Benchmarking of algorithms for 3D tissue reconstruction

Kimmo Kartasalo; Leena Latonen; Tapio Visakorpi; Matti Nykter; Pekka Ruusuvuori

doi:10.1109/icip.2016.7532781

Benchmarking of algorithms for 3D tissue reconstruction

Kimmo Kartasalo, Leena Latonen, Tapio Visakorpi, Matti Nykter, Pekka Ruusuvuori

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

Abstract

Studying tissue structure in 3D is beneficial in many applications. Reconstructing the structure based on histological sections has the advantages of high resolution and compatibility with conventional staining and interpretation techniques. However, obtaining an accurate 3D reconstruction based on a sequence of 2D sections is a difficult task. Evaluating the accuracy of such reconstructions is also challenging and it is often performed based only on visual inspections or a single indirect numerical measure. Here, we present a benchmarking framework composed of a panel of complementary metrics for assessing the quality of 3D reconstructions. We then apply the framework to evaluate the performance of several popular image registration algorithms in this context.

Original language	English
Title of host publication	2016 IEEE International Conference on Image Processing (ICIP)
Publisher	IEEE
Pages	2360-2364
Number of pages	5
ISBN (Electronic)	978-1-4673-9961-6
DOIs	https://doi.org/10.1109/icip.2016.7532781
Publication status	Published - 2016
Publication type	A4 Article in conference proceedings
Event	IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING - Duration: 1 Jan 2016 → …

Conference

Conference	IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING
Period	1/01/16 → …

Keywords

3D reconstruction
Benchmark testing
Image reconstruction
Image registration
Indexes
Measurement
Standards
Three-dimensional displays
benchmark
digital pathology
histology

Publication forum classification

Publication forum level 1

Access to Document

10.1109/icip.2016.7532781

Cite this

@inproceedings{6b77bda6675d46b18cd102dbe34e3aa5,

title = "Benchmarking of algorithms for 3D tissue reconstruction",

abstract = "Studying tissue structure in 3D is beneficial in many applications. Reconstructing the structure based on histological sections has the advantages of high resolution and compatibility with conventional staining and interpretation techniques. However, obtaining an accurate 3D reconstruction based on a sequence of 2D sections is a difficult task. Evaluating the accuracy of such reconstructions is also challenging and it is often performed based only on visual inspections or a single indirect numerical measure. Here, we present a benchmarking framework composed of a panel of complementary metrics for assessing the quality of 3D reconstructions. We then apply the framework to evaluate the performance of several popular image registration algorithms in this context.",

keywords = "3D reconstruction, Benchmark testing, Image reconstruction, Image registration, Indexes, Measurement, Standards, Three-dimensional displays, benchmark, digital pathology, histology, 3D reconstruction, Benchmark testing, Image reconstruction, Image registration, Indexes, Measurement, Standards, Three-dimensional displays, benchmark, digital pathology, histology",

author = "Kimmo Kartasalo and Leena Latonen and Tapio Visakorpi and Matti Nykter and Pekka Ruusuvuori",

year = "2016",

doi = "10.1109/icip.2016.7532781",

language = "English",

pages = "2360--2364",

booktitle = "2016 IEEE International Conference on Image Processing (ICIP)",

publisher = "IEEE",

address = "United States",

note = "IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING ; Conference date: 01-01-2016",

}

TY - GEN

T1 - Benchmarking of algorithms for 3D tissue reconstruction

AU - Kartasalo, Kimmo

AU - Latonen, Leena

AU - Visakorpi, Tapio

AU - Nykter, Matti

AU - Ruusuvuori, Pekka

PY - 2016

Y1 - 2016

N2 - Studying tissue structure in 3D is beneficial in many applications. Reconstructing the structure based on histological sections has the advantages of high resolution and compatibility with conventional staining and interpretation techniques. However, obtaining an accurate 3D reconstruction based on a sequence of 2D sections is a difficult task. Evaluating the accuracy of such reconstructions is also challenging and it is often performed based only on visual inspections or a single indirect numerical measure. Here, we present a benchmarking framework composed of a panel of complementary metrics for assessing the quality of 3D reconstructions. We then apply the framework to evaluate the performance of several popular image registration algorithms in this context.

AB - Studying tissue structure in 3D is beneficial in many applications. Reconstructing the structure based on histological sections has the advantages of high resolution and compatibility with conventional staining and interpretation techniques. However, obtaining an accurate 3D reconstruction based on a sequence of 2D sections is a difficult task. Evaluating the accuracy of such reconstructions is also challenging and it is often performed based only on visual inspections or a single indirect numerical measure. Here, we present a benchmarking framework composed of a panel of complementary metrics for assessing the quality of 3D reconstructions. We then apply the framework to evaluate the performance of several popular image registration algorithms in this context.

KW - 3D reconstruction

KW - Benchmark testing

KW - Image reconstruction

KW - Image registration

KW - Indexes

KW - Measurement

KW - Standards

KW - Three-dimensional displays

KW - benchmark

KW - digital pathology

KW - histology

KW - 3D reconstruction

KW - Benchmark testing

KW - Image reconstruction

KW - Image registration

KW - Indexes

KW - Measurement

KW - Standards

KW - Three-dimensional displays

KW - benchmark

KW - digital pathology

KW - histology

U2 - 10.1109/icip.2016.7532781

DO - 10.1109/icip.2016.7532781

M3 - Conference contribution

SP - 2360

EP - 2364

BT - 2016 IEEE International Conference on Image Processing (ICIP)

PB - IEEE

T2 - IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING

Y2 - 1 January 2016

ER -

Benchmarking of algorithms for 3D tissue reconstruction

Abstract

Conference

Keywords

Publication forum classification

Access to Document

Fingerprint

Cite this