Saved in:
Bibliographic Details
Main Authors: Sekhri, Aymen, Tliba, Marouane, Kerkouri, Mohamed Amine, Nasser, Yassine, Chetouani, Aladine, Bruno, Alessandro, Jennane, Rachid
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.09947
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929278023630848
author Sekhri, Aymen
Tliba, Marouane
Kerkouri, Mohamed Amine
Nasser, Yassine
Chetouani, Aladine
Bruno, Alessandro
Jennane, Rachid
author_facet Sekhri, Aymen
Tliba, Marouane
Kerkouri, Mohamed Amine
Nasser, Yassine
Chetouani, Aladine
Bruno, Alessandro
Jennane, Rachid
contents Conventional imaging diagnostics frequently encounter bottlenecks due to manual inspection, which can lead to delays and inconsistencies. Although deep learning offers a pathway to automation and enhanced accuracy, foundational models in computer vision often emphasize global context at the expense of local details, which are vital for medical imaging diagnostics. To address this, we harness the Swin Transformer's capacity to discern extended spatial dependencies within images through the hierarchical framework. Our novel contribution lies in refining local feature representations, orienting them specifically toward the final distribution of the classifier. This method ensures that local features are not only preserved but are also enriched with task-specific information, enhancing their relevance and detail at every hierarchical level. By implementing this strategy, our model demonstrates significant robustness and precision, as evidenced by extensive validation of two established benchmarks for Knee OsteoArthritis (KOA) grade classification. These results highlight our approach's effectiveness and its promising implications for the future of medical imaging diagnostics. Our implementation is available on https://github.com/mtliba/KOA_NLCS2024
format Preprint
id arxiv_https___arxiv_org_abs_2403_09947
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Shifting Focus: From Global Semantics to Local Prominent Features in Swin-Transformer for Knee Osteoarthritis Severity Assessment
Sekhri, Aymen
Tliba, Marouane
Kerkouri, Mohamed Amine
Nasser, Yassine
Chetouani, Aladine
Bruno, Alessandro
Jennane, Rachid
Computer Vision and Pattern Recognition
Conventional imaging diagnostics frequently encounter bottlenecks due to manual inspection, which can lead to delays and inconsistencies. Although deep learning offers a pathway to automation and enhanced accuracy, foundational models in computer vision often emphasize global context at the expense of local details, which are vital for medical imaging diagnostics. To address this, we harness the Swin Transformer's capacity to discern extended spatial dependencies within images through the hierarchical framework. Our novel contribution lies in refining local feature representations, orienting them specifically toward the final distribution of the classifier. This method ensures that local features are not only preserved but are also enriched with task-specific information, enhancing their relevance and detail at every hierarchical level. By implementing this strategy, our model demonstrates significant robustness and precision, as evidenced by extensive validation of two established benchmarks for Knee OsteoArthritis (KOA) grade classification. These results highlight our approach's effectiveness and its promising implications for the future of medical imaging diagnostics. Our implementation is available on https://github.com/mtliba/KOA_NLCS2024
title Shifting Focus: From Global Semantics to Local Prominent Features in Swin-Transformer for Knee Osteoarthritis Severity Assessment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.09947