Top

International Journal of Computer Assisted Radiology and Surgery

Published in:

Open Access 02-02-2023 | Original Article

Multiclass datasets expand neural network utility: an example on ankle radiographs

Authors: Suam Kim, Philipp Rebmann, Phuong Hien Tran, Elias Kellner, Marco Reisert, David Steybe, Jörg Bayer, Fabian Bamberg, Elmar Kotter, Maximilian Russe

Published in: International Journal of Computer Assisted Radiology and Surgery | Issue 5/2023

Abstract

Purpose

Artificial intelligence in computer vision has been increasingly adapted in clinical application since the implementation of neural networks, potentially providing incremental information beyond the mere detection of pathology. As its algorithmic approach propagates input variation, neural networks could be used to identify and evaluate relevant image features. In this study, we introduce a basic dataset structure and demonstrate a pertaining use case.

Methods

A multidimensional classification of ankle x-rays (n = 1493) rating a variety of features including fracture certainty was used to confirm its usability for separating input variations. We trained a customized neural network on the task of fracture detection using a state-of-the-art preprocessing and training protocol. By grouping the radiographs into subsets according to their image features, the influence of selected features on model performance was evaluated via selective training.

Results

The models trained on our dataset outperformed most comparable models of current literature with an ROC AUC of 0.943. Excluding ankle x-rays with signs of surgery improved fracture classification performance (AUC 0.955), while limiting the training set to only healthy ankles with and without fracture had no consistent effect.

Conclusion

Using multiclass datasets and comparing model performance, we were able to demonstrate signs of surgery as a confounding factor, which, following elimination, improved our model. Also eliminating pathologies other than fracture in contrast had no effect on model performance, suggesting a beneficial influence of feature variability for robust model training. Thus, multiclass datasets allow for evaluation of distinct image features, deepening our understanding of pathology imaging.

Available only for authorised users

Oakden-Rayner L, Gale W, Bonham TA, Lungren MP, Carneiro G, Bradley AP, Palmer LJ (2022) Validation and algorithmic audit of a deep learning system for the detection of proximal femoral fractures in patients in the emergency department: a diagnostic accuracy study. Lancet Digit. Health 4:e351–e358. https://doi.org/10.1016/S2589-7500(22)00004-8CrossRefPubMed

Gan K, Xu D, Lin Y, Shen Y, Zhang T, Hu K, Zhou K, Bi M, Pan L, Wu W, Liu Y (2019) Artificial intelligence detection of distal radius fractures: a comparison between the convolutional neural network and professional assessments. Acta Orthop 90(4):394–400. https://doi.org/10.1080/17453674.2019.1600125CrossRefPubMedPubMedCentral

Chung SW, Han SS, Lee JW, Oh KS, Kim NR, Yoon JP, Kim JY, Moon SH, Kwon J, Lee HJ, Noh YM, Kim Y (2018) Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop 89(4):468–473. https://doi.org/10.1080/17453674.2018.1453714CrossRefPubMedPubMedCentral

Wu JT, Wong KCL, Gur Y, Ansari N, Karargyris A, Sharma A, Morris M, Saboury B, Ahmad H, Boyko O, Syed A, Jadhav A, Wang H, Pillai A, Kashyap S, Moradi M, Syeda-Mahmood T (2020) Comparison of chest radiograph interpretations by artificial intelligence algorithm vs radiology residents. JAMA Netw Open 3(10):e2022779. https://doi.org/10.1001/jamanetworkopen.2020.22779CrossRefPubMedPubMedCentral

Kuo RYL, Harrison C, Curran TA, Jones B, Freethy A, Cussons D, Stewart M, Collins GS, Furniss D (2022) Artificial intelligence in fracture detection: a systematic review and meta-analysis. Radiology. https://doi.org/10.1148/radiol.211785CrossRefPubMed

Duron L, Ducarouge A, Gillibert A, Lainé J, Allouche C, Cherel N, Zhang Z, Nitche N, Lacave E, Pourchot A, Felter A, Lassalle L, Regnard NE, Feydy A (2021) Assessment of an AI Aid in detection of adult appendicular skeletal fractures by emergency physicians and radiologists: a multicenter cross-sectional diagnostic study. Radiology 300(1):120–129. https://doi.org/10.1148/radiol.2021203886CrossRefPubMed

Lindsey R, Daluiski A, Chopra S, Lachapelle A, Mozer M, Sicular S, Hanel D, Gardner M, Gupta A, Hotchkiss R, Potter H (2018) Deep neural network improves fracture detection by clinicians. Proc Natl Acad Sci U S A 115(45):11591–11596. https://doi.org/10.1073/pnas.1806905115CrossRefPubMedPubMedCentral

Russakovsky O et al (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252. https://doi.org/10.1007/s11263-015-0816-yCrossRef

“Nora - The medical imaging platform.” https://www.nora-imaging.com/ (accessed Oct. 28, 2021).

10.

Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, Miami, FL, 2009, pp. 248–255. doi: https://doi.org/10.1109/CVPR.2009.5206848

11.

Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the Inception Architecture for Computer Vision. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, pp. 2818–2826. doi: https://doi.org/10.1109/CVPR.2016.308.

12.

Chollet F (2015) “InceptionV3,” https://keras.io, 2015. https://keras.io/api/applications/inceptionv3/ (accessed Mar. 04, 2022)

13.

Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, Kudlur M, Levenberg J, Monga R, Moore S, Murray DG, Steiner B, Tucker P, Vasudevan V, Warden P, Wicke M, Yu Y, Zheng X (2016) TensorFlow: A system for large-scale machine learning. In: Proceedings of the 12th USENIX conference on operating systems design and implementation, USA, 2016, pp. 265–283

14.

Elsoe R, Ostgaard SE, Larsen P (2018) Population-based epidemiology of 9767 ankle fractures. Foot Ankle Surg 24(1):34–39. https://doi.org/10.1016/j.fas.2016.11.002CrossRefPubMed

15.

Juto H, Nilsson H, Morberg P (2018) Epidemiology of adult ankle fractures: 1756 cases identified in Norrbotten County during 2009–2013 and classified according to AO/OTA. BMC Musculoskelet Disord 19(1):441. https://doi.org/10.1186/s12891-018-2326-xCrossRefPubMedPubMedCentral

16.

Kim J-H, Mo Y-C, Choi S-M, Hyun Y, Lee JW (2021) Detecting Ankle fractures in plain radiographs using deep learning with accurately labeled datasets aided by computed tomography: a retrospective observational study. Appl Sci 11(19):8791. https://doi.org/10.3390/app11198791CrossRef

17.

Kitamura G, Chung CY, Moore BE (2019) Ankle fracture detection utilizing a convolutional neural network ensemble implemented with a small sample, De Novo training, and multiview incorporation. J Digit Imaging 32(4):672–677. https://doi.org/10.1007/s10278-018-0167-7CrossRefPubMedPubMedCentral

18.

Wu M, Sun H, Sun Z, Guo X, Duan L, Tan Y, Cui R (2021) A machine learning-based method for automatic diagnosis of ankle fracture using X-ray images. Int J Imaging Syst Technol 32:831–842. https://doi.org/10.1002/ima.22665CrossRef

19.

Jones RM, Sharma A, Hotchkiss R, Sperling JW, Hamburger J, Ledig C, O'Toole R, Gardner M, Venkatesh S, Roberts MM, Sauvestre R, Shatkhin M, Gupta A, Chopra S, Kumaravel M, Daluiski A, Plogger W, Nascone J, Potter HG, Lindsey RV (2020) Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs. Npj Digit Med 3(1):144. https://doi.org/10.1038/s41746-020-00352-wCrossRefPubMedPubMedCentral

Title: Multiclass datasets expand neural network utility: an example on ankle radiographs
Authors: Suam Kim
Philipp Rebmann
Phuong Hien Tran
Elias Kellner
Marco Reisert
David Steybe
Jörg Bayer
Fabian Bamberg
Elmar Kotter
Maximilian Russe
Publication date: 02-02-2023
Publisher: Springer International Publishing
Published in: International Journal of Computer Assisted Radiology and Surgery / Issue 5/2023
Print ISSN: 1861-6410
Electronic ISSN: 1861-6429
DOI: https://doi.org/10.1007/s11548-023-02839-9

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Multiclass datasets expand neural network utility: an example on ankle radiographs

Abstract

Purpose

Methods

Results

Conclusion

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 5/2023

EndoTrainer: a novel hybrid training platform for endoscopic surgery

Development of panorama vision ring for thoracoscopy

Lesion-preserving unpaired image-to-image translation between MRI and CT from ischemic stroke patients

Keyword-augmented and semi-automatic generation of FESS reports: a proof-of-concept study

Correction to: Gaussian affinity and GIoU-based loss for perforation detection and localization from colonoscopy videos

Surgery assistance system for continuous resection of brain tumors-proposal of continuous tumor resection forceps, tumor cell separation, dehydration, and isolation mechanism