Octave Bioscience

Author Of 3 Presentations

Imaging Poster Presentation

P0552 - BrainGraph A Novel Visualization of MRI Data as a 3D Graph to Reveal Temporal Features of Disease Progression In Patients with Multiple Sclerosis (ID 1229)

Speakers
Presentation Number
P0552
Presentation Topic
Imaging

Abstract

Background

Novel visualization of neuroimaging data can lead to clinical insights and ultimately new imaging analysis capabilities. Graph models of magnetic resonance imaging (MRI) data can reveal the topology and temporal nature of multiple sclerosis disease progression, by exposing novel structural features of the brain through representation of data as interactive 3D projections. Existing standards and evolving approaches to neuroimaging can benefit from an integration of graph analytics and visualization.

Objectives

To develop a cloud-based workflow to translate DICOM imaging data files into a visual, interactive graph schema. The resulting application will enhance and support the current evaluation of disease features on conventional MRI and reveal the temporal features of lesion and disease progression in patients with multiple sclerosis.

Methods

3D voxels from DICOM data were modeled as a graph data structure on cloud infrastructure (Amazon). The graph is composed of nodes which represent voxels and the spatial relationships that exist between them. Nodes contain properties including a voxel’s x,y,z coordinates as well as features such as signal intensities across modalities. Nodes are projected on a 3D grid using their coordinates for placement. Relationships between voxels model spatial neighborhoods in x,y, and z dimensions and across time. For a given voxel, up to six other unique voxels are potentially designated as spatial neighbors, and another relationship across time.

Results

Visual graph representation of MRI data revealed temporal progression of all lesions simultaneously. Lesions can be visually classified as consolidating/merging, expanding, or splitting across time using an interactive slider. Using graph algorithms we established lesion nodes, separated lesion surfaces from internal components, and characterized lesion shapes, temporal changes, and volumetrics.

Conclusions

Interactive 3D graph representations of MRI graph data augment traditional visualization and analysis by providing connectedness and temporal resolution into the disease process. Graphs highlight the connectedness of MRI data, the communities that compose structural features and disease processes, and the temporal relationships revealed during MS disease progression.

Collapse
Imaging Poster Presentation

P0583 - High throughput lesion evaluation and quality control for incorporating quantitative imaging metrics into clinical practice (ID 1502)

Speakers
Presentation Number
P0583
Presentation Topic
Imaging

Abstract

Background

Automated multiple sclerosis lesion counts and volumes are poised to be salient clinical biomarkers of disease progression; however, algorithmic variability and low expert agreement prevents widespread adoption in clinical practice. Because every method has a non-negligible error rate, visual quality control (QC) is required before a clinical decision can be made. QC is a bottleneck to the use of automated lesion count and volume metrics in the clinic. A method is needed to 1) quickly evaluate experts and non-experts to understand and resolve disagreements, and 2) quickly QC the output of automated lesion segmentation methods.

Objectives

To evaluate the feasibility of a web application called braindr (Keshavan et al., 2019) for high-throughput QC of automated lesion segmentation by measuring the 1) intra-rater reliability, 2) the inter-rater reliability, and 3) to characterize the types of lesions that are disagreed upon.

Methods

3D T1 and FLAIR images from 32 subjects were registered, N4 bias field corrected, and z-scored. Subtraction images (Z_FLAIR-Z_T1) were thresholded at varying levels. A triplanar image of each resulting segmentation (called a potential lesion, PL) was generated, resulting in over 80,000 individual PL’s needing QC, which simulates a high-throughput scenario with a high error rate. Expert and non-expert raters were asked to pass or fail PLs based on the 2D triplanar image on the app. We measured variability between and within raters by calculating the intraclass correlation coefficients (ICC).

Results

1) Feasibility: 14,973 PLs were labelled by 5 raters. The raters were a neuroradiologist (MI), a general neurologist (BD), 2 experienced technicians (AK, KL), and 1 beginner (MB). 2) Intra-rater reliability (ICC(1,1)) : a) neuroradiologist: 0.97, b) beginner: 0.90, c) experienced techs: 0.87, 0.85, and d) neurologist: 0.84. 3) Inter-rater reliability for an average rating ICC(2,k) = 0.92, and individual ICC(2,1) = 0.74. 4) Disagreements occurred more frequently on PL’s in the brainstem, cerebellum, hippocampal, and basal ganglia.

Conclusions

We simultaneously evaluated raters, and QC’d lesions from an automated method using a quick, scalable, web application. This enables us to 1) improve expert agreement on lesion identification, 2) develop better quality education materials for experts and non-experts alike, 3) train new raters quickly, and 4) ensure the quality of the measurements at scale.

Collapse
Imaging Poster Presentation

P0590 - Improved detection of clinically relevant MRI findings in Multiple Sclerosis radiology reports using FDA-approved quantitative software (ID 1501)

Speakers
Presentation Number
P0590
Presentation Topic
Imaging

Abstract

Background

Quantitative metrics such as lesion count and brain volume can provide objective data of disease progression in Multiple Sclerosis (MS). However, implementing FDA-approved quantitative software in clinical practice requires significant effort and investment. It has not yet been established if quantitative software can consistently improve the detection of clinically relevant MRI findings in MS-specific radiology reports.

Objectives

To characterize clinically relevant findings in MS-specific radiology reports generated by a neuroradiologist after visual interpretation of images alone and with FDA-approved software.

Methods

26 patients with MS who had MRIs performed between 2013-2017 were retrospectively selected from an anonymized database. Each patient had 2 MRIs (average 1 year apart) consisting of 3D T1 and T2 FLAIR sequences. Images were processed using FDA-approved software (NeuroQuant and LesionQuant 3.0.1) to generate lesion count and brain volume data and a color-coded map that highlighted lesion changes between MRI timepoints.

A neuroradiologist visually compared MRIs in each patient and reported the number of new, enlarging, shrinking, and enhancing lesions, and provided an assessment of brain atrophy in a qualitative report (qual). To avoid recall bias, cases were randomized and re-anonymized, and one month later, the neuroradiologist used the post-processed data and images to generate a second quantitative report (quant). Interpretation time was recorded during both sessions. Two neuroimaging experts coded differences in the reports and verified lesion accuracy.

Results

Upon review of qual reports, a total of 44 new, 10 enlarging, and 5 shrinking T2 lesions and 3 enhancing lesions were reported, compared with 50 new, 15 enlarging, 8 shrinking, and 3 enhancing lesions on quant reports. Of the 13 cases that reported differences in lesion counts, one additional new lesion, on average, was detected in quant reports (SD= 2.4). Brain atrophy descriptions changed with the addition of quantitative metrics in 7 cases, where 5 cases were upgraded and 2 cases were downgraded in severity. No significant difference (p=.16, paired t-test) was found in interpretation time (qual 12.3 minutes; quant 11.4 minutes).

Conclusions

The use of FDA-approved quantitative software improved the detection of clinically relevant neuroimaging findings in MS patients, without adding time to image interpretation, suggesting its potential value in clinical practice.

Collapse