Evolutionary Strategies Enable Systematic and Reliable Uncertainty Quantification: A Proof-of-Concept Pilot Study on Resting-State Functional MRI Language Lateralization.

Reliable and trustworthy artificial intelligence (AI), particularly in high-stake medical diagnoses, necessitates effective uncertainty quantification (UQ). Existing UQ methods using model ensembles often introduce invalid variability or computational complexity, rendering them impractical and ineffective in clinical workflow. We propose a UQ approach based on deep neuroevolution (DNE), a data-efficient optimization strategy. Our goal is to replicate trends observed in expert-based UQ. We focused on language lateralization maps from resting-state functional MRI (rs-fMRI). Fifty rs-fMRI maps were divided into training/testing (30:20) sets, representing two labels: "left-dominant" and "co-dominant." DNE facilitated acquiring an ensemble of 100 models with high training and testing set accuracy. Model uncertainty was derived from distribution entropies over the 100 model predictions. Expert reviewers provided user-based uncertainties for comparison. Model (epistemic) and user-based (aleatoric) uncertainties were consistent in the independently and identically distributed (IID) testing set, mainly indicating low uncertainty. In a mostly out-of-distribution (OOD) holdout set, both model and user-based entropies correlated but displayed a bimodal distribution, with one peak representing low and another high uncertainty. We also found a statistically significant positive correlation between epistemic and aleatoric uncertainties. DNE-based UQ effectively mirrored user-based uncertainties, particularly highlighting increased uncertainty in OOD images. We conclude that DNE-based UQ correlates with expert assessments, making it reliable for our use case and potentially for other radiology applications.

Longitudinal Evaluation of DCE-MRI as an Early Indicator of Progression after Standard Therapy in Glioblastoma.

Background and Purpose: Distinguishing treatment-induced imaging changes from progressive disease has important implications for avoiding inappropriate discontinuation of a treatment. Our goal in this study is to evaluate the utility of dynamic contrast-enhanced (DCE) perfusion MRI as a biomarker for the early detection of progression. We hypothesize that DCE-MRI may have the potential as an early predictor for the progression of disease in GBM patients when compared to the current standard of conventional MRI. Methods: We identified 26 patients from 2011 to 2023 with newly diagnosed primary glioblastoma by histopathology and gross or subtotal resection of the tumor. Then, we classified them into two groups: patients with progression of disease (POD) confirmed by pathology or change in chemotherapy and patients with stable disease without evidence of progression or need for therapy change. Finally, at least three DCE-MRI scans were performed prior to POD for the progression cohort, and three consecutive DCE-MRI scans were performed for those with stable disease. The volume of interest (VOI) was delineated by a neuroradiologist to measure the maximum values for Ktrans and plasma volume (Vp). A Friedman test was conducted to evaluate the statistical significance of the parameter changes between scans. Results: The mean interval between subsequent scans was 57.94 days, with POD-1 representing the first scan prior to POD and POD-3 representing the third scan. The normalized maximum Vp values for POD-3, POD-2, and POD-1 are 1.40, 1.86, and 3.24, respectively (FS = 18.00, p = 0.0001). It demonstrates that Vp max values are progressively increasing in the three scans prior to POD when measured by routine MRI scans. The normalized maximum Ktrans values for POD-1, POD-2, and POD-3 are 0.51, 0.09, and 0.51, respectively (FS = 1.13, p < 0.57). Conclusions: Our analysis of the longitudinal scans leading up to POD significantly correlated with increasing plasma volume (Vp). A longitudinal study for tumor perfusion change demonstrated that DCE perfusion could be utilized as an early predictor of tumor progression.

Dynamic Contrast Enhanced MR Perfusion and Diffusion-Weighted Imaging of Marrow-Replacing Disorders of the Spine: A Comprehensive Review.

Significant advancements in cancer treatment have led to improved survival rates for patients, particularly in the context of spinal metastases. However, early detection and monitoring of treatment response remain crucial for optimizing patient outcomes. Although conventional imaging methods such as bone scan, PET, MR imaging, and computed tomography are commonly used for diagnosing and monitoring treatment, they present challenges in differential diagnoses and treatment response monitoring. This review article provides a comprehensive overview of the principles, applications, and practical uses of dynamic contrast-enhanced MR imaging and diffusion-weighted imaging in the assessment and monitoring of marrow-replacing disorders of the spine.

T1-Weighted, Dynamic Contrast-Enhanced MR Perfusion Imaging Can Differentiate between Treatment Success and Failure in Spine Metastases Undergoing Radiation Therapy.

BACKGROUND AND PURPOSE: Current imaging techniques have difficulty differentiating treatment success and failure in spinal metastases undergoing radiation therapy. This study investigated the correlation between changes in dynamic contrast-enhanced MR imaging perfusion parameters and clinical outcomes following radiation therapy for spinal metastases. We hypothesized that perfusion parameters will outperform traditional size measurements in discriminating treatment success and failure. MATERIALS AND METHODS: This retrospective study included 49 patients (mean age, 63 [SD, 13] years; 29 men) with metastatic lesions treated with radiation therapy who underwent dynamic contrast-enhanced MR imaging. The median time between radiation therapy and follow-up dynamic contrast-enhanced MR imaging was 62 days. We divided patients into 2 groups: clinical success (n = 38) and failure (n = 11). Failure was defined as PET recurrence (n = 5), biopsy-proved (n = 1) recurrence, or an increase in tumor size (n = 7), while their absence defined clinical success. A Mann-Whitney U test was performed to assess differences between groups. RESULTS: The reduction in plasma volume was greater in the success group than in the failure group (-57.3% versus +88.2%, respectively; P < .001). When we assessed the success of treatment, the sensitivity of plasma volume was 91% (10 of 11; 95% CI, 82%-97%) and the specificity was 87% (33 of 38; 95% CI, 73%-94%). The sensitivity of size measurements was 82% (9 of 11; 95% CI, 67%-90%) and the specificity was 47% (18 of 38; 95% CI, 37%-67%). CONCLUSIONS: The specificity of plasma volume was higher than that of conventional size measurements, suggesting that dynamic contrast-enhanced MR imaging is a powerful tool to discriminate between treatment success and failure.

Extracranial Carotid Plaque Calcification and Cerebrovascular Ischemia: A Systematic Review and Meta-Analysis.

BACKGROUND: Although coronary calcification quantification is an established approach for cardiovascular risk assessment, the value of quantifying carotid calcification is less clear. As a result, we performed a systematic review and meta-analysis to evaluate the association between extracranial carotid artery plaque calcification burden and ipsilateral cerebrovascular ischemic events. METHODS: A comprehensive literature search was performed in the following databases: Ovid MEDLINE(R) 1946 to July 6, 2022; OVID Embase 1974 to July 6, 2022; and The Cochrane Library (Wiley). We performed meta-analyses including studies in which investigators performed a computed tomography assessment of calcification volume, percentage, or other total calcium burden summarizable in a single continuous imaging biomarker and determined the association of these features with the occurrence of ipsilateral stroke or transient ischemic attack. RESULTS: Our overall meta-analysis consisted of 2239 carotid arteries and 9 studies. The presence of calcification in carotid arteries ipsilateral to ischemic stroke or in stroke patients compared with asymptomatic patients did not demonstrate a significant association with ischemic cerebrovascular events (relative risk of 0.75 [95% CI, 0.44-1.28]; P=0.29). When restricted to studies of significant carotid artery stenosis (>50%), the presence of calcification was associated with a reduced risk of ischemic stroke (relative risk of 0.56 [95% CI, 0.38-0.85]; P=0.006). When the analysis was limited to studies of patients with mainly nonstenotic plaques, there was an increased relative risk of ipsilateral ischemic stroke of 1.72 ([95% CI, 1.01-2.91]; P=0.04). Subgroup meta-analyses of total calcium burden and morphological features of calcium showed wide variability in their strength of association with ischemic stroke and demonstrated significant heterogeneity. CONCLUSIONS: The presence of calcification in carotid plaque confers a reduced association with ipsilateral ischemic events, although these results seem to be limited among carotid arteries with higher degrees of stenosis. Adoption of carotid calcification measures in clinical decision-making will require additional studies providing more reproducible and standardized methods of calcium characterization and testing these imaging strategies in prospective studies.

Dynamic Contrast-Enhanced MR Perfusion: Role in Diagnosis and Treatment Follow-Up in Patients with Vertebral Body Tumors.

Recent therapeutic advances have led to increased survival times for patients with metastatic disease. Key to survival is early diagnosis and subsequent treatment as well as early detection of treatment failure allowing for therapy modifications. Conventional MR imaging techniques of the spine can be at times suboptimal for identifying viable tumor, as structural changes and imaging characteristics may not differ pretreatment and posttreatment. Advanced imaging techniques such as DCE-MRI can allow earlier and more accurate noninvasive assessment of viable disease by characterizing physiologic changes and tumor microvasculature.

Delay of Aortic Arterial Input Function Time Improves Detection of Malignant Vertebral Body Lesions on Dynamic Contrast-Enhanced MRI Perfusion.

Dynamic contrast-enhanced MRI (DCE) is an emerging modality in the study of vertebral body malignancies. DCE-MRI analysis relies on a pharmacokinetic model, which assumes that contrast uptake is simultaneous in the feeding of arteries and tissues of interest. While true in the highly vascularized brain, the perfusion of the spine is delayed. This delay of contrast reaching vertebral body lesions can affect DCE-MRI analyses, leading to misdiagnosis for the presence of active malignancy in the bone marrow. To overcome the limitation of delayed contrast arrival to vertebral body lesions, we shifted the arterial input function (AIF) curve over a series of phases and recalculated the plasma volume values (Vp) for each phase shift. We hypothesized that shifting the AIF tracer curve would better reflect actual contrast perfusion, thereby improving the accuracy of Vp maps in metastases. We evaluated 18 biopsy-proven vertebral body metastases in which standard DCE-MRI analysis failed to demonstrate the expected increase in Vp. We manually delayed the AIF curve for multiple phases, defined as the scan-specific phase temporal resolution, and analyzed DCE-MRI parameters with the new AIF curves. All patients were found to require at least one phase-shift delay in the calculated AIF to better visualize metastatic spinal lesions and improve quantitation of Vp. Average normalized Vp values were 1.78 ± 1.88 for zero phase shifts (P0), 4.72 ± 4.31 for one phase shift (P1), and 5.59 ± 4.41 for two phase shifts (P2). Mann-Whitney U tests obtained p-values = 0.003 between P0 and P1, and 0.0004 between P0 and P2. This study demonstrates that image processing analysis for DCE-MRI in patients with spinal metastases requires a careful review of signal intensity curve, as well as a possible adjustment of the phase of aortic AIF to increase the accuracy of Vp.

Machine Learning and Improved Quality Metrics in Acute Intracranial Hemorrhage by Noncontrast Computed Tomography.

OBJECTIVE: The timely reporting of critical results in radiology is paramount to improved patient outcomes. Artificial intelligence has the ability to improve quality by optimizing clinical radiology workflows. We sought to determine the impact of a United States Food and Drug Administration-approved machine learning (ML) algorithm, meant to mark computed tomography (CT) head examinations pending interpretation as higher probability for intracranial hemorrhage (ICH), on metrics across our healthcare system. We hypothesized that ML is associated with a reduction in report turnaround time (RTAT) and length of stay (LOS) in emergency department (ED) and inpatient populations. MATERIALS AND METHODS: An ML algorithm was incorporated across CT scanners at imaging sites in January 2018. RTAT and LOS were derived for reports and patients between July 2017 and December 2017 prior to implementation of ML and compared to those between January 2018 and June 2018 after implementation of ML. A total of 25,658 and 24,996 ED and inpatient cases were evaluated across the entire healthcare system before and after ML, respectively. RESULTS: RTAT decreased from 75 to 69 minutes (P <0.001) at all facilities in the healthcare system. At the level 1 trauma center specifically, RTAT decreased from 67 to 59 minutes (P <0.001). ED LOS decreased from 471 to 425 minutes (P <0.001) for patients without ICH, and from 527 to 491 minutes for those with ICH (P = 0.456). Inpatient LOS decreased from 18.4 to 15.8 days for those without ICH (P = 0.001) and 18.1 to 15.8 days for those with ICH (P = 0.02). CONCLUSION: We demonstrated that utilization of ML was associated with a statistically significant decrease in RTAT. There was also a significant decrease in LOS for ED patients without ICH, but not for ED patients with ICH. Further evaluation of the impact of such tools on patient care and outcomes is needed.

Utility of Artificial Intelligence Tool as a Prospective Radiology Peer Reviewer - Detection of Unreported Intracranial Hemorrhage.

RATIONALE AND OBJECTIVES: Misdiagnosis of intracranial hemorrhage (ICH) can adversely impact patient outcomes. The increasing workload on the radiologists may increase the chance of error and compromise the quality of care provided by the radiologists. MATERIALS AND METHODS: We used an FDA approved artificial intelligence (AI) solution based on a convolutional neural network to assess the prevalence of ICH in scans, which were reported as negative for ICH. We retrospectively applied the AI solution to all consecutive noncontrast computed tomography (CT) head scans performed at eight imaging sites affiliated to our institution. RESULTS: In the 6565 noncontrast CT head scans, which met the inclusion criteria, 5585 scans were reported to have no ICH ("negative-by-report" cases). We applied AI solution to these "negative-by-report" cases. AI solution suggested there were ICH in 28 of these scans ("negative-by-report" and "positive-by-AI solution"). After consensus review by three neuroradiologists, 16 of these scans were found to have ICH, which was not reported (missed diagnosis by radiologists), with a false-negative rate of radiologists for ICH detection at 1.6%. Most commonly missed ICH was overlying the cerebral convexity and in the parafalcine regions. CONCLUSION: Our study demonstrates that an AI solution can help radiologists to diagnose ICH and thus decrease the error rate. AI solution can serve as a prospective peer review tool for non-contrast head CT scans to identify ICH and thus minimize false negatives.

Cellular Angiofibroma Presenting as a Subepithelial Rectal Mass.

A very rare case of cellular angiofibroma arising from the rectum in a 62-year-old man with a normal colonoscopy 2 years earlier is reported. To our knowledge, this is the first such case reported in the literature. The tumor was transanally excised with clear margins, and the patient had no postoperative complications. It is key to accurately differentiate this lesion from other subepithelial rectal tumors and more aggressive genital soft tissue tumors because clinical management varies. We performed a review of clinical records and pathology as well as an extensive literature review.

Calcifying pseudoneoplasm of the spine: imaging and pathological features.

Calcifying pseudoneoplasms of the neuraxis are extremely rare calcified lesions that can occur anywhere in the central nervous system. These non-neoplastic lesions have been reported to arise both in the brain and spine with similar frequency and can be found intra-axially as well as extra-axially. The associated symptoms are generally due to mass effect rather than local invasion as calcifying pseudoneoplasms of the neuraxis are usually considered to be benign non-infiltrative lesions. We report a unique case of a 67-year-old male patient who developed lower extremity weakness and gait instability with imaging and histological features of calcifying pseudoneoplasm of the neuraxis occurring in the spine with adhesive features and intradural extension. Calcifying pseudoneoplasms are benign, slow-growing masses that can present with a wide variety of symptoms depending on the size and location of the tumor. The differential diagnosis for these entities can be narrowed taking into consideration relevant imaging features as well as important clinical information.

Dynamic contrast-enhanced magnetic resonance imaging of osseous spine metastasis before and 1 hour after high-dose image-guided radiation therapy.

OBJECTIVE High-dose image-guided radiation therapy (HD IGRT) has been instrumental in mitigating some limitations of conventional RT. The recent emergence of dynamic contrast-enhanced (DCE) MRI to investigate tumor physiology can be used to verify the response of human tumors to HD IGRT. The purpose of this study was to evaluate the near-immediate effects of HD IGRT on spine metastases through the use of DCE MRI perfusion studies. METHODS Six patients with spine metastases from prostate, thyroid, and renal cell carcinoma who underwent HD IGRT were studied using DCE MRI prior to and 1 hour after HD IGRT. The DCE perfusion parameters plasma volume (Vp) and vascular permeability (Ktrans) were measured to assess the near-immediate and long-term tumor response. A Mann-Whitney U-test was performed to compare significant changes (at p ≤ 0.05) in perfusion parameters before and after RT. RESULTS The authors observed a precipitous drop in Vp within 1 hour of HD IGRT, with a mean decrease of 65.2%. A significant difference was found between Vp values for before and 1 hour after RT (p ≤ 0.05). No significant change was seen in Vp (p = 0.31) and Ktrans (p = 0.1) from 1 hour after RT to the first follow-up. CONCLUSIONS The data suggest that there is an immediate effect of HD IGRT on the vascularity of spine metastases, as demonstrated by a precipitous decrease in Vp. The DCE MRI studies can detect such changes within 1 hour after RT, and findings are concordant with existing animal models.

Magnetic resonance perfusion characteristics of hypervascular renal and hypovascular prostate spinal metastases: clinical utilities and implications.

STUDY DESIGN: A total of 40 patients with spinal metastases from renal cell carcinomas (RCCs) or prostate carcinomas (PCs) were studied using DCE-MRI (dynamic contrast-enhanced magnetic resonance imaging). OBJECTIVE: To evaluate spinal metastases from RCC and PC to assess the sensitivity and specificity of perfusion parameters obtained by quantitative and semiquantitative methods, which would allow for noninvasive discrimination between hypovascular and hypervascular lesions. SUMMARY OF BACKGROUND DATA: Conventional MRI can be inconclusive in assessing diagnostically complex spinal lesions in patients with cancer in whom fibrosis, infarction, edema related to compression fractures, and infection may simulate malignant neoplasm. Conventional MRI is also of limited value in assessing tumor vascularity and identifying hypervascular tumors. DCE-MRI offers an advantage over conventional MRI in that it provides anatomical, physiological, and hemodynamic information about neoplastic lesions. METHODS: DCE perfusion parameters: vascular permeability, plasma volume (V(p)), wash-in slope, and peak-enhancement parameter were measured to assess their potential as discriminators of tumor vascularity. A Mann-Whitney U test (at P ≤ 0.01), was performed to quantify and compare significance of perfusion parameters between the 2 groups. RESULTS: Of the 4 perfusion parameters studied, V(p) was observed to have the largest difference in mean (µ) between PC (µ = 3.29/s) and RCC metastases (µ = 5.92/s). This was followed by the peak-enhancement, vascular permeability, and wash-in parameters. A Mann-Whitney U test showed a significant difference between V(p) values for PC and RCC lesions (P ≤ 0.001). Similarly, peak-enhancement parameter showed a significant difference between the 2 histologies (P ≤ 0.001), as did vascular permeability (P ≤ 0.01). The receiver operating characteristic curve showed that V(p) recorded the highest area under the curve (0.867). CONCLUSION: V(p) was shown to be the best discriminator between spinal metastases from PC and RCC with the mean V(p) of RCC metastasis being 1.8 times that of the PC lesions, thus discriminating between hyper- and hypovascular metastases, which has important clinical implications.