Automated assessment of ischemic core on non-contrast computed tomography: a multicenter comparative analysis with CT perfusion.

BACKGROUND: Application of machine learning (ML) algorithms has shown promising results in estimating ischemic core volumes using non-contrast CT (NCCT). OBJECTIVE: To assess the performance of the e-Stroke Suite software (Brainomix) in assessing ischemic core volumes on NCCT compared with CT perfusion (CTP) in patients with acute ischemic stroke. METHODS: In this retrospective multicenter study, patients with anterior circulation large vessel occlusions who underwent pretreatment NCCT and CTP, successful reperfusion (modified Thrombolysis in Cerbral Infarction ≥2b), and post-treatment MRI, were included from three stroke centers. Automated calculation of ischemic core volumes was obtained on NCCT scans using ML algorithm deployed by e-Stroke Suite and from CTP using Olea software (Olea Medical). Comparative analysis was performed between estimated core volumes on NCCT and CTP and against MRI calculated final infarct volume (FIV). RESULTS: A total of 111 patients were included. Estimated ischemic core volumes (mean±SD, mL) were 20.4±19.0 on NCCT and 19.9±18.6 on CTP, not significantly different (P=0.82). There was moderate (r=0.40) and significant (P<0.001) correlation between estimated core on NCCT and CTP. The mean difference between FIV and estimated core volume on NCCT and CTP was 29.9±34.6 mL and 29.6±35.0 mL, respectively (P=0.94). Correlations between FIV and estimated core volume were similar for NCCT (r=0.30, P=0.001) and CTP (r=0.36, P<0.001). CONCLUSIONS: Results show that ML-based estimated ischemic core volumes on NCCT are comparable to those obtained from concurrent CTP in magnitude and in degree of correlation with MR-assessed FIV.

Lumbar Spinal Canal Segmentation in Cases with Lumbar Stenosis Using Deep-U-Net Ensembles.

BACKGROUND: Narrowing of the lumbar spinal canal, or lumbar stenosis (LS), may cause debilitating radicular pain or muscle weakness. It is the most frequent indication for spinal surgery in the elderly population. Modern diagnosis relies on magnetic resonance imaging and its inherently subjective interpretation. Diagnostic rigor, accuracy, and speed may be improved by automation. In this work, we aimed to determine whether a deep-U-Net ensemble trained to segment spinal canals on a heterogeneous mix of clinical data is comparable to radiologists' segmentation of these canals in patients with LS. METHODS: The deep U-nets were trained on spinal canals segmented by physicians on 100 axial T2 lumbar magnetic resonance imaging selected randomly from our institutional database. Test data included a total of 279 elderly patients with LS that were separate from the training set. RESULTS: Machine-generated segmentations (MA) were qualitatively similar to expert-generated segmentations (ME1, ME2). Machine- and expert-generated segmentations were quantitatively similar, as evidenced by Dice scores (MA vs. ME1: 0.88 ± 0.04, MA vs. ME2: 0.89 ± 0.04), the Hausdorff distance (MA vs. ME1: 11.7 mm ± 13.8, MA vs. ME2: 13.1 mm ± 16.3), and average surface distance (MAvs. ME1: 0.18 mm ± 0.13, MA vs. ME2 0.18 mm ± 0.16) metrics. These metrics are comparable to inter-rater variation (ME1 vs. ME2 Dice scores: 0.94 ± 0.02, the Hausdorff distances: 9.3 mm ± 15.6, average surface distances: 0.08 mm ± 0.09). CONCLUSION: We conclude that machine learning algorithms can segment lumbar spinal canals in LS patients, and automatic delineations are both qualitatively and quantitatively comparable to expert-generated segmentations.

Upper lumbar spine far lateral disc herniations masquerading as peripheral nerve sheath tumors: illustrative cases.

BACKGROUND: Migratory disc herniations can mimic neoplasms clinically and on imaging. Far lateral lumbar disc herniations usually compress the exiting nerve root and can be challenging to distinguish from a nerve sheath tumor due to the proximity of the nerve and characteristics on magnetic resonance imaging (MRI). These lesions can occasionally present in the upper lumbar spine region at the L1-2 and L2-3 levels. OBSERVATIONS: The authors describe 2 extraforaminal lesions in the far lateral space at the L1-2 and L2-3 levels, respectively. On MRI, both lesions tracked along the corresponding exiting nerve roots with avid postcontrast rim enhancement and edema in the adjacent muscle tissue. Thus, they were initially concerning for peripheral nerve sheath tumors. One patient underwent fluorodeoxyglucose positron emission tomography-computed tomography (FDG PET-CT) screening and demonstrated moderate FDG uptake on PET-CT scan. In both cases, intraoperative and postoperative pathology revealed fibrocartilage disc fragments. LESSONS: Differential diagnosis for lumbar far lateral lesions that are peripherally enhancing on MRI should include migratory disc herniation, regardless of the level of the disc herniations. Accurate preoperative diagnosis can aid in decision making for management, surgical approach, and resection.

Multi-Parametric Radiomic Model to Predict 1p/19q Co-Deletion in Patients with IDH-1 Mutant Glioma: Added Value to the T2-FLAIR Mismatch Sign.

PURPOSE: The T2-FLAIR mismatch sign has shown promise in determining IDH mutant 1p/19q non-co-deleted gliomas with a high specificity and modest sensitivity. To develop a multi-parametric radiomic model using MRI to predict 1p/19q co-deletion status in patients with newly diagnosed IDH1 mutant glioma and to perform a comparative analysis to T2-FLAIR mismatch sign+. METHODS: In this retrospective study, patients with diagnosis of IDH1 mutant gliomas with known 1p/19q status who had preoperative MRI were included. T2-FLAIR mismatch was evaluated independently by two board-certified neuroradiologists. Texture features were extracted from glioma segmentation of FLAIR images. eXtremeGradient Boosting (XGboost) classifiers were used for model development. Leave-one-out-cross-validation (LOOCV) and external validation performances were reported for both the training and external validation sets. RESULTS: A total of 103 patients were included for model development and 18 patients for external testing validation. The diagnostic performance (sensitivity/specificity/accuracy) in the determination of the 1p/19q co-deletion status was 59%/83%/67% (training) and 62.5%/70.0%/66.3% (testing) for the T2-FLAIR mismatch sign. This was significantly improved (p = 0.04) using the radiomics model to 77.9%/82.8%/80.3% (training) and 87.5%/89.9%/88.8% (testing), respectively. The addition of radiomics as a computer-assisted tool resulted in significant (p = 0.02) improvement in the performance of the neuroradiologist with 13 additional corrected cases in comparison to just using the T2-FLAIR mismatch sign. CONCLUSION: The proposed radiomic model provides much needed sensitivity to the highly specific T2-FLAIR mismatch sign in the determination of the 1p/19q non-co-deletion status and improves the overall diagnostic performance of neuroradiologists when used as an assistive tool.

MR Angiography in Assessment of Collaterals in Patients with Acute Ischemic Stroke: A Comparative Analysis with Digital Subtraction Angiography.

Collateral status has prognostic and treatment implications in acute ischemic stroke (AIS) patients. Unlike CTA, grading collaterals on MRA is not well studied. We aimed to evaluate the accuracy of assessing collaterals on pretreatment MRA in AIS patients against DSA. AIS patients with anterior circulation proximal arterial occlusion with baseline MRA and subsequent endovascular treatment were included. MRA collaterals were evaluated by two neuroradiologists independently using the Tan and Maas scoring systems. DSA collaterals were evaluated by using the American Society of Interventional and Therapeutic Neuroradiology grading system and were used as the reference for comparative analysis against MRA. A total of 104 patients met the inclusion criteria (59 female, age (mean ± SD): 70.8 ± 18.1). The inter-rater agreement (k) for collateral scoring was 0.49, 95% CI 0.37-0.61 for the Tan score and 0.44, 95% CI 0.26-0.62 for the Maas score. Total number (%) of sufficient vs. insufficient collaterals based on DSA was 49 (47%) and 55 (53%) respectively. Using the Tan score, 45% of patients with sufficient collaterals and 64% with insufficient collaterals were correctly identified in comparison to DSA, resulting in a poor agreement (0.09, 95% CI 0.1-0.28). Using the Maas score, only 4% of patients with sufficient collaterals and 93% with insufficient collaterals were correctly identified against DSA, resulting in poor agreement (0.03, 95% CI 0.06-0.13). Pretreatment MRA in AIS patients has limited concordance with DSA when grading collaterals using the Tan and Maas scoring systems.

Imaging Biomarker Development for Lower Back Pain Using Machine Learning: How Image Analysis Can Help Back Pain.

State-of-the-art diagnosis of radiculopathy relies on "highly subjective" radiologist interpretation of magnetic resonance imaging of the lower back. Currently, the treatment of lumbar radiculopathy and associated lower back pain lacks coherence due to an absence of reliable, objective diagnostic biomarkers. Using emerging machine learning techniques, the subjectivity of interpretation may be replaced by the objectivity of automated analysis. However, training computer vision methods requires a curated database of imaging data containing anatomical delineations vetted by a team of human experts. In this chapter, we outline our efforts to develop such a database of curated imaging data alongside the required delineations. We detail the processes involved in data acquisition and subsequent annotation. Then we explain how the resulting database can be utilized to develop a machine learning-based objective imaging biomarker. Finally, we present an explanation of how we validate our machine learning-based anatomy delineation algorithms. Ultimately, we hope to allow validated machine learning models to be used to generate objective biomarkers from imaging data-for clinical use to diagnose lumbar radiculopathy and guide associated treatment plans.

Predicting Spinal Surgery Candidacy From Imaging Data Using Machine Learning.

BACKGROUND: The referral process for consultation with a spine surgeon remains inefficient, given a substantial proportion of referrals to spine surgeons are nonoperative. OBJECTIVE: To develop a machine-learning-based algorithm which accurately identifies patients as candidates for consultation with a spine surgeon, using only magnetic resonance imaging (MRI). METHODS: We trained a deep U-Net machine learning model to delineate spinal canals on axial slices of 100 normal lumbar MRI scans which were previously delineated by expert radiologists and neurosurgeons. We then tested the model against lumbar MRI scans for 140 patients who had undergone lumbar spine MRI at our institution (60 of whom ultimately underwent surgery, and 80 of whom did not). The model generated automated segmentations of the lumbar spinal canals and calculated a maximum degree of spinal stenosis for each patient, which served as our biomarker for surgical pathology warranting expert consultation. RESULTS: The machine learning model correctly predicted surgical candidacy (ie, whether patients ultimately underwent lumbar spinal decompression) with high accuracy (area under the curve = 0.88), using only imaging data from lumbar MRI scans. CONCLUSION: Automated interpretation of lumbar MRI scans was sufficient to correctly determine surgical candidacy in nearly 90% of cases. Given that a significant proportion of referrals placed for spine surgery evaluation fail to meet criteria for surgical intervention, our model could serve as a valuable tool for patient triage and thereby address some of the inefficiencies within the outpatient surgical referral process.

Eigenrank by committee: Von-Neumann entropy based data subset selection and failure prediction for deep learning based medical image segmentation.

Manual delineation of anatomy on existing images is the basis of developing deep learning algorithms for medical image segmentation. However, manual segmentation is tedious. It is also expensive because clinician effort is necessary to ensure correctness of delineation. Consequently most algorithm development is based on a tiny fraction of the vast amount of imaging data collected at a medical center. Thus, selection of a subset of images from hospital databases for manual delineation - so that algorithms trained on such data are accurate and tolerant to variation, becomes an important challenge. We address this challenge using a novel algorithm. The proposed algorithm named 'Eigenrank by Committee' (EBC) first computes the degree of disagreement between segmentations generated by each DL model in a committee. Then, it iteratively adds to the committee, a DL model trained on cases where the disagreement is maximal. The disagreement between segmentations is quantified by the maximum eigenvalue of a Dice coefficient disagreement matrix a measure closely related to the Von Neumann entropy. We use EBC for selecting data subsets for manual labeling from a larger database of spinal canal segmentations as well as intervertebral disk segmentations. U-Nets trained on these subsets are used to generate segmentations on the remaining data. Similar sized data subsets are also randomly sampled from the respective databases, and U-Nets are trained on these random subsets as well. We found that U-Nets trained using data subsets selected by EBC, generate segmentations with higher average Dice coefficients on the rest of the database than U-Nets trained using random sampling (p < 0.05 using t-tests comparing averages). Furthermore, U-Nets trained using data subsets selected by EBC generate segmentations with a distribution of Dice coefficients that demonstrate significantly (p < 0.05 using Bartlett's test) lower variance in comparison to U-Nets trained using random sampling for all datasets. We believe that this lower variance indicates that U-Nets trained with EBC are more robust than U-Nets trained with random sampling.

24/7/365 Neuroradiologist Coverage Improves Resident Perception of Educational Experience, Referring Physician Satisfaction, and Turnaround Time.

PURPOSE: To quantitatively and qualitatively assess the impact of attending neuroradiology coverage on radiology resident perceptions of the on-call experience, referring physician satisfaction, and final report turnaround times. MATERIALS AND METHODS: 24/7/365 attending neuroradiologist coverage began in October 2016 at our institution. In March 2017, an online survey of referring physicians, (emergency medicine, neurosurgery, and stroke neurology) and radiology residents was administered at a large academic medical center. Referring physicians were queried regarding their perceptions of patient care, report accuracy, timeliness, and availability of attending radiologists before and after the implementation of overnight neuroradiology coverage. Radiology residents were asked about their level of independence, workload, and education while on-call. Turnaround time (TAT) was measured over a 5-month period before and after the implementation of overnight neuroradiology coverage. RESULTS: A total of 28 of 64 referring physicians surveyed responded, for a response rate of 67%. Specifically, 19 of 23 second (junior resident on-call) and third year radiology residents (senior resident on-call) replied, 4 of 4 stroke neurology fellows replied, 8 of 21 neurosurgery residents, and 16 of 39 emergency medicine residents replied. Ninety-five percent of radiology residents stated they had adequate independence on call, 100% felt they have enough faculty support while on call, and 84% reported that overnight attending coverage has improved the educational value of their on-call experience. Residents who were present both before and after the implementation of TAT metrics thought their education, and independence had been positively affected. After overnight neuroradiology coverage, 85% of emergency physicians perceived improved accuracy of reports, 69% noted improved timeliness, and 77% found that attending radiologists were more accessible for consultation. The surveyed stroke neurology fellows and neurosurgery residents reported positive perception of the TAT, report quality, and availability of accessibility of attending radiologist. CONCLUSIONS: In concordance with prior results, overnight attending coverage significantly reduced turnaround time. As expected, referring physicians report increased satisfaction with overnight attending coverage, particularly with respect to patient care and report accuracy. In contrast to some prior studies, radiology residents reported both improved educational value of the on-call shifts and preserved independence. This may be due to the tasking the overnight neuroradiology attending with dual goals of optimized TAT, and trainee growth. Unique implementation including subspecialty trained attendings may facilitate radiology resident independence and educational experience with improved finalized report turnaround.

A Story in Black and White: Radiologic Evaluation in the Multidisciplinary Setting.

Strong engagement from expert radiologists is essential in ensuring the optimal function of a multidisciplinary group focused on the treatment of head and neck cancer. Active participation in multidisciplinary conference can be among the most rewarding roles for radiologists. Despite many benefits to radiologist involvement in multidisciplinary teams, there are obstacles and challenges that can prevent full participation. This article highlights the key issues that should be considered by radiologists and multidisciplinary team leaders when planning participation in a new or existing multidisciplinary group that focuses on the care of patients with head and neck cancer.

Spleen size in cirrhosis of different etiologies.

OBJECTIVES: The purpose of this study was to evaluate the impact of cirrhosis etiology on spleen size as measured by sonography and computed tomography (CT). METHODS: The spleen images of 139 patients with cirrhosis secondary to alcohol abuse, hepatitis C, or nonalcoholic steatohepatitis were reviewed retrospectively. The maximum diagonal spleen length on a single sonogram and maximum spleen diameter on axial, coronal, or sagittal CT, whichever was largest, was compared among the etiologic groups. RESULTS: In 127 patients who underwent sonography, the mean spleen size ± SD on sonography in the alcohol group (13.1 ± 2.5 cm) was significantly smaller than in the hepatitis C (15.0 ± 3.4 cm) and nonalcoholic steatohepatitis (15.2 ± 3.0 cm) groups (95% confidence intervals of the mean difference, 0.6 to 3.3 and 0.8 to 3.4 cm, respectively). In 87 patients who underwent CT, the mean spleen size on CT in the alcohol group (14.0 ± 2.7 cm) was smaller than in the hepatitis C (15.9 ± 3.4 cm) and nonalcoholic steatohepatitis (15.5 ± 3.6 cm) groups, but the difference was not statistically significant. The spleen sizes on both sonography and CT in 79 patients were strongly correlated (r = 0.88; P < .0001). CONCLUSIONS: Spleen size in patients with cirrhosis varies by the etiology of the disease. Therefore, to apply spleen size as a diagnostic or prognostic criterion in this context, it is important to recognize that cutoff values derived from spleen size in one etiologic group may not produce the same results when extrapolated to another etiologic group.