Improving the Efficiency of Manual Ground Truth Labeling Using - - PowerPoint PPT Presentation

Improving the Efficiency of Manual Ground Truth Labeling Using Automated Anatomy Segmentation

Hongzhi Wang PhD, Prasanth Prasanna MD, Jose Morey MD, Tanveer F. Syeda-Mahmood PhD Medical Sieve Group, IBM Almaden Research Center

Anatomy Segmentation: labeling anatomical structures of interest in medical images

• Corner stone for quantitative image analysis

Gold standard: manual segmentation

Manual tracing in ITK-SNAP Manual tracing in Amira

Gold standard: manual segmentation

Manual tracing in ITK-SNAP Manual tracing in Amira

• Very time consuming, hours or even days to annotate a single 3D volume

Techniques for Assisting Manual Segmentation

• Interactive manual segmentation enhanced with interpolation techniques,

e.g. MITK and Amira

• Only a subset of 2D slices are manually annotated
• Annotation for the full 3D volume is generated through interpolation
• Annotation time is a fraction of standard manual segmentation, depending on

percentage of manually annotated slices

• Semi-automatic segmentation, e.g. Pluta et al. 2009, Daisne & Blumhofer 2013
• Automatic segmentation produces initial annotation
• Mistakes corrected by human experts
• Most focusing on single anatomical structure
• ~ 40% time reduction comparing to standard manual segmentation

(Daisne & Blumhofer 2013)

Aims

• Investigate full potential in time reduction by semi-automatic

segmentation

• Employing state of the art automatic anatomy segmentation algorithm
• Challenging multi-structure segmentation task
• cardiac CT anatomy segmentation with 20 anatomical structures
• Comparison with interpolation-based interactive manual segmentation

Data Description

• 33 cardiac CT studies
• 28 cases used for training automatic

segmentation

• 5 testing cases for experimental validation
• 20 structures studied
• Bone: sternum, vertebrae
• Artery/vein: pulmonary artery (left/right/trunk),

aorta (root/ascending/arch/descending), Superior/inferior vena cava

• Cardiac structure: Left/right ventricle/atrium,

left ventricular myocardium

• Valve : aortic valve, tricuspid valve, pulmonary

valve, mitral valve

Experimental Setup

• Semi-Automatic Segmentation:
• Automatic segmentation by multi-atlas label

fusion

• Manual correction by one clinician (PP) using

Amira commercial software (FEI Corporate,

Hillsboro, Oregon USA)

• Manual segmentation
• produced by the same clinician one week

after semi-automatic segmentation is finished using Amira with the interpolation technique

Overview for Automatic Anatomy Segmentation

Target Image

Training Image 1 Training Image k . . .

Registration and Warping Registration and Warping

Candidate Segmentation Candidate Segmentation Joint Label Fusion Initial Segmentation Post Processing Final Segmentation

Overview for Automatic Anatomy Segmentation

Target Image

Training Image 1 Training Image k . . .

Registration and Warping Registration and Warping

Candidate Segmentation Candidate Segmentation Joint Label Fusion Initial Segmentation Post Processing Final Segmentation Multi-Atlas Label Fusion

Multi-Atlas Label Fusion

Atlases (Training anatomical volumes)

Image Registration

. . .

Warped Atlases

registration

Label Fusion

A t ti R lt Given CT Scan

. . .

Automatic segmentation: Post processing

• Remove small isolated segments
• Ensure boundaries between right ventricle and pulmonary artery and

boundaries between substructures of aorta do not cross axial planes.

image multi-atlas segmentation after post processing after manual correction The colored anatomical structures are: sternum; right ventricle; pulmonary artery trunk; myocardium; aortic root; ascending aorta; descending aorta; left atrium; right atrium; vertebrae.

Results: Leave-One-Out Performance of Multi-Atlas Segmentation

Automatic Segmentation

Inter-rater precision for non-valve structures

Results: Overall Time Reduction

37% time reduction

statistically significant with p<0.0001

Conclusions and Discussion

• Multi-atlas anatomy segmentation is accurate enough to save time for

manual segmentation, even with advanced interpolation tools

• Without post processing, manual correction does not save time!
• Manually correcting small, isolated segments is time consuming!
• Having smooth segmentation is important for efficient manual correction!

Backup Material

Results: Ratio of Corrected Voxels

Results: Corrections are Heterogeneous with respect to Anatomical Structures