26
© Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries Lesion Activity Assessment Hui Zhang, Guangchen Ruan, Hongwei Shen, Michael Boyles, Huian Li, Masatoshi Ando Hui Zhang [email protected] XSEDE'13 San Diego July 24 th , 2013

© Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Embed Size (px)

Citation preview

Page 1: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

© Trustees of Indiana UniversityReleased under Creative Commons 3.0 unported license; license terms on last slide.

XSEDE-enabled High-throughput Caries Lesion Activity Assessment

Hui Zhang, Guangchen Ruan, Hongwei Shen, Michael Boyles, Huian Li, Masatoshi Ando

Hui [email protected]

XSEDE'13 San DiegoJuly 24th , 2013

Page 2: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Outline

• Background– What is caries lesion activity– Scientific goal and computing objective

• Dataset and Methods– Computing task implemented in a serial means– How Map-Reduce framework can be applied

• Assessment Examples– Visualization and analysis – Qualitative and quantitative lesion activity

assessment

• Conclusion and Future Work

Page 3: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Introduction

• Dental caries management project in IUSD (2010 ~)– Scientific goal: reduce, or reverse the prevalence

of dental caries lesion active → inactive → reversed • Active lesion is a caries lesion that exhibits evidence

of progression for a specific period of time» losing mineral content (or, demineralization)

• Inactive/arrested lesion is a caries lesion that exhibits no evidence of progression for a specific period of time

• Reversed (with treatments)» gaining mineral content (or, remineralization )

Page 4: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Introduction

• Lesion activity assessement (arrested or active) is important

– essential and critical in dental studies– critical impact on dental treatment decision-

making– incorrect determination can easily result in

wrong treatment

Page 5: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Introduction

• But …….Today in dental clinical practice visual and tactile

inspections are commonly used :– subjective– dependent on observer's experience to be accurate– results often in-consistent

» tracking» temporal comparison

Visual Assessment

Tactile Sensation

Page 6: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Introduction

• (Dental) Computing objective– Bring computers and computing technologies to

dentistry research» dental imaging technology

(µ-CT imaging→ cross-sectional dental scans)» image segmentation

(cross-sectional scans→ ROIs)» visualization and analysis

(lesion activity assessment → 3D-time series analysis)

– Design methods not only for "marking" on dental scans, but also quantifying the volumetric information in the assessment

– Use HPC and parallel computing to scale to larger datasets

Page 7: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods

• The study reported195 ground/polished 3x3x2mm blocks prepared from extracted human teeth collected from Indiana dental practitioners (approved by IU IRB#0306-64)

a: Dimension b: Region of interest (ROI)

Schematic diagrams showing specimen dimension (a), and region of interest (b).

Page 8: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods

• Longitudinal dental experiment• uses 5-phase dem./rem. model • healthy1→dem2 →dem3→dem4 →rem5

• temporal evaluation– U-CTs– specimen/phase

Page 9: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods

• µ-CT Dental Scans– ~1000 scans per specimen per time point– each u-CT scan

• 16-bit gray-scale image• 1548×1120 resolution • ~1.65 MB size• lesion on u-CT scan shows observable gray-scale difference

Page 10: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods• 3D-Time Series Analysis Workflow (to quantify and

compare volumetric lesion information over time)– Pre-analysis training

• threshold, pivot values (based on histograms)

– Region-of-interest (ROI) segmentation• blob detection, morphological operation

– 3D construction• stacking ROIs, generating isosurface and

geometry

– Visual analysis (on volumetric models)• temporal comparison

– How lesion evolves on same specimen

• cross-conditional comparison– How lesion evolves with different treatments

Page 11: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods

• The Serial Implementation Model – A small collection of representative dental scans

• threshold, valley grayscales, pivot values

Page 12: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods

• The Serial Implementation Model – A small collection of representative dental scans

• threshold, pivot values– Segment ROIs on all scans (with established parameters)

• binary image conversion• apply morphological operations (erosion and dilation)

to remove false ROI candidates• blob detection → ROI boundary• processing images to keep only relevant pixels

Page 13: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods

• The Serial Implementation Model – Select representative dental scans

• Threshold, pivot values– Segment ROIs on all scans

• binary image conversion• apply morphological operations (erosion and dilation)

to remove false ROI candidates• blob detection → ROI boundary• processing images to keep only relevant pixels

– 3D construction• stack ROIs and visual analysis

Page 14: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods

• The Parallel Model • MapReduce - center around 2 func. to

represent domain problems• General pattern

Map(Di) → list(Ki,Vi); Reduce(Ki, list(Vi)) → list(Vf)• Divide the dataset D into individual data values Di

• Map(Di) is applied to each individual value, producing many lists of key value pairs list(Ki,Vi)

• Data produced by Map operations will be grouped by key Ki, producing associated values list(Vi)

• Reduce(Ki, list(Vi)) takes each key Ki and associated list of values list(Vi) to produce a list of final output values

Page 15: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods• Lesion activity assessment using Map-

Reduce

D ∑ Ii

Di Ii

Ki PhaseID

Vi roiByteArray

Vf 3DModelByteArray

Map(Di) → list(Ki,Vi):•performs ROI segmentation; •extract image phaseID (encoded in filename); •produce (phaseID, roiByteArray) as key-value pair

Reduce(Ki, list(Vi)) → list(Vf) :•receives ROI collections keyed to phaseID;•performs 3D construction;•produce (phaseID, 3DModelByteArray) pair

Page 16: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods

• Better performance with sequence files and data compression• Hadoop excels in processing small # of large files • Too many I/O operations → extra burden • Implementation

– Data packing before 3D-time series workflow– Map task loads images– Reduce task

» produce sequence files» apply compression

Page 17: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Datasets and Methods• Computing setup and parameters

– 64-node cluster on SDSC-Gordon• 8 Map slots 4 Reduce slots

– Used DEFLATE codec and block compression for sequence files

– 40,000 images in 12.62 minutes– More performance and scalability data reported in “

Exploting MapReduce and Data Compression for Data-intensive Applications“

Page 18: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Lesion Activity Assessment

• Quantitative Assessment– lesion and its volumetric change measured in

pixel^3– objective and consistent comparisons across

specimen and across different experimental conditions

– scalable to larger datasets

Page 19: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Lesion Activity Assessment

• 3D-Time Series Visualization– highlight lesion's volumetric changes B/A treatment

Page 20: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Lesion Activity Assessment

• 3D-Time Series Visualization– show lesion's volumetric changes B/A treatment– combine dem. and rem.

enamel in an integrated view with transparency

Page 21: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Lesion Activity Assessment

• Shape Generation and Depth Measure– some studies concern finding the association

between lesion depth and treatment variables

previous effort:approximate lesion depth based grayscale on QLF images

Page 22: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Lesion Activity Assessment

• Shape Generation and Depth Measure– some studies concern finding the association

between lesion depth and treatment variables

Page 23: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Lesion Activity Assessment

• Shape Generation and Depth Measure– some studies concern finding the association

between lesion depth and treatment variables– 3D Poisson surfaces constructed for interactive

depth measurement and comparison

Page 24: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Conclusion

• Dental computing gives rise to a broad range of educational and treatment planning applications for dentistry;

• A promising research approach that allows users to use imaging technology, computational algorithm, and visualization methods to make lesion activity assessment faster and more accurate;

• The workflow can be supported computationally; implemented using parallel programming model such as MapReduce; further automated using HPC resources.

Page 25: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Future Work

• Provide templates to other domains with similar computing task

• Potential improvement of the workflow– The final result is much lighter compared to

raw inputs• Data transfer with ROI boundary vectors

instead of heavy image arrays • Compression of intermediate analysis results

Page 26: © Trustees of Indiana University Released under Creative Commons 3.0 unported license; license terms on last slide. XSEDE-enabled High-throughput Caries

Thank you!Questions?