PACS-integrated machine learning breast density classifier: clinical validation.

OBJECTIVE: To test the performance of a novel machine learning-based breast density tool. The tool utilizes a convolutional neural network to predict the BI-RADS based density assessment of a study. The clinical density assessments of 33,000 mammographic examinations (164,000 images) from one academic medical center (Site A) were used for training. MATERIALS AND METHODS: This was an IRB approved HIPAA compliant study performed at two academic medical centers. The validation data set was composed of 500 studies from one site (Site A) and 700 from another (Site B). At Site A, each study was assessed by three breast radiologists and the majority (consensus) assessment was used as truth. At Site B, if the tool agreed with the clinical reading, then it was considered to have correctly predicted the clinical reading. In cases where the tool and the clinical reading disagreed, then the study was evaluated by three radiologists and the consensus reading was used as the clinical reading. RESULTS: For the classification into the four categories of the Breast Imaging Reporting and Data System (BI-RADS®), the AI classifier had an accuracy of 84.6% at Site A and 89.7% at Site B. For binary classification (dense vs. non-dense), the AI classifier had an accuracy of 94.4% at Site A and 97.4% at Site B. In no case did the classifier disagree with the consensus reading by more than one category. CONCLUSIONS: The automated breast density tool showed high agreement with radiologists' assessments of breast density.

Novel Radiomic Measurements of Tumor-Associated Vasculature Morphology on Clinical Imaging as a Biomarker of Treatment Response in Multiple Cancers.

PURPOSE: The tumor-associated vasculature (TAV) differs from healthy blood vessels by its convolutedness, leakiness, and chaotic architecture, and these attributes facilitate the creation of a treatment-resistant tumor microenvironment. Measurable differences in these attributes might also help stratify patients by likely benefit of systemic therapy (e.g., chemotherapy). In this work, we present a new category of computational image-based biomarkers called quantitative tumor-associated vasculature (QuanTAV) features, and demonstrate their ability to predict response and survival across multiple cancer types, imaging modalities, and treatment regimens involving chemotherapy. EXPERIMENTAL DESIGN: We isolated tumor vasculature and extracted mathematical measurements of twistedness and organization from routine pretreatment radiology (CT or contrast-enhanced MRI) of a total of 558 patients, who received one of four first-line chemotherapy-based therapeutic intervention strategies for breast (n = 371) or non-small cell lung cancer (NSCLC, n = 187). RESULTS: Across four chemotherapy-based treatment strategies, classifiers of QuanTAV measurements significantly (P < 0.05) predicted response in held out testing cohorts alone (AUC = 0.63-0.71) and increased AUC by 0.06-0.12 when added to models of significant clinical variables alone. Similarly, we derived QuanTAV risk scores that were prognostic of recurrence-free survival in treatment cohorts who received surgery following chemotherapy for breast cancer [P = 0.0022; HR = 1.25; 95% confidence interval (CI), 1.08-1.44; concordance index (C-index) = 0.66] and chemoradiation for NSCLC (P = 0.039; HR = 1.28; 95% CI, 1.01-1.62; C-index = 0.66). From vessel-based risk scores, we further derived categorical QuanTAV high/low risk groups that were independently prognostic among all treatment groups, including patients with NSCLC who received chemotherapy only (P = 0.034; HR = 2.29; 95% CI, 1.07-4.94; C-index = 0.62). QuanTAV response and risk scores were independent of clinicopathologic risk factors and matched or exceeded models of clinical variables including posttreatment response. CONCLUSIONS: Across these domains, we observed an association of vascular morphology on CT and MRI-as captured by metrics of vessel curvature, torsion, and organizational heterogeneity-and treatment outcome. Our findings suggest the potential of shape and structure of the TAV in developing prognostic and predictive biomarkers for multiple cancers and different treatment strategies.

Association of Peritumoral Radiomics With Tumor Biology and Pathologic Response to Preoperative Targeted Therapy for HER2 (ERBB2)-Positive Breast Cancer.

Importance: There has been significant recent interest in understanding the utility of quantitative imaging to delineate breast cancer intrinsic biological factors and therapeutic response. No clinically accepted biomarkers are as yet available for estimation of response to human epidermal growth factor receptor 2 (currently known as ERBB2, but referred to as HER2 in this study)-targeted therapy in breast cancer. Objective: To determine whether imaging signatures on clinical breast magnetic resonance imaging (MRI) could noninvasively characterize HER2-positive tumor biological factors and estimate response to HER2-targeted neoadjuvant therapy. Design, Setting, and Participants: In a retrospective diagnostic study encompassing 209 patients with breast cancer, textural imaging features extracted within the tumor and annular peritumoral tissue regions on MRI were examined as a means to identify increasingly granular breast cancer subgroups relevant to therapeutic approach and response. First, among a cohort of 117 patients who received an MRI prior to neoadjuvant chemotherapy (NAC) at a single institution from April 27, 2012, through September 4, 2015, imaging features that distinguished HER2+ tumors from other receptor subtypes were identified. Next, among a cohort of 42 patients with HER2+ breast cancers with available MRI and RNaseq data accumulated from a multicenter, preoperative clinical trial (BrUOG 211B), a signature of the response-associated HER2-enriched (HER2-E) molecular subtype within HER2+ tumors (n = 42) was identified. The association of this signature with pathologic complete response was explored in 2 patient cohorts from different institutions, where all patients received HER2-targeted NAC (n = 28, n = 50). Finally, the association between significant peritumoral features and lymphocyte distribution was explored in patients within the BrUOG 211B trial who had corresponding biopsy hematoxylin-eosin-stained slide images. Data analysis was conducted from January 15, 2017, to February 14, 2019. Main Outcomes and Measures: Evaluation of imaging signatures by the area under the receiver operating characteristic curve (AUC) in identifying HER2+ molecular subtypes and distinguishing pathologic complete response (ypT0/is) to NAC with HER2-targeting. Results: In the 209 patients included (mean [SD] age, 51.1 [11.7] years), features from the peritumoral regions better discriminated HER2-E tumors (maximum AUC, 0.85; 95% CI, 0.79-0.90; 9-12 mm from the tumor) compared with intratumoral features (AUC, 0.76; 95% CI, 0.69-0.84). A classifier combining peritumoral and intratumoral features identified the HER2-E subtype (AUC, 0.89; 95% CI, 0.84-0.93) and was significantly associated with response to HER2-targeted therapy in both validation cohorts (AUC, 0.80; 95% CI, 0.61-0.98 and AUC, 0.69; 95% CI, 0.53-0.84). Features from the 0- to 3-mm peritumoral region were significantly associated with the density of tumor-infiltrating lymphocytes (R2 = 0.57; 95% CI, 0.39-0.75; P = .002). Conclusions and Relevance: A combination of peritumoral and intratumoral characteristics appears to identify intrinsic molecular subtypes of HER2+ breast cancers from imaging, offering insights into immune response within the peritumoral environment and suggesting potential benefit for treatment guidance.

Segment-specific associations between local haemodynamic and imaging markers of early atherosclerosis at the carotid artery: an in vivo human study.

Low and oscillatory wall shear stress (WSS) has long been hypothesized as a risk factor for atherosclerosis; however, evidence has been inferred primarily from model and post-mortem studies, or clinical studies of patients with already-developed plaques. This study aimed to identify associations between local haemodynamic and imaging markers of early atherosclerosis. Comprehensive magnetic resonance imaging allowed quantification of contrast enhancement (CE) (a marker of endothelial dysfunction) and vessel wall thickness at two distinct segments: the internal carotid artery bulb and the common carotid artery (CCA). Strict criteria were applied to a large dataset to exclude inward remodelling, resulting in 41 cases for which personalized computational fluid dynamic simulations were performed. After controlling for cardiovascular risk factors, bulb wall thickening was found to be weakly, but not significantly, associated with oscillatory WSS. CE at the bulb was significantly associated with low WSS (p < 0.001) and low flow helicity (p < 0.05). No significant associations were found for the CCA segment. Local haemodynamics at the bulb were significantly correlated with blood flow rates and heart rates, but not carotid bifurcation geometry (flare and curvature). Therefore low, but not oscillatory, WSS is an early independent marker of atherosclerotic changes preceding intimal thickening at the carotid bulb.

Detector-based spectral CT with a novel dual-layer technology: principles and applications.

Detector-based spectral computed tomography is a novel dual-energy CT technology that employs two layers of detectors to simultaneously collect low- and high-energy data in all patients using standard CT protocols. In addition to the conventional polyenergetic images created for each patient, projection-space decomposition is used to generate spectral basis images (photoelectric and Compton scatter) for creating multiple spectral images, including material decomposition (iodine-only, virtual non-contrast, effective atomic number) and virtual monoenergetic images, on-demand according to clinical need. These images are useful in multiple clinical applications, including- improving vascular contrast, improving lesion conspicuity, decreasing artefacts, material characterisation and reducing radiation dose. In this article, we discuss the principles of this novel technology and also illustrate the common clinical applications. Teaching points • The top and bottom layers of dual-layer CT absorb low- and high-energy photons, respectively.• Multiple spectral images are generated by projection-space decomposition.• Spectral images can be generated in all patients scanned in this scanner.

Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI.

BACKGROUND: In this study, we evaluated the ability of radiomic textural analysis of intratumoral and peritumoral regions on pretreatment breast cancer dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to predict pathological complete response (pCR) to neoadjuvant chemotherapy (NAC). METHODS: A total of 117 patients who had received NAC were retrospectively analyzed. Within the intratumoral and peritumoral regions of T1-weighted contrast-enhanced MRI scans, a total of 99 radiomic textural features were computed at multiple phases. Feature selection was used to identify a set of top pCR-associated features from within a training set (n = 78), which were then used to train multiple machine learning classifiers to predict the likelihood of pCR for a given patient. Classifiers were then independently tested on 39 patients. Experiments were repeated separately among hormone receptor-positive and human epidermal growth factor receptor 2-negative (HR+, HER2-) and triple-negative or HER2+ (TN/HER2+) tumors via threefold cross-validation to determine whether receptor status-specific analysis could improve classification performance. RESULTS: Among all patients, a combined intratumoral and peritumoral radiomic feature set yielded a maximum AUC of 0.78 ± 0.030 within the training set and 0.74 within the independent testing set using a diagonal linear discriminant analysis (DLDA) classifier. Receptor status-specific feature discovery and classification enabled improved prediction of pCR, yielding maximum AUCs of 0.83 ± 0.025 within the HR+, HER2- group using DLDA and 0.93 ± 0.018 within the TN/HER2+ group using a naive Bayes classifier. In HR+, HER2- breast cancers, non-pCR was characterized by elevated peritumoral heterogeneity during initial contrast enhancement. However, TN/HER2+ tumors were best characterized by a speckled enhancement pattern within the peritumoral region of nonresponders. Radiomic features were found to strongly predict pCR independent of choice of classifier, suggesting their robustness as response predictors. CONCLUSIONS: Through a combined intratumoral and peritumoral radiomics approach, we could successfully predict pCR to NAC from pretreatment breast DCE-MRI, both with and without a priori knowledge of receptor status. Further, our findings suggest that the radiomic features most predictive of response vary across different receptor subtypes.

Utility of late gadolinium enhancement in pediatric cardiac MRI.

Late gadolinium enhancement (LGE) cardiac magnetic resonance (MR) imaging sequence is increasingly used in the evaluation of pediatric cardiovascular disorders, and although LGE might be a normal feature at the sites of previous surgeries, it is pathologically seen as a result of extracellular space expansion, either from acute cell damage or chronic scarring or fibrosis. LGE is broadly divided into ischemic and non-ischemic patterns. LGE caused by myocardial infarction occurs in a vascular distribution and always involves the subendocardial portion, progressively involving the outer regions in a waveform pattern. Non-ischemic cardiomyopathies can have a mid-myocardial (either linear or patchy), subepicardial or diffuse subendocardial distribution. Idiopathic dilated cardiomyopathy can have a linear mid-myocardial pattern, while hypertrophic cardiomyopathy can have fine, patchy enhancement in hypertrophied and non-hypertrophied segments as well as right ventricular insertion points. Myocarditis and sarcoidosis have a mid-myocardial or subepicardial pattern of LGE. Fabry disease typically affects the basal inferolateral segment while Danon disease typically spares the septum. Pericarditis is characterized by diffuse or focal pericardial thickening and enhancement. Thrombus, the most common non-neoplastic cardiac mass, is characterized by absence of enhancement in all sequences, while neoplastic masses show at least some contrast enhancement, depending on the pathology. Regardless of the etiology, presence of LGE is associated with a poor prognosis. In this review, we describe the technical modifications required for performing LGE cardiac MR sequence in children, review and illustrate the patterns of LGE in children, and discuss their clinical significance.

Impact of T2 decay on carotid artery wall thickness measurements.

PURPOSE: To investigate the impact of T2 relaxation of the carotid wall on measurements of its thickness. MATERIALS AND METHODS: The common carotid artery wall was imaged using a spin echo sequence acquired at four echo times (17 ms to 68 ms) in 65 participants as part of VALIDATE study. Images were acquired transverse to the artery 1.5 cm proximal to the flow divider. Mean wall thickness, mean wall signal intensity, lumen area, and outer wall area were measured for each echo. Contours were also traced on the image from the fourth echo and then propagated to the images from the preceding echoes. This was repeated using the image from the first echo. Mean wall signal intensity measurements at the four echo times were fit to a mono-exponential decay curve to derive the mean T2 relaxation time for each set of contours. RESULTS: Mean wall thickness decreased with increasing echo time, with an average thickness reduction of 8.6% between images acquired at the first and last echo times (TE) (0.93 mm at TE 17 ms versus 0.85 mm at TE 68 ms, P < 0.001). Average T2 relaxation time of the carotid wall decreased by 3% when the smaller contours from the last echo were used, which excluded the outer-most layer (54.3 ± 7.6 ms versus 52.7 ± 6.6 ms, P = 0.03). CONCLUSION: Carotid wall thickness measurements decrease with echo time as expected by the fast T2 relaxation time of the outer-most layer, namely the adventitia. A short echo time is needed for thickness measurements to include adventitia, which plays an important role in plaque development.

Intracranial arterial wall imaging using three-dimensional high isotropic resolution black blood MRI at 3.0 Tesla.

PURPOSE: To develop a high isotropic-resolution sequence to evaluate intracranial vessels at 3.0 Tesla (T). MATERIALS AND METHODS: Thirteen healthy volunteers and 4 patients with intracranial stenosis were imaged at 3.0T using 0.5-mm isotropic-resolution three-dimensional (3D) Volumetric ISotropic TSE Acquisition (VISTA; TSE, turbo spin echo), with conventional 2D-TSE for comparison. VISTA was repeated for 6 volunteers and 4 patients at 0.4-mm isotropic-resolution to explore the trade-off between SNR and voxel volume. Wall signal-to-noise-ratio (SNR(wall) ), wall-lumen contrast-to-noise-ratio (CNR(wall-lumen) ), lumen area (LA), wall area (WA), mean wall thickness (MWT), and maximum wall thickness (maxWT) were compared between 3D-VISTA and 2D-TSE sequences, as well as 3D images acquired at both resolutions. Reliability was assessed by intraclass correlations (ICC). RESULTS: Compared with 2D-TSE measurements, 3D-VISTA provided 58% and 74% improvement in SNR(wall) and CNR(wall-lumen) , respectively. LA, WA, MWT and maxWT from 3D and 2D techniques highly correlated (ICCs of 0.96, 0.95, 0.96, and 0.91, respectively). CNR(wall-lumen) using 0.4-mm resolution VISTA decreased by 27%, compared with 0.5-mm VISTA but with reduced partial-volume-based overestimation of wall thickness. Reliability for 3D measurements was good to excellent. CONCLUSION: The 3D-VISTA provides SNR-efficient, highly reliable measurements of intracranial vessels at high isotropic-resolution, enabling broad coverage in a clinically acceptable time.