Robust 3D image reconstruction of pancreatic cancer tumors from histopathological images with different stains and its quantitative performance evaluation

Mauricio Kugler, Yushi Goto, Yuki Tamura, Naoki Kawamura, Hirokazu Kobayashi, Tatsuya Yokota, Chika Iwamoto, Kenoki Ohuchida, Makoto Hashizume, Akinobu Shimizu, Hidekata Hontani

Research output: Contribution to journalArticle

Abstract

Purpose: Histopathological imaging is widely used for the analysis and diagnosis of multiple diseases. Several methods have been proposed for the 3D reconstruction of pathological images, captured from thin sections of a given specimen, which get nonlinearly deformed due to the preparation process. The majority of the available methods for registering such images use the degree of matching of adjacent images as the criteria for registration, which can result in unnatural deformations of the anatomical structures. Moreover, most methods assume that the same staining is used for all images, when in fact multiple staining is usually applied in order to enhance different structures in the images. Methods: This paper proposes a non-rigid 3D reconstruction method based on the assumption that internal structures on the original tissue must be smooth and continuous. Landmarks are detected along anatomical structures using template matching based on normalized cross-correlation (NCC), forming jagged shape trajectories that traverse several slices. The registration process smooths out these trajectories and deforms the images accordingly. Artifacts are automatically handled by using the confidence of the NCC in order to reject unreliable landmarks. Results: The proposed method was applied to a large series of histological sections from the pancreas of a KPC mouse. Some portions were dyed primarily with HE stain, while others were dyed alternately with HE, CK19, MT and Ki67 stains. A new evaluation method is proposed to quantitatively evaluate the smoothness and isotropy of the obtained reconstructions, both for single and multiple staining. Conclusions: The experimental results show that the proposed method produces smooth and nearly isotropic 3D reconstructions of pathological images with either single or multiple stains. From these reconstructions, microanatomical structures enhanced by different stains can be simultaneously observed.

Original languageEnglish
Pages (from-to)2047-2055
Number of pages9
JournalInternational Journal of Computer Assisted Radiology and Surgery
Volume14
Issue number12
DOIs
Publication statusPublished - Dec 1 2019

Fingerprint

Computer-Assisted Image Processing
Image reconstruction
Pancreatic Neoplasms
Tumors
Coloring Agents
Trajectories
Template matching
Neoplasms
Tissue
Imaging techniques
Staining and Labeling
Artifacts
Pancreas

All Science Journal Classification (ASJC) codes

  • Surgery
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Cite this

Robust 3D image reconstruction of pancreatic cancer tumors from histopathological images with different stains and its quantitative performance evaluation. / Kugler, Mauricio; Goto, Yushi; Tamura, Yuki; Kawamura, Naoki; Kobayashi, Hirokazu; Yokota, Tatsuya; Iwamoto, Chika; Ohuchida, Kenoki; Hashizume, Makoto; Shimizu, Akinobu; Hontani, Hidekata.

In: International Journal of Computer Assisted Radiology and Surgery, Vol. 14, No. 12, 01.12.2019, p. 2047-2055.

Research output: Contribution to journalArticle

Kugler, Mauricio ; Goto, Yushi ; Tamura, Yuki ; Kawamura, Naoki ; Kobayashi, Hirokazu ; Yokota, Tatsuya ; Iwamoto, Chika ; Ohuchida, Kenoki ; Hashizume, Makoto ; Shimizu, Akinobu ; Hontani, Hidekata. / Robust 3D image reconstruction of pancreatic cancer tumors from histopathological images with different stains and its quantitative performance evaluation. In: International Journal of Computer Assisted Radiology and Surgery. 2019 ; Vol. 14, No. 12. pp. 2047-2055.
@article{4aeddeda52fe44308d96c05c0da965ae,
title = "Robust 3D image reconstruction of pancreatic cancer tumors from histopathological images with different stains and its quantitative performance evaluation",
abstract = "Purpose: Histopathological imaging is widely used for the analysis and diagnosis of multiple diseases. Several methods have been proposed for the 3D reconstruction of pathological images, captured from thin sections of a given specimen, which get nonlinearly deformed due to the preparation process. The majority of the available methods for registering such images use the degree of matching of adjacent images as the criteria for registration, which can result in unnatural deformations of the anatomical structures. Moreover, most methods assume that the same staining is used for all images, when in fact multiple staining is usually applied in order to enhance different structures in the images. Methods: This paper proposes a non-rigid 3D reconstruction method based on the assumption that internal structures on the original tissue must be smooth and continuous. Landmarks are detected along anatomical structures using template matching based on normalized cross-correlation (NCC), forming jagged shape trajectories that traverse several slices. The registration process smooths out these trajectories and deforms the images accordingly. Artifacts are automatically handled by using the confidence of the NCC in order to reject unreliable landmarks. Results: The proposed method was applied to a large series of histological sections from the pancreas of a KPC mouse. Some portions were dyed primarily with HE stain, while others were dyed alternately with HE, CK19, MT and Ki67 stains. A new evaluation method is proposed to quantitatively evaluate the smoothness and isotropy of the obtained reconstructions, both for single and multiple staining. Conclusions: The experimental results show that the proposed method produces smooth and nearly isotropic 3D reconstructions of pathological images with either single or multiple stains. From these reconstructions, microanatomical structures enhanced by different stains can be simultaneously observed.",
author = "Mauricio Kugler and Yushi Goto and Yuki Tamura and Naoki Kawamura and Hirokazu Kobayashi and Tatsuya Yokota and Chika Iwamoto and Kenoki Ohuchida and Makoto Hashizume and Akinobu Shimizu and Hidekata Hontani",
year = "2019",
month = "12",
day = "1",
doi = "10.1007/s11548-019-02019-8",
language = "English",
volume = "14",
pages = "2047--2055",
journal = "Computer-Assisted Radiology and Surgery",
issn = "1861-6410",
publisher = "Springer Verlag",
number = "12",

}

TY - JOUR

T1 - Robust 3D image reconstruction of pancreatic cancer tumors from histopathological images with different stains and its quantitative performance evaluation

AU - Kugler, Mauricio

AU - Goto, Yushi

AU - Tamura, Yuki

AU - Kawamura, Naoki

AU - Kobayashi, Hirokazu

AU - Yokota, Tatsuya

AU - Iwamoto, Chika

AU - Ohuchida, Kenoki

AU - Hashizume, Makoto

AU - Shimizu, Akinobu

AU - Hontani, Hidekata

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Purpose: Histopathological imaging is widely used for the analysis and diagnosis of multiple diseases. Several methods have been proposed for the 3D reconstruction of pathological images, captured from thin sections of a given specimen, which get nonlinearly deformed due to the preparation process. The majority of the available methods for registering such images use the degree of matching of adjacent images as the criteria for registration, which can result in unnatural deformations of the anatomical structures. Moreover, most methods assume that the same staining is used for all images, when in fact multiple staining is usually applied in order to enhance different structures in the images. Methods: This paper proposes a non-rigid 3D reconstruction method based on the assumption that internal structures on the original tissue must be smooth and continuous. Landmarks are detected along anatomical structures using template matching based on normalized cross-correlation (NCC), forming jagged shape trajectories that traverse several slices. The registration process smooths out these trajectories and deforms the images accordingly. Artifacts are automatically handled by using the confidence of the NCC in order to reject unreliable landmarks. Results: The proposed method was applied to a large series of histological sections from the pancreas of a KPC mouse. Some portions were dyed primarily with HE stain, while others were dyed alternately with HE, CK19, MT and Ki67 stains. A new evaluation method is proposed to quantitatively evaluate the smoothness and isotropy of the obtained reconstructions, both for single and multiple staining. Conclusions: The experimental results show that the proposed method produces smooth and nearly isotropic 3D reconstructions of pathological images with either single or multiple stains. From these reconstructions, microanatomical structures enhanced by different stains can be simultaneously observed.

AB - Purpose: Histopathological imaging is widely used for the analysis and diagnosis of multiple diseases. Several methods have been proposed for the 3D reconstruction of pathological images, captured from thin sections of a given specimen, which get nonlinearly deformed due to the preparation process. The majority of the available methods for registering such images use the degree of matching of adjacent images as the criteria for registration, which can result in unnatural deformations of the anatomical structures. Moreover, most methods assume that the same staining is used for all images, when in fact multiple staining is usually applied in order to enhance different structures in the images. Methods: This paper proposes a non-rigid 3D reconstruction method based on the assumption that internal structures on the original tissue must be smooth and continuous. Landmarks are detected along anatomical structures using template matching based on normalized cross-correlation (NCC), forming jagged shape trajectories that traverse several slices. The registration process smooths out these trajectories and deforms the images accordingly. Artifacts are automatically handled by using the confidence of the NCC in order to reject unreliable landmarks. Results: The proposed method was applied to a large series of histological sections from the pancreas of a KPC mouse. Some portions were dyed primarily with HE stain, while others were dyed alternately with HE, CK19, MT and Ki67 stains. A new evaluation method is proposed to quantitatively evaluate the smoothness and isotropy of the obtained reconstructions, both for single and multiple staining. Conclusions: The experimental results show that the proposed method produces smooth and nearly isotropic 3D reconstructions of pathological images with either single or multiple stains. From these reconstructions, microanatomical structures enhanced by different stains can be simultaneously observed.

UR - http://www.scopus.com/inward/record.url?scp=85068755575&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068755575&partnerID=8YFLogxK

U2 - 10.1007/s11548-019-02019-8

DO - 10.1007/s11548-019-02019-8

M3 - Article

C2 - 31267332

AN - SCOPUS:85068755575

VL - 14

SP - 2047

EP - 2055

JO - Computer-Assisted Radiology and Surgery

JF - Computer-Assisted Radiology and Surgery

SN - 1861-6410

IS - 12

ER -