A Sub-Pixel Accurate Quantification of Joint Space Narrowing Progression in Rheumatoid Arthritis

Abstract

Rheumatoid arthritis (RA) is a chronic autoimmune disease that primarily affects peripheral synovial joints, like fingers, wrists and feet. Radiology plays a critical role in the diagnosis and monitoring of RA. Limited by the current spatial resolution of radiographic imaging, joint space narrowing (JSN) progression of RA for the same reason above can be less than one pixel per year with universal spatial resolution. Insensitive monitoring of JSN can hinder the radiologist/rheumatologist from making a proper and timely clinical judgment. In this paper, we propose a novel and sensitive method that we call partial image phaseonly correlation which aims to automatically quantify JSN progression in the early RA. The majority of the current literature utilizes the mean error, root-mean-square deviation and standard deviation to report the accuracy at pixel level. Our work measures JSN progression between a baseline and its follow-up finger joint images by using the phase spectrum in the frequency domain. Using this study, the mean error can be reduced to 0.0130 mm when applied to phantom radiographs with ground truth, and 0.0519 mm standard deviation for clinical radiography. With the subpixel accuracy far beyond usual manual measurements, we are optimistic that the proposed work is a promising scheme for automatically quantifying JSN progression.

Sacroiliitis diagnosis based on interpretable features and multi-task learning

“…Lighter et al (2019) detected joints of inflammatory arthritis patients by analyzing the amplitude spectrum in frequency domain. Ou et al (2022) measured the finger joint space narrowing of patients with rheumatoid arthritis on x-ray images and further segmented the joint space, using the phase spectrum in frequency domain. While These traditional FDA methods have achieved some success in arthritis, the FDA in deep learning is still under research.…”

“…Narrowing or widening of the joint space is a crucial indicator for diagnosing the arthritis. The phase component determines the position of the feature, and further, it is used for distance measurement, such as joint space narrowing (Ou et al 2022). The variation in phase spectrum leads to a transition between sharp and blurry edges.…”

“…In the second approach PRNet, which considers the importance of amplitude spectrum and phase spectrum in the recognition of inflammatory arthritis (Lighter et al 2019, Ou et al 2022, spatial signal x[m, n] is analyzed in terms of its amplitude spectrum A[u, v] and phase spectrum P[u, v], which are defined below:…”

Corrections to “A Sub-Pixel Accurate Quantification of Joint Space Narrowing Progression in Rheumatoid Arthritis”

“…Corrections to "A Sub-Pixel Accurate Quantification of Joint Space Narrowing Progression in Rheumatoid Arthritis" Yafei Ou, Member, IEEE, Prasoon Ambalathankandy , Member, IEEE, Ryunosuke Furuya, Seiya Kawada, Tianyu Zeng, Yujie An, Tamotsu Kamishima , Kenichi Tamura, and Masayuki Ikebe , Member, IEEE Rheumatoid arthritis (RA) is an autoimmune disease that poses significant diagnostic and monitoring challenges. Our previous work [1] contributed to this field by focusing on the role of radiography in detecting and monitoring joint space narrowing (JSN), a critical marker of RA progression. However, during our investigation, we inadvertently misquoted data in Table V This paper primarily addresses a correction of our previous work [1].…”

“…Our previous work [1] contributed to this field by focusing on the role of radiography in detecting and monitoring joint space narrowing (JSN), a critical marker of RA progression. However, during our investigation, we inadvertently misquoted data in Table V This paper primarily addresses a correction of our previous work [1]. We aim to clarify the mistaken reference numbers, ensuring that our findings and conclusions are accurately represented.…”