pith. sign in

arxiv: 2507.05193 · v4 · pith:SQ6ACUT5new · submitted 2025-07-07 · 📡 eess.IV · cs.CV

RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis

Songxiao Yang , Haolin Wang , Yao Fu , Ye Tian , Tamotsu Kamishima , Masayuki Ikebe , Yafei Ou , Masatoshi Okutomi This is my paper

Pith reviewed 2026-05-19 05:54 UTC · model grok-4.3

classification 📡 eess.IV cs.CV
keywords rheumatoid arthritiswrist radiographsinstance segmentationbone erosion scoringmulti-task datasetconventional radiographycomputer-aided diagnosis
0
0 comments X p. Extension
pith:SQ6ACUT5 Add to your LaTeX paper What is a Pith Number? 
\usepackage{pith}
\pithnumber{SQ6ACUT5}

Prints a linked pith:SQ6ACUT5 badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

The pith

A new public dataset supplies pixel-level annotations for wrist bone segmentation and Sharp/van der Heijde bone erosion scores in rheumatoid arthritis radiographs.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents RAM-W600 as the first public multi-task resource for wrist conventional radiographs in rheumatoid arthritis research. It tackles the scarcity of high-quality instance-level labels for small overlapping bones whose shapes change with disease. The collection draws 1048 images from 388 patients at six centers, supplying segmentation masks on 618 images and SvdH bone erosion scores on 800 images. These labels can underpin tasks such as joint space narrowing quantification, erosion detection, and deformity assessment. Release of the data is intended to reduce the effort required to begin computer-aided diagnosis studies in this area.

Core claim

The authors establish that a multi-center collection of 1048 wrist radiographs, annotated at the pixel level for bone instances on 618 cases and scored for bone erosion on 800 cases, constitutes the first openly available resource for wrist bone instance segmentation and simultaneously supports Sharp/van der Heijde bone erosion scoring in rheumatoid arthritis.

What carries the argument

The RAM-W600 dataset, which pairs conventional wrist radiographs with pixel-level instance segmentation masks and SvdH bone erosion scores.

If this is right

  • The annotations enable training of models for automated joint space narrowing measurement across multiple centers.
  • The scores support development of algorithms that detect and quantify bone erosion progression.
  • The same images can be used to evaluate bone deformity and osteophyte formation.
  • The resource extends to non-RA wrist tasks such as locating carpal bone fractures.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Models trained on this data could be tested for cross-center robustness using the multi-site collection.
  • Automated scoring pipelines built from these labels might reduce the time experts spend on routine RA monitoring.
  • Future releases could add follow-up images to support longitudinal studies of disease progression.

Load-bearing premise

The provided pixel-level segmentation masks and SvdH scores are sufficiently consistent and accurate to function as reliable ground truth even though small bones, narrow spaces, overlaps, and disease changes make expert annotation difficult.

What would settle it

Re-annotation of a random subset of the images by independent rheumatology experts that produces substantially different bone boundaries or erosion scores from the released labels would undermine the dataset's value as ground truth.

Figures

Figures reproduced from arXiv: 2507.05193 by Haolin Wang, Masatoshi Okutomi, Masayuki Ikebe, Songxiao Yang, Tamotsu Kamishima, Yafei Ou, Yao Fu, Ye Tian.

Figure 1
Figure 1. Figure 1: Overview of the RAM-W600 dataset, designed for wrist bone segmentation and SvdH [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Distribution and Statistics for the age, gender, institution, number of shots, and BE scores [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Wrist bone segmentation visualization results. The solid box indicates segmentation [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: BE & nonBE confusion matrix results for classification of BE. Implementation details The dataset was split according to the configuration shown in [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: A total of 1048 DICOM-format wrist radiographs were collected, including 916 internal [PITH_FULL_IMAGE:figures/full_fig_p020_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Wrist bone segmentation.(A) Original wrist radiograph. (B) Predicted instance segmentation [PITH_FULL_IMAGE:figures/full_fig_p021_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Image input and annotation.(A) Raw wrist radiograph. (B) Instance bone segmentation [PITH_FULL_IMAGE:figures/full_fig_p021_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: BE and nonBE Classification. The left panel shows six annotated joint regions used for BE [PITH_FULL_IMAGE:figures/full_fig_p022_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Additional visual results for wrist bone segmentation (Part A). [PITH_FULL_IMAGE:figures/full_fig_p029_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Additional visual results for wrist bone segmentation (Part B). [PITH_FULL_IMAGE:figures/full_fig_p030_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Confusion matrix results for classification of BE and nonBE. [PITH_FULL_IMAGE:figures/full_fig_p030_11.png] view at source ↗
read the original abstract

Rheumatoid arthritis (RA) is a common autoimmune disease that has been the focus of research in computer-aided diagnosis (CAD) and disease monitoring. In clinical settings, conventional radiography (CR) is widely used for the screening and evaluation of RA due to its low cost and accessibility. The wrist is a critical region for the diagnosis of RA. However, CAD research in this area remains limited, primarily due to the challenges in acquiring high-quality instance-level annotations. (i) The wrist comprises numerous small bones with narrow joint spaces, complex structures, and frequent overlaps, requiring detailed anatomical knowledge for accurate annotation. (ii) Disease progression in RA often leads to osteophyte, bone erosion (BE), and even bony ankylosis, which alter bone morphology and increase annotation difficulty, necessitating expertise in rheumatology. This work presents a multi-task dataset for wrist bone in CR, including two tasks: (i) wrist bone instance segmentation and (ii) Sharp/van der Heijde (SvdH) BE scoring, which is the first public resource for wrist bone instance segmentation. This dataset comprises 1048 wrist conventional radiographs of 388 patients from six medical centers, with pixel-level instance segmentation annotations for 618 images and SvdH BE scores for 800 images. This dataset can potentially support a wide range of research tasks related to RA, including joint space narrowing (JSN) progression quantification, BE detection, bone deformity evaluation, and osteophyte detection. It may also be applied to other wrist-related tasks, such as carpal bone fracture localization. We hope this dataset will significantly lower the barrier to research on wrist RA and accelerate progress in CAD research within the RA-related domain.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The paper introduces the RAM-W600 dataset, a multi-task collection of 1048 wrist conventional radiographs from 388 patients across six medical centers. It provides pixel-level instance segmentation annotations for 618 images and Sharp/van der Heijde (SvdH) bone erosion (BE) scores for 800 images. The central claim is that this is the first public resource for wrist bone instance segmentation in conventional radiography, intended to support CAD research on rheumatoid arthritis tasks including BE detection, joint space narrowing quantification, and related applications.

Significance. If the ground-truth annotations prove reliable, the dataset would represent a meaningful contribution by filling a gap in public resources for wrist-specific RA imaging analysis. The multi-center design and dual-task structure (segmentation plus scoring) could facilitate development of generalizable models and support downstream tasks such as osteophyte detection or carpal fracture localization.

major comments (1)
  1. [Annotation Protocol / Methods] Annotation Protocol / Methods section: The manuscript acknowledges that accurate pixel-level annotation of wrist bones requires detailed anatomical and rheumatology expertise due to small bones, narrow joint spaces, overlaps, and RA-induced morphological changes, yet provides no quantitative inter-annotator agreement statistics (e.g., mean Dice or IoU across multiple experts) for the 618 segmentation masks. Without such metrics or a description of the adjudication process, the reliability of the instance-segmentation ground truth remains unsubstantiated and directly undermines the dataset's utility as a benchmark.
minor comments (2)
  1. [Abstract] The abstract and introduction would benefit from explicit clarification on the overlap between the 618 segmentation-annotated images and the 800 scored images, including whether any images carry both labels.
  2. [Dataset Statistics] Figure captions and dataset statistics tables should include the exact number of images per center and per task to allow readers to assess potential center-specific biases.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their thoughtful review and for identifying a key area where the manuscript can be strengthened. We address the major comment below and outline the revisions we will make.

read point-by-point responses

  1. Referee: [Annotation Protocol / Methods] Annotation Protocol / Methods section: The manuscript acknowledges that accurate pixel-level annotation of wrist bones requires detailed anatomical and rheumatology expertise due to small bones, narrow joint spaces, overlaps, and RA-induced morphological changes, yet provides no quantitative inter-annotator agreement statistics (e.g., mean Dice or IoU across multiple experts) for the 618 segmentation masks. Without such metrics or a description of the adjudication process, the reliability of the instance-segmentation ground truth remains unsubstantiated and directly undermines the dataset's utility as a benchmark.

    Authors: We agree that quantitative measures of annotation reliability are essential for establishing the dataset as a robust benchmark. The current manuscript describes the general annotation challenges and the involvement of experts with anatomical and rheumatology knowledge but does not report inter-annotator agreement or detail the adjudication steps. In the revised manuscript we will expand the Methods section to include: (i) the number of annotators and their specific qualifications, (ii) a description of the multi-stage annotation and adjudication workflow, and (iii) quantitative agreement statistics (mean Dice and IoU) computed on a representative subset of images that were annotated independently by multiple experts. These additions will directly address the concern and strengthen the evidence for ground-truth quality. revision: yes

Circularity Check

0 steps flagged

Dataset release paper with no derivations or predictions exhibits no circularity

full rationale

This is a dataset introduction paper whose central claims concern the composition, scale, and public availability of a new multi-task wrist radiograph collection (1048 images, 618 with instance segmentation, 800 with SvdH scores). No mathematical derivations, equations, fitted parameters, or predictive models are present. The claims rest directly on the described data acquisition and annotation process rather than any self-referential reduction, self-citation chain, or renaming of prior results. The paper is therefore self-contained against external benchmarks of dataset utility, warranting a score of 0 with no circular steps.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper is a dataset introduction rather than a theoretical or modeling contribution; it rests on domain assumptions about annotation difficulty but introduces no free parameters, fitted values, or new postulated entities.

axioms (1)
  • domain assumption Accurate wrist bone instance segmentation in conventional radiographs requires detailed anatomical knowledge and rheumatology expertise because of small bones, narrow joint spaces, complex structures, overlaps, and disease-induced changes such as osteophytes and bone erosion.
    Explicitly stated in the abstract as the primary reasons why CAD research in this area remains limited.

pith-pipeline@v0.9.0 · 5873 in / 1418 out tokens · 33590 ms · 2026-05-19T05:54:20.476922+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

81 extracted references · 81 canonical work pages · 4 internal anchors

  1. [1]

    Fracatlas: A dataset for fracture classification, localization and segmentation of musculoskeletal radiographs.Scientific data, 10(1):521, 2023

    Iftekharul Abedeen, Md Ashiqur Rahman, Fatema Zohra Prottyasha, Tasnim Ahmed, Tareque Mohmud Chowdhury, and Swakkhar Shatabda. Fracatlas: A dataset for fracture classification, localization and segmentation of musculoskeletal radiographs.Scientific data, 10(1):521, 2023

    work page 2023

  2. [2]

    Diagnosis and management of rheumatoid arthritis: a review.Jama, 320(13):1360–1372, 2018

    Daniel Aletaha and Josef S Smolen. Diagnosis and management of rheumatoid arthritis: a review.Jama, 320(13):1360–1372, 2018

    work page 2018

  3. [3]

    Diagnostic tests

    Douglas G Altman and J Martin Bland. Diagnostic tests. 1: Sensitivity and specificity.BMJ: British Medical Journal, 308(6943):1552, 1994

    work page 1994

  4. [4]

    Automatic segmentation of wrist bones in ct using a statistical wrist shape + pose model.IEEE transactions on medical imaging, 35(8):1789–1801, 2016

    Emran Mohammad Abu Anas, Abtin Rasoulian, Alexander Seitel, Kathryn Darras, David Wil- son, Paul St John, David Pichora, Parvin Mousavi, Robert Rohling, and Purang Abolmaesumi. Automatic segmentation of wrist bones in ct using a statistical wrist shape + pose model.IEEE transactions on medical imaging, 35(8):1789–1801, 2016

    work page 2016

  5. [5]

    Radiographic imaging of the wrist

    Anil K Bhat, Bhaskaranand Kumar, and Ashwath Acharya. Radiographic imaging of the wrist. Indian journal of plastic surgery: official publication of the Association of Plastic Surgeons of India, 44(2):186, 2011. 10

    work page 2011

  6. [6]

    Deep learning models to automate the scoring of hand radiographs for rheumatoid arthritis

    Zhiyan Bo, Laura C Coates, and Bartłomiej W Papie˙z. Deep learning models to automate the scoring of hand radiographs for rheumatoid arthritis. InAnnual Conference on Medical Image Understanding and Analysis, pages 398–413. Springer, 2024

    work page 2024

  7. [7]

    Convolutional kolmogorov-arnold networks.arXiv preprint arXiv:2406.13155, 2024

    Alexander Dylan Bodner, Antonio Santiago Tepsich, Jack Natan Spolski, and Santiago Pourteau. Convolutional kolmogorov-arnold networks.arXiv preprint arXiv:2406.13155, 2024

    work page arXiv 2024

  8. [8]

    The balanced accuracy and its posterior distribution

    Kay Henning Brodersen, Cheng Soon Ong, Klaas Enno Stephan, and Joachim M Buhmann. The balanced accuracy and its posterior distribution. In2010 20th international conference on pattern recognition, pages 3121–3124. IEEE, 2010

    work page 2010

  9. [9]

    Karin Bruynesteyn, Désirée van der Heijde, Maarten Boers, Ariane Saudan, Paul Peloso, Harold Paulus, Harry Houben, Bridget Griffiths, John Edmonds, Barry Bresnihan, et al. Determination of the minimal clinically important difference in rheumatoid arthritis joint damage of the sharp/van der heijde and larsen/scott scoring methods by clinical experts and co...

    work page 2002

  10. [10]

    Digital hand atlas and web-based bone age assessment: system design and implementation.Computerized medical imaging and graphics, 24(5):297–307, 2000

    Fei Cao, HK Huang, Ewa Pietka, and Vicente Gilsanz. Digital hand atlas and web-based bone age assessment: system design and implementation.Computerized medical imaging and graphics, 24(5):297–307, 2000

    work page 2000

  11. [11]

    TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

    Jieneng Chen, Yongyi Lu, Qihang Yu, Xiangde Luo, Ehsan Adeli, Yan Wang, Le Lu, Alan L Yuille, and Yuyin Zhou. Transunet: Transformers make strong encoders for medical image segmentation.arXiv preprint arXiv:2102.04306, 2021

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  12. [12]

    Rethinking Atrous Convolution for Semantic Image Segmentation

    Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. Rethinking atrous convolution for semantic image segmentation.arXiv preprint arXiv:1706.05587, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  13. [13]

    Encoder-decoder with atrous separable convolution for semantic image segmentation

    Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, and Hartwig Adam. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), pages 801–818, 2018

    work page 2018

  14. [14]

    Muc-5 evaluation metrics

    Nancy Chinchor and Beth M Sundheim. Muc-5 evaluation metrics. InFifth Message Under- standing Conference (MUC-5): Proceedings of a Conference Held in Baltimore, Maryland, August 25-27, 1993, 1993

    work page 1993

  15. [15]

    Measures of the amount of ecologic association between species.Ecology, 26(3):297–302, 1945

    Lee R Dice. Measures of the amount of ecologic association between species.Ecology, 26(3):297–302, 1945

    work page 1945

  16. [16]

    Hand bone extraction and segmentation based on a convolutional neural network.Biomedical Signal Processing and Control, 89:105788, 2024

    Hongbo Du, Hai Wang, Chunlai Yang, Luyando Kabalata, Henian Li, and Changfu Qiang. Hand bone extraction and segmentation based on a convolutional neural network.Biomedical Signal Processing and Control, 89:105788, 2024

    work page 2024

  17. [17]

    Anatomy, biomechanics, and loads of the wrist joint.Life, 12(2):188, 2022

    Jörg Eschweiler, Jianzhang Li, Valentin Quack, Björn Rath, Alice Baroncini, Frank Hildebrand, and Filippo Migliorini. Anatomy, biomechanics, and loads of the wrist joint.Life, 12(2):188, 2022

    work page 2022

  18. [18]

    Radiographic findings of inflammatory arthritis and mimics in the hands.Diagnostics, 12(9):2134, 2022

    Fatemeh Ezzati and Parham Pezeshk. Radiographic findings of inflammatory arthritis and mimics in the hands.Diagnostics, 12(9):2134, 2022

    work page 2022

  19. [19]

    deep dive

    Lukas Folle, David Simon, Koray Tascilar, Gerhard Krönke, Anna-Maria Liphardt, Andreas Maier, Georg Schett, and Arnd Kleyer. Deep learning-based classification of inflammatory arthritis by identification of joint shape patterns—how neural networks can tell us where to “deep dive” clinically.Frontiers in Medicine, 9:850552, 2022

    work page 2022

  20. [20]

    Wrist: A wrist image segmentation toolkit for carpal bone delineation from mri.Computerized Medical Imaging and Graphics, 63:31–40, 2018

    Brent Foster, Anand A Joshi, Marissa Borgese, Yasser Abdelhafez, Robert D Boutin, and Abhijit J Chaudhari. Wrist: A wrist image segmentation toolkit for carpal bone delineation from mri.Computerized Medical Imaging and Graphics, 63:31–40, 2018

    work page 2018

  21. [21]

    The elements of statistical learning: Data mining, inference, and prediction

    Jerome Friedman. The elements of statistical learning: Data mining, inference, and prediction. (No Title), 2009. 11

    work page 2009

  22. [22]

    The diagnostic odds ratio: a single indicator of test performance.Journal of clinical epidemiology, 56(11):1129–1135, 2003

    Afina S Glas, Jeroen G Lijmer, Martin H Prins, Gouke J Bonsel, and Patrick MM Bossuyt. The diagnostic odds ratio: a single indicator of test performance.Journal of clinical epidemiology, 56(11):1129–1135, 2003

    work page 2003

  23. [23]

    Levit: a vision transformer in convnet’s clothing for faster inference

    Benjamin Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jégou, and Matthijs Douze. Levit: a vision transformer in convnet’s clothing for faster inference. InProceedings of the IEEE/CVF international conference on computer vision, pages 12259– 12269, 2021

    work page 2021

  24. [24]

    The rsna pediatric bone age machine learning challenge.Radiology, 290(2):498– 503, 2019

    Safwan S Halabi, Luciano M Prevedello, Jayashree Kalpathy-Cramer, Artem B Mamonov, Alexander Bilbily, Mark Cicero, Ian Pan, Lucas Araújo Pereira, Rafael Teixeira Sousa, Nitamar Abdala, et al. The rsna pediatric bone age machine learning challenge.Radiology, 290(2):498– 503, 2019

    work page 2019

  25. [25]

    Deep residual learning for image recognition

    Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016

    work page 2016

  26. [26]

    Evaluation method of rheumatoid arthritis by the x-ray photograph using deep learning

    Yuri Hioki, Koji Makino, Kensuke Koyama, Hirotaka Haro, and Hidetsugu Terada. Evaluation method of rheumatoid arthritis by the x-ray photograph using deep learning. In2021 IEEE 3rd Global Conference on Life Sciences and Technologies (LifeTech), pages 444–447. IEEE, 2021

    work page 2021

  27. [27]

    Development and validation of a deep-learning model for scoring of radiographic finger joint destruction in rheumatoid arthritis

    T Hirano, M Nishide, N Nonaka, J Seita, K Ebina, K Sakurada, et al. Development and validation of a deep-learning model for scoring of radiographic finger joint destruction in rheumatoid arthritis. rheumatol adv pract. 2019. available from:; 3

    work page 2019

  28. [28]

    Toru Hirano, Masayuki Nishide, Naoki Nonaka, Jun Seita, Kosuke Ebina, Kazuhiro Sakurada, and Atsushi Kumanogoh. Development and validation of a deep-learning model for scoring of radiographic finger joint destruction in rheumatoid arthritis.Rheumatology advances in practice, 3(2):rkz047, 2019

    work page 2019

  29. [29]

    Corrective osteotomies of phalangeal and metacarpal malunions using patient-specific guides: Ct-based evaluation of the reduction accuracy.Hand, 13(6):627–636, 2018

    Stefanie Hirsiger, Andreas Schweizer, Junichi Miyake, Ladislav Nagy, and Philipp Fürnstahl. Corrective osteotomies of phalangeal and metacarpal malunions using patient-specific guides: Ct-based evaluation of the reduction accuracy.Hand, 13(6):627–636, 2018

    work page 2018

  30. [30]

    A comparison of magnetic resonance imaging, sonography, and radiography of the hand in patients with early rheumatoid arthritis.The Journal of rheumatology, 31(4):663–675, 2004

    Jan Lucas Hoving, Rachelle Buchbinder, Stephen Hall, Gary Lawler, Peter Coombs, Stephen McNealy, Paul Bird, and David Connell. A comparison of magnetic resonance imaging, sonography, and radiography of the hand in patients with early rheumatoid arthritis.The Journal of rheumatology, 31(4):663–675, 2004

    work page 2004

  31. [31]

    MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

    Andrew G Howard. Mobilenets: Efficient convolutional neural networks for mobile vision applications.arXiv preprint arXiv:1704.04861, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  32. [32]

    Automatic quantification of radiographic wrist joint space width of patients with rheumatoid arthritis.IEEE Transactions on Biomedical Engineering, 64(11):2695–2703, 2017

    Yinghe Huo, Koen L Vincken, Desiree Van Der Heijde, Maria JH De Hair, Floris P Lafeber, and Max A Viergever. Automatic quantification of radiographic wrist joint space width of patients with rheumatoid arthritis.IEEE Transactions on Biomedical Engineering, 64(11):2695–2703, 2017

    work page 2017

  33. [33]

    Predictors of radiographic joint damage in patients with early rheumatoid arthritis

    LMA Jansen, IE Van der Horst-Bruinsma, D Van Schaardenburg, PD Bezemer, and BAC Dijkmans. Predictors of radiographic joint damage in patients with early rheumatoid arthritis. Annals of the rheumatic diseases, 60(10):924–927, 2001

    work page 2001

  34. [34]

    Automatic segmentation for favourable delineation of ten wrist bones on wrist radiographs using convolutional neural network.Journal of Personalized Medicine, 12(5):776, 2022

    Bo-kyeong Kang, Yelin Han, Jaehoon Oh, Jongwoo Lim, Jongbin Ryu, Myeong Seong Yoon, Juncheol Lee, and Soorack Ryu. Automatic segmentation for favourable delineation of ten wrist bones on wrist radiographs using convolutional neural network.Journal of Personalized Medicine, 12(5):776, 2022

    work page 2022

  35. [35]

    An introduction to machine learning and analysis of its use in rheumatic diseases.Nature Reviews Rheumatology, 17(12):710–730, 2021

    Kathryn M Kingsmore, Christopher E Puglisi, Amrie C Grammer, and Peter E Lipsky. An introduction to machine learning and analysis of its use in rheumatic diseases.Nature Reviews Rheumatology, 17(12):710–730, 2021. 12

    work page 2021

  36. [36]

    Segment anything

    Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C Berg, Wan-Yen Lo, et al. Segment anything. In Proceedings of the IEEE/CVF international conference on computer vision, pages 4015–4026, 2023

    work page 2023

  37. [37]

    Osteoporosis prediction from hand and wrist x-rays using image segmentation and self-supervised learning

    Hyungeun Lee, Ung Hwang, Seungwon Yu, Chang-Hun Lee, and Kijung Yoon. Osteoporosis prediction from hand and wrist x-rays using image segmentation and self-supervised learning. arXiv preprint arXiv:2311.06834, 2023

    work page arXiv 2023

  38. [38]

    U-kan makes strong backbone for medical image segmentation and generation

    Chenxin Li, Xinyu Liu, Wuyang Li, Cheng Wang, Hengyu Liu, Yifan Liu, Zhen Chen, and Yixuan Yuan. U-kan makes strong backbone for medical image segmentation and generation. InProceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 4652–4660, 2025

    work page 2025

  39. [39]

    Efficientformer: Vision transformers at mobilenet speed.Advances in Neural Information Processing Systems, 35:12934–12949, 2022

    Yanyu Li, Geng Yuan, Yang Wen, Ju Hu, Georgios Evangelidis, Sergey Tulyakov, Yanzhi Wang, and Jian Ren. Efficientformer: Vision transformers at mobilenet speed.Advances in Neural Information Processing Systems, 35:12934–12949, 2022

    work page 2022

  40. [40]

    Chung-Yueh Lien, Hao-Jan Wang, Cheng-Kai Lu, Tzu-Hsuan Hsu, Woei-Chyn Chu, and Chien- Chih Lai. Deep learning with an attention mechanism for enhancing automated modified total sharp/van der heijde scoring of hand x-ray images in rheumatoid arthritis.Journal of Medical and Biological Engineering, pages 1–9, 2025

    work page 2025

  41. [41]

    Feature pyramid networks for object detection

    Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. Feature pyramid networks for object detection. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 2117–2125, 2017

    work page 2017

  42. [42]

    Swin-umamba: Mamba-based unet with imagenet-based pretraining

    Jiarun Liu, Hao Yang, Hong-Yu Zhou, Yan Xi, Lequan Yu, Cheng Li, Yong Liang, Guangming Shi, Yizhou Yu, Shaoting Zhang, et al. Swin-umamba: Mamba-based unet with imagenet-based pretraining. InInternational Conference on Medical Image Computing and Computer-Assisted Intervention, pages 615–625. Springer, 2024

    work page 2024

  43. [43]

    Segment anything in medical images.Nature Communications, 15:654, 2024

    Jun Ma, Yuting He, Feifei Li, Lin Han, Chenyu You, and Bo Wang. Segment anything in medical images.Nature Communications, 15:654, 2024

    work page 2024

  44. [44]

    U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

    Jun Ma, Feifei Li, and Bo Wang. U-mamba: Enhancing long-range dependency for biomedical image segmentation.arXiv preprint arXiv:2401.04722, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  45. [45]

    Deep learning for rheumatoid arthritis: Joint detection and damage scoring in x-rays.arXiv preprint arXiv:2104.13915, 2021

    Krzysztof Maziarz, Anna Krason, and Zbigniew Wojna. Deep learning for rheumatoid arthritis: Joint detection and damage scoring in x-rays.arXiv preprint arXiv:2104.13915, 2021

    work page arXiv 2021

  46. [46]

    Mobilevit: light-weight, general-purpose, and mobile- friendly vision transformer.arXiv preprint arXiv:2110.02178, 2021

    Sachin Mehta and Mohammad Rastegari. Mobilevit: light-weight, general-purpose, and mobile- friendly vision transformer.arXiv preprint arXiv:2110.02178, 2021

    work page arXiv 2021

  47. [47]

    Deep learning-based automatic-bone-destruction-evaluation system using contextual information from other joints

    Kazuki Miyama, Ryoma Bise, Satoshi Ikemura, Kazuhiro Kai, Masaya Kanahori, Shinkichi Arisumi, Taisuke Uchida, Yasuharu Nakashima, and Seiichi Uchida. Deep learning-based automatic-bone-destruction-evaluation system using contextual information from other joints. Arthritis Research & Therapy, 24(1):227, 2022

    work page 2022

  48. [48]

    A digital database of wrist bone anatomy and carpal kinematics.Journal of biomechanics, 40(11):2537– 2542, 2007

    Douglas C Moore, Joseph J Crisco, Theodore G Trafton, and Evan L Leventhal. A digital database of wrist bone anatomy and carpal kinematics.Journal of biomechanics, 40(11):2537– 2542, 2007

    work page 2007

  49. [49]

    3d mri brain tumor segmentation using autoencoder regularization

    Andriy Myronenko. 3d mri brain tumor segmentation using autoencoder regularization. In International MICCAI brainlesion workshop, pages 311–320. Springer, 2018

    work page 2018

  50. [50]

    Triquetrum fracture with pisiform dislocation.Orthopedic Reviews, 14(2):32339, 2022

    Arjun Nanduri, Alison Kim, Carolyn Nolan, Jesse Dubey, and Andrew Barbera. Triquetrum fracture with pisiform dislocation.Orthopedic Reviews, 14(2):32339, 2022

    work page 2022

  51. [51]

    Stanislav Nikolov, Sam Blackwell, Alexei Zverovitch, Ruheena Mendes, Michelle Livne, Jeffrey De Fauw, Yojan Patel, Clemens Meyer, Harry Askham, Bernadino Romera-Paredes, et al. Clinically applicable segmentation of head and neck anatomy for radiotherapy: deep learning algorithm development and validation study.Journal of medical Internet research, 23(7):e...

    work page 2021

  52. [52]

    A sub-pixel accurate quantifi- cation of joint space narrowing progression in rheumatoid arthritis.IEEE Journal of Biomedical and Health Informatics, 27(1):53–64, 2023

    Yafei Ou, Prasoon Ambalathankandy, Ryunosuke Furuya, Seiya Kawada, Tianyu Zeng, Yujie An, Tamotsu Kamishima, Kenichi Tamura, and Masayuki Ikebe. A sub-pixel accurate quantifi- cation of joint space narrowing progression in rheumatoid arthritis.IEEE Journal of Biomedical and Health Informatics, 27(1):53–64, 2023

    work page 2023

  53. [53]

    Artificial intelligence model for segmentation and severity scoring of osteophytes in hand osteoarthritis on ultrasound images.Frontiers in Medicine, 11:1297088, 2024

    Benjamin Schultz Overgaard, Anders Bossel Holst Christensen, Lene Terslev, Thiusius Rajeeth Savarimuthu, and Søren Andreas Just. Artificial intelligence model for segmentation and severity scoring of osteophytes in hand osteoarthritis on ultrasound images.Frontiers in Medicine, 11:1297088, 2024

    work page 2024

  54. [54]

    Raj Ponnusamy, Ming Zhang, Zhiheng Chang, Yue Wang, Carmine Guida, Samantha Kuang, Xinyue Sun, Jordan Blackadar, Jeffrey B Driban, Timothy McAlindon, et al. Automatic measuring of finger joint space width on hand radiograph using deep learning and conventional computer vision methods.Biomedical signal processing and control, 84:104713, 2023

    work page 2023

  55. [55]

    Deep learning-based post-processing of real-time mri to assess and quantify dynamic wrist movement in health and disease.Diagnostics, 11(6):1077, 2021

    Karl Ludger Radke, Lena Marie Wollschläger, Sven Nebelung, Daniel Benjamin Abrar, Christoph Schleich, Matthias Boschheidgen, Miriam Frenken, Justus Schock, Dirk Klee, Jens Frahm, et al. Deep learning-based post-processing of real-time mri to assess and quantify dynamic wrist movement in health and disease.Diagnostics, 11(6):1077, 2021

    work page 2021

  56. [56]

    Multi-label segmentation of carpal bones in mri using expansion transfer learning.Physics in Medicine and Biology, 2025

    Stefan Raith, Matthias Deitermann, Tobias Pankert, Jianzhang Li, Ali Modabber, Frank Hölzle, Frank Hildebrand, and Jörg Eschweiler. Multi-label segmentation of carpal bones in mri using expansion transfer learning.Physics in Medicine and Biology, 2025

    work page 2025

  57. [57]

    Ra- diocarpal and midcarpal instability in rheumatoid patients: a systematic review.The Open Orthopaedics Journal, 9:246, 2015

    Eric EJ Raven, Michel PJ van den Bekerom, Annechien Beumer, and C Niek van Dijk. Ra- diocarpal and midcarpal instability in rheumatoid patients: a systematic review.The Open Orthopaedics Journal, 9:246, 2015

    work page 2015

  58. [58]

    U-net: Convolutional networks for biomedical image segmentation

    Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. InMedical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pages 234–241. Springer, 2015

    work page 2015

  59. [59]

    Deep learning-based classification of erosion, synovitis and osteitis in hand mri of patients with inflammatory arthritis.RMD open, 10(2):e004273, 2024

    Maja Schlereth, Melek Yalcin Mutlu, Jonas Utz, Sara Bayat, Tobias Heimann, Jingna Qiu, Chris Ehring, Chang Liu, Michael Uder, Arnd Kleyer, et al. Deep learning-based classification of erosion, synovitis and osteitis in hand mri of patients with inflammatory arthritis.RMD open, 10(2):e004273, 2024

    work page 2024

  60. [60]

    Machine learning for opportunistic screening for osteoporosis from ct scans of the wrist and forearm.Diagnostics, 12(3):691, 2022

    Ronnie Sebro and Cynthia De la Garza-Ramos. Machine learning for opportunistic screening for osteoporosis from ct scans of the wrist and forearm.Diagnostics, 12(3):691, 2022

    work page 2022

  61. [61]

    Rheumatoid arthritis in review: Clinical, anatomical, cellular and molecular points of view.Clinical Anatomy, 31(2):216–223, 2018

    Kassem Sharif, Alaa Sharif, Fareed Jumah, Rod Oskouian, and R Shane Tubbs. Rheumatoid arthritis in review: Clinical, anatomical, cellular and molecular points of view.Clinical Anatomy, 31(2):216–223, 2018

    work page 2018

  62. [62]

    A systematic analysis of performance measures for classification tasks.Information processing & management, 45(4):427–437, 2009

    Marina Sokolova and Guy Lapalme. A systematic analysis of performance measures for classification tasks.Information processing & management, 45(4):427–437, 2009

    work page 2009

  63. [63]

    Deep learning in rheumatological image interpretation.Nature Reviews Rheumatology, 20(3):182–195, 2024

    Berend C Stoel, Marius Staring, Monique Reijnierse, and Annette HM van der Helm-van Mil. Deep learning in rheumatological image interpretation.Nature Reviews Rheumatology, 20(3):182–195, 2024

    work page 2024

  64. [64]

    A crowdsourcing approach to develop machine learning models to quantify radiographic joint damage in rheumatoid arthritis.JAMA network open, 5(8):e2227423–e2227423, 2022

    Dongmei Sun, Thanh M Nguyen, Robert J Allaway, Jelai Wang, Verena Chung, Thomas V Yu, Michael Mason, Isaac Dimitrovsky, Lars Ericson, Hongyang Li, et al. A crowdsourcing approach to develop machine learning models to quantify radiographic joint damage in rheumatoid arthritis.JAMA network open, 5(8):e2227423–e2227423, 2022

    work page 2022

  65. [65]

    Metrics for evaluating 3d medical image segmentation: analysis, selection, and tool.BMC medical imaging, 15:1–28, 2015

    Abdel Aziz Taha and Allan Hanbury. Metrics for evaluating 3d medical image segmentation: analysis, selection, and tool.BMC medical imaging, 15:1–28, 2015

    work page 2015

  66. [66]

    Rheumatoid arthritis of the hand and wrist: comparison of three imaging techniques.American Journal of Roentgenology, 182(4):937–943, 2004

    Bachir Taouli, Souhil Zaim, Charles G Peterfy, John A Lynch, Alexander Stork, Ali Guermazi, Bo Fan, Kenneth H Fye, and Harry K Genant. Rheumatoid arthritis of the hand and wrist: comparison of three imaging techniques.American Journal of Roentgenology, 182(4):937–943, 2004. 14

    work page 2004

  67. [67]

    Automatic segmentation and labelling of wrist bones in four-dimensional computed tomography datasets via deep learning

    EHS Teule, N Lessmann, EPA van der Heijden, and S Hummelink. Automatic segmentation and labelling of wrist bones in four-dimensional computed tomography datasets via deep learning. Journal of Hand Surgery (European Volume), 49(4):507–509, 2024

    work page 2024

  68. [68]

    Detection of rheumatoid arthritis from hand radiographs using a convolutional neural network.Clinical rheumatology, 39:969–974, 2020

    Kemal Üreten, Hasan Erbay, and Hadi Hakan Mara¸ s. Detection of rheumatoid arthritis from hand radiographs using a convolutional neural network.Clinical rheumatology, 39:969–974, 2020

    work page 2020

  69. [69]

    How to read radiographs according to the sharp/van der heijde method

    DMFM Van der Heijde. How to read radiographs according to the sharp/van der heijde method. The Journal of rheumatology, 27(1):261–263, 2000

    work page 2000

  70. [70]

    Reliability and sensitivity to change of a simplification of the sharp/van der heijde radiological assessment in rheumatoid arthritis.Rheumatology, 38(10):941–947, 1999

    DMFM Van der Heijde, T Dankert, F Nieman, R Rau, and M Boers. Reliability and sensitivity to change of a simplification of the sharp/van der heijde radiological assessment in rheumatoid arthritis.Rheumatology, 38(10):941–947, 1999

    work page 1999

  71. [71]

    Deep learning-based computer-aided diagnosis of rheumatoid arthritis with hand x-ray images conforming to modified total sharp/van der heijde score.Biomedicines, 10(6):1355, 2022

    Hao-Jan Wang, Chi-Ping Su, Chien-Chih Lai, Wun-Rong Chen, Chi Chen, Liang-Ying Ho, Woei-Chyn Chu, and Chung-Yueh Lien. Deep learning-based computer-aided diagnosis of rheumatoid arthritis with hand x-ray images conforming to modified total sharp/van der heijde score.Biomedicines, 10(6):1355, 2022

    work page 2022

  72. [72]

    Bls-gan: A deep layer separation framework for eliminating bone overlap in conventional radiographs

    Haolin Wang, Yafei Ou, Prasoon Ambalathankandy, Gen Ota, Pengyu Dai, Masayuki Ikebe, Kenji Suzuki, and Tamotsu Kamishima. Bls-gan: A deep layer separation framework for eliminating bone overlap in conventional radiographs. InProceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 7674–7681, 2025

    work page 2025

  73. [73]

    Layer separation: Adjustable joint space width images synthesis in conventional radiography.arXiv preprint arXiv:2502.01972, 2025

    Haolin Wang, Yafei Ou, Prasoon Ambalathankandy, Gen Ota, Pengyu Dai, Masayuki Ikebe, Kenji Suzuki, and Tamotsu Kamishima. Layer separation: Adjustable joint space width images synthesis in conventional radiography.arXiv preprint arXiv:2502.01972, 2025

    work page arXiv 2025

  74. [74]

    A deep registration method for accurate quantification of joint space narrowing progression in rheumatoid arthritis

    Haolin Wang, Yafei Ou, Wanxuan Fang, Prasoon Ambalathankandy, Naoto Goto, Gen Ota, Taichi Okino, Jun Fukae, Kenneth Sutherland, Masayuki Ikebe, et al. A deep registration method for accurate quantification of joint space narrowing progression in rheumatoid arthritis. Computerized Medical Imaging and Graphics, 108:102273, 2023

    work page 2023

  75. [75]

    Segformer: Simple and efficient design for semantic segmentation with transformers.Advances in neural information processing systems, 34:12077–12090, 2021

    Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M Alvarez, and Ping Luo. Segformer: Simple and efficient design for semantic segmentation with transformers.Advances in neural information processing systems, 34:12077–12090, 2021

    work page 2021

  76. [76]

    Deep learning approach for automatic segmentation of ulna and radius in dual-energy x-ray imaging.Insights into Imaging, 12:1–9, 2021

    Fan Yang, Xin Weng, Yuehong Miao, Yuhui Wu, Hong Xie, and Pinggui Lei. Deep learning approach for automatic segmentation of ulna and radius in dual-energy x-ray imaging.Insights into Imaging, 12:1–9, 2021

    work page 2021

  77. [77]

    A radiograph dataset for the classification, localization, and segmentation of primary bone tumors.Scientific Data, 12(1):88, 2025

    Shunhan Yao, Yuanxiang Huang, Xiaoyu Wang, Yiwen Zhang, Ian Costa Paixao, Zhikang Wang, Charla Lu Chai, Hongtao Wang, Dinggui Lu, Geoffrey I Webb, et al. A radiograph dataset for the classification, localization, and segmentation of primary bone tumors.Scientific Data, 12(1):88, 2025

    work page 2025

  78. [78]

    Automated quantification of wrist bone marrow oedema, pre-and post-treatment, in early rheumatoid arthritis.Rheumatology Advances in Practice, 8(3):rkae073, 2024

    Chungwun Yiu, James Francis Griffith, Fan Xiao, Lin Shi, Bingjing Zhou, Su Wu, and Lai-Shan Tam. Automated quantification of wrist bone marrow oedema, pre-and post-treatment, in early rheumatoid arthritis.Rheumatology Advances in Practice, 8(3):rkae073, 2024

    work page 2024

  79. [79]

    Medmamba: Vision mamba for medical image classification

    Yubiao Yue and Zhenzhang Li. Medmamba: Vision mamba for medical image classification. arXiv preprint arXiv:2403.03849, 2024

    work page arXiv 2024

  80. [80]

    Pyramid scene parsing network

    Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, and Jiaya Jia. Pyramid scene parsing network. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 2881–2890, 2017

    work page 2017

Showing first 80 references.