Dynamic contrast-enhanced (DCE) imaging: state of the art and applications in whole-body imaging

Data set terminology of deep learning in medicine: a historical review and recommendation

Medicine and deep learning-based artificial intelligence (AI) engineering represent two distinct fields each with decades of published history. The current rapid convergence of deep learning and medicine has led to significant advancements, yet it has also introduced ambiguity regarding data set terms common to both fields, potentially leading to miscommunication and methodological discrepancies. This narrative review aims to give historical context for these terms, accentuate the importance of clarity when these terms are used in medical deep learning contexts, and offer solutions to mitigate misunderstandings by readers from either field. Through an examination of historical documents, including articles, writing guidelines, and textbooks, this review traces the divergent evolution of terms for data sets and their impact. Initially, the discordant interpretations of the word 'validation' in medical and AI contexts are explored. We then show that in the medical field as well, terms traditionally used in the deep learning domain are becoming more common, with the data for creating models referred to as the 'training set', the data for tuning of parameters referred to as the 'validation (or tuning) set', and the data for the evaluation of models as the 'test set'. Additionally, the test sets used for model evaluation are classified into internal (random splitting, cross-validation, and leave-one-out) sets and external (temporal and geographic) sets. This review then identifies often misunderstood terms and proposes pragmatic solutions to mitigate terminological confusion in the field of deep learning in medicine. We support the accurate and standardized description of these data sets and the explicit definition of data set splitting terminologies in each publication. These are crucial methods for demonstrating the robustness and generalizability of deep learning applications in medicine. This review aspires to enhance the precision of communication, thereby fostering more effective and transparent research methodologies in this interdisciplinary field.

Recent trends in AI applications for pelvic MRI: a comprehensive review

Magnetic resonance imaging (MRI) is an essential tool for evaluating pelvic disorders affecting the prostate, bladder, uterus, ovaries, and/or rectum. Since the diagnostic pathway of pelvic MRI can involve various complex procedures depending on the affected organ, the Reporting and Data System (RADS) is used to standardize image acquisition and interpretation. Artificial intelligence (AI), which encompasses machine learning and deep learning algorithms, has been integrated into both pelvic MRI and the RADS, particularly for prostate MRI. This review outlines recent developments in the use of AI in various stages of the pelvic MRI diagnostic pathway, including image acquisition, image reconstruction, organ and lesion segmentation, lesion detection and classification, and risk stratification, with special emphasis on recent trends in multi-center studies, which can help to improve the generalizability of AI.

Development and validation of a prediction model for malignant sinonasal tumors based on MR radiomics and machine learning

OBJECTIVES

This study aimed to utilize MR radiomics-based machine learning classifiers on a large-sample, multicenter dataset to develop an optimal model for predicting malignant sinonasal tumors and tumor-like lesions.

METHODS

This study included 1711 adult patients (875 benign and 836 malignant) with sinonasal tumors or tumor-like lesions from three institutions. Patients from institution 1 (n = 1367) constituted both the training and validation cohorts, while those from institution 2 and 3 (n = 158/186) made up the test cohorts. Manual segmentation of the region of interest of the tumor was performed on T1WI, T2WI, and contrast-enhanced T1WI (CE-T1WI). Data normalization, dimensional reductions, feature selection, and classifications were performed using ten machine-learning classifiers. Four fusion models, namely T1WI + T2WI, T1WI + CE-T1WI, T2WI + CE-T1WI, and T1WI + T2WI + CE-T1WI, were constructed using the top ten features with the highest contribution in feature selection in the optimal models of T1WI, T2WI, and CE-T1WI. The Delong test compared areas under the curve (AUC) between models.

RESULTS

The AUCs of training/validation/test1/test2 datasets for T1WI, T2WI, and CE-T1WI were 0.900/0.842/0.872/0.839, 0.876/0.789/0.842/0.863, and 0.899/0.824/0.831/0.707, respectively. The fusion model from T1WI + T2WI + CE-T1WI had the highest AUC. The AUCs of training/validation/test1/test2 datasets were 0.947/0.849/0.871/0.887. The T1WI + T2WI + CE-T1WI model demonstrated a significantly higher AUC than the T2WI + CE-T1WI model in both cohorts (p < 0.05) and outperformed the T2WI model in test 1 (p = 0.008) and the T1WI model in test 2 (p = 0.006).

CONCLUSIONS

This fusion model based on radiomics from T1WI + T2WI + CE-T1WI images and machine learning can improve the power in predicting malignant sinonasal tumors with high accuracy, resilience, and robustness.

CLINICAL RELEVANCE STATEMENT

Our study proposes a radiomics-based machine learning fusion model from T1- and T2-weighted images and contrast-enhanced T1-weighted images, which can non-invasively identify the nature of sinonasal tumors and improve the performance in predicting malignant sinonasal tumors.

KEY POINTS

Differentiating benign and malignant sinonasal tumors is difficult due to similar clinical presentations. A radiomics model from T1 + T2 + contrast-enhanced T1 images can identify the nature of sinonasal tumors. This model can help distinguish benign and malignant sinonasal tumors.

Color Maps: Facilitating the Clinical Impact of Quantitative MRI

Presenting quantitative data using non-standardized color maps potentially results in unrecognized misinterpretation of data. Clinically meaningful color maps should intuitively and inclusively represent data without misleading interpretation. Uniformity of the color gradient for color maps is critically important. Maximal color and lightness contrast, readability for color vision-impaired individuals, and recognizability of the color scheme are highly desirable features. This article describes the use of color maps in five key quantitative MRI techniques: relaxometry, diffusion-weighted imaging (DWI), dynamic contrast-enhanced (DCE)-MRI, MR elastography (MRE), and water-fat MRI. Current display practice of color maps is reviewed and shortcomings against desirable features are highlighted. EVIDENCE LEVEL: 5 TECHNICAL EFFICACY: Stage 2.

Value of Quantitative Susceptibility Mapping in Clinical Neuroradiology

Quantitative susceptibility mapping (QSM) is a unique technique for providing quantitative information on tissue magnetic susceptibility using phase image data. QSM can provide valuable information regarding physiological and pathological processes such as iron deposition, hemorrhage, calcification, and myelin. QSM has been considered for use as an imaging biomarker to investigate physiological status and pathological changes. Although various studies have investigated the clinical applications of QSM, particularly regarding the use of QSM in clinical practice, have not been examined well. This review provides on an overview of the basics of QSM and its clinical applications in neuroradiology. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 2.

HER2 in Gastric Cancer: A Comprehensive Analysis Combining Meta-Analysis and DCE-MRI Radiomics

OBJECTIVE

Advanced gastric cancer (AGC) is a severe malignant tumor, and overexpression of HER2/ERBB2 may play a crucial role in its development. The purpose of this study is to investigate the overexpression of HER2/ERBB2 in gastric cancer through a meta-analysis and examine its relationship with perfusion parameters using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) technology.

METHODS

We conducted an extensive literature search and collected relevant studies for the meta-analysis. We used a random-effects model and assigned weights using the "inverse variance" method. Additionally, we included 95 AGC patients diagnosed pathologically between April 2018 and October 2021. They all underwent DCE-MRI scans, and the data were subsequently analyzed using the Omni kinetic software. HER2 expression was assessed using immunohistochemistry.

RESULTS

The meta-analysis revealed an overall odds ratio (OR) of .21 for HER2/ERBB2 overexpression in gastric cancer, with a 95% confidence interval of [.14, .30]. DCE-MRI results showed a significant association between high HER2 expression and poor tumor differentiation (P < .005). The extracellular volume fraction (Ecv) quantile, mean, relative deviation, median intensity, and difference entropy were significantly higher in the low HER2 expression group compared to the high HER2 expression group. Receiver operating characteristic (ROC) curve analysis demonstrated that the area under the curve (AUC) values of DCE-MRI radiomic parameters with significant differences were close to .7.

CONCLUSION

Overexpression of HER2/ERBB2 in gastric cancer is significantly associated with certain radiomic parameters of DCE-MRI, providing a valuable diagnostic tool for clinical practice. Furthermore, the meta-analysis further confirmed the critical role of HER2/ERBB2 in the development of gastric cancer.

Current State of Artificial Intelligence in Clinical Applications for Head and Neck MR Imaging

Due primarily to the excellent soft tissue contrast depictions provided by MRI, the widespread application of head and neck MRI in clinical practice serves to assess various diseases. Artificial intelligence (AI)-based methodologies, particularly deep learning analyses using convolutional neural networks, have recently gained global recognition and have been extensively investigated in clinical research for their applicability across a range of categories within medical imaging, including head and neck MRI. Analytical approaches using AI have shown potential for addressing the clinical limitations associated with head and neck MRI. In this review, we focus primarily on the technical advancements in deep-learning-based methodologies and their clinical utility within the field of head and neck MRI, encompassing aspects such as image acquisition and reconstruction, lesion segmentation, disease classification and diagnosis, and prognostic prediction for patients presenting with head and neck diseases. We then discuss the limitations of current deep-learning-based approaches and offer insights regarding future challenges in this field.

Association between radiomics features of DCE-MRI and CD8+ and CD4+ TILs in advanced gastric cancer

Objective: The aim of this investigation was to explore the correlation between the levels of tumor-infiltrating CD8⁺ and CD4⁺ T cells and the quantitative pharmacokinetic parameters of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in patients with advanced gastric cancer. Methods: We retrospectively analyzed the data of 103 patients with histopathologically confirmed advanced gastric cancer (AGC). Three pharmacokinetic parameters, K_ep, K^trans, and V_e, and their radiomics characteristics were obtained by Omni Kinetics software. Immunohistochemical staining was used to determine CD4⁺ and CD8⁺ TILs. Statistical analysis was subsequently performed to assess the correlation between radiomics characteristics and CD4⁺ and CD8⁺ TIL density. Results: All patients included in this study were finally divided into either a CD8⁺ TILs low-density group (n = 51) (CD8⁺ TILs < 138) or a high-density group (n = 52) (CD8⁺ TILs ≥ 138), and a CD4⁺ TILs low-density group (n = 51) (CD4⁺ TILs < 87) or a high-density group (n = 52) (CD4⁺ TILs ≥ 87). ClusterShade and Skewness based on K_ep and Skewness based on K^trans both showed moderate negative correlation with CD8⁺ TIL levels (r = 0.630-0.349, p < 0.001), with ClusterShade based on K_ep having the highest negative correlation (r = -0.630, p < 0.001). Inertia-based K_ep showed a moderate positive correlation with the CD4⁺ TIL level (r = 0.549, p < 0.001), and the Correlation based on K_ep showed a moderate negative correlation with the CD4⁺ TIL level, which also had the highest correlation coefficient (r = -0.616, p < 0.001). The diagnostic efficacy of the above features was assessed by ROC curves. For CD8⁺ TILs, ClusterShade of K_ep had the highest mean area under the curve (AUC) (0.863). For CD4⁺ TILs, the Correlation of K_ep had the highest mean AUC (0.856). Conclusion: The radiomics features of DCE-MRI are associated with the expression of tumor-infiltrating CD8⁺ and CD4⁺ T cells in AGC, which have the potential to noninvasively evaluate the expression of CD8⁺ and CD4⁺ TILs in AGC patients.

Advances in Bone Marrow Imaging: Strengths and Limitations from a Clinical Perspective

Conventional magnetic resonance imaging (MRI) remains the modality of choice to image bone marrow. However, the last few decades have witnessed the emergence and development of novel MRI techniques, such as chemical shift imaging, diffusion-weighted imaging, dynamic contrast-enhanced MRI, and whole-body MRI, as well as spectral computed tomography and nuclear medicine techniques. We summarize the technical bases behind these methods, in relation to the common physiologic and pathologic processes involving the bone marrow. We present the strengths and limitations of these imaging methods and consider their added value compared with conventional imaging in assessing non-neoplastic disorders like septic, rheumatologic, traumatic, and metabolic conditions. The potential usefulness of these methods to differentiate between benign and malignant bone marrow lesions is discussed. Finally, we consider the limitations hampering a more widespread use of these techniques in clinical practice.

Dynamic Contrast-Enhanced MRI Parameters and Normalized ADC Values Could Aid Differentiation of Skull Base Osteomyelitis from Nasopharyngeal Cancer

BACKGROUND AND PURPOSE

The skull base osteomyelitis sometimes can be difficult to distinguish from nasopharyngeal cancer. This study aimed to investigate the differences between skull base osteomyelitis and nasopharyngeal cancer using dynamic contrast-enhanced MR imaging and normalized ADC values.

MATERIALS AND METHODS

This study included 8 and 12 patients with skull base osteomyelitis and nasopharyngeal cancer, respectively, who underwent dynamic contrast-enhanced MR imaging and DWI before primary treatment. Quantitative dynamic contrast-enhanced MR imaging parameters and ADC values of the ROIs were analyzed. Normalized ADC parameters were calculated by dividing the ROIs of the lesion by that of the spinal cord.

RESULTS

The rate transfer constant between extravascular extracellular space and blood plasma per minute (Kep) was significantly lower in patients with skull base osteomyelitis than in those with nasopharyngeal cancer (median, 0.43 versus 0.57; P = .04). The optimal cutoff value of Kep was 0.48 (area under the curve, 0.78; 95% CI, 0.55-1). The normalized mean ADC was significantly higher in patients with skull base osteomyelitis than in those with nasopharyngeal cancer (median, 1.90 versus 0.87; P < .001). The cutoff value of normalized mean ADC was 1.55 (area under the curve, 0.96; 95% CI, 0.87-1). The area under the curve of the combination of dynamic contrast-enhanced MR imaging parameters (Kep and extravascular extracellular space volume per unit tissue volume) was 0.89 (95% CI, 0.73-1), and the area under the curve of the combination of dynamic contrast-enhanced MR imaging parameters and normalized mean ADC value was 0.98 (95% CI, 0.93-1).

CONCLUSIONS

Quantitative dynamic contrast-enhanced MR imaging parameters and normalized ADC values may be useful in differentiating skull base osteomyelitis and nasopharyngeal cancer. The combination of dynamic contrast-enhanced MR imaging parameters and normalized ADC values outperformed each measure in isolation.

Comparison of the axillary lymph node between rheumatoid arthritis and psoriatic arthritis with computed tomography

Backgrounds

There is a lack of universally available biomarker to differentiate rheumatoid arthritis (RA) and psoriatic arthritis (PsA).

Purpose

to see if the size of the axillary lymphnodes (ALNs) and the frequency of lymphadenopathy are useful biomarker to differentiate RA and PsA.

Material and Methods

Forty RA and 19 PsA patients without previous biologics usage were retrospectively included. Chest CT was assessed for the presence of lymphadenopathy and the size of the largest ALN. Frequency of lymphadenopathies was statistically compared between RA and PsA. The short axis and the long axis of the largest ALN were also compared and receiver operating characteristic (ROC) curve analysis was performed.

Results

Frequency of axillary lymphadenopathy was significantly higher in RA than in PsA (80% vs 31.6%, p < .001). Number of lymphadenopathies in each patient was also significantly higher in RA than in PsA (3.0 vs 1.2 per patient, p = .005). Sensitivity and specificity for differentiating RA from PsA by the presence of at least one axillary lymphadenopathy were 0.8 and 0.68, respectively. The short axis of the largest ALNs in RA was significantly longer than in PsA (6.5 ± 1.6 mm vs 4.7 ± 1.7 mm, p < .001). ROC curve analysis of the short axis showed AUC of 0.75 ( p = .002) and the cutoff value of 5.1 mm with a sensitivity of 0.83 and specificity of 0.74, when differentiating RA and PsA.

Conclusion

Presence of ALN lymphadenopathy and the short axis of the largest ALN may have a potential utility in differentiating RA and PsA.

Lymph Nodes Evaluation in Rectal Cancer: Where Do We Stand and Future Perspective

The assessment of nodal involvement in patients with rectal cancer (RC) is fundamental in disease management. Magnetic Resonance Imaging (MRI) is routinely used for local and nodal staging of RC by using morphological criteria. The actual dimensional and morphological criteria for nodal assessment present several limitations in terms of sensitivity and specificity. For these reasons, several different techniques, such as Diffusion Weighted Imaging (DWI), Intravoxel Incoherent Motion (IVIM), Diffusion Kurtosis Imaging (DKI), and Dynamic Contrast Enhancement (DCE) in MRI have been introduced but still not fully validated. Positron Emission Tomography (PET)/CT plays a pivotal role in the assessment of LNs; more recently PET/MRI has been introduced. The advantages and limitations of these imaging modalities will be provided in this narrative review. The second part of the review includes experimental techniques, such as iron-oxide particles (SPIO), and dual-energy CT (DECT). Radiomics analysis is an active field of research, and the evidence about LNs in RC will be discussed. The review also discusses the different recommendations between the European and North American guidelines for the evaluation of LNs in RC, from anatomical considerations to structured reporting.