T2ID-CAS: Diffusion Model and Class Aware Sampling to Mitigate Class Imbalance in Neck Ultrasound Anatomical Landmark Detection

2025/04/29 by Manikanta Varaganti, Amulya Vankayalapati, Varaganti, Manikanta +7 · 1 citation
Medicine · #Airway Management and Intubation Techniques #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Tracheal and airway disorders #Voice and Speech Disorders

paper · pdf · doi:10.48550/arxiv.2504.21231

openalex publication_date 2025/04/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Neck ultrasound (US) plays a vital role in airway management by providing non-invasive, real-time imaging that enables rapid and precise interventions. Deep learning-based anatomical landmark detection in neck US can further facilitate procedural efficiency. However, class imbalance within datasets, where key structures like tracheal rings and vocal folds are underrepresented, presents significant challenges for object detection models. To address this, we propose T2ID-CAS, a hybrid approach that combines a text-to-image latent diffusion model with class-aware sampling to generate high-quality synthetic samples for underrepresented classes. This approach, rarely explored in the ultrasound domain, improves the representation of minority classes. Experimental results using YOLOv9 for anatomical landmark detection in neck US demonstrated that T2ID-CAS achieved a mean Average Precision of 88.2, significantly surpassing the baseline of 66. This highlights its potential as a computationally efficient and scalable solution for mitigating class imbalance in AI-assisted ultrasound-guided interventions.

Citations

• YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
• MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images
• SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems
• SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
• CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning
• High-Resolution Image Synthesis with Latent Diffusion Models
• High-Resolution Image Synthesis with Latent Diffusion Models
• Score-based diffusion models for accelerated MRI
• LoRA: Low-Rank Adaptation of Large Language Models
• Learning Transferable Visual Models From Natural Language Supervision
• Denoising Diffusion Probabilistic Models
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Imbalance Problems in Object Detection: A Review
• LVIS: A Dataset for Large Vocabulary Instance Segmentation
• mixup: Beyond Empirical Risk Minimization
• Improved Techniques for Training GANs
• Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
• SSD: Single Shot MultiBox Detector
• You Only Look Once: Unified, Real-Time Object Detection
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• SMOTE: Synthetic Minority Over-sampling Technique

Cited by

• Multimodal Deep Learning for Phyllodes Tumor Classification from Ultrasound and Clinical Data

Related

• Ultrasound Image Synthesis Using Generative AI for Lung Ultrasound Detection
• Learning the Imaging Landmarks: Unsupervised Key point Detection in Lung Ultrasound Videos
• Deep Learning-based Segmentation of Pleural Effusion From Ultrasound Using Coordinate Convolutions
• Diagnostic Performance of Universal-Learning Ultrasound AI Across Multiple Organs and Tasks: the UUSIC25 Challenge
• Diffusion as Sound Propagation: Physics-inspired Model for Ultrasound Image Generation