Octave Bioscience
Data Engineering

Author Of 1 Presentation

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

Presenter Of 1 Presentation

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