Intro
Preface
Organization
Contents - Part VI
Computer-Aided Diagnosis II
Mining Negative Temporal Contexts for False Positive Suppression in Real-Time Ultrasound Lesion Detection
1 Introduction
2 Related Works
3 Method
3.1 Basic Real-Time Detector
3.2 Negative Temporal Context Aggregation
3.3 UltraDet for Real-Time Lesion Detection
4 Experiments
4.1 Dateset
4.2 Evaluation Metrics
4.3 Implementation Details
4.4 Main Results
4.5 Ablation Study
5 Conclusion
References

Combat Long-Tails in Medical Classification with Relation-Aware Consistency and Virtual Features Compensation
1 Introduction
2 Methodology
2.1 Multi-view Relation-Aware Consistency
2.2 Virtual Features Compensation
3 Experiments
3.1 Datasets
3.2 Implementation Details
3.3 Comparison on ISIC-2019-LT Dataset
3.4 Comparison on ISIC-Archive-LT Dataset
4 Conclusion
References
Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering
1 Introduction
2 Methodology
3 Experiments
4 Conclusion
References

Joint Segmentation and Sub-pixel Localization in Structured Light Laryngoscopy
1 Introduction
2 Related Work
3 Method
4 Evaluation
5 Conclusion
References
A Style Transfer-Based Augmentation Framework for Improving Segmentation and Classification Performance Across Different Sources in Ultrasound Images
1 Introduction
2 Methods
2.1 Mixed Style Augmentation (MixStyleAug)
2.2 Network Architecture and Feature Augmentation (FeatAug)
2.3 Mask-Based Style Augmentation (MaskAug)
2.4 Loss Function and Implementation Details
3 Experimental Results and Discussion

4 Conclusion
References
HC-Net: Hybrid Classification Network for Automatic Periodontal Disease Diagnosis
1 Introduction
2 Method
2.1 Task Formulation and Method Overview
2.2 Tooth-Level Classification
2.3 Patient-Level Classification
2.4 Learnable Adaptive Noisy-OR Gate
3 Experiments
3.1 Dataset and Evaluation Metrics
3.2 Comparison with Other Methods
3.3 Ablation Studies
3.4 Implementation Details
4 Conclusion
References
SegNetr: Rethinking the Local-Global Interactions and Skip Connections in U-Shaped Networks
1 Introduction
2 Method

2.1 SegNetr Block
2.2 Information Retention Skip Connection
3 Experiments and Discussion
3.1 Comparison with State-of-the-Arts
3.2 Ablation Study
4 Conclusion
References
Gradient and Feature Conformity-Steered Medical Image Classification with Noisy Labels
1 Introduction
2 Method
2.1 Gradient and Feature Conformity-Based Clean Data Selection
2.2 Sample Reliability-Based Mixup (SRMix)
3 Experiments
3.1 Datasets and Implementation Details
3.2 Experimental Results
4 Conclusion
References