Inconsistent Partitioning and Unproductive Feature Associations Yield Idealized Radiomic Models

Image-based artificial intelligence for the prediction of pathological complete response to neoadjuvant chemoradiotherapy in patients with rectal cancer: a systematic review and meta-analysis

OBJECTIVE

Artificial intelligence (AI) holds enormous potential for noninvasively identifying patients with rectal cancer who could achieve pathological complete response (pCR) following neoadjuvant chemoradiotherapy (nCRT). We aimed to conduct a meta-analysis to summarize the diagnostic performance of image-based AI models for predicting pCR to nCRT in patients with rectal cancer.

METHODS

This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. A literature search of PubMed, Embase, Cochrane Library, and Web of Science was performed from inception to July 29, 2023. Studies that developed or utilized AI models for predicting pCR to nCRT in rectal cancer from medical images were included. The Quality Assessment of Diagnostic Accuracy Studies-AI was used to appraise the methodological quality of the studies. The bivariate random-effects model was used to summarize the individual sensitivities, specificities, and areas-under-the-curve (AUCs). Subgroup and meta-regression analyses were conducted to identify potential sources of heterogeneity. Protocol for this study was registered with PROSPERO (CRD42022382374).

RESULTS

Thirty-four studies (9933 patients) were identified. Pooled estimates of sensitivity, specificity, and AUC of AI models for pCR prediction were 82% (95% CI: 76-87%), 84% (95% CI: 79-88%), and 90% (95% CI: 87-92%), respectively. Higher specificity was seen for the Asian population, low risk of bias, and deep-learning, compared with the non-Asian population, high risk of bias, and radiomics (all P < 0.05). Single-center had a higher sensitivity than multi-center (P = 0.001). The retrospective design had lower sensitivity (P = 0.012) but higher specificity (P < 0.001) than the prospective design. MRI showed higher sensitivity (P = 0.001) but lower specificity (P = 0.044) than non-MRI. The sensitivity and specificity of internal validation were higher than those of external validation (both P = 0.005).

CONCLUSIONS

Image-based AI models exhibited favorable performance for predicting pCR to nCRT in rectal cancer. However, further clinical trials are warranted to verify the findings.

MRI radiomics for hamstring strain injury identification and return to sport classification: a pilot study

OBJECTIVE

To determine if MRI-based radiomics from hamstring muscles are related to injury and if the features could be used to perform a time to return to sport (RTS) classification. We hypothesize that radiomics from hamstring muscles, especially T2-weighted and diffusion tensor imaging-based features, are related to injury and can be used for RTS classification.

SUBJECTS AND METHODS

MRI data from 32 athletes at the University of Wisconsin-Madison that sustained a hamstring strain injury were collected. Diffusion tensor imaging and T1- and T2-weighted images were processed, and diffusion maps were calculated. Radiomics features were extracted from the four hamstring muscles in each limb and for each MRI modality, individually. Feature selection was performed and multiple support vector classifiers were cross-validated to differentiate between involved and uninvolved limbs and perform binary (≤ or > 25 days) and multiclass (< 14 vs. 14-42 vs. > 42 days) classification of RTS.

RESULT

The combination of radiomics features from all diffusion tensor imaging and T2-weighted images provided the most accurate differentiation between involved and uninvolved limbs (AUC ≈ 0.84 ± 0.16). For the binary RTS classification, the combination of all extracted radiomics offered the most accurate classification (AUC ≈ 0.95 ± 0.15). While for the multiclass RTS classification, the combination of features from all the diffusion tensor imaging maps provided the most accurate classification (weighted one vs. rest AUC ≈ 0.81 ± 0.16).

CONCLUSION

This pilot study demonstrated that radiomics features from hamstring muscles are related to injury and have the potential to predict RTS.

METhodological RadiomICs Score (METRICS): a quality scoring tool for radiomics research endorsed by EuSoMII

PURPOSE

To propose a new quality scoring tool, METhodological RadiomICs Score (METRICS), to assess and improve research quality of radiomics studies.

METHODS

We conducted an online modified Delphi study with a group of international experts. It was performed in three consecutive stages: Stage#1, item preparation; Stage#2, panel discussion among EuSoMII Auditing Group members to identify the items to be voted; and Stage#3, four rounds of the modified Delphi exercise by panelists to determine the items eligible for the METRICS and their weights. The consensus threshold was 75%. Based on the median ranks derived from expert panel opinion and their rank-sum based conversion to importance scores, the category and item weights were calculated.

RESULT

In total, 59 panelists from 19 countries participated in selection and ranking of the items and categories. Final METRICS tool included 30 items within 9 categories. According to their weights, the categories were in descending order of importance: study design, imaging data, image processing and feature extraction, metrics and comparison, testing, feature processing, preparation for modeling, segmentation, and open science. A web application and a repository were developed to streamline the calculation of the METRICS score and to collect feedback from the radiomics community.

CONCLUSION

In this work, we developed a scoring tool for assessing the methodological quality of the radiomics research, with a large international panel and a modified Delphi protocol. With its conditional format to cover methodological variations, it provides a well-constructed framework for the key methodological concepts to assess the quality of radiomic research papers.

CRITICAL RELEVANCE STATEMENT

A quality assessment tool, METhodological RadiomICs Score (METRICS), is made available by a large group of international domain experts, with transparent methodology, aiming at evaluating and improving research quality in radiomics and machine learning.

KEY POINTS

• A methodological scoring tool, METRICS, was developed for assessing the quality of radiomics research, with a large international expert panel and a modified Delphi protocol. • The proposed scoring tool presents expert opinion-based importance weights of categories and items with a transparent methodology for the first time. • METRICS accounts for varying use cases, from handcrafted radiomics to entirely deep learning-based pipelines. • A web application has been developed to help with the calculation of the METRICS score ( https://metricsscore.github.io/metrics/METRICS.html ) and a repository created to collect feedback from the radiomics community ( https://github.com/metricsscore/metrics ).

Artificial intelligence-based image analysis in clinical testing: lessons from cervical cancer screening

Novel screening and diagnostic tests based on artificial intelligence (AI) image recognition algorithms are proliferating. Some initial reports claim outstanding accuracy followed by disappointing lack of confirmation, including our own early work on cervical screening. This is a presentation of lessons learned, organized as a conceptual step-by-step approach to bridge the gap between the creation of an AI algorithm and clinical efficacy. The first fundamental principle is specifying rigorously what the algorithm is designed to identify and what the test is intended to measure (eg, screening, diagnostic, or prognostic). Second, designing the AI algorithm to minimize the most clinically important errors. For example, many equivocal cervical images cannot yet be labeled because the borderline between cases and controls is blurred. To avoid a misclassified case-control dichotomy, we have isolated the equivocal cases and formally included an intermediate, indeterminate class (severity order of classes: case>indeterminate>control). The third principle is evaluating AI algorithms like any other test, using clinical epidemiologic criteria. Repeatability of the algorithm at the borderline, for indeterminate images, has proven extremely informative. Distinguishing between internal and external validation is also essential. Linking the AI algorithm results to clinical risk estimation is the fourth principle. Absolute risk (not relative) is the critical metric for translating a test result into clinical use. Finally, generating risk-based guidelines for clinical use that match local resources and priorities is the last principle in our approach. We are particularly interested in applications to lower-resource settings to address health disparities. We note that similar principles apply to other domains of AI-based image analysis for medical diagnostic testing.

Machine Learning Combined with Radiomics Facilitating the Personal Treatment of Malignant Liver Tumors

In the realm of managing malignant liver tumors, the convergence of radiomics and machine learning has redefined the landscape of medical practice. The field of radiomics employs advanced algorithms to extract thousands of quantitative features (including intensity, texture, and structure) from medical images. Machine learning, including its subset deep learning, aids in the comprehensive analysis and integration of these features from diverse image sources. This potent synergy enables the prediction of responses of malignant liver tumors to various treatments and outcomes. In this comprehensive review, we examine the evolution of the field of radiomics and its procedural framework. Furthermore, the applications of radiomics combined with machine learning in the context of personalized treatment for malignant liver tumors are outlined in aspects of surgical therapy and non-surgical treatments such as ablation, transarterial chemoembolization, radiotherapy, and systemic therapies. Finally, we discuss the current challenges in the amalgamation of radiomics and machine learning in the study of malignant liver tumors and explore future opportunities.

A novel CT-responsive hydrogel for the construction of an organ simulation phantom for the repeatability and stability study of radiomic features

Radiomic features have demonstrated reliable outcomes in tumor grading and detecting precancerous lesions in medical imaging analysis. However, the repeatability and stability of these features have faced criticism. In this study, we aim to enhance the repeatability and stability of radiomic features by introducing a novel CT-responsive hydrogel material. The newly developed CT-responsive hydrogel, mineralized by in situ metal ions, exhibits exceptional repeatability, stability, and uniformity. Moreover, by adjusting the concentration of metal ions, it achieves remarkable CT similarity comparable to that of human organs on CT scans. To create a phantom, the hydrogel was molded into a universal model, displaying controllable CT values ranging from 53 HU to 58 HU, akin to human liver tissue. Subsequently, 1218 radiomic features were extracted from the CT-responsive hydrogel organ simulation phantom. Impressively, 85-97.2% of the extracted features exhibited good repeatability and stability during coefficient of variability analysis. This finding emphasizes the potential of CT-responsive hydrogel in consistently extracting the same features, providing a novel approach to address the issue of repeatability in radiomic features.

Predictive IDH Genotyping Based on the Evaluation of Spatial Metabolic Heterogeneity by Compartmental Uptake Characteristics in Preoperative Glioma Using 18F-FET PET

Molecular markers are of increasing importance for classifying, treating, and determining the prognosis for central nervous system tumors. Isocitrate dehydrogenase (IDH) is a critical regulator of glucose and amino acid metabolism. Our objective was to investigate metabolic reprogramming of glioma using compartmental uptake (CU) characteristics in O-(2-18F-fluoroethyl)-l-tyrosine (FET) PET and to evaluate its diagnostic potential for IDH genotyping. Methods: Between 2017 and 2022, patients with confirmed glioma were preoperatively investigated using static 18F-FET PET. Metabolic tumor volume (MTV), MTV for 60%-100% uptake (MTV60), and T2-weighted and contrast-enhancing lesion volumes were automatically segmented using U-Net neural architecture and isocontouring. Volume intersections were determined using the Dice coefficient. Uptake characteristics were determined for metabolically defined compartments (central [80%-100%] and peripheral [60%-75%] areas of 18F-FET uptake). CU ratio was defined as the fraction between the peripheral and central compartments. Mean target-to-background ratio was calculated. Comparisons were performed using parametric and nonparametric tests. Receiver-operating-characteristic curves, regression, and correlation were used for statistical analysis. Results: In total, 52 participants (male, 27, female, 25; mean age ± SD, 51 ± 16 y) were evaluated. MTV60 was greater and distinct from contrast-enhancing lesion volume (P = 0.046). IDH-mutated tumors presented a greater volumetric CU ratio and SUV CU ratio than IDH wild-type tumors (P < 0.05). Volumetric CU ratio determined IDH genotype with excellent diagnostic performance (area under the curve [AUC], 0.88; P < 0.001) at more than 5.49 (sensitivity, 86%, specificity, 90%), because IDH-mutated tumors presented a greater peripheral metabolic compartment than IDH wild-type tumors (P = 0.045). MTV60 and MTV were not suitable for IDH classification (P > 0.05). SUV CU ratio (AUC, 0.72; P = 0.005) and target-to-background ratio (AUC, 0.68; P = 0.016) achieved modest diagnostic performance-inferior to the volumetric CU ratio. Furthermore, the classification of loss of heterozygosity of chromosomes 1p and 19q (AUC, 0.75; P = 0.019), MGMT promoter methylation (AUC, 0.70; P = 0.011), and ATRX loss (AUC, 0.73; P = 0.004) by amino acid PET was evaluated. Conclusion: We proposed parametric 18F-FET PET as a noninvasive metabolic biomarker for the evaluation of CU characteristics, which differentiated IDH genotype with excellent diagnostic performance, establishing a critical association between spatial metabolic heterogeneity, mitochondrial tricarboxylic acid cycle, and genomic features with critical implications for clinical management and the diagnostic workup of patients with central nervous system cancer.

Artificial intelligence-based radiomics in bone tumors: Technical advances and clinical application

Radiomics is the extraction of predefined mathematic features from medical images for predicting variables of clinical interest. Recent research has demonstrated that radiomics can be processed by artificial intelligence algorithms to reveal complex patterns and trends for diagnosis, and prediction of prognosis and response to treatment modalities in various types of cancer. Artificial intelligence tools can utilize radiological images to solve next-generation issues in clinical decision making. Bone tumors can be classified as primary and secondary (metastatic) tumors. Osteosarcoma, Ewing sarcoma, and chondrosarcoma are the dominating primary tumors of bone. The development of bone tumor model systems and relevant research, and the assessment of novel treatment methods are ongoing to improve clinical outcomes, notably for patients with metastases. Artificial intelligence and radiomics have been utilized in almost full spectrum of clinical care of bone tumors. Radiomics models have achieved excellent performance in the diagnosis and grading of bone tumors. Furthermore, the models enable to predict overall survival, metastases, and recurrence. Radiomics features have exhibited promise in assisting therapeutic planning and evaluation, especially neoadjuvant chemotherapy. This review provides an overview of the evolution and opportunities for artificial intelligence in imaging, with a focus on hand-crafted features and deep learning-based radiomics approaches. We summarize the current application of artificial intelligence-based radiomics both in primary and metastatic bone tumors, and discuss the limitations and future opportunities of artificial intelligence-based radiomics in this field. In the era of personalized medicine, our in-depth understanding of emerging artificial intelligence-based radiomics approaches will bring innovative solutions to bone tumors and achieve clinical application.

Advances in the Radiological Evaluation of and Theranostics for Glioblastoma

Imaging is essential for evaluating patients with glioblastoma. Traditionally a multimodality undertaking, CT, including CT cerebral blood profusion, PET/CT with traditional fluorine-18 fluorodeoxyglucose (18F-FDG), and MRI have been the mainstays for diagnosis and post-therapeutic assessment. However, recent advances in these modalities, in league with the emerging fields of radiomics and theranostics, may prove helpful in improving diagnostic accuracy and treating the disease.

Evaluation of parametrial infiltration in patients with IB-IIB cervical cancer by a radiomics model integrating features from tumoral and peritumoral regions in 18 F-fluorodeoxy glucose positron emission tomography/MR images

Parametrial infiltration (PMI) is an essential factor in staging and planning treatment of cervical cancer. The purpose of this study was to develop a radiomics model for accessing PMI in patients with IB-IIB cervical cancer using features from ¹⁸ F-fluorodeoxy glucose (¹⁸ F-FDG) positron emission tomography (PET)/MR images. In this retrospective study, 66 patients with International Federation of Gynecology and Obstetrics stage IB-IIB cervical cancer (22 with PMI and 44 without PMI) who underwent ¹⁸ F-FDG PET/MRI were divided into a training dataset (n = 46) and a testing dataset (n = 20). Features were extracted from both the tumoral and peritumoral regions in ¹⁸ F-FDG PET/MR images. Single-modality and multimodality radiomics models were developed with random forest to predict PMI. The performance of the models was evaluated with F1 score, accuracy, and area under the curve (AUC). The Kappa test was used to observe the differences between PMI evaluated by radiomics-based models and pathological results. The intraclass correlation coefficient for features extracted from each region of interest (ROI) was measured. Three-fold crossvalidation was conducted to confirm the diagnostic ability of the features. The radiomics models developed by features from the tumoral region in T₂ -weighted images (F1 score = 0.400, accuracy = 0.700, AUC = 0.708, Kappa = 0.211, p = 0.329) and the peritumoral region in PET images (F1 score = 0.533, accuracy = 0.650, AUC = 0.714, Kappa = 0.271, p = 0.202) achieved the best performances in the testing dataset among the four single-ROI radiomics models. The combined model using features from the tumoral region in T₂ -weighted images and the peritumoral region in PET images achieved the best performance (F1 score = 0.727, accuracy = 0.850, AUC = 0.774, Kappa = 0.625, p < 0.05). The results suggest that ¹⁸ F-FDG PET/MRI can provide complementary information regarding cervical cancer. The radiomics-based method integrating features from the tumoral and peritumoral regions in ¹⁸ F-FDG PET/MR images gave a superior performance for evaluating PMI.

MRI radiomics and potential applications to glioblastoma

MRI plays an important role in the evaluation of glioblastoma, both at initial diagnosis and follow up after treatment. Quantitative analysis via radiomics can augment the interpretation of MRI in terms of providing insights regarding the differential diagnosis, genotype, treatment response, and prognosis. The various MRI radiomic features of glioblastoma are reviewed in this article.