Semi-automatic Tool Research Articles

Effect of Construction Work Zone on Rear-End Conflicts by Vehicle Type under Heterogeneous Traffic Conditions

Road transportation is a critical mode of transportation because of its mobility characteristics. Road construction work zones (WZ) are widespread on roads because of increased travel demand. Thus, it is necessary to study traffic safety for WZs and regular sections. In this study, traffic safety is analyzed in terms of the conflict probability at selected roads with WZ and without work zone (WWZ) sections along the same road. Vehicular trajectory data for three traffic flow levels (free flow, near capacity, and congestion) were extracted using a newly developed machine learning–based semiautomated trajectory extractor tool. The derived trajectory data from both sections were used to identify the leader-follower vehicle pairs using MATLAB. Two surrogate safety measures were estimated to compute the rear-end conflicts: time-to-collision and deceleration rate to avoid a collision. Hence, the variation of the rear-end conflicts was further examined using the generalized extreme value theory. It is found that the conflict probability is more in the WWZ section than the WZ section, which may be attributed to the variation in speed and acceleration. It is also found that the conflict probability for the WWZ and WZ sections is reduced as the angle between the two vehicles increases. The study results should help highway authorities to implement suitable safety measures to reduce conflicts and crashes in the work zones.

Zyxin contributes to coupling between cell junctions and contractile actomyosin networks during apical constriction

One of the most common cell shape changes driving morphogenesis in diverse animals is the constriction of the apical cell surface. Apical constriction depends on contraction of an actomyosin network in the apical cell cortex, but such actomyosin networks have been shown to undergo continual, conveyor belt-like contractions before the shrinking of an apical surface begins. This finding suggests that apical constriction is not necessarily triggered by the contraction of actomyosin networks, but rather can be triggered by unidentified, temporally-regulated mechanical links between actomyosin and junctions. Here, we used C. elegans gastrulation as a model to seek genes that contribute to such dynamic linkage. We found that α-catenin and β-catenin initially failed to move centripetally with contracting cortical actomyosin networks, suggesting that linkage is regulated between intact cadherin-catenin complexes and actomyosin. We used proteomic and transcriptomic approaches to identify new players, including the candidate linkers AFD-1/afadin and ZYX-1/zyxin, as contributing to C. elegans gastrulation. We found that ZYX-1/zyxin is among a family of LIM domain proteins that have transcripts that become enriched in multiple cells just before they undergo apical constriction. We developed a semi-automated image analysis tool and used it to find that ZYX-1/zyxin contributes to cell-cell junctions' centripetal movement in concert with contracting actomyosin networks. These results identify several new genes that contribute to C. elegans gastrulation, and they identify zyxin as a key protein important for actomyosin networks to effectively pull cell-cell junctions inward during apical constriction. The transcriptional upregulation of ZYX-1/zyxin in specific cells in C. elegans points to one way that developmental patterning spatiotemporally regulates cell biological mechanisms in vivo. Because zyxin and related proteins contribute to membrane-cytoskeleton linkage in other systems, we anticipate that its roles in regulating apical constriction in this manner may be conserved.

Automatic measuring of finger joint space width on hand radiograph using deep learning and conventional computer vision methods

Hand osteoarthritis (OA) severity can be assessed visually through radiographs using semi-quantitative grading systems. However, these grading systems are subjective and cannot distinguish minor differences. Joint space width (JSW) compensates for these disadvantages, as it quantifies the severity of OA by accurately measuring the distances between joint bones. Current methods used to assess JSW require users’ interaction to identify the joints and delineate the initial joint boundary, which is time-consuming. To automate this process and offer a robust measurement for JSW, we proposed two novel methods to measure JSW: (1) The segmentation-based (SEG) method, which uses traditional computer vision techniques to calculate JSW; (2) The regression-based (REG) method, which is a deep learning approach employing a modified VGG-19 network to predict JSW. On a dataset with 3591 hand radiographs, 10,845 DIP joints were cut as ROI and served as input to the SEG and REG methods. The bone masks of the ROI images generated by a U-Net model were sent as input in addition to the ROIs. The ground truth of JSW was labeled by a trained research assistant using a semi-automatic tool. Compared with the ground truth, the REG method achieved a correlation coefficient (r) of 0.88 and a mean square error (MSE) of 0.02 mm on the testing set; the SEG method achieved a correlation coefficient of 0.42 and an MSE of 0.15 mm. Results show the REG method has promising performance in JSW measurement and, in general, Deep Learning approaches can facilitate the automatic quantification of distance features in medical images.

Examining craniofacial variation among crispant and mutant zebrafish models of human skeletal diseases.

Genetic diseases affecting the skeletal system present with a wide range of symptoms that make diagnosis and treatment difficult. Genome-wide association and sequencing studies have identified genes linked to human skeletal diseases. Gene editing of zebrafish models allows researchers to further examine the link between genotype and phenotype, with the long-term goal of improving diagnosis and treatment. While current automated tools enable rapid and in-depth phenotyping of the axial skeleton, characterizing the effects of mutations on the craniofacial skeleton has been more challenging. The objective of this study was to evaluate a semi-automated screening tool can be used to quantify craniofacial variations in zebrafish models using four genes that have been associated with human skeletal diseases (meox1, plod2, sost, and wnt16) as test cases. We used traditional landmarks to ground truth our dataset and pseudolandmarks to quantify variation across the 3D cranial skeleton between the groups (somatic crispant, germline mutant, and control fish). The proposed pipeline identified variation between the crispant or mutant fish and control fish for four genes. Variation in phenotypes parallel human craniofacial symptoms for two of the four genes tested. This study demonstrates the potential as well as the limitations of our pipeline as a screening tool to examine multi-dimensional phenotypes associated with the zebrafish craniofacial skeleton.

Gaia-ESO survey: Massive stars in the Carina Nebula

Context. The Carina Nebula is one of the major massive star-forming regions in the Galaxy. Its relatively nearby distance (2.35 kpc) makes it an ideal laboratory for the study of massive star formation, structure, and evolution, both for individual stars and stellar systems. Thanks to the high-quality spectra provided by the Gaia-ESO survey and the LiLiMaRlin library, as well as Gaia EDR3 astrometry, a detailed and homogeneous spectroscopic characterization of its massive stellar content can be carried out. Aims. Our main objective is to spectroscopically characterize all massive members of the Carina Nebula in the Gaia-ESO survey footprint to provide an updated census of massive stars in the region and an updated estimate of the binary fraction of O stars. Methods. We performed accurate spectral classification using an interactive code that compares spectra with spectral libraries of OB standard stars, as well as line-based classic methods. We calculated membership using our own algorithm based on Gaia EDR3 astrometry. To check the correlation between the spectroscopic n-qualifier and the rotational velocity, we used a semi-automated tool for the line-broadening characterization of OB stars based on a combined Fourier transform and goodness-of-fit methodology. Results. The Gaia-ESO survey sample of massive OB stars in the Carina Nebula consists of 234 stars. The addition of brighter sources from the Galactic O-Star Spectroscopic Survey and additional sources from the literature allows us to create the most complete census of massive OB stars so far in the region. It contains a total of 316 stars, with 18 of them in the background and 4 in the foreground. Of the 294 stellar systems in Car OB1, 74 are of O type, 214 are of nonsupergiant B type, and 6 are of WR or nonO supergiant (II to Ia) spectral class. We identify 20 spectroscopic binary systems with an O-star primary, of which 6 are reported for the first time, and another 18 with a B-star primary, of which 13 are new detections. The average observed double-lined binary fraction of O-type stars in the surveyed region is 0.35, which represents a lower limit. We find a good correlation between the spectroscopic n-qualifier and the projected rotational velocity of the stars. The fraction of candidate runaways among the stars with and without the n-qualifier is 4.4% and 2.4%, respectively, although nonresolved double-lined binaries could be contaminating the sample of fast rotators.

Imaging-calculated splenic volume is associated with response in melanoma patients treated with immunotherapy.

Background: Predicting the roughly 50% of melanoma patients that will respond to immunotherapy is challenging. We tested if splenic volume could be a predictive biomarker. Methods: Splenic volume was measured by asemiautomated commercial software tool in pre- and post-treatment PET/CT, CTor MRI in 50 melanoma patients treated with immune checkpoint inhibitors. Results: Subjects with smaller spleens had better progression-free survival (mediannot achieved after 30.6months of follow-up vs median 11.2months;p=0.0213) than their counterparts. A cut-off of <244cm3 yielded a sensitivity of 83% and specificity of 54% to identify responders. Conclusion: Measuring splenic volume on imaging scans is feasible. Smaller pretreatment spleen volume is associated with better responses to immune checkpoint inhibitors.

Integrated diffusion image operator (iDIO): A pipeline for automated configuration and processing of diffusion MRI data.

The preprocessing of diffusion magnetic resonance imaging (dMRI) data involve numerous steps, including the corrections for head motion, susceptibility distortion, low signal-to-noise ratio, and signal drifting. Researchers or clinical practitioners often need to configure different preprocessing steps depending on disparate image acquisition schemes, which increases the technical threshold for dMRI analysis for nonexpert users. This could cause disparities in data processing approaches and thus hinder the comparability between studies. To make the dMRI data processing steps transparent and adapt to various dMRI acquisition schemes for researchers, we propose a semi-automated pipeline tool for dMRI named integrated diffusion image operator or iDIO. This pipeline integrates features from a wide range of advanced dMRI software tools and targets at providing a one-click solution for dMRI data analysis, via adaptive configuration for a set of suggested processing steps based on the image header of the input data. Additionally, the pipeline provides options for post-processing, such as estimation of diffusion tensor metrics and whole-brain tractography-based connectomes reconstruction using common brain atlases. The iDIO pipeline also outputs an easy-to-interpret quality control report to facilitate users to assess the data quality. To keep the transparency of data processing, the execution log and all the intermediate images produced in the iDIO's workflow are accessible. The goal of iDIO is to reduce the barriers for clinical or nonspecialist users to adopt the state-of-art dMRI processing steps.

Systematic dosimetric evaluation of risk of osteoradionecrosis (DERO): First results of dose reporting for preventing teeth osteoradionecrosis after head and neck irradiation

PurposeOsteoRadioNecrosis (ORN) is a late complication of radiation for head and neck cancer. Predicting ORN is a major challenge. We developed DERO (Dosimetric Evaluation of Risk of ORN), a semi-automatic tool which reports doses delivered to tooth-bearing sectors, to guide post-therapeutic dental care. We present the method and the first results of a 125-patient prospective cohort. Material and methodsDosimetric data of patients treated with IMRT for head and neck cancer were prospectively segmented to the DERO algorithm. Four arches corresponding to 8-tooth sectors were semi-automatically generated. Thirty-two cylindrical Regions Of Interest (ROI) corresponding to each tooth and surrounding periodontium were created by linear interpolation. Mean doses (Dmean) of ROI were extracted and included in a database, along with data about primary tumor site, laterality and dose values from organs at risk. Dmean to tooth sectors were computed for molar sectors, (teeth X5 to X8) and anterior sectors (teeth X1 to X4). An individual dose map was generated and delivered to patients and dentists. ResultsDosimetric data from 125 patients treated with Tomotherapy® were prospectively collected and analyzed: 9 parotid tumors (PA), 41 Sub-Hyoid tumors (larynx, hypopharynx) (SH), 43 Oropharynx tumors (OR), 32 Oral Cavity tumors (OC). Irradiation was unilateral for 100% of PA tumors (9), 12% of OR tumors (5) and 47% of OC tumors (15). For unilateral cervical irradiation, Dmean in ipsilateral molar sectors was 54Gy for OC tumors, 45Gy for OR tumors, 20Gy for PA tumors. For Oral Cavity bilateral irradiation, Dmean was high in all tooth sectors, 49 to 55Gy. For SH tumors, Dmean in molar sectors was 27Gy. A dose gradient of 10 to 20Gy was observed between molar and anterior sectors whether radiation was uni or bilateral. ConclusionMandibular molar sectors of Oropharynx and Oral Cavity tumors were exposed to high Dmean of 40 to 50Gy. On the other hand, tooth sectors received lower doses for SH radiation. The DERO tool guide post-radiation dental care with a personalized dosimetric cartography to patient. With data update and patient follow-up, we will be able to determine ORN risk after head and neck radiation.

The architectural characteristics of the hamstring muscles do not differ between male and female elite-level rugby union players.

Purpose: To determine whether differences exist in the architectural characteristics of the hamstring muscles of elite-level male and female rugby union players. Methods: Forty elite-level rugby union players (male n = 20, female n = 20) participated in this cross-sectional study. A sonographer acquired static ultrasound images using a 92mm linear transducer to quantify (via a semi-automated tracing software tool) the architectural characteristics (muscle length, fascicle length, pennation angle, and muscle thickness) of the biceps femoris long head and semimembranosus muscles of participants' left limb. Muscle length and muscle thickness of the biceps femoris short head and semitendinosus muscles of participants' left limb were also quantified. Bonferroni adjusted independent samples t-tests were performed to evaluate whether differences exist in the architectural characteristics of the hamstring muscles of elite-level male and female rugby union players. Results: There were no significant differences in fascicle length or pennation angle of the hamstring muscles of elite-level male and female rugby union players. Some significant differences in muscle thickness (biceps femoris short head, and semimembranosus) and muscle length (biceps femoris short head, biceps femoris long head, semitendinosus, and semimembranosus) were observed; in all cases the male players had thicker and longer muscles. Conclusion: At a group level, hamstring muscle fascicle length and pennation angle are unlikely to be a sex-specific intrinsic risk factor for Hamstring strain injuries.

Quality issues in co-authorship data of a national scientific community

AbstractA stream of research on co-authorship, used as a proxy of scholars’ collaborative behavior, focuses on members of a given scientific community defined at discipline and/or national basis for which co-authorship data have to be retrieved. Recent literature pointed out that international digital libraries provide partial coverage of the entire scholar scientific production as well as under-coverage of the scholars in the community. Bias in retrieving co-authorship data of the community of interest can affect network construction and network measures in several ways, providing a partial picture of the real collaboration in writing papers among scholars. In this contribution, we collected bibliographic records of Italian academic statisticians from an online platform (IRIS) available at most universities. Even if it guarantees a high coverage rate of our population and its scientific production, it is necessary to deal with some data quality issues. Thus, a web scraping procedure based on a semi-automatic tool to retrieve publication metadata, as well as data management tools to detect duplicate records and to reconcile authors, is proposed. As a result of our procedure, it emerged that collaboration is an active and increasing practice for Italian academic statisticians with some differences according to the gender, the academic ranking, and the university location of scholars. The heuristic procedure to accomplish data quality issues in the IRIS platform can represent a working case report to adapt to other bibliographic archives with similar characteristics.

Validation of a semi-automatic method to measure total liver volumes in polycystic liver disease on computed tomography — high speed and accuracy

ObjectivesPolycystic liver disease (PLD) is characterized by growth of hepatic cysts, causing hepatomegaly. Disease severity is determined using total liver volume (TLV), which can be measured from computed tomography (CT). The gold standard is manual segmentation which is time-consuming and requires expert knowledge of the anatomy. This study aims to validate the commercially available semi-automatic MMWP (Multimodality Workplace) Volume tool for CT scans of PLD patients.MethodsWe included adult patients with one (n = 60) or two (n = 46) abdominal CT scans. Semi-automatic contouring was compared with manual segmentation, using comparison of observed volumes (cross-sectional) and growth (longitudinal), correlation coefficients (CC), and Bland-Altman analyses with bias and precision, defined as the mean difference and SD from this difference. Inter- and intra-reader variability were assessed using coefficients of variation (CV) and we assessed the time to perform both procedures.ResultsMedian TLV was 5292.2 mL (IQR 3141.4–7862.2 mL) at baseline. Cross-sectional analysis showed high correlation and low bias and precision between both methods (CC 0.998, bias 1.62%, precision 2.75%). Absolute volumes were slightly higher for semi-automatic segmentation (manual 5292.2 (3141.4–7862.2) versus semi-automatic 5432.8 (3071.9–7960.2) mL, difference 2.7%, p < 0.001). Longitudinal analysis demonstrated that semi-automatic segmentation accurately measures liver growth (CC 0.908, bias 0.23%, precision 4.04%). Inter- and intra-reader variability were small (2.19% and 0.66%) and comparable to manual segmentation (1.21% and 0.63%) (p = 0.26 and p = 0.37). Semi-automatic segmentation was faster than manual tracing (19 min versus 50 min, p = 0.009).ConclusionsSemi-automatic liver segmentation is a fast and accurate method to determine TLV and liver growth in PLD patients.Key Points• Semi-automatic liver segmentation using the commercially available MMWP volume tool accurately determines total liver volume as well as liver growth over time in polycystic liver disease patients.• This method is considerably faster than manual segmentation through the use of Hounsfield unit settings.• We used a real-life CT set for the validation and showed that the semi-automatic tool measures accurately regardless of contrast used for the CT scan or not, presence of polycystic kidneys, liver volume, and previous invasive treatment for polycystic liver disease.

Utility of Fully Automated Body Composition Measures on Pretreatment Abdominal CT for Predicting Survival in Patients With Colorectal Cancer.

BACKGROUND. CT examinations contain opportunistic body composition data with potential prognostic utility. Previous studies have primarily used manual or semiautomated tools to evaluate body composition in patients with colorectal cancer (CRC). OBJECTIVE. The purpose of this article is to assess the utility of fully automated body composition measures derived from pretreatment CT examinations in predicting survival in patients with CRC. METHODS. This retrospective study included 1766 patients (mean age, 63.7 ± 14.4 [SD] years; 862 men, 904 women) diagnosed with CRC between January 2001 and September 2020 who underwent pretreatment abdominal CT. A panel of fully automated artificial intelligence-based algorithms was applied to portal venous phase images to quantify skeletal muscle attenuation at the L3 lumbar level, visceral adipose tissue (VAT) area and subcutaneous adipose tissue (SAT) area at L3, and abdominal aorta Agatston score (aortic calcium). The electronic health record was reviewed to identify patients who died of any cause (n = 848). ROC analyses and logistic regression analyses were used to identify predictors of survival, with attention to highest- and lowest-risk quartiles. RESULTS. Patients who died, compared with patients who survived, had lower median muscle attenuation (19.2 vs 26.2 HU, p < .001), SAT area (168.4 cm2 vs 197.6 cm2, p < .001), and aortic calcium (620 vs 182, p < .001). Measures with highest 5-year AUCs for predicting survival in patients without (n = 1303) and with (n = 463) metastatic disease were muscle attenuation (0.666 and 0.701, respectively) and aortic calcium (0.677 and 0.689, respectively). A combination of muscle attenuation, SAT area, and aortic calcium yielded 5-year AUCs of 0.758 and 0.732 in patients without and with metastases, respectively. Risk of death was increased (p < .05) in patients in the lowest quartile for muscle attenuation (hazard ratio [HR] = 1.55) and SAT area (HR = 1.81) and in the highest quartile for aortic calcium (HR = 1.37) and decreased (p < .05) in patients in the highest quartile for VAT area (HR = 0.79) and SAT area (HR = 0.76). In 423 patients with available BMI, BMI did not significantly predict death (p = .75). CONCLUSION. Fully automated CT-based body composition measures including muscle attenuation, SAT area, and aortic calcium predict survival in patients with CRC. CLINICAL IMPACT. Routine pretreatment body composition evaluation could improve initial risk stratification of patients with CRC.

A natural language interface for automatic generation of data flow diagram using web extraction techniques

To model the data and functions in various computer science applications, the researcher uses a Data Flow Diagram (DFD). DFD has been constructed using [open-source software tools that provide users with different shapes and environments. However, the existing approaches require substantial human effort, the validity of the generated output is still a loophole, and they have never gained traction in practice. Our research objective is to develop a semi-automated tool for drawing complex Data Flow Diagrams in the shortest time according to the specified features of the intended system. We developed a Natural Language Interface (NLI) that allows the user to compose a query and identify the system functionality and constraints for the composition of DFD. Natural Language Processing (NLP) techniques are applied to scrapped data to extract the keywords and develop a data repository. Also, we developed rule-based algorithms to map user queries onto respective token shapes to draw the required functionality into appropriate levels of DFD. For verification, output DFDs were converted into conceptual digraphs using adjacency and permutation matrices to evaluate isomorphism. The empirical results reflect that the DFDs generated by the system are correct, complete, and significant.

Analysis of cerebral glucose metabolism following experimental subarachnoid hemorrhage over 7 days

Little is known about changes in brain metabolism following SAH, possibly leading towards secondary brain damage. Despite sustained progress in the last decade, analysis of in vivo acquired data still remains challenging. The present interdisciplinary study uses a semi-automated data analysis tool analyzing imaging data independently from the administrated radiotracer. The uptake of 2-[18F]Fluoro-2-deoxy-glucose ([18F]FDG) was evaluated in different brain regions in 14 male Sprague–Dawley rats, randomized into two groups: (1) SAH induced by the endovascular filament model and (2) sham operated controls. Serial [18F]FDG-PET measurements were carried out. Quantitative image analysis was performed by uptake ratio using a self-developed MRI-template based data analysis tool. SAH animals showed significantly higher [18F]FDG accumulation in gray matter, neocortex and olfactory system as compared to animals of the sham group, while white matter and basal forebrain region showed significant reduced tracer accumulation in SAH animals. All significant metabolic changes were visualized from 3 h, over 24 h (day 1), day 4 and day 7 following SAH/sham operation. This [18F]FDG-PET study provides important insights into glucose metabolism alterations following SAH—for the first time in different brain regions and up to day 7 during course of disease.

SegPC-2021: A challenge &amp; dataset on segmentation of Multiple Myeloma plasma cells from microscopic images

Multiple Myeloma (MM) is an emerging ailment of global concern. Its diagnosis at the early stages is critical for recovery. Therefore, efforts are underway to produce digital pathology tools with human-level intelligence that are efficient, scalable, accessible, and cost-effective. Following the trend, a medical imaging challenge on "Segmentation of Multiple Myeloma Plasma Cells in Microscopic Images (SegPC-2021)" was organized at the IEEE International Symposium on Biomedical Imaging (ISBI), 2021, France. The challenge addressed the problem of cell segmentation in microscopic images captured from the slides prepared from the bone marrow aspirate of patients diagnosed with Multiple Myeloma. The challenge released a total of 775 images with 690 and 85 images of sizes 2040×1536 and 1920×2560 pixels, respectively, captured from two different (microscope and camera) setups. The participants had to segment the plasma cells with a separate label on each cell's nucleus and cytoplasm. This problem comprises many challenges, including a reduced color contrast between the cytoplasm and the background, and the clustering of cells with a feeble boundary separation of individual cells. To our knowledge, the SegPC-2021 challenge dataset is the largest publicly available annotated data on plasma cell segmentation in MM so far. The challenge targets a semi-automated tool to ensure the supervision of medical experts. It was conducted for a span of five months, from November 2020 to April 2021. Initially, the data was shared with 696 people from 52 teams, of which 41 teams submitted the results of their models on the evaluation portal in the validation phase. Similarly, 20 teams qualified for the last round, of which 16 teams submitted the results in the final test phase. All the top-5 teams employed DL-based approaches, and the best mIoU obtained on the final test set of 277 microscopic images was 0.9389. All these five models have been analyzed and discussed in detail. This challenge task is a step towards the target of creating an automated MM diagnostic tool.

2358. Dementia and Cognitive Concerns are Risk Factors for Mortality in People with Human Immunodeficiency Virus and COVID-19

Abstract Background Despite higher prevalence of cognitive disorders in people with human immunodeficiency virus (PWH) and dementia being a risk factor for COVID-19 mortality, the association between dementia and adverse outcomes in PWH with COVID-19 has not been well established. Methods This was a matched case-control study (1:10) of patients with and without HIV at an academic institution with documented SARS-CoV-2 polymerase chain reaction (PCR) positivity from March 2020-March 2021. Data were extracted from the electronic health record data registry. PWH were matched to people without HIV (PWoH) by age, sex, race, and zip code. The primary exposures were dementia (identified using International Classification of Diseases, Tenth Revision codes) and cognitive concerns, defined as documentation of possible cognitive impairment up to 12 months prior to COVID-19 diagnosis and ascertained using a semi-automated natural language processing annotation tool. VACS 2.0 Index (including age, sex, body mass index, CD4+ T-cell count and HIV-1 RNA) was calculated. Logistic regression models assessed the effect of dementia and cognitive concerns on the odds of death (OR [95% confidence interval]), adjusted for VACS 2.0 Index. Results Sixty-four (0.45%) PWH were identified among 14129 patients with COVID-19 and were matched to 463 PWoH. Among PWH, 59% were virally suppressed, and 14% had CD4&amp;lt; 200 cells/μL. Compared to 463 matched PWoH, PWH had higher prevalence of dementia (16% vs. 6%, p=0.01) and cognitive concerns (22% vs. 16%, p=0.04). Death was more frequent in PWH (17% vs. 6%, p&amp;lt; 0.01) and at younger ages (58 vs. 66 years, p=0.03). Cognitive concerns (2.5 [1.1–5.9], p=0.03) and dementia (3.4 [1.3–8.1], p=0.01) were significantly associated with increased adjusted odds of death in the overall group. Among PWH, cognitive concerns (7.2 [1.1–48], p=0.04) and dementia (6.0 [0.8–43.8], p=0.08) remained associated with mortality. Conclusion Dementia and cognitive concerns were associated with mortality among PWH with COVID-19. The magnitude of the effect of cognitive impairment on COVID-19 outcomes may be greater in HIV, and additional studies with larger cohorts will help to assess this association further. Assessment of cognitive status is an important component to care for aging PWH in the COVID-19 era. Disclosures All Authors: No reported disclosures.

An Artificial Intelligence Tool for Clinical Decision Support and Protocol Selection for Brain MRI.

Protocolling, the process of determining the most appropriate acquisition parameters for an imaging study, is time-consuming and produces variable results depending on the performing physician. The purpose of this study was to assess the potential of an artificial intelligence-based semiautomated tool in reducing the workload and decreasing unwarranted variation in the protocolling process. We collected 19,721 MR imaging brain examinations at a large academic medical center. Criterion standard labels were created using physician consensus. A model based on the Long Short-Term Memory network was trained to predict the most appropriate protocol for any imaging request. The model was modified into a clinical decision support tool in which high-confidence predictions, determined by the values the model assigns to each possible choice, produced the best protocol automatically and low confidence predictions provided a shortened list of protocol choices for review. The model achieved 90.5% accuracy in predicting the criterion standard labels and demonstrated higher agreement than the original protocol assignments, which achieved 85.9% accuracy (κ = 0.84 versus 0.72, P value < .001). As a clinical decision support tool, the model automatically assigned 70% of protocols with 97.3% accuracy and, for the remaining 30% of examinations, achieved 94.7% accuracy when providing the top 2 protocols. Our model achieved high accuracy on a standard based on physician consensus. It showed promise as a clinical decision support tool to reduce the workload by automating the protocolling of a sizeable portion of examinations while maintaining high accuracy for the remaining examinations.

Left ventricular non-compaction in paediatrics: a novel semi-automated imaging technique bridging imaging findings and clinical outcomes.

We set out to design a reliable, semi-automated, and quantitative imaging tool using cardiac magnetic resonance (CMR) imaging that captures LV trabeculations in relation to the morphologic endocardial and epicardial surface, or perimeter-derived ratios, and assess its diagnostic and prognostic utility. We queried our institutional database between January 2008 and December 2018. Non-compacted (NC)-to-compacted (C) (NC/C) myocardium ratios were calculated and our tool was used to calculate fractal dimension (FD), total mass ratio (TMR), and composite surface ratios (SRcomp). NC/C, FD, TMR, and SRcomp were assessed in relation to LVNC diagnosis and outcomes. Univariate hazard ratios with cut-offs were performed using clinically significant variables to find 'at-risk' patients and imaging parameters were compared in 'at-risk' patients missed by Petersen Index (PI). Ninety-six patients were included. The average time to complete the semi-automated measurements was 3.90 min (SEM: 0.06). TMR, SRcomp, and NC/C were negatively correlated with LV ejection fraction (LVEF) and positively correlated with indexed LV end-systolic volumes (iLVESVs), with TMR showing the strongest correlation with LVEF (-0.287; P = 0.005) and SRcomp with iLVESV (0.260; P = 0.011). We found 29 'at-risk' patients who were classified as non-LVNC by PI and hence, were missed. When compared with non-LVNC and 'low-risk' patients, only SRcomp differentiated between both groups (1.91 SEM 0.03 vs. 1.80 SEM 0.03; P = 0.019). This method of semi-automatic calculation of SRcomp captured changes in at-risk patients missed by standard methods, was strongly correlated with LVEF and LV systolic volumes and may better capture outcome events.

Clinical validation of a semi-automated segmentation algorithm for target volume definition on planning CT and CBCT in stereotactic body radiotherapy (SBRT) for peripheral lung lesions.

Stereotactic body radiotherapy (SBRT) is an ablative method for lung malignancies. Here, the definition of the gross target volume (GTV) is subject to interobserver variation. In this study, we aimed to evaluate the interobserver variability during SBRT and its dosimetric impact, as well as to introduce a semi-automated delineation tool for both planning computer tomography (P-CT) and cone beam CT (CBCT) to help to standardise GTV delineation and adaptive volume-change registration. The interobserver variation of GTV manual contours from five physicians was analysed in 15 patients after lung SBRT on free breathing (FB) P-CT (n=15) and CBCT (n=90) before and after each fraction. The dosimetric impact from interobserver variations of GTV based on the original treatment plan was analysed. Next, the accuracy of an in-house easy-to-use semi-automated-segmentation algorithm for pulmonary lesions was compared with gold standard contours in FB P-CT and CBCT, as well as 4D P-CT of additional 10 patients. The interobserver variability in manual contours resulted in violations of dose coverage of the planning target volume (PTV), which, in turn, resulted in compromised tumour control probability in contours from four physicians. The validation of the semi-automated delineation algorithm using thorax phantom led to a highly reliable accuracy in defining GTVs. Comparing the unsupervised auto-contours with the gold standard delineation revealed high equal high concordance for FB P-CT, 4D P-CT and CBCT, with a DSC of 0.83, 0.76 and 0.8, respectively. The supervised use of the semi-automated delineation tool improved its accuracy, with DSCs of 0.86, 0.86 and 0.8 for FB P-CT, 4D P-CT and CBCT, respectively. The use of the algorithm was associated with a significantly shorter working time. The semi-automated delineation tool can accurately register volume changes in CBCTs. The segmentation algorithm provides a reliable, standardised and time-saving alternative for manual delineation in lung SBRT in P-CT and CBCT.

SURG-29. CAN NEOADJUVANT CHEMOTHERAPY INCREASE EXTENT OF RESECTION IN DIFFUSE LOWER-GRADE GLIOMA?

Abstract INTRODUCTION Maximal safe surgical resection remains front-line treatment for diffuse lower-grade gliomas (DLGGs). Greater extent of resection (EOR) can delay transformation, control seizures, and improve survival. EOR is limited by the infiltrative nature of DLGGs and eloquent brain location preponderance. We investigated the role of neoadjuvant chemotherapy in tumour volume reduction (TVR) for cases in which a meaningful EOR was deemed unachievable. METHODS Retrospective review (2000-2020) of patients in a large tertiary UK brain tumor centre who serendipitously underwent management that did or could mimic a neoadjuvant chemotherapy pathway. Inclusion criteria: &amp;gt;18 years at diagnosis; histologically-proven WHO grade 2 supratentorial glioma; received chemotherapy alone after biopsy then +/- debulking. Tumour volume delta +/- EOR were calculated on serial MRI T2/FLAIR sequences using a semi-automated quantitative analysis tool (Smartbrush, BrainLab® AG). RESULTS Group 1 (neoadjuvant chemotherapy and then surgery, n=4): debulking was considered unachievable initially but then possible post-chemotherapy. Median TVR post-chemotherapy was 16.90% (range 0.45–64.90%). Mean EOR was 68.67% (33.72–100%). Median overall survival (OS) and progression free survival (PFS) were 85 (18–154) and 62 (13–153) months, respectively. Group 2 (biopsy followed by chemotherapy alone, n=7): debulking was considered unachievable initially. Median TVR post-chemotherapy was 25.68% (-294.95–46.02%, one patient progressed during chemotherapy). Median OS and PFS were 92 (6–135) and 27 (3–80) months, respectively. On re-review, and based on Group 1 results, some Group 2 patients may have been able to undergo debulking with meaningful EOR post-chemotherapy. CONCLUSIONS Chemotherapy can have a significant impact on reducing tumour volumes, such that cases initially deemed unsuitable for debulking may be converted into those in which a meaningful EOR can be achieved. Larger, multicentre, retrospective studies, and prospective trials are needed to determine the role of chemotherapy as a neoadjuvant tool in the management of DLGGs.