15 April 2025 in Journal of Ultrasound
AHAbhilash Rakkunedeth Hareendranathan
Abhilash Rakkunedeth Hareendranathan
27 April 2026 in IEEE Access
Elbow and wrist fractures are the most common fractures in pediatric populations. Automatic segmentation of musculoskeletal structures in ultrasound (US) can improve diagnostic accuracy and treatment planning. Fractures appear as cortical defects but require expert interpretation. Artificial Intelligence (AI) can provide real-time feedback and highlight key structures, helping lightly trained users perform exams more confidently. However, pixel-wise human expert annotations required for AI model training remain time-consuming and costly. To address this challenge, we propose FlexICL, a novel and flexible in-context learning (ICL) framework designed for segmenting bony regions in US images. We applied it to a label-sparse setting, where only a very small subset of training frames contained human annotations, and the model segmented unseen test frames from different videos. We systematically investigated various image concatenation techniques and training strategies for visual ICL and introduced novel concatenation methods that significantly enhance model performance with limited labeled data. By integrating multiple context focus enhancement strategies, FlexICL achieves robust segmentation performance across four wrist and elbow US datasets while requiring only 5% of the training images. It outperforms state-of-the-art visual ICL models like Painter, MAE-VQGAN, and its backbone ViT-CNN by up to 52% Dice coefficient on 210 US sweeps. These initial results highlight the potential of FlexICL as an efficient and scalable solution for US image segmentation well-suited for medical imaging use cases where labeled data is scarce.
18 September 2023 in arXiv
AHAbhilash Rakkunedeth Hareendranathan
Abhilash Rakkunedeth Hareendranathan
Supervised deep learning offers great promise to automate analysis of medical images from segmentation to diagnosis. However, their performance highly relies on the quality and quantity of the data annotation. Meanwhile, curating large annotated datasets for medical images requires a high level of expertise, which is time-consuming and expensive. Recently, to quench the thirst for large data sets with high-quality annotation, self-supervised learning (SSL) methods using unlabeled domain-specific data, have attracted attention. Therefore, designing an SSL method that relies on minimal quantities of labeled data has far-reaching significance in medical images. This paper investigates the feasibility of deploying the Masked Autoencoder for SSL (SSL-MAE) of TransUNet, for segmenting bony regions from children's wrist ultrasound scans. We found that changing the embedding and loss function in SSL-MAE can produce better downstream results compared to the original SSL-MAE. In addition, we determined that only pretraining TransUNet embedding and encoder with SSL-MAE does not work as well as TransUNet without SSL-MAE pretraining on downstream segmentation tasks.
3 June 2026 in Computers in Biology and Medicine
It is often desirable to generalize medical imaging AI models trained with dense annotations to data acquired from different ultrasound scanners or clinical sites; however, retraining these models with new annotations is often difficult and costly. We examine this challenge in pediatric wrist fracture assessment using point-of-care ultrasound (POCUS), where fractures are common and can be effectively triaged via ultrasound. AI has shown radiologist-level performance for fracture detection, often aided by high-quality bony structure segmentation. However, due to significant domain shifts, models perform poorly on data from other centers or probes, and obtaining segmentation labels across devices is impractical due to manual annotation effort and data privacy concerns. To address this, we propose a target-informed self-supervised pretraining and model-ensemble strategy. Specifically, our approach combines masked image modeling (MIM) and contrastive learning to learn target-domain structural representations without labels, and introduces a confidence-aware infusion head to adaptively integrate predictions. The source dataset, collected with a Philips Lumify probe, contained dense labels, while the target dataset, acquired with a TeleMED portable probe, was unlabeled. The datasets were kept strictly separate throughout the entire process. Our method used labeled source data for supervised training and leveraged target-domain pretraining to improve generalization. On 318 images from 62 pediatric POCUS videos, this approach significantly improved cross-device performance, achieving over 6% Dice improvement on the target domain versus the baseline. These results demonstrate a label-efficient and privacy-preserving approach for cross-device-robust ultrasound AI, offering a framework that can be extended to multi-center studies or federated learning setups. GitHub Repository:https://github.com/yuyue2uofa/CrossDomainPOCUS.