OMSF2: optimizing multi-scale feature fusion learning for pneumoconiosis staging diagnosis through data specificity augmentation
Abstract Diagnosing pneumoconiosis is challenging because the lesions are not easily visible on chest X-rays, and the images often lack clear details. Existing deep detection models utilize Feature Pyramid Networks (FPNs) to identify objects at different scales. However, they struggle with insuffici...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-12-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01729-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571186493521920 |
|---|---|
| author | Xueting Ren Surong Chu Guohua Ji Zijuan Zhao Juanjuan Zhao Yan Qiang Yangyang Wei Yan Wang |
| author_facet | Xueting Ren Surong Chu Guohua Ji Zijuan Zhao Juanjuan Zhao Yan Qiang Yangyang Wei Yan Wang |
| author_sort | Xueting Ren |
| collection | DOAJ |
| description | Abstract Diagnosing pneumoconiosis is challenging because the lesions are not easily visible on chest X-rays, and the images often lack clear details. Existing deep detection models utilize Feature Pyramid Networks (FPNs) to identify objects at different scales. However, they struggle with insufficient perception of small targets and gradient inconsistency in medical image detection tasks, hindering the full utilization of multi-scale features. To address these issues, we propose an Optimized Multi-Scale Feature Fusion learning framework, OMSF2, which includes the following components: (1) Data specificity augmentation module is introduced to capture intrinsic data representations and introduce diversity by learning morphological variations and lesion locations. (2) Multi-scale feature learning module is utilized that refines micro-feature localization guided by heatmaps, enabling full extraction of multi-directional features of subtle diffuse targets. (3) Multi-scale feature fusion module is employed that facilitates the fusion of high-level and low-level features to better understand subtle differences between disease stages. Notably, this paper innovatively proposes a method for fine learning of low-resolution micro-features in pneumoconiosis, addressing the issue of maintaining cross-layer gradient consistency under multi-scale feature fusion. We established an enhanced pneumoconiosis X-ray dataset to optimize the lesion detection capability of the OMSF2 model. We also introduced an external dataset to evaluate other chest X-rays with complex lesions. On the AP-50 and R-50 evaluation metrics, OMSF2 improved by 3.25% and 3.31% on the internal dataset, and by 2.28% and 0.24% on the external dataset, respectively. Experimental results show that OMSF2 achieves significantly better performance than state-of-the-art baselines in medical image detection tasks. |
| format | Article |
| id | doaj-art-9da4e13f06814dfda5a50888518984cd |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-9da4e13f06814dfda5a50888518984cd2025-02-02T12:48:53ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-12-0111112310.1007/s40747-024-01729-0OMSF2: optimizing multi-scale feature fusion learning for pneumoconiosis staging diagnosis through data specificity augmentationXueting Ren0Surong Chu1Guohua Ji2Zijuan Zhao3Juanjuan Zhao4Yan Qiang5Yangyang Wei6Yan Wang7College of Computer Science and Technology (College of Data Science), Taiyuan University of TechnologyCollege of Computer Science and Technology (College of Data Science), Taiyuan University of TechnologyCollege of Computer Science and Technology (College of Data Science), Taiyuan University of TechnologySchool of Software, Taiyuan University of TechnologyCollege of Computer Science and Technology (College of Data Science), Taiyuan University of TechnologyCollege of Computer Science and Technology (College of Data Science), Taiyuan University of TechnologyFirst Hospital of Shanxi Medical UniversityJincheng HospitalAbstract Diagnosing pneumoconiosis is challenging because the lesions are not easily visible on chest X-rays, and the images often lack clear details. Existing deep detection models utilize Feature Pyramid Networks (FPNs) to identify objects at different scales. However, they struggle with insufficient perception of small targets and gradient inconsistency in medical image detection tasks, hindering the full utilization of multi-scale features. To address these issues, we propose an Optimized Multi-Scale Feature Fusion learning framework, OMSF2, which includes the following components: (1) Data specificity augmentation module is introduced to capture intrinsic data representations and introduce diversity by learning morphological variations and lesion locations. (2) Multi-scale feature learning module is utilized that refines micro-feature localization guided by heatmaps, enabling full extraction of multi-directional features of subtle diffuse targets. (3) Multi-scale feature fusion module is employed that facilitates the fusion of high-level and low-level features to better understand subtle differences between disease stages. Notably, this paper innovatively proposes a method for fine learning of low-resolution micro-features in pneumoconiosis, addressing the issue of maintaining cross-layer gradient consistency under multi-scale feature fusion. We established an enhanced pneumoconiosis X-ray dataset to optimize the lesion detection capability of the OMSF2 model. We also introduced an external dataset to evaluate other chest X-rays with complex lesions. On the AP-50 and R-50 evaluation metrics, OMSF2 improved by 3.25% and 3.31% on the internal dataset, and by 2.28% and 0.24% on the external dataset, respectively. Experimental results show that OMSF2 achieves significantly better performance than state-of-the-art baselines in medical image detection tasks.https://doi.org/10.1007/s40747-024-01729-0Multi-scale feature fusion learningData-specific augmentationDense pooling pyramid networkMicro-feature localizationPneumoconiosis staging diagnosis |
| spellingShingle | Xueting Ren Surong Chu Guohua Ji Zijuan Zhao Juanjuan Zhao Yan Qiang Yangyang Wei Yan Wang OMSF2: optimizing multi-scale feature fusion learning for pneumoconiosis staging diagnosis through data specificity augmentation Complex & Intelligent Systems Multi-scale feature fusion learning Data-specific augmentation Dense pooling pyramid network Micro-feature localization Pneumoconiosis staging diagnosis |
| title | OMSF2: optimizing multi-scale feature fusion learning for pneumoconiosis staging diagnosis through data specificity augmentation |
| title_full | OMSF2: optimizing multi-scale feature fusion learning for pneumoconiosis staging diagnosis through data specificity augmentation |
| title_fullStr | OMSF2: optimizing multi-scale feature fusion learning for pneumoconiosis staging diagnosis through data specificity augmentation |
| title_full_unstemmed | OMSF2: optimizing multi-scale feature fusion learning for pneumoconiosis staging diagnosis through data specificity augmentation |
| title_short | OMSF2: optimizing multi-scale feature fusion learning for pneumoconiosis staging diagnosis through data specificity augmentation |
| title_sort | omsf2 optimizing multi scale feature fusion learning for pneumoconiosis staging diagnosis through data specificity augmentation |
| topic | Multi-scale feature fusion learning Data-specific augmentation Dense pooling pyramid network Micro-feature localization Pneumoconiosis staging diagnosis |
| url | https://doi.org/10.1007/s40747-024-01729-0 |
| work_keys_str_mv | AT xuetingren omsf2optimizingmultiscalefeaturefusionlearningforpneumoconiosisstagingdiagnosisthroughdataspecificityaugmentation AT surongchu omsf2optimizingmultiscalefeaturefusionlearningforpneumoconiosisstagingdiagnosisthroughdataspecificityaugmentation AT guohuaji omsf2optimizingmultiscalefeaturefusionlearningforpneumoconiosisstagingdiagnosisthroughdataspecificityaugmentation AT zijuanzhao omsf2optimizingmultiscalefeaturefusionlearningforpneumoconiosisstagingdiagnosisthroughdataspecificityaugmentation AT juanjuanzhao omsf2optimizingmultiscalefeaturefusionlearningforpneumoconiosisstagingdiagnosisthroughdataspecificityaugmentation AT yanqiang omsf2optimizingmultiscalefeaturefusionlearningforpneumoconiosisstagingdiagnosisthroughdataspecificityaugmentation AT yangyangwei omsf2optimizingmultiscalefeaturefusionlearningforpneumoconiosisstagingdiagnosisthroughdataspecificityaugmentation AT yanwang omsf2optimizingmultiscalefeaturefusionlearningforpneumoconiosisstagingdiagnosisthroughdataspecificityaugmentation |