Machine learning: from radiomics to discovery and routine

Predicting lymph node metastasis in thyroid cancer: systematic review and meta-analysis on the CT/MRI-based radiomics and deep learning models

BACKGROUND

Thyroid cancer, a common endocrine malignancy, has seen increasing incidence, making lymph node metastasis (LNM) a critical factor for recurrence and survival. Radiomics and deep learning (DL) advancements offer the potential for improved LNM prediction using CT and MRI, though challenges in diagnostic accuracy remain.

METHODS

A systematic review and meta-analysis were conducted per established guidelines, with searches across PubMed, Scopus, Web of Science, and Embase up to February 15, 2024. Studies developing CT/MRI-based radiomics and/or DL models for preoperative LNM assessment in thyroid cancer patients were included. Data were extracted and analyzed using R software.

RESULTS

Sixteen studies were analyzed. In internal validation sets, sensitivity was 81.1 % (95 % CI: 75.6 %-85.6 %) and specificity 76.4 % (95 % CI: 68.4 %-82.9 %). Training sets showed a sensitivity of 84.4 % (95 % CI: 81.5 %-87 %) and a specificity of 84.7 % (95 % CI: 74.4 %-91.4 %). The pooled AUC was 86 % for internal validation and 87 % for training. Handcrafted radiomics had a sensitivity of 79.4 % and specificity of 69.2 %, while DL models showed 80.8 % sensitivity and 78.7 % specificity. Subgroup analysis revealed that models for papillary thyroid cancer (PTC) had a pooled specificity of 76.3 %, while those including other or unspecified cancers showed 68.3 % specificity. Despite heterogeneity, significant differences (p = 0.037) were noted between models with and without clinical data.

CONCLUSION

Radiomics and DL models show promising potential for detecting LNM in thyroid cancer, particularly in PTC. However, study heterogeneity underscores the need for further research to optimize these imaging tools.

A Novel Ultrasound-Based Radiomics Model for the Preoperative Prediction of Lymph Node Metastasis in Cervical Cancer

OBJECTIVE

The purpose of this retrospective study was to establish a combined model based on ultrasound (US)-radiomics and clinical factors to predict preoperative lymph node metastasis (LNM) in cervical cancer (CC) patients non-invasively.

METHODS

A total of 131 CC patients who had cervical lesions found by transvaginal sonography (TVS) from the First Affiliated Hospital of Anhui Medical University (Hefei, China) were retrospectively analyzed. The clinical independent predictors were selected using univariate and multivariate logistic regression analysis. US-radiomics features were extracted from US images; after selecting the most significant features by univariate analysis, Spearman's correlation analysis, and the least absolute shrinkage and selection operator (LASSO) algorithm; four machine-learning classification algorithms were used to build the US-radiomics model. Fivefold cross-validation was then used to test the performance of the model and compare the ability of the clinical, US-radiomics and combined models to predict LNM in CC patients.

RESULTS

Red blood cell, platelet and squamous cell carcinoma-associated antigen were independent clinical predictors of LNM (+) in CC patients. eXtreme Gradient Boosting performed the best among the four machine-learning classification algorithms. Fivefold cross-validation confirmed that eXtreme Gradient Boosting indeed performs the best, with average area under the curve values in the training and validation sets of 0.897 and 0.898. In the three prediction models, both the US-radiomics model and the combined model showed good predictive efficacy, with average area under the curve values in the training and validation sets of 0.897, 0.898 and 0.912, 0.905, respectively.

CONCLUSION

US-radiomics features combined with clinical factors can preoperatively predict LNM in CC patients non-invasively.

Optimizing evaluation of endometrial receptivity in recurrent pregnancy loss: a preliminary investigation integrating radiomics from multimodal ultrasound via machine learning

Background

Recurrent pregnancy loss (RPL) frequently links to a prolonged endometrial receptivity (ER) window, leading to the implantation of non-viable embryos. Existing ER assessment methods face challenges in reliability and invasiveness. Radiomics in medical imaging offers a non-invasive solution for ER analysis, but complex, non-linear radiomic-ER relationships in RPL require advanced analysis. Machine learning (ML) provides precision for interpreting these datasets, although research in integrating radiomics with ML for ER evaluation in RPL is limited.

Objective

To develop and validate an ML model that employs radiomic features derived from multimodal transvaginal ultrasound images, focusing on improving ER evaluation in RPL.

Methods

This retrospective, controlled study analyzed data from 346 unexplained RPL patients and 369 controls. The participants were divided into training and testing cohorts for model development and accuracy validation, respectively. Radiomic features derived from grayscale (GS) and shear wave elastography (SWE) images, obtained during the window of implantation, underwent a comprehensive five-step selection process. Five ML classifiers, each trained on either radiomic, clinical, or combined datasets, were trained for RPL risk stratification. The model demonstrating the highest performance in identifying RPL patients was selected for further validation using the testing cohort. The interpretability of this optimal model was augmented by applying Shapley additive explanations (SHAP) analysis.

Results

Analysis of the training cohort (242 RPL, 258 controls) identified nine key radiomic features associated with RPL risk. The extreme gradient boosting (XGBoost) model, combining radiomic and clinical data, demonstrated superior discriminatory ability. This was evidenced by its area under the curve (AUC) score of 0.871, outperforming other ML classifiers. Validation in the testing cohort of 215 subjects (104 RPL, 111 controls) confirmed its accuracy (AUC: 0.844) and consistency. SHAP analysis identified four endometrial SWE features and two GS features, along with clinical variables like age, SAPI, and VI, as key determinants in RPL risk stratification.

Conclusion

Integrating ML with radiomics from multimodal endometrial ultrasound during the WOI effectively identifies RPL patients. The XGBoost model, merging radiomic and clinical data, offers a non-invasive, accurate method for RPL management, significantly enhancing diagnosis and treatment.

Enhancing Ki-67 Prediction in Breast Cancer: Integrating Intratumoral and Peritumoral Radiomics From Automated Breast Ultrasound via Machine Learning

RATIONALE AND OBJECTIVES

Traditional Ki-67 evaluation in breast cancer (BC) via core needle biopsy is limited by repeatability and heterogeneity. The automated breast ultrasound system (ABUS) offers reproducibility but is constrained to morphological and echoic assessments. Radiomics and machine learning (ML) offer solutions, but their integration for improving Ki-67 predictive accuracy in BC remains unexplored. This study aims to enhance ABUS by integrating ML-assisted radiomics for Ki-67 prediction in BC, with a focus on both intratumoral and peritumoral regions.

MATERIALS AND METHODS

A retrospective analysis was conducted on 936 BC patients, split into training (n = 655) and testing (n = 281) cohorts. Radiomics features were extracted from intra- and peritumoral regions via ABUS. Feature selection involved Z-score normalization, intraclass correlation, Wilcoxon rank sum tests, minimum redundancy maximum relevance, and least absolute shrinkage and selection operator logistic regression. ML classifiers were trained and optimized for enhanced predictive accuracy. The interpretability of the optimized model was further augmented by employing Shapley additive explanations (SHAP).

RESULTS

Of the 2632 radiomics features in each patient, 15 were significantly associated with Ki-67 levels. The support vector machine (SVM) was identified as the optimal classifier, with area under the receiver operating characteristic curve values of 0.868 (training) and 0.822 (testing). SHAP analysis indicated that five peritumoral and two intratumoral features, along with age and lymph node status, were key determinants in the predictive model.

CONCLUSION

Integrating ML with ABUS-based radiomics effectively enhances Ki-67 prediction in BC, demonstrating the SVM model's strong performance with both radiomics and clinical factors.

Placental T2WI MRI-based radiomics-clinical nomogram predicts suspicious placenta accreta spectrum in patients with placenta previa

BACKGROUND

The incidence of placenta accreta spectrum (PAS) increases in women with placenta previa (PP). Many radiologists sometimes cannot completely and accurately diagnose PAS through the simple visual feature analysis of images, which can affect later treatment decisions. The study is to develop a T2WI MRI-based radiomics-clinical nomogram and evaluate its performance for non-invasive prediction of suspicious PAS in patients with PP.

METHODS

The preoperative MR images and related clinical data of 371 patients with PP were retrospectively collected from our hospital, and the intraoperative examination results were used as the reference standard of the PAS. Radiomics features were extracted from sagittal T2WI MR images and further selected by LASSO regression analysis. The radiomics score (Radscore) was calculated with logistic regression (LR) classifier. A nomogram integrating Radscore and selected clinical factors was also developed. The model performance was assessed with respect to discrimination, calibration and clinical usefulness.

RESULTS

A total of 6 radiomics features and 1 clinical factor were selected for model construction. The Radscore was significantly associated with suspicious PAS in both the training (p < 0.001) and validation (p < 0.001) datasets. The AUC of the nomogram was also higher than that of the Radscore in the training dataset (0.891 vs. 0.803, p < 0.001) and validation dataset (0.897 vs. 0.780, p < 0.001), respectively. The calibration was good, and the decision curve analysis demonstrated the nomogram had higher net benefit than the Radscore.

CONCLUSIONS

The T2WI MRI-based radiomics-clinical nomogram showed favorable diagnostic performance for predicting PAS in patients with PP, which could potentially facilitate the obstetricians for making clinical decisions.

Predictive modeling and web-based tool for cervical cancer risk assessment: A comparative study of machine learning models

In today's digital era, the rapid growth of databases presents significant challenges in data management. In order to address this, we have developed and designed CHAMP (Cervical Health Assessment using machine learning for Prediction), which is a user interface tool that can effectively and efficiently handle cervical cancer databases to detect patterns for future prediction diagnosis. CHAMP employs various machine learning algorithms which include XGBoost, SVM, Naive Bayes, AdaBoost, Decision Tree, and K-Nearest Neighbors in order to predict cervical cancer accurately. Moreover, this tool also designates to evaluate and optimize processes, to retrieve the significantly augmented algorithm for predicting cervical cancer. Although, the developed user interface tool was implemented in Python 3.9.0 using Flask, which provides a personalized and intuitive platform for pattern detection. The current study approach contributes to the accurate prediction and early detection of cervical cancer by leveraging the power of machine learning algorithms and comprehensive validation tools, which aim to provide learned decision-making.•CHAMP is a user interface tool which is designed for the detection of patterns for future diagnosis and prognosis of cervical cancer.•Various machine learning algorithms are employed for accurate prediction.•This tool provides personalized and intuitive data analysis which enables informed decision-making in healthcare.

Enhancing Prediction of Myocardial Recovery After Coronary Revascularization: Integrating Radiomics from Myocardial Contrast Echocardiography with Machine Learning

Introduction

Chronic coronary artery disease (CAD) management often relies on myocardial contrast echocardiography (MCE), yet its effectiveness is limited by subjective interpretations and difficulty in distinguishing hibernating from necrotic myocardium. This study explores the integration of machine learning (ML) with radiomics to predict functional recovery in dyskinetic myocardial segments in CAD patients undergoing revascularization, aiming to overcome these limitations.

Methods

This prospective study enrolled 55 chronic CAD patients, dividing into training (39 patients, 205 segments) and testing sets (16 patients, 68 segments). Dysfunctional myocardial segments were identified by initial wall motion scores (WMS) of ≥2 (hypokinesis or higher). Functional recovery was defined as a decrease of ≥1 grade in WMS during follow-up echocardiography. Radiomics features were extracted from dyssynergic segments in end-systolic phase MCE images across five cardiac cycles post- "flash" impulse and processed through a five-step feature selection. Four ML classifiers were trained and compared using these features and MCE parameters, to identify the optimal model for myocardial recovery prediction.

Results

Functional improvement was noted in 139 out of 273 dyskinetic segments (50.9%) following revascularization. Receiver Operating Characteristic (ROC) analysis determined that myocardial blood flow (MBF) was the most precise clinical predictor of recovery, with an area under the curve (AUC) of 0.770. Approximately 1.34 million radiomics features were extracted, with nine features identified as key predictors of myocardial recovery. The random forest (RF) model, integrating MBF values and radiomics features, demonstrated superior predictive accuracy over other ML classifiers. Validation of the RF model on the testing dataset demonstrated its effectiveness, evidenced by an AUC of 0.821, along with consistent calibration and clinical utility.

Conclusion

The integration of ML with radiomics from MCE effectively predicts myocardial recovery in CAD. The RF model, combining radiomics and MBF values, presents a non-invasive, precise approach, significantly enhancing CAD management.

An interpretable clinical ultrasound-radiomics combined model for diagnosis of stage I cervical cancer

Objective

The purpose of this retrospective study was to establish a combined model based on ultrasound (US)-radiomics and clinical factors to predict patients with stage I cervical cancer (CC) before surgery.

Materials and methods

A total of 209 CC patients who had cervical lesions found by transvaginal sonography (TVS) from the First Affiliated Hospital of Anhui Medical University were retrospectively reviewed, patients were divided into the training set (n = 146) and internal validation set (n = 63), and 52 CC patients from Anhui Provincial Maternity and Child Health Hospital and Nanchong Central Hospital were taken as the external validation set. The clinical independent predictors were selected by univariate and multivariate logistic regression analyses. US-radiomics features were extracted from US images. After selecting the most significant features by univariate analysis, Spearman's correlation analysis, and the least absolute shrinkage and selection operator (LASSO) algorithm, six machine learning (ML) algorithms were used to build the radiomics model. Next, the ability of the clinical, US-radiomics, and clinical US-radiomics combined model was compared to diagnose stage I CC. Finally, the Shapley additive explanations (SHAP) method was used to explain the contribution of each feature.

Results

Long diameter of the cervical lesion (L) and squamous cell carcinoma-associated antigen (SCCa) were independent clinical predictors of stage I CC. The eXtreme Gradient Boosting (Xgboost) model performed the best among the six ML radiomics models, with area under the curve (AUC) values in the training, internal validation, and external validation sets being 0.778, 0.751, and 0.751, respectively. In the final three models, the combined model based on clinical features and rad-score showed good discriminative power, with AUC values in the training, internal validation, and external validation sets being 0.837, 0.828, and 0.839, respectively. The decision curve analysis validated the clinical utility of the combined nomogram. The SHAP algorithm illustrates the contribution of each feature in the combined model.

Conclusion

We established an interpretable combined model to predict stage I CC. This non-invasive prediction method may be used for the preoperative identification of patients with stage I CC.

Texture-Based Radiomic SD-OCT Features Associated With Response to Anti-VEGF Therapy in a Phase III Neovascular AMD Clinical Trial

Purpose

The goal of this study was to evaluate the role of texture-based baseline radiomic features (Fr) and dynamic radiomics alterations (delta, FΔr) within multiple targeted compartments on optical coherence tomography (OCT) scans to predict response to anti-vascular endothelial growth factor (VEGF) therapy in neovascular age-related macular degeneration (nAMD).

Methods

HAWK is a phase 3 clinical trial data set of active nAMD patients (N = 1082) comparing brolucizumab and aflibercept. This analysis included patients receiving 6 mg brolucizumab or 2 mg aflibercept and categorized as complete responders (n = 280) and incomplete responders (n = 239) based on whether or not the eyes achieved/maintained fluid resolution on OCT. A total of 481 Fr were extracted from each of the fluid, subretinal hyperreflective material (SHRM), retinal tissue, and sub-retinal pigment epithelium (RPE) compartments. Most discriminating eight baseline features, selected by the minimum redundancy, maximum relevance feature selection, were evaluated using a quadratic discriminant analysis (QDA) classifier on the training set (Str, n = 363) to differentiate between the two patient groups. Classifier performance was subsequently validated on independent test set (St, n = 156).

Results

In total, 519 participants were included in this analysis from the HAWK phase 3 study. There were 280 complete responders and 219 incomplete responders. Compartmental analysis of radiomics featured identified the sub-RPE and SHRM compartments as the most distinguishing between the two response groups. The QDA classifier yielded areas under the curve of 0.78, 0.79, and 0.84, respectively, using Fr, FΔr, and combined Fr, FΔr, and Fc on St.

Conclusions

Utilizing compartmental static and dynamic radiomics features, unique differences were identified between eyes that respond differently to anti-VEGF therapy in a large phase 3 trial that may provide important predictive value.

Translational Relevance

Imaging biomarkers, such as radiomics features identified in this analysis, for predicting treatment response are needed to enhanced precision medicine in the management of nAMD.

Predicting Pathological Response to Preoperative Chemotherapy in Pancreatic Ductal Adenocarcinoma Using Post-Chemotherapy Computed Tomography Radiomics

INTRODUCTION

Assessing the response to preoperative treatment in pancreatic cancer provides valuable information for guiding subsequent treatment strategies. The present study aims to develop and validate a computed tomography (CT) radiomics-based machine learning (ML) model for predicting pathological response (PR) to preoperative chemotherapy in pancreatic ductal adenocarcinoma (PDAC).

METHODS

Retrospective data were analyzed from 86 PDAC patients undergoing neoadjuvant or conversion chemotherapy followed by surgical resection from January 2018 to May 2023. The cohort was randomly divided into training (70%, n = 60) and testing (30%, n = 26) sets. Favorable PR was defined as Evans grade IIb or greater. Radiomic features were extracted from post-chemotherapy CT images, and dimensionality reduction was performed using the least absolute shrinkage and selection operator (LASSO) logistic regression. Four ML classifiers (Light Gradient Boosting Machine (LGBM), Random Forest, AdaBoost, and Quadratic Discriminant Analysis) were evaluated for predicting a favorable PR. Model performance was primarily assessed using the area under the receiver operating characteristic curve (AUC), Brier score, and decision curve analysis.

RESULTS

Forty-one (47.7%) patients had a favorable PR. LASSO analysis on the training set identified five radiomic features. The LGBM model demonstrated the best performance, with a training AUC of 0.902 and a testing AUC of 0.923. It also exhibited the lowest Brier scores, both in training (0.136) and testing (0.135). Decision curve analysis further confirmed its clinical potential.

CONCLUSION

The CT radiomics-based ML model exhibited promising performance in predicting PR in PDAC after neoadjuvant/conversion chemotherapy. This suggests clinical utility in optimizing surgical candidates and timing of surgery, leading to personalized treatment strategies.

Radiomics in colorectal cancer patients

The main therapeutic options for colorectal cancer are surgical resection and adjuvant chemotherapy in non-metastatic disease. However, the evaluation of the overall adjuvant chemotherapy benefit in patients with a high risk of recurrence is challenging. Radiological images can represent a source of data that can be analyzed by using automated computer-based techniques, working on numerical information coded within Digital Imaging and Communications in Medicine files: This image numerical analysis has been named "radiomics". Radiomics allows the extraction of quantitative features from radiological images, mainly invisible to the naked eye, that can be further analyzed by artificial intelligence algorithms. Radiomics is expanding in oncology to either understand tumor biology or for the development of imaging biomarkers for diagnosis, staging, and prognosis, prediction of treatment response and diseases monitoring and surveillance. Several efforts have been made to develop radiomics signatures for colorectal cancer patient using computed tomography (CT) images with different aims: The preoperative prediction of lymph node metastasis, detecting BRAF and RAS gene mutations. Moreover, the use of delta-radiomics allows the analysis of variations of the radiomics parameters extracted from CT scans performed at different timepoints. Most published studies concerning radiomics and magnetic resonance imaging (MRI) mainly focused on the response of advanced tumors that underwent neoadjuvant therapy. Nodes status is the main determinant of adjuvant chemotherapy. Therefore, several radiomics model based on MRI, especially on T2-weighted images and ADC maps, for the preoperative prediction of nodes metastasis in rectal cancer has been developed. Current studies mostly focused on the applications of radiomics in positron emission tomography/CT for the prediction of survival after curative surgical resection and assessment of response following neoadjuvant chemoradiotherapy. Since colorectal liver metastases develop in about 25% of patients with colorectal carcinoma, the main diagnostic tasks of radiomics should be the detection of synchronous and metachronous lesions. Radiomics could be an additional tool in clinical setting, especially in identifying patients with high-risk disease. Nevertheless, radiomics has numerous shortcomings that make daily use extremely difficult. Further studies are needed to assess performance of radiomics in stratifying patients with high-risk disease.

An Automated Method for Artifical Intelligence Assisted Diagnosis of Active Aortitis Using Radiomic Analysis of FDG PET-CT Images

The aim of this study was to develop and validate an automated pipeline that could assist the diagnosis of active aortitis using radiomic imaging biomarkers derived from [18F]-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (FDG PET-CT) images. The aorta was automatically segmented by convolutional neural network (CNN) on FDG PET-CT of aortitis and control patients. The FDG PET-CT dataset was split into training (43 aortitis:21 control), test (12 aortitis:5 control) and validation (24 aortitis:14 control) cohorts. Radiomic features (RF), including SUV metrics, were extracted from the segmented data and harmonized. Three radiomic fingerprints were constructed: A-RFs with high diagnostic utility removing highly correlated RFs; B used principal component analysis (PCA); C-Random Forest intrinsic feature selection. The diagnostic utility was evaluated with accuracy and area under the receiver operating characteristic curve (AUC). Several RFs and Fingerprints had high AUC values (AUC > 0.8), confirmed by balanced accuracy, across training, test and external validation datasets. Good diagnostic performance achieved across several multi-centre datasets suggests that a radiomic pipeline can be generalizable. These findings could be used to build an automated clinical decision tool to facilitate objective and standardized assessment regardless of observer experience.

Impact of the Rise of Artificial Intelligence in Radiology: What Do Students Think?

The rise of artificial intelligence (AI) in medicine, and particularly in radiology, is becoming increasingly prominent. Its impact will transform the way the specialty is practiced and the current and future education model. The aim of this study is to analyze the perception that undergraduate medical students have about the current situation of AI in medicine, especially in radiology. A survey with 17 items was distributed to medical students between 3 January to 31 March 2022. Two hundred and eighty-one students correctly responded the questionnaire; 79.3% of them claimed that they knew what AI is. However, their objective knowledge about AI was low but acceptable. Only 24.9% would choose radiology as a specialty, and only 40% of them as one of their first three options. The applications of this technology were valued positively by most students, who give it an important Support Role, without fear that the radiologist will be replaced by AI (79.7%). The majority (95.7%) agreed with the need to implement well-established ethical principles in AI, and 80% valued academic training in AI positively. Surveyed medical students have a basic understanding of AI and perceive it as a useful tool that will transform radiology.

A methodological framework for AI-assisted diagnosis of active aortitis using radiomic analysis of FDG PET-CT images: Initial analysis

BACKGROUND

The aim of this study was to explore the feasibility of assisted diagnosis of active (peri-)aortitis using radiomic imaging biomarkers derived from [18F]-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (FDG PET-CT) images.

METHODS

The aorta was manually segmented on FDG PET-CT in 50 patients with aortitis and 25 controls. Radiomic features (RF) (n = 107), including SUV (Standardized Uptake Value) metrics, were extracted from the segmented data and harmonized using the ComBat technique. Individual RFs and groups of RFs (i.e., signatures) were used as input in Machine Learning classifiers. The diagnostic utility of these classifiers was evaluated with area under the receiver operating characteristic curve (AUC) and accuracy using the clinical diagnosis as the ground truth.

RESULTS

Several RFs had high accuracy, 84% to 86%, and AUC scores 0.83 to 0.97 when used individually. Radiomic signatures performed similarly, AUC 0.80 to 1.00.

CONCLUSION

A methodological framework for a radiomic-based approach to support diagnosis of aortitis was outlined. Selected RFs, individually or in combination, showed similar performance to the current standard of qualitative assessment in terms of AUC for identifying active aortitis. This framework could support development of a clinical decision-making tool for a more objective and standardized assessment of aortitis.

OCT-Derived Radiomic Features Predict Anti-VEGF Response and Durability in Neovascular Age-Related Macular Degeneration

PURPOSE

No established biomarkers currently exist for therapeutic efficacy and durability of anti-VEGF therapy in neovascular age-related macular degeneration (nAMD). This study evaluated radiomic-based quantitative OCT biomarkers that may be predictive of anti-VEGF treatment response and durability.

DESIGN

Assessment of baseline biomarkers using machine learning (ML) classifiers to predict tolerance to anti-VEGF therapy.

PARTICIPANTS

Eighty-one participants with treatment-naïve nAMD from the OSPREY study, including 15 super responders (patients who achieved and maintained retinal fluid resolution) and 66 non-super responders (patients who did not achieve or maintain retinal fluid resolution).

METHODS

A total of 962 texture-based radiomic features were extracted from fluid, subretinal hyperreflective material (SHRM), and different retinal tissue compartments of OCT scans. The top 8 features, chosen by the minimum redundancy maximum relevance feature selection method, were evaluated using 4 ML classifiers in a cross-validated approach to distinguish between the 2 patient groups. Longitudinal assessment of changes in different texture-based radiomic descriptors (delta-texture features) between baseline and month 3 also was performed to evaluate their association with treatment response. Additionally, 8 baseline clinical parameters and a combination of baseline OCT, delta-texture features, and the clinical parameters were evaluated in a cross-validated approach in terms of association with therapeutic response.

MAIN OUTCOME MEASURES

The cross-validated area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to validate the classifier performance.

RESULTS

The cross-validated AUC by the quadratic discriminant analysis classifier was 0.75 ± 0.09 using texture-based baseline OCT features. The delta-texture features within different OCT compartments between baseline and month 3 yielded an AUC of 0.78 ± 0.08. The baseline clinical parameters sub-retinal pigment epithelium volume and intraretinal fluid volume yielded an AUC of 0.62 ± 0.07. When all the baseline, delta, and clinical features were combined, a statistically significant improvement in the classifier performance (AUC, 0.81 ± 0.07) was obtained.

CONCLUSIONS

Radiomic-based quantitative assessment of OCT images was shown to distinguish between super responders and non-super responders to anti-VEGF therapy in nAMD. The baseline fluid and SHRM delta-texture features were found to be most discriminating across groups.

Machine learning in electron microscopy for advanced nanocharacterization: current developments, available tools and future outlook

In the last few years, electron microscopy has experienced a new methodological paradigm aimed to fix the bottlenecks and overcome the challenges of its analytical workflow. Machine learning and artificial intelligence are answering this call providing powerful resources towards automation, exploration, and development. In this review, we evaluate the state-of-the-art of machine learning applied to electron microscopy (and obliquely, to materials and nano-sciences). We start from the traditional imaging techniques to reach the newest higher-dimensionality ones, also covering the recent advances in spectroscopy and tomography. Additionally, the present review provides a practical guide for microscopists, and in general for material scientists, but not necessarily advanced machine learning practitioners, to straightforwardly apply the offered set of tools to their own research. To conclude, we explore the state-of-the-art of other disciplines with a broader experience in applying artificial intelligence methods to their research (e.g., high-energy physics, astronomy, Earth sciences, and even robotics, videogames, or marketing and finances), in order to narrow down the incoming future of electron microscopy, its challenges and outlook.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Stakeholders' perspectives on the future of artificial intelligence in radiology: a scoping review

OBJECTIVES

Artificial intelligence (AI) has the potential to impact clinical practice and healthcare delivery. AI is of particular significance in radiology due to its use in automatic analysis of image characteristics. This scoping review examines stakeholder perspectives on AI use in radiology, the benefits, risks, and challenges to its integration.

METHODS

A search was conducted from 1960 to November 2019 in EMBASE, PubMed/MEDLINE, Web of Science, Cochrane Library, CINAHL, and grey literature. Publications reflecting stakeholder attitudes toward AI were included with no restrictions.

RESULTS

Commentaries (n = 32), surveys (n = 13), presentation abstracts (n = 8), narrative reviews (n = 8), and a social media study (n = 1) were included from 62 eligible publications. These represent the views of radiologists, surgeons, medical students, patients, computer scientists, and the general public. Seven themes were identified (predicted impact, potential replacement, trust in AI, knowledge of AI, education, economic considerations, and medicolegal implications). Stakeholders anticipate a significant impact on radiology, though replacement of radiologists is unlikely in the near future. Knowledge of AI is limited for non-computer scientists and further education is desired. Many expressed the need for collaboration between radiologists and AI specialists to successfully improve patient care.

CONCLUSIONS

Stakeholder views generally suggest that AI can improve the practice of radiology and consider the replacement of radiologists unlikely. Most stakeholders identified the need for education and training on AI, as well as collaborative efforts to improve AI implementation. Further research is needed to gain perspectives from non-Western countries, non-radiologist stakeholders, on economic considerations, and medicolegal implications.

KEY POINTS

Stakeholders generally expressed that AI alone cannot be used to replace radiologists. The scope of practice is expected to shift with AI use affecting areas from image interpretation to patient care. Patients and the general public do not know how to address potential errors made by AI systems while radiologists believe that they should be "in-the-loop" in terms of responsibility. Ethical accountability strategies must be developed across governance levels. Students, residents, and radiologists believe that there is a lack in AI education during medical school and residency. The radiology community should work with IT specialists to ensure that AI technology benefits their work and centres patients.

Imaging Biomarkers in Thoracic Oncology: Current Advances in the Use of Radiomics in Lung Cancer Patients and its Potential Use for Therapy Response Prediction and Monitoring

BACKGROUND

 Non-small cell lung cancer (NSCLC) is the leading cause of cancer-related deaths. The development of therapies targeting molecular alterations has significantly improved the treatment of NSCLC patients. To identify these targets, tumor phenotyping is required, with tissue biopsies and molecular pathology being the gold standard. Some patients do not respond to targeted therapies and many patients suffer from tumor recurrence, which can in part be explained by tumor heterogeneity. This points out the need for new biomarkers allowing for better tumor phenotyping and monitoring during treatment to assess patient outcome.

METHOD

 The contents of this review are based on a literature search conducted using the PubMed database in March 2021 and the authors' experience.

RESULTS AND CONCLUSION

 The use of radiomics and artificial intelligence-based approaches allows for the identification of imaging biomarkers in NSCLC patients for tumor phenotyping. Several studies show promising results for models predicting molecular alterations, with the best results being achieved by combining structural and functional imaging. Radiomics could help solve the pressing clinical need for assessing and predicting therapy response. To reach this goal, advanced tumor phenotyping, considering tumor heterogeneity, is required. This could be achieved by integrating structural and functional imaging biomarkers with clinical data sources, such as liquid biopsy results. However, to allow for radiomics-based approaches to be introduced into clinical practice, further standardization using large, multi-center datasets is required.

KEY POINTS

  · Some NSCLC patients do not benefit from targeted therapies, and many patients suffer from tumor recurrence, pointing out the need for new biomarkers allowing for better tumor phenotyping and monitoring during treatment.. · The use of radiomics-based approaches allows for the identification of imaging biomarkers in NSCLC patients for tumor phenotyping.. · A multi-omics approach integrating not only structural and functional imaging biomarkers but also clinical data sources, such as liquid biopsy results, could further enhance the prediction and assessment of therapy response..

CITATION FORMAT

· Kroschke J, von Stackelberg O, Heußel CP et al. Imaging Biomarkers in Thoracic Oncology: Current Advances in the Use of Radiomics in Lung Cancer Patients and its Potential Use for Therapy Response Prediction and Monitoring. Fortschr Röntgenstr 2022; DOI: 10.1055/a-1729-1516.

Visualization of tumor heterogeneity and prediction of isocitrate dehydrogenase mutation status for human gliomas using multiparametric physiologic and metabolic MRI

This study aimed to differentiate isocitrate dehydrogenase (IDH) mutation status with the voxel-wise clustering method of multiparametric magnetic resonance imaging (MRI) and to discover biological underpinnings of the clusters. A total of 69 patients with treatment-naïve diffuse glioma were scanned with pH-sensitive amine chemical exchange saturation transfer MRI, diffusion-weighted imaging, fluid-attenuated inversion recovery, and contrast-enhanced T1-weighted imaging at 3 T. An unsupervised two-level clustering approach was used for feature extraction from acquired images. The logarithmic ratio of the labels in each class within tumor regions was applied to a support vector machine to differentiate IDH status. The highest performance to predict IDH mutation status was found for 10-class clustering, with a mean area under the curve, accuracy, sensitivity, and specificity of 0.94, 0.91, 0.90, and 0.91, respectively. Targeted biopsies revealed that the tissues with labels 7-10 showed high expression levels of hypoxia-inducible factor 1-alpha, glucose transporter 3, and hexokinase 2, which are typical of IDH wild-type glioma, whereas those with labels 1 showed low expression of these proteins. In conclusion, A machine learning model successfully predicted the IDH mutation status of gliomas, and the resulting clusters properly reflected the metabolic status of the tumors.

AI-Driven Image Analysis in Central Nervous System Tumors-Traditional Machine Learning, Deep Learning and Hybrid Models

The interpretation of imaging in medicine in general and in oncology specifically remains problematic due to several limitations which include the need to incorporate detailed clinical history, patient and disease-specific history, clinical exam features, previous and ongoing treatment, and account for the dependency on reproducible human interpretation of multiple factors with incomplete data linkage. To standardize reporting, minimize bias, expedite management, and improve outcomes, the use of Artificial Intelligence (AI) has gained significant prominence in imaging analysis. In oncology, AI methods have as a result been explored in most cancer types with ongoing progress in employing AI towards imaging for oncology treatment, assessing treatment response, and understanding and communicating prognosis. Challenges remain with limited available data sets, variability in imaging changes over time augmented by a growing heterogeneity in analysis approaches. We review the imaging analysis workflow and examine how hand-crafted features also referred to as traditional Machine Learning (ML), Deep Learning (DL) approaches, and hybrid analyses, are being employed in AI-driven imaging analysis in central nervous system tumors. ML, DL, and hybrid approaches coexist, and their combination may produce superior results although data in this space is as yet novel, and conclusions and pitfalls have yet to be fully explored. We note the growing technical complexities that may become increasingly separated from the clinic and enforce the acute need for clinician engagement to guide progress and ensure that conclusions derived from AI-driven imaging analysis reflect that same level of scrutiny lent to other avenues of clinical research.

CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network

BACKGROUND

At present, numerous challenges exist in the diagnosis of pancreatic SCNs and MCNs. After the emergence of artificial intelligence (AI), many radiomics research methods have been applied to the identification of pancreatic SCNs and MCNs.

PURPOSE

A deep neural network (DNN) model termed Multi-channel-Multiclassifier-Random Forest-ResNet (MMRF-ResNet) was constructed to provide an objective CT imaging basis for differential diagnosis between pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs).

MATERIALS AND METHODS

This study is a retrospective analysis of pancreatic unenhanced and enhanced CT images in 63 patients with pancreatic SCNs and 47 patients with MCNs (3 of which were mucinous cystadenocarcinoma) confirmed by pathology from December 2010 to August 2016. Different image segmented methods (single-channel manual outline ROI image and multi-channel image), feature extraction methods (wavelet, LBP, HOG, GLCM, Gabor, ResNet, and AlexNet) and classifiers (KNN, Softmax, Bayes, random forest classifier, and Majority Voting rule method) are used to classify the nature of the lesion in each CT image (SCNs/MCNs). Then, the comparisons of classification results were made based on sensitivity, specificity, precision, accuracy, F1 score, and area under the receiver operating characteristic curve (AUC), with pathological results serving as the gold standard.

RESULTS

Multi-channel-ResNet (AUC 0.98) was superior to Manual-ResNet (AUC 0.91).CT image characteristics of lesions extracted by ResNet are more representative than wavelet, LBP, HOG, GLCM, Gabor, and AlexNet. Compared to the use of three classifiers alone and Majority Voting rule method, the use of the MMRF-ResNet model exhibits a better evaluation effect (AUC 0.96) for the classification of the pancreatic SCNs and MCNs.

CONCLUSION

The CT image classification model MMRF-ResNet is an effective method to distinguish between pancreatic SCNs and MCNs.

Applying artificial intelligence for cancer immunotherapy

Artificial intelligence (AI) is a general term that refers to the use of a machine to imitate intelligent behavior for performing complex tasks with minimal human intervention, such as machine learning; this technology is revolutionizing and reshaping medicine. AI has considerable potential to perfect health-care systems in areas such as diagnostics, risk analysis, health information administration, lifestyle supervision, and virtual health assistance. In terms of immunotherapy, AI has been applied to the prediction of immunotherapy responses based on immune signatures, medical imaging and histological analysis. These features could also be highly useful in the management of cancer immunotherapy given their ever-increasing performance in improving diagnostic accuracy, optimizing treatment planning, predicting outcomes of care and reducing human resource costs. In this review, we present the details of AI and the current progression and state of the art in employing AI for cancer immunotherapy. Furthermore, we discuss the challenges, opportunities and corresponding strategies in applying the technology for widespread clinical deployment. Finally, we summarize the impact of AI on cancer immunotherapy and provide our perspectives about underlying applications of AI in the future.

Deep learning and radiomics analysis for prediction of placenta invasion based on T2WI

The purpose of this study was to explore whether the Nomogram, which was constructed by combining the Deep learning and Radiomic features of T2-weighted MR images with Clinical factors (NDRC), could accurately predict placenta invasion. This retrospective study included 72 pregnant women with pathologically confirmed placenta invasion and 40 pregnant women with normal placenta. After 24 gestational weeks, all participants underwent magnetic resonance imaging. The uterus and placenta regions were segmented in magnetic resonance images on sagittal T2WI. Ninety-three radiomics features were extracted from the placenta region, and 128 deep features were extracted from the uterus region using a deep neural network. The least absolute shrinkage and selection operator (LASSO) algorithm was used to filter these 221 features and to form the combined signature. Then the combined signature (CS) and clinical factors were combined to construct a nomogram. The accuracy, sensitivity, specificity and AUC of the nomogram were compared with four machine learning methods. The model NDRC was trained on the dataset of 78 pregnant women in the training cohort. Finally, the model NDRC was compared with four machine learning methods on the independent validation cohort of 34 pregnant women. The results showed that the prediction accuracy, sensitivity, specificity and AUC of the NDRC model were 0.941, 0.952, 0.923 and 0.985 respectively, which outperforms the traditional machine learning methods which rely on radiomics features and deep learning features alone.

Radiomics: The Next Frontier of Cardiac Computed Tomography

Radiomics uses advanced image analysis to extract massive amounts of quantitative information from digital images, which is not otherwise distinguishable to the human eye. The mined data can be used to explore and establish new and undiscovered correlations between these imaging features and clinical end points. Cardiac computed tomography (CT) is a first-line imaging modality for evaluating coronary artery disease and has a primary role in the assessment of cardiac structures. Conventional interpretation of cardiac CT images relies mostly on subjective and qualitative analysis, as well as basic geometric quantification. To date, some proof-of-concept studies have demonstrated the feasibility and diagnostic performance of cardiac CT radiomics analysis. This review describes the current literature on radiomics in cardiac CT and discusses its advantages, challenges, and future directions. Although much evidences are needed in this field, cardiac CT radiomics has a lot to offer to patients and physicians with potential to define cardiac disease phenotypes on imaging with higher precision.

Artificial intelligence in radiology: relevance of collaborative work between radiologists and engineers for building a multidisciplinary team

The use of artificial intelligence (AI) algorithms in the field of radiology is becoming more common. Several studies have demonstrated the potential utility of machine learning (ML) and deep learning (DL) techniques as aids for radiologists to solve specific radiological challenges. The decision-making process, the establishment of specific clinical or radiological targets, the profile of the different professionals involved in the development of AI solutions, and the relation with partnerships and stakeholders are only some of the main issues that have to be faced and solved prior to starting the development of radiological AI solutions. Among all the players in this multidisciplinary team, the communication between radiologists and data scientists is essential for a successful collaborative work. There are specific skills that are inherent to radiological and medical training that are critical for identifying anatomical or clinical targets as well as for segmenting or labelling lesions. These skills would then have to be transferred, explained, and taught to the data science experts to facilitate their comprehension and integration into ML or DL algorithms. On the other hand, there is a wide range of complex software packages, deep neural-network architectures, and data transfer processes for which radiologists need the expertise of software engineers and data scientists in order to select the optimal manner to analyse and post-process this amount of data. This paper offers a summary of the top five challenges faced by radiologists and data scientists including tips and tricks to build a successful AI team.

How does Radiomics actually work? - Review

Personalized precision medicine requires highly accurate diagnostics. While radiological research has focused on scanner and sequence technologies in recent decades, applications of artificial intelligence are increasingly attracting scientific interest as they could substantially expand the possibility of objective quantification and diagnostic or prognostic use of image information.In this context, the term "radiomics" describes the extraction of quantitative features from imaging data such as those obtained from computed tomography or magnetic resonance imaging examinations. These features are associated with predictive goals such as diagnosis or prognosis using machine learning models. It is believed that the integrative assessment of the feature patterns thus obtained, in combination with clinical, molecular and genetic data, can enable a more accurate characterization of the pathophysiology of diseases and more precise prediction of therapy response and outcome.This review describes the classical radiomics approach and discusses the existing very large variability of approaches. Finally, it outlines the research directions in which the interdisciplinary field of radiology and computer science is moving, characterized by increasingly close collaborations and the need for new educational concepts. The aim is to provide a basis for responsible and comprehensible handling of the data and analytical methods used. KEY POINTS::   · Radiomics is playing an increasingly important role in imaging research.. · Radiomics has great potential to meet the requirements of precision medicine.. · Radiomics analysis is still subject to great variability.. · There is a need for quality-assured application of radiomics in medicine.. CITATION FORMAT: · Attenberger UI, Langs G, . How does Radiomics actually work? - Review. Fortschr Röntgenstr 2021; 193: 652 - 657.

Radiomics at a Glance: A Few Lessons Learned from Learning Approaches

Simple Summary

Radiomics has become a prominent component of medical imaging research and many studies show its specific value as a support tool for clinical decision-making processes. Radiomic data are typically analyzed with statistical and machine learning methods, which change depending on the disease context and the imaging modality. We found a certain bias in the literature towards the use of such methods and believe that this limitation may influence the capacity of producing accurate and reliable decisions. Therefore, in view of the relevance of various types of learning methods, we report their significance and discuss their unrevealed potential.

Abstract

Processing and modeling medical images have traditionally represented complex tasks requiring multidisciplinary collaboration. The advent of radiomics has assigned a central role to quantitative data analytics targeting medical image features algorithmically extracted from large volumes of images. Apart from the ultimate goal of supporting diagnostic, prognostic, and therapeutic decisions, radiomics is computationally attractive due to specific strengths: scalability, efficiency, and precision. Optimization is achieved by highly sophisticated statistical and machine learning algorithms, but it is especially deep learning that stands out as the leading inference approach. Various types of hybrid learning can be considered when building complex integrative approaches aimed to deliver gains in accuracy for both classification and prediction tasks. This perspective reviews some selected learning methods by focusing on both their significance for radiomics and their unveiled potential.

Strengths, Weaknesses, Opportunities, and Threats Analysis of Artificial Intelligence and Machine Learning Applications in Radiology

Currently, the use of artificial intelligence (AI) in radiology, particularly machine learning (ML), has become a reality in clinical practice. Since the end of the last century, several ML algorithms have been introduced for a wide range of common imaging tasks, not only for diagnostic purposes but also for image acquisition and postprocessing. AI is now recognized to be a driving initiative in every aspect of radiology. There is growing evidence of the advantages of AI in radiology creating seamless imaging workflows for radiologists or even replacing radiologists. Most of the current AI methods have some internal and external disadvantages that are impeding their ultimate implementation in the clinical arena. As such, AI can be considered a portion of a business trying to be introduced in the health care market. For this reason, this review analyzes the current status of AI, and specifically ML, applied to radiology from the scope of strengths, weaknesses, opportunities, and threats (SWOT) analysis.

Introduction to Radiomics

Radiomics is a rapidly evolving field of research concerned with the extraction of quantitative metrics-the so-called radiomic features-within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape and may, alone or in combination with demographic, histologic, genomic, or proteomic data, be used for clinical problem solving. The goal of this continuing education article is to provide an introduction to the field, covering the basic radiomics workflow: feature calculation and selection, dimensionality reduction, and data processing. Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.

[Machine learning in radiology : Terminology from individual timepoint to trajectory]

METHODICAL ISSUE

Machine learning (ML) algorithms have an increasingly relevant role in radiology tackling tasks such as the automatic detection and segmentation of diagnosis-relevant markers, the quantification of progression and response, and their prediction in individual patients.

STANDARD RADIOLOGICAL METHODS

ML algorithms are relevant for all image acquisition techniques from computed tomography (CT) and magnetic resonance imaging (MRI) to ultrasound. However, different modalities result in different challenges with respect to standardization and variability.

METHODICAL INNOVATIONS

ML algorithms are increasingly able to analyze longitudinal data for the training of prediction models. This is relevant since it enables the use of comprehensive information for predicting individual progression and response, and the associated support of treatment decisions by ML models.

PERFORMANCE

The quality of detection and segmentation algorithms of lesions has reached an acceptable level in several areas. The accuracy of prediction models is still increasing, but is dependent on the availability of representative training data.

ACHIEVEMENTS

The development of ML algorithms in radiology is progressing although many solutions are still at a validation stage. It is accompanied by a parallel and increasingly interlinked development of basic methods and techniques which will gradually be put into practice in radiology.

PRACTICAL CONSIDERATIONS

Two factors will impact the relevance of ML in radiological practice: the thorough validation of algorithms and solutions, and the creation of representative diverse data for the training and validation in a realistic context.

[Artificial intelligence in the diagnosis of breast cancer : Yesterday, today and tomorrow]

BACKGROUND

Artificial intelligence (AI) is increasingly applied in the field of breast imaging.

OBJECTIVES

What are the main areas where AI is applied in breast imaging and what AI and computer-aided diagnosis (CAD) systems are already available?

MATERIALS AND METHODS

Basic literature and vendor-supplied information are screened for relevant information, which is then pooled, structured and discussed from the perspective of breast imaging.

RESULTS

Original CAD systems in mammography date almost 25 years back. They are much more widely applied in the United States than in Europe. The initial CAD systems exhibited limited diagnostic abilities and disproportionally high rates of false positive results. Since 2012, deep learning mechanisms have been applied and expand the application possibilities of AI.

CONCLUSION

To date there is no algorithm that has beyond doubt been proven to outperform double reporting by two certified breast radiologists. AI could, however, in the foreseeable future, take over the following tasks: preselection of abnormal examinations to substantially reduce workload of the radiologists by either excluding normal findings from human review or by replacing the double reader in screening. Furthermore, the establishment of radio-patho-genomic correlations and their translation into clinical practice is hardly conceivable without AI.

Identification of suspicious invasive placentation based on clinical MRI data using textural features and automated machine learning

OBJECTIVE

The aim of this study was to investigate whether intraplacental texture features from routine placental MRI can objectively and accurately predict invasive placentation.

MATERIAL AND METHODS

This retrospective study includes 99 pregnant women with pathologically confirmed placental invasion and 56 pregnant women with simple placenta previa. All participants underwent magnetic resonance imaging after 24 gestational weeks. The placenta was segmented in sagittal images from both turbo spin echo (TSE) and balanced turbo field echo (bTFE) sequences. Textural features were extracted from the both original and Laplacian of Gaussian (LoG)-filtered MRI images. An automated machine learning algorithm was applied to the extracted feature sets to obtain the optimal preprocessing steps, classification algorithm, and corresponding hyper-parameters.

RESULTS

A gradient boosting classifier using all textual features from original and LoG-filtered TSE images and bTFE images identified by the automated machine learning algorithm achieved the optimal performance with sensitivity, specificity, accuracy, and area under ROC curve (AUC) of 100%, 88.5%, 95.2%, and 0.98 in the prediction of placental invasion. In addition, textural features that contributed to the prediction of placental invasion differ from the features significantly affected by normal placenta maturation.

CONCLUSIONS

Quantifying intraplacental heterogeneity using LoG filtration and texture analysis highlights the different heterogeneous appearance caused by abnormal placentation relative to normal maturation. The predictive model derived from automated machine learning yielded good performance, indicating the proposed radiomic analysis pipeline can accurately predict placental invasion and facilitate clinical decision-making for pregnant women with suspicious placental invasion.

KEY POINTS

• The intraplacental texture features have high efficiency in prediction of invasive placentation after 24 gestational weeks. • The features with dominated predictive power did not overlap with the features significantly affected by gestational age.

Machine learning for differentiating metastatic and completely responded sclerotic bone lesion in prostate cancer: a retrospective radiomics study

OBJECTIVE

Using CT texture analysis and machine learning methods, this study aims to distinguish the lesions imaged via 68Ga-prostate-specific membrane antigen (PSMA) positron emission tomography (PET)/CT as metastatic and completely responded in patients with known bone metastasis and who were previously treated.

METHODS

We retrospectively reviewed the 68Ga-PSMA PET/CT images of 75 patients after treatment, who were previously diagnosed with prostate cancer and had known bone metastasis. A texture analysis was performed on the metastatic lesions showing PSMA expression and completely responded sclerotic lesions without PSMA expression through CT images. Textural features were compared in two groups. Thus, the distinction of metastasis/completely responded lesions and the most effective parameters in this issue were determined by using various methods [decision tree, discriminant analysis, support vector machine (SVM), k-nearest neighbor (KNN), ensemble classifier] in machine learning.

RESULTS

In 28 of the 35 texture analysis findings, there was a statistically significant difference between the two groups. The Weighted KNN method had the highest accuracy and area under the curve, has been chosen as the best model. The weighted KNN algorithm was succeeded to differentiate sclerotic lesion from metastasis or completely responded lesions with 0.76 area under the curve. GLZLM_SZHGE and histogram-based kurtosis were found to be the most important parameters in differentiating metastatic and completely responded sclerotic lesions.

CONCLUSIONS

Metastatic lesions and completely responded sclerosis areas in CT images, as determined by 68Ga-PSMA PET, could be distinguished with good accuracy using texture analysis and machine learning (Weighted KNN algorithm) in prostate cancer.

ADVANCES IN KNOWLEDGE

Our findings suggest that, with the use of newly emerging software, CT imaging can contribute to identifying the metastatic lesions in prostate cancer.

The Bionic Radiologist: avoiding blurry pictures and providing greater insights

Radiology images and reports have long been digitalized. However, the potential of the more than 3.6 billion radiology examinations performed annually worldwide has largely gone unused in the effort to digitally transform health care. The Bionic Radiologist is a concept that combines humanity and digitalization for better health care integration of radiology. At a practical level, this concept will achieve critical goals: (1) testing decisions being made scientifically on the basis of disease probabilities and patient preferences; (2) image analysis done consistently at any time and at any site; and (3) treatment suggestions that are closely linked to imaging results and are seamlessly integrated with other information. The Bionic Radiologist will thus help avoiding missed care opportunities, will provide continuous learning in the work process, and will also allow more time for radiologists' primary roles: interacting with patients and referring physicians. To achieve that potential, one has to cope with many implementation barriers at both the individual and institutional levels. These include: reluctance to delegate decision making, a possible decrease in image interpretation knowledge and the perception that patient safety and trust are at stake. To facilitate implementation of the Bionic Radiologist the following will be helpful: uncertainty quantifications for suggestions, shared decision making, changes in organizational culture and leadership style, maintained expertise through continuous learning systems for training, and role development of the involved experts. With the support of the Bionic Radiologist, disparities are reduced and the delivery of care is provided in a humane and personalized fashion.

A pilot study of radiomics technology based on X-ray mammography in patients with triple-negative breast cancer

PURPOSE

To explore the radiomics features of triple negative breast cancer (TNBC) and non-triple negative breast cancer (non-TNBC) based on X-ray mammography, and to differentiate the two groups of cases.

MATERIALS AND METHODS

Preoperative mammograms of 120 patients with breast ductal carcinoma confirmed by surgical pathology were retrospectively analyzed, which include 30 TNBC and 90 non-TNBC patients. The manual segmentation of breast lesions was performed by ITK-SNAP software and 12 radiomics features were extracted by Omni-Kinetics software. The differences of these radiomics features between TNBC and non-TNBC groups were compared, and the receiver operating characteristic (ROC) curve was used to determine the optimal cutoff value of each radiomics parameter for differentiating TNBC from non-TNBC, and the corresponding area under the curve (AUC), sensitivity and specificity were obtained.

RESULTS

There were statistically significant differences for 4 radiomics features between TNBC and non-TNBC datasets (P < 0.05). They were the roundness, concavity, gray average and skewness of breast lesions. Compared with non-TNBC, TNBC cases have following characteristics of (1) more round with the roundness of 0.621 vs. 0.413 (P < 0.001), (2) more regular with the concavity of 0.087 vs. 0.141 (P < 0.01), (3) higher density or gray average (67.261 vs. 56.842, P < 0.05), and (4) lower skewness (- 0.837 vs.- 0.671, P = 0.034). AUCs of ROC curves computed using features of the roundness and concavity were both larger than 0.70.

CONCLUSION

Radiomics features based on X-ray mammography may be helpful to distinguish between TNBC and non-TNBC, which were associated with breast tumor histology.