Transferability of Non-contrastive Self-supervised Learning to Chronic Wound Image Recognition
J.M. Akay, W. Schenck, in: M. Wand, K. Malinovská, J. Schmidhuber, I.V. Tetko (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2024. 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part VIII, Springer Nature Switzerland, Cham, 2024, pp. 427–444.
Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Konferenzbeitrag
| Veröffentlicht
| Englisch
Autor*in
Akay, Julien Marteen;
Schenck, Wolfram



Herausgeber*in
Wand, Michael;
Malinovská, Kristína;
Schmidhuber, Jürgen;
Tetko, Igor V.
Forschungsgruppe
CareTech OWL - Zentrum für Gesundheit, Soziales und Technologie
Abstract
Chronic wounds pose significant challenges in medical practice, necessitating effective treatment approaches and reduced burden on healthcare staff. Computer-aided diagnosis (CAD) systems offer promising solutions to enhance treatment outcomes. However, the effective processing of wound images remains a challenge. Deep learning models, particularly convolutional neural networks (CNNs), have demonstrated proficiency in this task, typically relying on extensive labeled data for optimal generalization. Given the limited availability of medical images, a common approach involves pretraining models on data-rich tasks to transfer that knowledge as a prior to the main task, compensating for the lack of labeled wound images. In this study, we investigate the transferability of CNNs pretrained with non-contrastive self-supervised learning (SSL) to enhance generalization in chronic wound image recognition. Our findings indicate that leveraging non-contrastive SSL methods in conjunction with ConvNeXt models yields superior performance compared to other work’s multimodal models that additionally benefit from affected body part location data. Furthermore, analysis using Grad-CAM reveals that ConvNeXt models pretrained with VICRegL exhibit improved focus on relevant wound properties compared to the conventional approach of ResNet-50 models pretrained with ImageNet classification. These results underscore the crucial role of the appropriate combination of pretraining method and model architecture in effectively addressing limited wound data settings. Among the various approaches explored, ConvNeXt-XL pretrained by VICRegL emerges as a reliable and stable method. This study makes a novel contribution by demonstrating the effectiveness of latest non-contrastive SSL-based transfer learning in advancing the field of chronic wound image recognition.
Erscheinungsjahr
Titel des Konferenzbandes
Artificial Neural Networks and Machine Learning – ICANN 2024. 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part VIII
Seite
427-444
Konferenz
33rd International Conference on Artificial Neural Networks
Konferenzort
Lugano, Switzerland
Konferenzdatum
2024-09-17 – 2024-09-20
ISBN
ISSN
eISSN
FH-PUB-ID
Zitieren
Akay, Julien Marteen ; Schenck, Wolfram: Transferability of Non-contrastive Self-supervised Learning to Chronic Wound Image Recognition. In: Wand, M. ; Malinovská, K. ; Schmidhuber, J. ; Tetko, I. V. (Hrsg.): Artificial Neural Networks and Machine Learning – ICANN 2024. 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part VIII, Lecture Notes in Computer Science. Cham : Springer Nature Switzerland, 2024, S. 427–444
Akay JM, Schenck W. Transferability of Non-contrastive Self-supervised Learning to Chronic Wound Image Recognition. In: Wand M, Malinovská K, Schmidhuber J, Tetko IV, eds. Artificial Neural Networks and Machine Learning – ICANN 2024. 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part VIII. Lecture Notes in Computer Science. Cham: Springer Nature Switzerland; 2024:427-444. doi:10.1007/978-3-031-72353-7_31
Akay, J. M., & Schenck, W. (2024). Transferability of Non-contrastive Self-supervised Learning to Chronic Wound Image Recognition. In M. Wand, K. Malinovská, J. Schmidhuber, & I. V. Tetko (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2024. 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part VIII (pp. 427–444). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-72353-7_31
@inproceedings{Akay_Schenck_2024, place={Cham}, series={Lecture Notes in Computer Science}, title={Transferability of Non-contrastive Self-supervised Learning to Chronic Wound Image Recognition}, DOI={10.1007/978-3-031-72353-7_31}, booktitle={Artificial Neural Networks and Machine Learning – ICANN 2024. 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part VIII}, publisher={Springer Nature Switzerland}, author={Akay, Julien Marteen and Schenck, Wolfram}, editor={Wand, Michael and Malinovská, Kristína and Schmidhuber, Jürgen and Tetko, Igor V.Editors}, year={2024}, pages={427–444}, collection={Lecture Notes in Computer Science} }
Akay, Julien Marteen, and Wolfram Schenck. “Transferability of Non-Contrastive Self-Supervised Learning to Chronic Wound Image Recognition.” In Artificial Neural Networks and Machine Learning – ICANN 2024. 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part VIII, edited by Michael Wand, Kristína Malinovská, Jürgen Schmidhuber, and Igor V. Tetko, 427–44. Lecture Notes in Computer Science. Cham: Springer Nature Switzerland, 2024. https://doi.org/10.1007/978-3-031-72353-7_31.
J. M. Akay and W. Schenck, “Transferability of Non-contrastive Self-supervised Learning to Chronic Wound Image Recognition,” in Artificial Neural Networks and Machine Learning – ICANN 2024. 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part VIII, Lugano, Switzerland, 2024, pp. 427–444.
Akay, Julien Marteen, and Wolfram Schenck. “Transferability of Non-Contrastive Self-Supervised Learning to Chronic Wound Image Recognition.” Artificial Neural Networks and Machine Learning – ICANN 2024. 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part VIII, edited by Michael Wand et al., Springer Nature Switzerland, 2024, pp. 427–44, doi:10.1007/978-3-031-72353-7_31.