Registration of Longitudinal Spine CTs for Monitoring Lesion Growth

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sanhinova, Malika, Haouchine, Nazim, Pieper, Steve D., Wells III, William M., Balboni, Tracy A., Spektor, Alexander, Huynh, Mai Anh, Guenette, Jeffrey P., Czajkowski, Bryan, Caplan, Sarah, Doyle, Patrick, Kang, Heejoo, Hackney, David B., Alkalay, Ron N.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916125193797632
author Sanhinova, Malika
Haouchine, Nazim
Pieper, Steve D.
Wells III, William M.
Balboni, Tracy A.
Spektor, Alexander
Huynh, Mai Anh
Guenette, Jeffrey P.
Czajkowski, Bryan
Caplan, Sarah
Doyle, Patrick
Kang, Heejoo
Hackney, David B.
Alkalay, Ron N.
author_facet Sanhinova, Malika
Haouchine, Nazim
Pieper, Steve D.
Wells III, William M.
Balboni, Tracy A.
Spektor, Alexander
Huynh, Mai Anh
Guenette, Jeffrey P.
Czajkowski, Bryan
Caplan, Sarah
Doyle, Patrick
Kang, Heejoo
Hackney, David B.
Alkalay, Ron N.
contents Accurate and reliable registration of longitudinal spine images is essential for assessment of disease progression and surgical outcome. Implementing a fully automatic and robust registration is crucial for clinical use, however, it is challenging due to substantial change in shape and appearance due to lesions. In this paper we present a novel method to automatically align longitudinal spine CTs and accurately assess lesion progression. Our method follows a two-step pipeline where vertebrae are first automatically localized, labeled and 3D surfaces are generated using a deep learning model, then longitudinally aligned using a Gaussian mixture model surface registration. We tested our approach on 37 vertebrae, from 5 patients, with baseline CTs and 3, 6, and 12 months follow-ups leading to 111 registrations. Our experiment showed accurate registration with an average Hausdorff distance of 0.65 mm and average Dice score of 0.92.
format Preprint
id arxiv_https___arxiv_org_abs_2402_09341
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Registration of Longitudinal Spine CTs for Monitoring Lesion Growth
Sanhinova, Malika
Haouchine, Nazim
Pieper, Steve D.
Wells III, William M.
Balboni, Tracy A.
Spektor, Alexander
Huynh, Mai Anh
Guenette, Jeffrey P.
Czajkowski, Bryan
Caplan, Sarah
Doyle, Patrick
Kang, Heejoo
Hackney, David B.
Alkalay, Ron N.
Image and Video Processing
Computer Vision and Pattern Recognition
Accurate and reliable registration of longitudinal spine images is essential for assessment of disease progression and surgical outcome. Implementing a fully automatic and robust registration is crucial for clinical use, however, it is challenging due to substantial change in shape and appearance due to lesions. In this paper we present a novel method to automatically align longitudinal spine CTs and accurately assess lesion progression. Our method follows a two-step pipeline where vertebrae are first automatically localized, labeled and 3D surfaces are generated using a deep learning model, then longitudinally aligned using a Gaussian mixture model surface registration. We tested our approach on 37 vertebrae, from 5 patients, with baseline CTs and 3, 6, and 12 months follow-ups leading to 111 registrations. Our experiment showed accurate registration with an average Hausdorff distance of 0.65 mm and average Dice score of 0.92.
title Registration of Longitudinal Spine CTs for Monitoring Lesion Growth
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.09341