Medical University First Affiliated Hospital and The First People's Hospital of Kashi Prefecture, between January 2014 and December 2022. The dataset was divided into training (91 cases) and testing (39 cases) sets. Three dimensional tumors were segmented by radiologists from contrast-enhanced T1WI images on open resources software 3D Slicer. Features were extracted on Pyradiomics, further feature reduction was carried out using univariate analysis, correlation analysis, and least absolute shrinkage and selection operator (LASSO). Finally, we built five machine learning models, support vector machine, logistic regression, linear discrimination analysis, k-nearest neighbors classifier, and Gaussian naïve bias and evaluated their performance via several metrics including sensitivity (recall), specificity, positive predictive value (precision), negative predictive value, accuracy and the area under the curve (AUC).

RESULTS

The area under curve (AUC) of support vector classifier (SVC), linear discrimination analysis (LDA), k-nearest neighbors (KNN), and gaussian naïve bias (NB) algorithms in training (testing) sets are 0.99 (0.94), 1.00 (0.87), 0.98 (0.92), 0.97 (0.97), and 0.98 (0.93), respectively. Nested cross-validation demonstrated the robustness and generalizability of the models. Additionally, the calibration plot and decision curve analysis demonstrated the practical usefulness of these models in clinical practice, with lower bias toward different subgroups during decision-making.

CONCLUSION

The combination of radiomics and machine learning approach based on contrast enhanced T1WI images could well distinguish CAE and BM. This approach holds promise in assisting doctors with accurate diagnosis and clinical decision-making.

Detection of Intracranial Aneurysms Using Multiphase CT Angiography with a Deep Learning Model

RATIONALE AND OBJECTIVES

Determine the effect of a multiphase fusion deep-learning model with automatic phase selection in detection of intracranial aneurysm (IA) from computed tomography angiography (CTA) images.

MATERIALS AND METHODS

CTA images of intracranial arteries from patients at Ningbo First Hospital were retrospectively analyzed. Images were randomly classified as training data, internal validation data, or test data. CTA images from cases examined by digital subtraction angiography (DSA) were examined for independent validation. A deep-learning model was constructed by automatic phase selection of multiphase fusion, and compared to the single-phase algorithm to evaluate algorithm sensitivity.

RESULTS

We analyzed 1110 patients (1493 aneurysms) as training data, 139 patients (174 aneurysms) as internal validation data, and 134 patients (175 aneurysms) as test data. The sensitivity of the multiphase analysis of the internal validation data, test data, and independent validation data were greater than from the single-phase analysis. The recall of the multiphase selection was greater or equal to that of single-phase selection in the aneurysm position, shape, size, and rupture status. Use of the test data to determine the presence and absence of aneurysm rupture led to a recall from multiphase selection of 94.8% and 87.6% respectively; both of these values were greater than those from single-phase selection (89.6% and 79.4%).

CONCLUSION

A multiphase fusion deep learning model with automatic phase selection provided automated detection of IAs with high sensitivity.

An Intelligent System to Improve Diagnostic Support for Oral Squamous Cell Carcinoma

Oral squamous cell carcinoma (OSCC) is one of the most-prevalent cancer types worldwide, and it poses a serious threat to public health due to its high mortality and morbidity rates. OSCC typically has a poor prognosis, significantly reducing the chances of patient survival. Therefore, early detection is crucial to achieving a favorable prognosis by providing prompt treatment and increasing the chances of remission. Salivary biomarkers have been established in numerous studies to be a trustworthy and non-invasive alternative for early cancer detection. In this sense, we propose an intelligent system that utilizes feed-forward artificial neural networks to classify carcinoma with salivary biomarkers extracted from control and OSCC patient samples. We conducted experiments using various salivary biomarkers, ranging from 1 to 51, to train the model, and we achieved excellent results with precision, sensitivity, and specificity values of 98.53%, 96.30%, and 97.56%, respectively. Our system effectively classified the initial cases of OSCC with different amounts of biomarkers, aiding medical professionals in decision-making and providing a more-accurate diagnosis. This could contribute to a higher chance of treatment success and patient survival. Furthermore, the minimalist configuration of our model presents the potential for incorporation into resource-limited devices or environments.

MRI radiomics for brain metastasis sub-pathology classification from non-small cell lung cancer: a machine learning, multicenter study

The objective of this study is to develop a machine-learning model that can accurately distinguish between different histologic types of brain lesions in patients with non-small cell lung cancer (NSCLC) when it is not safe or feasible to perform a biopsy. To achieve this goal, the study utilized data from two patient cohorts: 116 patients from Xiangya Hospital and 35 patients from Yueyang Central Hospital. A total of eight machine learning algorithms, including Xgboost, were compared. Additionally, a 3-dimensional convolutional neural network was trained using transfer learning to further evaluate the performance of these models. The SHapley Additive exPlanations (SHAP) method was developed to determine the most important features in the best-performing model after hyperparameter optimization. The results showed that the area under the curve (AUC) for the classification of brain lesions as either lung adenocarcinoma or squamous carcinoma ranged from 0.60 to 0.87. The model based on single radiomics features extracted from contrast-enhanced T1 MRI and utilizing the Xgboost algorithm demonstrated the highest performance (AUC: 0.85) in the internal validation set and adequate performance (AUC: 0.80) in the independent external validation set. The SHAP values also revealed the impact of individual features on the classification results. In conclusion, the use of a radiomics model incorporating contrast-enhanced T1 MRI, Xgboost, and SHAP algorithms shows promise in accurately and interpretably identifying brain lesions in patients with NSCLC.

Discrimination Between Glioblastoma and Solitary Brain Metastasis Using Conventional MRI and Diffusion-Weighted Imaging Based on a Deep Learning Algorithm

This study aims to develop and validate a deep learning (DL) model to differentiate glioblastoma from single brain metastasis (BM) using conventional MRI combined with diffusion-weighted imaging (DWI). Preoperative conventional MRI and DWI of 202 patients with solitary brain tumor (104 glioblastoma and 98 BM) were retrospectively obtained between February 2016 and September 2022. The data were divided into training and validation sets in a 7:3 ratio. An additional 32 patients (19 glioblastoma and 13 BM) from a different hospital were considered testing set. Single-MRI-sequence DL models were developed using the 3D residual network-18 architecture in tumoral (T model) and tumoral + peritumoral regions (T&P model). Furthermore, the combination model based on conventional MRI and DWI was developed. The area under the receiver operating characteristic curve (AUC) was used to assess the classification performance. The attention area of the model was visualized as a heatmap by gradient-weighted class activation mapping technique. For the single-MRI-sequence DL model, the T2WI sequence achieved the highest AUC in the validation set with either T models (0.889) or T&P models (0.934). In the combination models of the T&P model, the model of DWI combined with T2WI and contrast-enhanced T1WI showed increased AUC of 0.949 and 0.930 compared with that of single-MRI sequences in the validation set, respectively. And the highest AUC (0.956) was achieved by combined contrast-enhanced T1WI, T2WI, and DWI. In the heatmap, the central region of the tumoral was hotter and received more attention than other areas and was more important for differentiating glioblastoma from BM. A conventional MRI-based DL model could differentiate glioblastoma from solitary BM, and the combination models improved classification performance.

Radiomics and Machine Learning in Brain Tumors and Their Habitat: A Systematic Review

Radiomics is a rapidly evolving field that involves extracting and analysing quantitative features from medical images, such as computed tomography or magnetic resonance images. Radiomics has shown promise in brain tumor diagnosis and patient-prognosis prediction by providing more detailed and objective information about tumors' features than can be obtained from the visual inspection of the images alone. Radiomics data can be analyzed to determine their correlation with a tumor's genetic status and grade, as well as in the assessment of its recurrence vs. therapeutic response, among other features. In consideration of the multi-parametric and high-dimensional space of features extracted by radiomics, machine learning can further improve tumor diagnosis, treatment response, and patients' prognoses. There is a growing recognition that tumors and their microenvironments (habitats) mutually influence each other-tumor cells can alter the microenvironment to increase their growth and survival. At the same time, habitats can also influence the behavior of tumor cells. In this systematic review, we investigate the current limitations and future developments in radiomics and machine learning in analysing brain tumors and their habitats.

Quantitative evaluation of the infrapatellar fat pad in knee osteoarthritis: MRI-based radiomic signature

BACKGROUND

The infrapatellar fat pad (IFP) may have bilateral influence on knee osteoarthritis (KOA). IFP evaluation may be a key contributor to the diagnostic and clinical management of KOA. Few studies have evaluated KOA-related IFP alteration with radiomics. We investigated radiomic signature for the assessment of IFP for KOA progression in older adults.

METHODS

A total of 164 knees were enrolled and grouped based on Kellgren-Lawrence (KL) scoring. MRI-based radiomic features were calculated from IFP segmentation. The radiomic signature was developed using the most predictive subset of features and the machine-learning algorithm with minimum relative standard deviation. KOA severity and structure abnormality were assessed using a modified whole-organ magnetic resonance imaging score (WORMS). The performance of the radiomic signature was evaluated and the correlation with WORMS assessments was analyzed.

RESULTS

The area under the curve of the radiomic signature for diagnosing KOA was 0.83 and 0.78 in the training and test datasets, respectively. Rad-scores were 0.41 and 2.01 for the training dataset in the groups with and without KOA (P < 0.001) and 0.63 and 2.31 for the test dataset (P = 0.005), respectively. WORMS significantly and positively correlated with rad-scores.

CONCLUSIONS

The radiomic signature may be a reliable biomarker to detect IFP abnormality of KOA. Radiomic alterations in IFP were associated with severity and knee structural abnormalities of KOA in older adults.

Emerging role of artificial intelligence in diagnosis, classification and clinical management of glioma

Glioma represents a dominant primary intracranial malignancy in the central nervous system. Artificial intelligence that mainly includes machine learning, and deep learning computational approaches, presents a unique opportunity to enhance clinical management of glioma through improving tumor segmentation, diagnosis, differentiation, grading, treatment, prediction of clinical outcomes (prognosis, and recurrence), molecular features, clinical classification, characterization of the tumor microenvironment, and drug discovery. A growing body of recent studies apply artificial intelligence-based models to disparate data sources of glioma, covering imaging modalities, digital pathology, high-throughput multi-omics data (especially emerging single-cell RNA sequencing and spatial transcriptome), etc. While these early findings are promising, future studies are required to normalize artificial intelligence-based models to improve the generalizability and interpretability of the results. Despite prominent issues, targeted clinical application of artificial intelligence approaches in glioma will facilitate the development of precision medicine of this field. If these challenges can be overcome, artificial intelligence has the potential to profoundly change the way patients with or at risk of glioma are provided with more rational care.

Multisequence magnetic resonance imaging-based radiomics models for the prediction of microsatellite instability in endometrial cancer

PURPOSE

To evaluate the performance of multisequence magnetic resonance imaging (MRI)-based radiomics models in the assessment of microsatellite instability (MSI) status in endometrial cancer (EC).

MATERIALS AND METHODS

This retrospective multicentre study included 338 EC patients with available MSI status and preoperative MRI scans, divided into training (37 MSI, 123 microsatellite stability [MSS]), internal validation (15 MSI, 52 MSS), and external validation cohorts (30 MSI, 81 MSS). Radiomics features were extracted from T2-weighted images, diffusion-weighted images, and contrast-enhanced T1-weighted images. The ComBat harmonisation method was applied to remove intrascanner variability. The Boruta wrapper algorithm was used for key feature selection. Three classification algorithms, logistic regression (LR), random forest (RF), and support vector machine (SVM), were applied to build the radiomics models. The area under the receiver operating characteristic curve (AUC) was calculated to compare the diagnostic performance of the models. Decision curve analysis (DCA) was conducted to determine the clinical usefulness of the models.

RESULTS

Among the 1980 features, Boruta finally selected nine radiomics features. A higher MSI prediction performance was achieved after running the ComBat harmonisation method. The SVM algorithm had the best performance, with AUCs of 0.921, 0.903, and 0.937 in the training, internal validation, and external validation cohorts, respectively. The DCA results showed that the SVM algorithm achieved higher net benefits than the other classifiers over a threshold range of 0.581-0.783.

CONCLUSION

The multisequence MRI-based radiomics models showed promise in preoperatively predicting the MSI status in EC in this multicentre setting.

Firefly-SVM predictive model for breast cancer subgroup classification with clinicopathological parameters

Background

Breast cancer is a highly predominant destructive disease among women characterised with varied tumour biology, molecular subgroups and diverse clinicopathological specifications. The potentiality of machine learning to transform complex medical data into meaningful knowledge has led to its application in breast cancer detection and prognostic evaluation.

Objective

The emergence of data-driven diagnostic model for assisting clinicians in diagnostic decision making has gained an increasing curiosity in breast cancer identification and analysis. This motivated us to develop a breast cancer data-driven model for subtype classification more accurately.

Method

In this article, we proposed a firefly-support vector machine (SVM) breast cancer predictive model that uses clinicopathological and demographic data gathered from various tertiary care cancer hospitals or oncological centres to distinguish between patients with triple-negative breast cancer (TNBC) and non-triple-negative breast cancer (non-TNBC).

Results

The results of the firefly-support vector machine (firefly-SVM) predictive model were distinguished from the traditional grid search-support vector machine (Grid-SVM) model, particle swarm optimisation-support vector machine (PSO-SVM) and genetic algorithm-support vector machine (GA-SVM) hybrid models through hyperparameter tuning. The findings show that the recommended firefly-SVM classification model outperformed other existing models in terms of prediction accuracy (93.4%, 86.6%, 69.6%) for automated SVM parameter selection. The effectiveness of the prediction model was also evaluated using well-known metrics, such as the F1-score, mean square error, area under the ROC curve, logarithmic loss and precision-recall curve.

Conclusion

Firefly-SVM predictive model may be treated as an alternate tool for breast cancer subgroup classification that would benefit the clinicians for managing the patient with proper treatment and diagnostic outcome.

Brain metastases from NSCLC treated with stereotactic radiotherapy: prediction mismatch between two different radiomic platforms

BACKGROUND AND PURPOSE

Radiomics enables the mining of quantitative features from medical images. The influence of the radiomic feature extraction software on the final performance of models is still a poorly understood topic. This study aimed to investigate the ability of radiomic features extracted by two different radiomic platforms to predict clinical outcomes in patients treated with radiosurgery for brain metastases from non-small cell lung cancer. We developed models integrating pre-treatment magnetic resonance imaging (MRI)-derived radiomic features and clinical data.

MATERIALS AND METHODS

Pre-radiotherapy gadolinium enhanced axial T1-weighted MRI scans were used. MRI images were re-sampled, intensity-shifted, and histogram-matched before radiomic extraction by means of two different platforms (PyRadiomics and SOPHiA Radiomics). We adopted LASSO Cox regression models for multivariable analyses by creating radiomic, clinical, and combined models using three survival clinical endpoints (local control, distant progression, and overall survival). The statistical analysis was repeated 50 times with different random seeds and the median concordance index was used as performance metric of the models.

RESULTS

We analysed 276 metastases from 148 patients. The use of the two platforms resulted in differences in both the quality and the number of extractable features. That led to mismatches in terms of end-to-end performance, statistical significance of radiomic scores, and clinical covariates found significant in combined models.

CONCLUSION

This study shed new light on how extracting radiomic features from the same images using two different platforms could yield several discrepancies. That may lead to acute consequences on drawing conclusions, comparing results across the literature, and translating radiomics into clinical practice.

Computed tomography-based radiomics machine learning classifiers to differentiate type I and type II epithelial ovarian cancers

OBJECTIVES

To compare computed tomography (CT)-based radiomics for preoperatively differentiating type I and II epithelial ovarian cancers (EOCs) using different machine learning classifiers and to construct and validate the best diagnostic model.

METHODS

A total of 470 patients with EOCs were included retrospectively. Patients were divided into a training dataset (N = 329) and a test dataset (N = 141). A total of 1316 radiomics features were extracted from the portal venous phase of contrast-enhanced CT images for each patient, followed by dimension reduction of the features. The support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF), naïve Bayes (NB), logistic regression (LR), and eXtreme Gradient Boosting (XGBoost) classifiers were trained to obtain the radiomics signatures. The performance of each radiomics signature was evaluated and compared by the area under the receiver operating characteristic curve (AUC) and relative standard deviation (RSD). The best radiomics signature was selected and combined with clinical and radiological features to establish a combined model. The diagnostic value of the combined model was assessed.

RESULTS

The LR-based radiomics signature performed well in the test dataset, with an AUC of 0.879 and an accuracy of 0.773. The combined model performed best in both the training and test datasets, with AUCs of 0.900 and 0.934 and accuracies of 0.848 and 0.823, respectively.

CONCLUSION

The combined model showed the best diagnostic performance for distinguishing between type I and II EOCs preoperatively. Therefore, it can be a useful tool for clinical individualized EOC classification.

KEY POINTS

• Radiomics features extracted from computed tomography (CT) could be used to differentiate type I and II epithelial ovarian cancers (EOCs). • Machine learning can improve the performance of differentiating type I and II EOCs. • The combined model exhibited the best diagnostic capability over the other models in both the training and test datasets.

A hierarchical machine learning model based on Glioblastoma patients' clinical, biomedical, and image data to analyze their treatment plans

AIM OF STUDY

Glioblastoma Multiforme (GBM) is an aggressive brain cancer in adults that kills most patients in the first year due to ineffective treatment. Different clinical, biomedical, and image data features are needed to analyze GBM, increasing complexities. Besides, they lead to weak performances for machine learning models due to ignoring physicians' knowledge. Therefore, this paper proposes a hierarchical model based on Fuzzy C-mean (FCM) clustering, Wrapper feature selection, and twelve classifiers to analyze treatment plans.

METHODOLOGY/APPROACH

The proposed method finds the effectiveness of previous and current treatment plans, hierarchically determining the best decision for future treatment plans for GBM patients using clinical data, biomedical data, and different image data. A case study is presented based on the Cancer Genome Atlas Glioblastoma Multiforme dataset to prove the effectiveness of the proposed model. This dataset is analyzed using data preprocessing, experts' knowledge, and a feature reduction method based on the Principal Component Analysis. Then, the FCM clustering method is utilized to reinforce classifier learning.

OUTCOMES OF STUDY

The proposed model finds the best combination of Wrapper feature selection and classifier for each cluster based on different measures, including accuracy, sensitivity, specificity, precision, F-score, and G-mean according to a hierarchical structure. It has the best performance among other reinforced classifiers. Besides, this model is compatible with real-world medical processes for GBM patients based on clinical, biomedical, and image data.

Radiomics can differentiate high-grade glioma from brain metastasis: a systematic review and meta-analysis

OBJECTIVE

(1) To evaluate the diagnostic performance of radiomics in differentiating high-grade glioma from brain metastasis and how to improve the model. (2) To assess the methodological quality of radiomics studies and explore ways of embracing the clinical application of radiomics.

METHODS

Studies using radiomics to differentiate high-grade glioma from brain metastasis published by 26 July 2021 were systematically reviewed. Methodological quality and risk of bias were assessed using the Radiomics Quality Score (RQS) system and Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool, respectively. Pooled sensitivity and specificity of the radiomics model were also calculated.

RESULTS

Seventeen studies combining 1,717 patients were included in the systematic review, of which 10 studies without data leakage suspicion were employed for the quantitative statistical analysis. The average RQS was 5.13 (14.25% of total), with substantial or almost perfect inter-rater agreements. The inclusion of clinical features in the radiomics model was only reported in one study, as was the case for publicly available algorithm code. The pooled sensitivity and specificity were 84% (95% CI, 80-88%) and 84% (95% CI, 81-87%), respectively. The performances of feature extraction from the volume of interest (VOI) or (semi) automatic segmentation in the radiomics models were superior to those of protocols employing region of interest (ROI) or manual segmentation.

CONCLUSION

Radiomics can accurately differentiate high-grade glioma from brain metastasis. The adoption of standardized workflow to avoid potential data leakage as well as the integration of clinical features and radiomics are advised to consider in future studies.

KEY POINTS

• The pooled sensitivity and specificity of radiomics for differentiating high-grade gliomas from brain metastasis were 84% and 84%, respectively. • Avoiding potential data leakage by adopting an intensive and standardized workflow is essential to improve the quality and generalizability of the radiomics model. • The application of radiomics in combination with clinical features in differentiating high-grade gliomas from brain metastasis needs further validation.

Radiomic Features of the Edema Region May Contribute to Grading Meningiomas With Peritumoral Edema

BACKGROUND

Meningiomas are frequently accompanied by peritumoral edema (PTE). The potential value of radiomic features of edema region in meningioma grading has not been investigated.

PURPOSE

To investigate whether radiomic features of edema region contribute to grading meningiomas with PTE.

STUDY TYPE

Retrospective.

POPULATION

A total of 444 patients including 196 grade II and 248 WHO grade I meningiomas: 356 patients for training, 88 for validation.

FIELD STRENGTH/SEQUENCE

A 1.5-T/3.0-T, noncontrast T1-weighted (T1WI), T2-weighted (T2WI), contrast-enhanced T1-weighted (T1CE) spin echo sequences.

ASSESSMENT

A total of 851 radiomic features were extracted from each sequence on each region (tumor and edema region). These features were integrated by region respectively. Three subsets of clinical-radiomic features were constructed by joining clinical information (sex, age, tumor volume, and edema volume) and radiomic features of three regions: tumor, edema, and combined subsets. For each subset, features were filtered by the least absolute shrinkage and selection operator (LASSO) and Random Forest algorithm. Top 20 features of each subset were finally selected.

STATISTICAL TESTS

Stochastic Gradient Boosting, Random Forest, and Bagged AdaBoost predictive models were built based on each subset. Discriminative abilities of models were quantified using receiver operating characteristics (ROC) and the area under the curve (AUC). A P value < 0.05 was considered statistically significant.

RESULTS

Random Forest model based on combined subset (AUC [95% CI] = 0.880 [0.807-0.953]) had the best discriminative ability in grading meningiomas among the final models. The best model of edema subset and tumor subset were Random Forest model (AUC [95% CI] = 0.864 [0.791-0.938]) and Stochastic Gradient Boosting model (AUC [95% CI] = 0.844 [0.760-0.928]), respectively.

DATA CONCLUSION

Radiomic features of edema region may contribute to grading meningiomas with PTE. The Random Forest model based on combined subset surpasses the best model based on tumor or edema subset regarding grading meningiomas with PTE.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 3.

Differentiating Glioblastoma Multiforme from Brain Metastases Using Multidimensional Radiomics Features Derived from MRI and Multiple Machine Learning Models

Due to different treatment strategies, it is extremely important to differentiate between glioblastoma multiforme (GBM) and brain metastases (MET). It often proves difficult to distinguish between GBM and MET using MRI due to their similar appearance on the imaging modalities. Surgical methods are still necessary for definitive diagnosis, despite the importance of magnetic resonance imaging in detecting, characterizing, and monitoring brain tumors. We introduced an accurate, convenient, and user-friendly method to differentiate between GBM and MET through routine MRI sequence and radiomics analyses. We collected 91 patients from one institution, including 50 with GBM and 41 with MET, which were proven pathologically. The tumors separately were segmented on all MRI images (T1-weighted imaging (T1WI), contrast-enhanced T1-weighted imaging (T1C), T2-weighted imaging (T2WI), and fluid-attenuated inversion recovery (FLAIR)) to form the volume of interest (VOI). Eight ML models and feature reduction strategies were evaluated using routine MRI sequences (T1W, T2W, T1-CE, and FLAIR) in two methods with (second model) and without wavelet transform (first model) radiomics. The optimal model was selected based on each model’s accuracy, AUC-roc, and F1-score values. In this study, we have achieved the result of 0.98, 0.99, and 0.98 percent for accuracy, AUC-roc, and F1-score, respectively, which have yielded a better result than the first model. In most investigated models, there were significant improvements in the multidimensional wavelets model compared to the non-multidimensional wavelets model. Multidimensional discrete wavelet transform can analyze hidden features of the MRI from a different perspective and generate accurate features which are highly correlated with the model accuracy.

Multi-task learning-based feature selection and classification models for glioblastoma and solitary brain metastases

Purpose

To investigate the diagnostic performance of feature selection via a multi-task learning model in distinguishing primary glioblastoma from solitary brain metastases.

Method

The study involved 187 patients diagnosed at Xiangya Hospital, Yunnan Provincial Cancer Hospital, and Southern Cancer Hospital between January 2010 and December 2018. Radiomic features were extracted from conventional magnetic resonance imaging including T1-weighted, T2-weighted, and contrast-enhanced T1-weighted sequences. We proposed a new multi-task learning model using these three sequences as three tasks. Multi-series fusion was performed to complement the information from different dimensions in order to enhance model robustness. Logical loss was used in the model as the data-fitting item, and the feature weights were expressed in the logical loss space as the sum of shared weights and private weights to select the common features of each task and the characteristics having an essential impact on a single task. A diagnostic model was constructed as a feature selection method as well as a classification method. We calculated accuracy, recall, precision, and area under the curve (AUC) and compared the performance of our new multi-task model with traditional diagnostic model performance.

Results

A diagnostic model combining the support vector machine algorithm as a classification algorithm and our model as a feature selection method had an average AUC of 0.993 in the training set, with AUC, accuracy, precision, and recall rates respectively of 0.992, 0.920, 0.969, and 0.871 in the test set. The diagnostic model built on our multi-task model alone, in the training set, had an average AUC of 0.987, and in the test set, the AUC, accuracy, precision, and recall rates were 0.984, 0.895, 0.954, and 0.838.

Conclusion

It is feasible to implement the multi-task learning model developed in our study using logistic regression to differentiate between glioblastoma and solitary brain metastases.

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

Objectives

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

Methods

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

Results

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

Conclusions

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

The Application of DTCWT on MRI-Derived Radiomics for Differentiation of Glioblastoma and Solitary Brain Metastases

Background: While magnetic resonance imaging (MRI) is the imaging modality of choice for the evaluation of patients with brain tumors, it may still be challenging to differentiate glioblastoma multiforme (GBM) from solitary brain metastasis (SBM) due to their similar imaging features. This study aimed to evaluate the features extracted of dual-tree complex wavelet transform (DTCWT) from routine MRI protocol for preoperative differentiation of glioblastoma (GBM) and solitary brain metastasis (SBM). Methods: A total of 51 patients were recruited, including 27 GBM and 24 SBM patients. Their contrast-enhanced T1-weighted images (CET1WIs), T2 fluid-attenuated inversion recovery (T2FLAIR) images, diffusion-weighted images (DWIs), and apparent diffusion coefficient (ADC) images were employed in this study. The statistical features of the pre-transformed images and the decomposed images of the wavelet transform and DTCWT were utilized to distinguish between GBM and SBM. Results: The support vector machine (SVM) showed that DTCWT images have a better accuracy (82.35%), sensitivity (77.78%), specificity (87.50%), and the area under the curve of the receiver operating characteristic curve (AUC) (89.20%) than the pre-transformed and conventional wavelet transform images. By incorporating DTCWT and pre-transformed images, the accuracy (86.27%), sensitivity (81.48%), specificity (91.67%), and AUC (93.06%) were further improved. Conclusions: Our studies suggest that the features extracted from the DTCWT images can potentially improve the differentiation between GBM and SBM.

Differentiation of malignant brain tumor types using intratumoral and peritumoral radiomic features

Tumor infiltration of central nervous system (CNS) malignant tumors may extend beyond visible contrast enhancement. This study explored tumor habitat characteristics in the intratumoral and peritumoral regions to distinguish common malignant brain tumors such as glioblastoma, primary central nervous system lymphoma, and brain metastases. The preoperative MRI data of 200 patients with solitary malignant brain tumors were included from two datasets for training. Quantitative radiomic features from the intratumoral and peritumoral regions were extracted for model training. The performance of the model was evaluated using data (n = 50) from the third clinical center. When combining the intratumoral and peritumoral features, the Adaboost model achieved the best area under the curve (AUC) of 0.91 and accuracy of 76.9% in the test cohort. Based on the optimal features and classifier, the model in the binary classification diagnosis achieves AUC of 0.98 (glioblastoma and lymphoma), 0.86 (lymphoma and metastases), and 0.70 (glioblastoma and metastases) in the test cohort, respectively. In conclusion, quantitative features from non-enhanced peritumoral regions (especially features from the 10-mm margin around the tumor) can provide additional information for the characterization of regional tumoral heterogeneity, which may offer potential value for future individualized assessment of patients with CNS tumors.

Diagnostic Accuracy of Deep Learning and Radiomics in Lung Cancer Staging: A Systematic Review and Meta-Analysis

Background

Artificial intelligence has far surpassed previous related technologies in image recognition and is increasingly used in medical image analysis. We aimed to explore the diagnostic accuracy of the models based on deep learning or radiomics for lung cancer staging.

Methods

Studies were systematically reviewed using literature searches from PubMed, EMBASE, Web of Science, and Wanfang Database, according to PRISMA guidelines. Studies about the diagnostic accuracy of radiomics and deep learning, including the identifications of lung cancer, tumor types, malignant lung nodules and lymph node metastase, were included. After identifying the articles, the methodological quality was assessed using the QUADAS-2 checklist. We extracted the characteristic of each study; the sensitivity, specificity, and AUROC for lung cancer diagnosis were summarized for subgroup analysis.

Results

The systematic review identified 19 eligible studies, of which 14 used radiomics models and 5 used deep learning models. The pooled AUROC of 7 studies to determine whether patients had lung cancer was 0.83 (95% CI 0.78–0.88). The pooled AUROC of 9 studies to determine whether patients had NSCLC was 0.78 (95% CI 0.73–0.83). The pooled AUROC of the 6 studies that determined patients had malignant lung nodules was 0.79 (95% CI 0.77–0.82). The pooled AUROC of the other 6 studies that determined whether patients had lymph node metastases was 0.74 (95% CI 0.66–0.82).

Conclusion

The models based on deep learning or radiomics have the potential to improve diagnostic accuracy for lung cancer staging.

Systematic Review Registration

https://inplasy.com/inplasy-2022-3-0167/, identifier: INPLASY202230167.

Preoperative Prediction of Lymph Node Metastasis of Pancreatic Ductal Adenocarcinoma Based on a Radiomics Nomogram of Dual-Parametric MRI Imaging

Purpose

This study aims to uncover and validate an MRI-based radiomics nomogram for detecting lymph node metastasis (LNM) in pancreatic ductal adenocarcinoma (PDAC) patients prior to surgery.

Materials and Methods

We retrospectively collected 141 patients with pathologically confirmed PDAC who underwent preoperative T2-weighted imaging (T2WI) and portal venous phase (PVP) contrast-enhanced T1-weighted imaging (T1WI) scans between January 2017 and December 2021. The patients were randomly divided into training (n = 98) and validation (n = 43) cohorts at a ratio of 7:3. For each sequence, 1037 radiomics features were extracted and analyzed. After applying the gradient-boosting decision tree (GBDT), the key MRI radiomics features were selected. Three radiomics scores (rad-score 1 for PVP, rad-score 2 for T2WI, and rad-score 3 for T2WI combined with PVP) were calculated. Rad-score 3 and clinical independent risk factors were combined to construct a nomogram for the prediction of LNM of PDAC by multivariable logistic regression analysis. The predictive performances of the rad-scores and the nomogram were assessed by the area under the operating characteristic curve (AUC), and the clinical utility of the radiomics nomogram was assessed by decision curve analysis (DCA).

Results

Six radiomics features of T2WI, eight radiomics features of PVP and ten radiomics features of T2WI combined with PVP were found to be associated with LNM. Multivariate logistic regression analysis showed that rad-score 3 and MRI-reported LN status were independent predictors. In the training and validation cohorts, the AUCs of rad-score 1, rad-score 2 and rad-score 3 were 0.769 and 0.751, 0.807 and 0.784, and 0.834 and 0.807, respectively. The predictive value of rad-score 3 was similar to that of rad-score 1 and rad-score 2 in both the training and validation cohorts (P &gt; 0.05). The radiomics nomogram constructed by rad-score 3 and MRI-reported LN status showed encouraging clinical benefit, with an AUC of 0.845 for the training cohort and 0.816 for the validation cohort.

Conclusions

The radiomics nomogram derived from the rad-score based on MRI features and MRI-reported lymph status showed outstanding performance for the preoperative prediction of LNM of PDAC.

A Systematic Review of the Current Status and Quality of Radiomics for Glioma Differential Diagnosis

Simple Summary

Gliomas can be difficult to discern clinically and radiologically from other brain lesions (either neoplastic or non-neoplastic) since their clinical manifestations as well as preoperative imaging features often overlap and appear misleading. Radiomics could be extremely helpful for non-invasive glioma differential diagnosis (DDx). However, implementation in clinical practice is still distant and concerns have been raised regarding the methodological quality of radiomic studies. In this context, we aimed to summarize the current status and quality of radiomic studies concerning glioma DDx in a systematic review. In total, 42 studies were selected and examined in our work. Our study revealed that, despite promising and encouraging results, current studies on radiomics for glioma DDx still lack the quality required to allow its introduction into clinical practice. This work could provide new insights and help to reach a consensus on the use of the radiomic approach for glioma DDx.

Abstract

Radiomics is a promising tool that may increase the value of imaging in differential diagnosis (DDx) of glioma. However, implementation in clinical practice is still distant and concerns have been raised regarding the methodological quality of radiomic studies. Therefore, we aimed to systematically review the current status of radiomic studies concerning glioma DDx, also using the radiomics quality score (RQS) to assess the quality of the methodology used in each study. A systematic literature search was performed to identify original articles focused on the use of radiomics for glioma DDx from 2015. Methodological quality was assessed using the RQS tool. Spearman’s correlation (ρ) analysis was performed to explore whether RQS was correlated with journal metrics and the characteristics of the studies. Finally, 42 articles were selected for the systematic qualitative analysis. Selected articles were grouped and summarized in terms of those on DDx between glioma and primary central nervous system lymphoma, those aiming at differentiating glioma from brain metastases, and those based on DDx of glioma and other brain diseases. Median RQS was 8.71 out 36, with a mean RQS of all studies of 24.21%. Our study revealed that, despite promising and encouraging results, current studies on radiomics for glioma DDx still lack the quality required to allow its introduction into clinical practice. This work could provide new insights and help to reach a consensus on the use of the radiomic approach for glioma DDx.

Image-Based Differentiation of Intracranial Metastasis From Glioblastoma Using Automated Machine Learning

Purpose

The majority of solitary brain metastases appear similar to glioblastomas (GBMs) on magnetic resonance imaging (MRI). This study aimed to develop and validate an MRI-based model to differentiate intracranial metastases from GBMs using automated machine learning.

Materials and Methods

Radiomics features from 354 patients with brain metastases and 354 with GBMs were used to build prediction algorithms based on T2-weighted images, contrast-enhanced (CE) T1-weighted images, or both. The data of these subjects were subjected to a nested 10-fold split in the training and testing groups to build the best algorithms using the tree-based pipeline optimization tool (TPOT). The algorithms were independently validated using data from 124 institutional patients with solitary brain metastases and 103 patients with GBMs from the cancer genome atlas.

Results

Three groups of models were developed. The average areas under the receiver operating characteristic curve (AUCs) were 0.856 for CE T1-weighted images, 0.976 for T2-weighted images, and 0.988 for a combination in the testing groups, and the AUCs of the groups of models in the independent validation were 0.687, 0.831, and 0.867, respectively. A total of 149 radiomics features were considered as the most valuable features for the differential diagnosis of GBMs and metastases.

Conclusion

The models established by TPOT can distinguish glioblastoma from solitary brain metastases well, and its non-invasiveness, convenience, and robustness make it potentially useful for clinical applications.