Dynamic Contrast-enhanced Research Articles

Role of MRI in evaluation of residual tumor burden following neoadjuvant therapy in patients with breast cancer

Objectives To correlate the accuracy of MRI with pathology in assessing the response of neoadjuvant chemotherapy (NACT) in patients with breast cancer and assessment of factors affecting the accuracy of MRI. Materials and Methods Twenty-five patients (with 33 tumors) having biopsy-proven breast cancer were included to undergo dynamic contrast-enhanced MRI, mammography, and ultrasound prior to NACT and after completion of NACT before undergoing surgery. Tumor morphological features and receptor subtypes were compared between complete and non-complete responders, and the accuracy of MRI in estimating residual disease was assessed with respect to histopathology. The performance of MRI was also compared with ultrasound and mammography, wherever feasible. Results The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of MRI for predicting pathological complete response (pCR) were 100%, 70%, 83.3%, 100%, and 88%, respectively, which were significantly better (p = 0.02) in the triple-negative subtype. Size measured in preoperative MRI had a significant positive correlation with pathological size (r = 0.76, p < 0.001) with the lowest mean size difference in triple negative subtype and in tumors showing a concentric pattern of shrinkage. Among the baseline morphological features on MRI, significant difference was seen in the shape (p = 0.02) and enhancement (p = 0.036) of the tumors between complete and non-complete responders. Also, MRI had the highest overall accuracy in predicting pCR and residual tumor size as compared to mammography and ultrasound. Conclusion MRI is a sensitive modality for predicting pCR and residual tumor size with better accuracy for triple-negative tumors as compared to other subtypes.

Noninvasive in vivo assessment of placental insufficiency using pCASL: a prospective case–control study

BackgroundArterial spin labeling is a noninvasive imaging modality that does not use contrast for evaluation of placental perfusion in the placental pathological conditions. Our study enrolled 30 pregnant females with different risk factors for developing IUGR and other 30 females with the same age group having normal pregnancy. The two groups were evaluated by free breathing arterial spin labeling magnetic resonance imaging. Image findings of pseudo-continuous arterial spin labeling were compared to color duplex Doppler ultrasound of umbilical and middle cerebral arteries.AimThe aim of the present study was to evaluate the role of pseudo-continuous arterial spin labeling in measurement of placental perfusion with quantitative analysis of regional placental blood flow.MethodsThis prospective case–control study enrolled 30 pregnant females who had different causes of placental insufficiency, and another healthy group of matched ages, all were evaluated by 2D and color duplex Doppler ultrasound, conventional non-contrast magnetic resonance imaging and MRI perfusion using arterial spin labeling technique. The study was carried out from October 2021 to October 2023.ResultsSignificant relation was found between placental perfusion values and umbilical and middle cerebral artery resistive indices as indicator for placental insufficiency with sensitivity and specificity 77.8%, 80%, respectively, for umbilical artery resistive index and 90%, 83.3%, respectively, for middle cerebral artery resistive index. While the diagnostic value of ASL perfusion was as follows, it had sensitivity = 90%, specificity = 83.3%, PPV = 84.4%, NPV = 89.3% and accuracy = 86.7%.ConclusionsASL-MRI is an excellent noninvasive in vivo MRI technique for evaluation of placental perfusion and quantitative analysis of regional placental blood flow in cases of placental insufficiency. This study supported the value of the new noninvasive MRI techniques in the elaboration of placental pathology.

Probabilistic nested model selection in pharmacokinetic analysis of DCE-MRI data in animal model of cerebral tumor

Abstract Best current practice in the analysis of dynamic contrast enhanced (DCE)-MRI is to employ a voxel-by-voxel model selection from a hierarchy of nested models. This nested model selection (NMS) assumes that the observed time-trace of contrast-agent (CA) concentration within a voxel, corresponds to a singular physiologically nested model. However, admixtures of different models may exist within a voxel’s CA time-trace. This study introduces an unsupervised feature engineering technique (Kohonen-Self-Organizing-Map (K-SOM)) to estimate the voxel-wise probability of each nested model. Sixty-six immune-compromised-RNU rats were implanted with human U-251 N cancer cells, and DCE-MRI data were acquired from all the rat brains. The time-trace of change in the longitudinal-relaxivity (ΔR1) for all animals’ brain voxels was calculated. DCE-MRI pharmacokinetic (PK) analysis was performed using NMS to estimate three model regions: Model-1: normal vasculature without leakage, Model-2: tumor tissues with leakage without back-flux to the vasculature, Model-3: tumor vessels with leakage and back-flux. Approximately two hundred thirty thousand (229,314) normalized ΔR1 profiles of animals’ brain voxels along with their NMS results were used to build a K-SOM (topology-size: 8 × 8, with competitive-learning algorithm) and probability map of each model. K-fold nested-cross-validation (NCV, k = 10) was used to evaluate the performance of the K-SOM probabilistic-NMS (PNMS) technique against the NMS technique. The K-SOM PNMS’s estimation for the leaky tumor regions were strongly similar (Dice-Similarity-Coefficient, DSC = 0.774 [CI: 0.731–0.823], and 0.866 [CI: 0.828–0.912] for Models 2 and 3, respectively) to their respective NMS regions. The mean-percent-differences (MPDs, NCV, k = 10) for the estimated permeability parameters by the two techniques were: -28%, + 18%, and + 24%, for vp, Ktrans, and ve, respectively. The KSOM-PNMS technique produced microvasculature parameters and NMS regions less impacted by the arterial-input-function dispersion effect. This study introduces an unsupervised model-averaging technique (K-SOM) to estimate the contribution of different nested-models in PK analysis and provides a faster estimate of permeability parameters.

Imaging of Peripheral Intraneural Tumors: A Comprehensive Review for Radiologists

Background/Objectives: Intraneural tumors (INTs) pose a diagnostic challenge, owing to their varied origins within nerve fascicles and their wide spectrum, which includes both benign and malignant forms. Accurate diagnosis and management of these tumors depends upon the skills of the radiologist in identifying key imaging features and correlating them with the patient’s clinical symptoms and examination findings. Methods: This comprehensive review systematically analyzes the various imaging features in the diagnosis of intraneural tumors, ranging from basic MR to advanced MR imaging techniques such as MR neurography (MRN), diffusion tensor imaging (DTI), and dynamic contrast-enhanced (DCE) MRI. Results: The article emphasizes the differentiation of benign from malignant lesions using characteristic MRI features, such as the “target sign” and “split-fat sign” for tumor characterization. The role of advanced multiparametric MRI in improving biopsy planning, guiding surgical mapping, and enhancing post-treatment monitoring is also highlighted. The review also underlines the importance of common diagnostic pitfalls and highlights the need for a multi-disciplinary approach to achieve an accurate diagnosis, appropriate treatment strategy, and post-therapy surveillance planning. Conclusions: In this review, we illustrate the main imaging findings of intraneural tumors, focusing on specific MR imaging features that are crucial for an accurate diagnosis and the differentiation between benign and malignant lesions.

Predictive Value of Dynamic Contrast-Enhanced Breast Magnetic Resonance Imaging and Diffusion-Weighted Imaging Findings for Sentinel Lymph Node Metastasis in Early-Stage Invasive Breast Cancer.

This retrospective study aimed to evaluate the predictive value of the preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion-weighted imaging (DWI) findings of mass lesions for predicting sentinel lymph node (SLN) metastasis in early breast cancer. A total of 310 patients with suspicious mass lesions detected in preoperative MRI who subsequently underwent surgery and SLN biopsy (SLNB) between September 2015 and September 2022 were analyzed. The relationship between DCE-MRI and DWI findings and SLNB positivity was analyzed. SLNB was positive for SLN metastasis in 108 of 310 lesions. Younger age (p = 0.001) and larger lesion size (p < 0.001) were found to be associated with SLNB positivity. Findings associated with SLN metastasis included peritumoral edema in 53%, adjacent vessel sign (AVS) in 81%, and increased whole-breast vascularity (WBV) in 58% of patients with positive SLNB (p < 0.001). The SLNB positivity rate was higher in mass lesions with DCE-MRI findings of heterogenous enhancement pattern (p = 0.003), medium or rapid initial phase enhancement (p = 0.001), and washout delayed phase kinetic curve (p = 0.001). It was found that lower tumoral apparent diffusion coefficient (ADC) values (p = 0.003) and higher peritumoral/tumoral ADC ratios (p = 0.018) increased the probability of encountering SLN metastasis. Patient age, presence of peritumoral edema, presence of AVS, increased WBV, and initial phase kinetic curve of the lesions on MRI were found to be associated with SLN metastasis. We found that younger age and MR findings obtained from the perilesional area of breast cancer may be helpful in the preoperative prediction of SLN metastasis.

Dynamic Contrast-Enhanced Magnetic Resonance Imaging Findings and the Relevance of Histopathological Findings in Intraocular Solitary Fibrous Tumors

Dynamic Contrast-Enhanced Magnetic Resonance Imaging Findings and the Relevance of Histopathological Findings in Intraocular Solitary Fibrous Tumors

Comparative analysis of imaging and pathological features in diagnosis of endometrial carcinosarcoma based on multimodal MRI.

This case report aims to present a rare case of endometrial carcinosarcoma, a highly malignant tumor with a poor prognosis. The primary objective is to describe this unique case's clinical presentation, multimodal magnetic resonance imaging (MRI) features, typical histopathological characteristics and surgical treatment. A detailed analysis of the patient's medical history, preoperative imaging evaluation, and treatment approach was conducted. This case report includes high-resolution images and figures, showcasing MRI scans, surgical treatment, and histopathology slides related to the case. The case report outlines imaging findings of a rare case of endometrial carcinosarcoma. Multimodal imaging such as T1-weighted imaging (T1WI), T2-weighted imaging (T2WI) and multi-b-value diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) and dynamic contrast-enhanced (DCE) scanning could accurately identify the histopathological features of the case. Surgical resection is the best treatment, and preoperative imaging evaluation should be particularly important. This case report highlights endometrial carcinosarcoma's rarity and diagnostic challenges. Multimodal MRI has significant value in diagnosing endometrial carcinosarcoma. This technology not only improves the sensitivity, specificity, and accuracy of diagnosis, but also helps to more accurately evaluate the staging and grading of tumors. By comparing imaging features and pathological results, studies have found that multimodal MRI can clearly show the anatomical structure, pathological nature, and extent of the tumor, with a high degree of consistency with the pathological diagnosis. In particular, when differentiating endometrial carcinosarcoma from low-risk endometrial cancer, multimodal MRI combined with serum carbohydrate antigen 125 (CA125) and E-box binding zinc finger protein 1 (ZEB1) detection can further improve the sensitivity and specificity of differential diagnosis. In addition, research has found that the ADC value of the tumor tissue in different pathological grades is related to the multimodal MRI, which helps to better understand the biological behavior and prognosis of the tumor. In summary, multimodal MRI is an effective diagnostic tool that can provide important evidence for the precise diagnosis and treatment of endometrial carcinosarcoma.

Utility of Multiparametric Breast MRI Radiomics to Predict Cyclin D1 and TGF-β1 Expression.

To develop a machine learning model that integrates clinical features and multisequence MRI radiomics for noninvasively predicting the expression status of prognostic-related factors cyclin D1 and TGF-β1 in breast cancer, providing additional information for the clinical development of personalized treatment plans. A total of 123 breast cancer patients confirmed by surgical pathology were retrospectively enrolled in our Hospital from January 2016 to July 2022. The patients were randomly divided into a training group (87 cases) and a validation group (36 cases). Preoperative routine and dynamic contrast-enhanced magnetic resonance imaging scans of the breast were performed for treatment subjects. The region of interest was manually outlined, and texture features were extracted using AK software. Subsequently, the LASSO algorithm was employed for dimensionality reduction and feature selection to establish the MRI radiomics labels. The diagnostic efficacy and clinical value were assessed through receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA). In the cyclin D1 cohort, the area under the receiver operating characteristic (ROC) curve in the clinical prediction model training and validation groups was 0.738 and 0.656, respectively. The multisequence MRI radiomics prediction model achieved an AUC of 0.874 and 0.753 in these respective groups, while the combined prediction model yielded an AUC of 0.892 and 0.785. In the TGF-β1 cohort, the ROC AUC for the clinical prediction model was found to be 0.693 and 0.645 in the training and validation groups, respectively. For the multiseries MRI radiomics prediction model, it achieved an AUC of 0.875 and 0.760 in these respective groups; whereas for the combined prediction model, it reached an AUC of 0.904 and 0.833. Decision curve analysis (DCA) demonstrated that both cohorts indicated a higher clinical application value for the combined prediction model compared with both individual models-clinical prediction model alone or radiomics model. The integration of clinical features and multisequence MRI radiomics in a combined modeling approach holds significant predictive value for the expression status of cyclin D1 and TGF-β1. The model provides a noninvasive, dynamic evaluation method that provides effective guidance for clinical treatment.

The correlation histopathological and conventional/advanced MRI techniques in glial tumors.

We aimed to elucidate the histopathological pre-diagnosis of cranial gliomas with magnetic resonance imaging (MRI) techniques in gliomas. A total of 82 glioma patients were enrolled to our study. Pre-operative conventional MRI images (non-contrast T1/T2/flair/contrast-enhanced T1) and advanced MRI images (DAG and ADC mapping, MRI spectroscopy and perfusion MRI [PMRI]) were analyzed. Conventional MRI alone is useful in radiological pre-evaluation in low-grade glioma in 54.8% and 86.3% in high-grade glioma. Additional advanced MRI techniques were beneficial in comparing low-grade gliomas in 98% and 83.9% in high-grade glioma. On ROC analysis, ADC cutoff value 0.905 mm2/s (p = 0.001), rCBV cutoff value 1.77 (p = 0.001), Cho/NAA cut-off value 2.20 (p = 0.001), and Cho/Cr cutoff value 2.01 (p = 0.001) were achieved. Significant results were obtained when ADC, Cho/NAA, and Cho/Cr were analyzed into four histopathologically grade groups besides (p = 0.001). NAA/Cr values were not significant in pathological grading. rCBV measurements were statistically significant between Grades I and IV and between II and IV. Using additional advanced MRI techniques such as PMRI, magnetic resonance spectroscopy, and DWI with conventional MRI could enhance the accuracy of histopathological grading in cranial glioma.

Presence of Fragmented Intratumoral Thrombosed Microvasculature in the Necrotic and Peri-Necrotic Regions on SWI Differentiates IDH Wild-Type Glioblastoma From IDH Mutant Grade 4 Astrocytoma.

Isocitrate dehydrogenase (IDH) wild-type (IDHwt) glioblastomas (GB) are more aggressive and have a poorer prognosis than IDH mutant (IDHmt) tumors, emphasizing the need for accurate preoperative differentiation. However, a distinct imaging biomarker for differentiation mostly lacking. Intratumoral thrombosis has been reported as a histopathological biomarker for GB. To evaluate the fragmented intratumoral thrombosed microvasculature (FTV) signs on susceptibility-weighted imaging (SWI) for distinguishing IDHwt and IDHmt tumors. Retrospective. Ninety-seven treatment-naïve patients with histopathologically confirmed IDHwt GB (54 males, 26 females) and IDHmt grade 4 astrocytoma (13 males, 4 females). 3-T, SWI, fluid-attenuated-inversion-recovery (FLAIR), T1-weighted, T2-weighted, PD-weighted, post-contrast T1-weighted and dynamic-contrast-enhanced (DCE)-MRI. SWI data were evaluated by three experienced neuroradiologists (S.S., 11 years; J.S., 15 years; R.K.G., 40 years of experience), who assessed FTV presence in necrotic and peri-necrotic regions. FTV was identified as intratumoral susceptibility signal having minimal or no interslice connections. Quantitative DCE-MRI parameters were derived using first-pass-analysis and extended Tofts model. FLAIR abnormal, contrast-enhancing, and necrotic regions were segmented using in-house developed U-Net architecture. Fleiss' Kappa, Cohen's Kappa, Shapiro-Wilk test, t tests or Mann-Whitney U test, receiver-operating characteristic (ROC) analysis, confusion matrix. A P-value <0.05 was considered statistically significant. Fleiss' kappa test provided 91% inter-rater agreement, and Cohen's kappa provided intrarater agreement ranged from 81% to 97%. The raters' accuracy in distinguishing IDHwt from IDHmt ranged from 92% to 94%. Some of the quantitative DCE-MRI parameters (CBV, Ve, and Ktrans) provided statistically significant differences in differentiating IDHwt and IDHmt. Ktrans demonstrated 80.3% sensitivity and 81.2% specificity, with ROC analysis showing an AUC of 0.77. FTV signs in necrotic and peri-necrotic regions on SWI demonstrated a high accuracy in distinguishing IDHwt from IDHmt. Qualitative assessment of FTV signs showed almost perfect inter-rater and intrarater agreement. Quantitative DCE-MRI metrics also showed statistically significant differentiation of IDHwt and IDHmt. This study demonstrates that preoperative imaging, particularly the visualization of the fragmented thrombosed vasculature (FTV) sign on susceptibility-weighted imaging (SWI), effectively differentiates isocitrate dehydrogenase (IDH) wild-type (IDHwt) glioblastoma (GB) from IDH mutant (IDHmt) grade 4 astrocytomas. Over 90% of IDHwt GB patients displayed the FTV sign, a specific imaging biomarker absent in IDHmt cases. Perfusion parameters such as cerebral blood volume, Ve, and Ktrans were elevated in IDHwt gliomas, reflecting distinct vascular profiles. SWI offers a noninvasive and accurate diagnostic method, overcoming limitations of histopathology. Despite limitations like unequal sample sizes and retrospective analysis, this study underscores the clinical potential of SWI in improving glioma characterization and aiding treatment planning. 4 TECHNICAL EFFICACY: Stage 2.

Noninvasive blood-brain barrier integrity mapping in patients with high-grade glioma and metastasis by multi-echo time-encoded arterial spin labeling.

In brain tumors, disruption of the blood-brain barrier (BBB) indicates malignancy. Clinical assessment is qualitative; quantitative evaluation is feasible using the K2 leakage parameter from dynamic susceptibility contrast MRI. However, contrast agent-based techniques are limited in patients with renal dysfunction and insensitive to subtle impairments. Assessing water transport times across the BBB (Tex) by multi-echo arterial spin labeling promises to detect BBB impairments noninvasively and potentially more sensitively. We hypothesized that reduced Tex indicates impaired BBB. Furthermore, we assumed higher sensitivity for Tex than dynamic susceptibility contrast-based K2, because arterial spin labeling uses water as a freely diffusible tracer. We acquired 3T MRI data from 28 patients with intraparenchymal brain tumors (World Health Organization Grade 3 & 4 gliomas [n = 17] or metastases [n = 11]) and 17 age-matched healthy controls. The protocol included multi-echo and single-echo Hadamard-encoded arterial spin labeling, dynamic susceptibility contrast, and conventional clinical imaging. Tex was calculated using a T2-dependent multi-compartment model. Areas of contrast-enhancing tissue, edema, and normal-appearing tissue were automatically segmented, and parameter values were compared across volumes of interest and between patients and healthy controls. Tex was significantly reduced (-20.3%) in contrast-enhancing tissue compared with normal-appearing gray matter and correlated well with |K2| (r = -0.347). Compared with healthy controls, Tex was significantly lower in tumor patients' normal-appearing gray matter (Tex,tumor = 0.141 ± 0.032 s vs. Tex,HC = 0.172 ± 0.036 s) and normal-appearing white matter (Tex,tumor = 0.116 ± 0.015 vs. Tex,HC = 0.127 ± 0.017 s), whereas |K2| did not differ significantly. Receiver operating characteristic analysis showed a larger area under the curve for Tex (0.784) than K2 (0.604). Tex is sensitive to pathophysiologically impaired BBB. It agrees with contrast agent-based K2 in contrast-enhancing tissue and indicates sensitivity to subtle leakage.

GOLD grade-specific characterization of COPD in the COSYCONET multi-center trial: comparison of semiquantitative MRI and quantitative CT.

We hypothesized that semiquantitative visual scoring of lung MRI is suitable for GOLD-grade specific characterization of parenchymal and airway disease in COPD and that MRI scores correlate with quantitative CT (QCT) and pulmonary function test (PFT) parameters. Five hundred ninety-eight subjects from the COSYCONET study (median age = 67 (60-72)) at risk for COPD or with GOLD1-4 underwent PFT, same-day paired inspiratory/expiratory CT, and structural and contrast-enhanced MRI. QCT assessed total lung volume (TLV), emphysema, and air trapping by parametric response mapping (PRMEmph, PRMfSAD) and airway disease by wall percentage (WP). MRI was analyzed using a semiquantitative visual scoring system for parenchymal defects, perfusion defects, and airway abnormalities. Descriptive statistics, Spearman correlations, and ANOVA analyses were performed. TLV, PRMEmph, and MRI scores for parenchymal and perfusion defects were all higher with each GOLD grade, reflecting the extension of emphysema (all p < 0.001). Airway analysis showed the same trends with higher WP and higher MRI large airway disease scores in GOLD3 and lower WP and MRI scores in GOLD4 (p = 0.236 and p < 0.001). Regional heterogeneity was less evident on MRI, while PRMEmph and MRI perfusion defect scores were higher in the upper lobes, and WP and MRI large airway disease scores were higher in the lower lobes. MRI parenchymal and perfusion scores correlated moderately with PRMEmph (r = 0.61 and r = 0.60) and moderately with FEV1/FVC (r = -0.56). Multi-center semiquantitative MRI assessments of parenchymal and airway disease in COPD matched GOLD grade-specific imaging features on QCT and detected regional disease heterogeneity. MRI parenchymal disease scores were correlated with QCT and lung function parameters. Question Do MRI-based scores correlate with QCT and PFT parameters for GOLD-grade specific disease characterization of COPD? Findings MRI can visualize the parenchymal and airway disease features of COPD. Clinical relevance Lung MRI is suitable for GOLD-grade specific disease characterization of COPD and may serve as a radiation-free imaging modality in scientific and clinical settings, given careful consideration of its potential and limitations.

FastMRI Breast: A Publicly Available Radial K-space Dataset of Breast Dynamic Contrast-enhanced MRI.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. The fastMRI breast dataset is the first large-scale dataset of radial k-space and DICOM data for breast dynamic contrast-enhanced MRI with case-level labels. Its public availability aims to advance fast and quantitative machine learning research. ©RSNA, 2025.

The possibilities of the non-contrast MRI perfusion in the quantitative assessment of changes in cerebral blood flow

The possibilities of the non-contrast MRI perfusion in the quantitative assessment of changes in cerebral blood flow

Validation of Clinical Dynamic Contrast-Enhanced Magnetic Resonance Imaging Perfusion Modeling and Neoadjuvant Chemotherapy Response Prediction in Breast Cancer Using 18FDG and 64Cu-DOTA-Trastuzumab Positron Emission Tomography Studies.

Perfusion modeling presents significant opportunities for imaging biomarker development in breast cancer but has historically been held back by the need for data beyond the clinical standard of care (SoC) and uncertainty in the interpretability of results. We aimed to design a perfusion model applicable to breast cancer SoC dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) series with results stable to low temporal resolution imaging, comparable with published results using full-resolution DCE-MRI, and correlative with orthogonal imaging modalities indicative of biophysical markers. Subsampled high-temporal-resolution DCE-MRI series were run through our perfusion model and resulting fits were compared for consistency. The fits were also compared against previously published results from institutions using the full resolution series. The model was then evaluated on a separate cohort for validity of biomarker indications. Finally, the model was used as a fundamental part of predicting response to neoadjuvant chemotherapy (NACT). Temporally subsampled DCE-MRI series yield perfusion fit variations on the scale of 1% of the tumor median value when input frames are varied. Fits generated from pseudoclinical series are within the variation range seen between imaging sites (ρ = 0.55), voxel-wise. The model also demonstrates significant correlations with orthogonal positron emission tomography imaging, indicating potential for use as a biomarker proxy. Specifically, using the perfusion fits as the grounding for a biophysical simulation of response, we correctly predict the pathologic complete response status after NACT in 15 of 18 patients, for an accuracy of 0.83, with a specificity and sensitivity of 0.83 as well. Clinical DCE-MRI data may be leveraged to provide stable perfusion fit results and indirectly interrogate the tumor microenvironment. These fits can then be used downstream for prediction of response to NACT with high accuracy.

Time-Series MR Images Identifying Complete Response to Neoadjuvant Chemotherapy in Breast Cancer Using a Deep Learning Approach.

Pathological complete response (pCR) is an essential criterion for adjusting follow-up treatment plans for patients with breast cancer (BC). The value of the visual geometry group and long short-term memory (VGG-LSTM) network using time-series dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for pCR identification in BC is unclear. To identify pCR to neoadjuvant chemotherapy (NAC) using deep learning (DL) models based on the VGG-LSTM network. Retrospective. Center A: 235 patients (47.7 ± 10.0 years) were divided 7:3 into training (n = 164) and validation set (n = 71). Center B: 150 patients (48.5 ± 10.4 years) were used as test set. 3-T, T2-weighted spin-echo sequence imaging, and gradient echo DCE sequence imaging. Patients underwent MRI examinations at three sequential time points: pretreatment, after three cycles of treatment, and prior to surgery, with tumor regions of interest manually delineated. Histopathology was the gold standard. We used VGG-LSTM network to establish seven DL models using time-series DCE-MR images: pre-NAC images (t0 model), early NAC images (t1 model), post-NAC images (t2 model), pre-NAC and early NAC images (t0 + t1 model), pre-NAC and post-NAC images (t0 + t2 model), pre-NAC, early NAC and post-NAC images (t0 + t1 + t2 model), and the optimal model combined with the clinical features and imaging features (combined model). The models were trained and optimized on the training and validation set, and tested on the test set. The DeLong, Student's t-test, Mann-Whitney U, Chi-squared, Fisher's exact, Hosmer-Lemeshow tests, decision curve analysis, and receiver operating characteristics analysis were performed. P < 0.05 was considered significant. Compared with the other six models, the combined model achieved the best performance in the test set yielding an AUC of 0.927. The combined model that used time-series DCE-MR images, clinical features and imaging features shows promise for identifying pCR in BC. Stage 4.

Segmentation of Breast Lesion using Fuzzy Thresholding and Deep Learning

Breast cancer is a major cause of morbidity and mortality in women. In breast cancer screening, Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) has shown promise as a technique, providing enhanced temporal patterns of breast tissues. This study proposes an enhanced segmentation method for identifying breast lesions. The proposed experiments are done using the breast DCE-MRI images of 123 slices from seven patients in The Cancer Image Archive database. The three methods proposed and tested to segment the lesions are: i) Fuzzy C-mean Thresholding (FCMTH) with morphological operations ii) deep learning networks trained with original images iii) deep learning networks trained with three types of preprocessed images: the core breast image, the filtered core breast image, and the fuzzy thresholded image. In this study, the deep learning networks are trained with preprocessed images generated from the FCMTH technique, resulting in higher segmentation accuracy. FCMTH achieves Dice and Jaccard coefficients of 0.8458 and 0.7471, while DeepLabv3+ with MobileNetv2 trained by preprocessed images achieves 0.9468 and 0.8990, respectively. Thus, the combination of deep learning and FCMTH techniques provides the best performance for lesion detection.

The Road to a Realistic 3D Model for Estimating R2 and R2* Relaxation Versus Gd-DTPA Concentration in Whole Blood and Brain Tumor Vasculature.

Dynamic susceptibility contrast (DSC) MRI is commonly part of brain tumor imaging. For quantitative analysis, measurement of the arterial input function and tissue concentration time curve is required. Usually, a linear relationship between the MR signal changes and contrast agent concentration ([Gd]) is assumed, even though this is a known simplification. The aim of this study was to develop a realistic 3D simulation model as an efficient method to assess the relationship between ΔR2 (*) and [Gd] both in whole blood and brain tissue. We modified an open-source 3D simulation model to study different red blood cell configurations for assessing whole-blood ΔR2 (*) versus [Gd]. The results were validated against previously obtained 2D data and invitro data. Furthermore, hematocrit levels (30%-50%) and field strengths (1.5-3.0-7.0 T) were varied. Subsequently, realistic tumor vascular networks were derived from intraoperative high framerate Doppler ultrasound data to study the influence of vascular structure and orientation with respect to the main magnetic field (1.5-3.0-7.0 T) for the calculation of ΔR2 (*) versus [Gd] in brain tissue. For whole blood, good agreement of the 3D model was found with invitro and 2D simulation data when red blood cells were aligned with the blood flow. For brain tissue, minor differences were found between the vascular networks. The effect of vessel direction with respect to B0 was apparent in case of clear directionality of the main vessels. The dependency on field strength agreed with previous reports. In conclusion, we have shown that the relationship between ΔR2 (*) and [Gd] is affected by the organization of red blood cells and orientation of blood vessels with respect to the main magnetic field, as well as the field strength. These findings are important for further optimization of the realistic 3D model that could eventually be used to improve the estimation of hemodynamic parameters from DSC-MRI.

Improved Motion Correction in Dynamic Contrast-Enhanced MRI Using Low Rank With Soft Weighting

Improved Motion Correction in Dynamic Contrast-Enhanced MRI Using Low Rank With Soft Weighting

Time-dependent diffusion MRI and kinetic heterogeneity as potential imaging biomarkers for diagnosing suspicious breast lesions with 3.0-T breast MRI.

This study aimed to evaluate the diagnostic efficacy of time-dependent diffusion magnetic resonance imaging (td-dMRI) and dynamic contrast-enhanced MRI (DCE-MRI)-based kinetic heterogeneity in differentiating suspicious breast lesions (categorised as Breast Imaging Reporting and Data System 4 or 5). This prospective study included 51 females with suspicious breast lesions who underwent preoperative breast MRI, including DCE-MRI and td-dMRI. Six kinetic parameters, namely peak, persistent, plateau, washout component, predominant curve type, and heterogeneity, were extracted from the DCE series using MATLAB and SPM software. The td-dMRI data were analysed using the JOINT model to obtain five microstructural parameters and apparent diffusion coefficient at 50ms (ADC50ms). Chi-square or Fisher's exact test and the Mann-Whitney U test were used to compare these parameters between benign and malignant breast lesions. Univariate and multivariate logistic regression analyses with forward stepwise covariate selection were performed to identify significant clinical and radiologic variables. Differential diagnostic performance was evaluated using receiver operating characteristic curves and logistic regression analyses. For td-dMRI-derived parameters, the values of fin and cellularity were significantly higher in malignant breast lesions compared to benign lesions (P=0.001 and P<0.001, respectively), while ADC50ms was significantly lower in malignant lesions (P=0.001). In the kinetic heterogeneity analysis, the washout component was higher in malignant lesions compared to benign lesions (P=0.003). When combining significant td-dMRI and kinetic heterogeneity parameters, the area under the curve (AUC) value was 0.875, with an accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 82.69%, 86.11%, 75.00%, 88.57%, and 70.59%, respectively. Notably, margin and kinetic pattern emerged as independent predictors of malignant breast lesions (P=0.019 and 0.006, respectively). Furthermore, incorporating these two clinical-radiologic characteristics further enhanced diagnostic accuracy, yielding an AUC of 0.969, with accuracy, sensitivity, specificity, PPV, and NPV improving to 90.38%, 86.11%, 100%, 100%, and 76.19%, respectively. Kinetic heterogeneity- and td-dMRI-derived parameters are potentially non-invasive biomarkers for distinguishing suspicious breast lesions.