Simultaneous Bone and Shadow Segmentation Network using Task Correspondence Consistency

by   Aimon Rahman, et al.

Segmenting both bone surface and the corresponding acoustic shadow are fundamental tasks in ultrasound (US) guided orthopedic procedures. However, these tasks are challenging due to minimal and blurred bone surface response in US images, cross-machine discrepancy, imaging artifacts, and low signal-to-noise ratio. Notably, bone shadows are caused by a significant acoustic impedance mismatch between the soft tissue and bone surfaces. To leverage this mutual information between these highly related tasks, we propose a single end-to-end network with a shared transformer-based encoder and task independent decoders for simultaneous bone and shadow segmentation. To share complementary features, we propose a cross task feature transfer block which learns to transfer meaningful features from decoder of shadow segmentation to that of bone segmentation and vice-versa. We also introduce a correspondence consistency loss which makes sure that network utilizes the inter-dependency between the bone surface and its corresponding shadow to refine the segmentation. Validation against expert annotations shows that the method outperforms the previous state-of-the-art for both bone surface and shadow segmentation.


page 3

page 4

page 7

page 8


Simultaneous Segmentation and Classification of Bone Surfaces from Ultrasound Using a Multi-feature Guided CNN

Various imaging artifacts, low signal-to-noise ratio, and bone surfaces ...

Orientation-guided Graph Convolutional Network for Bone Surface Segmentation

Due to imaging artifacts and low signal-to-noise ratio in ultrasound ima...

Simultaneous Multiple Surface Segmentation Using Deep Learning

The task of automatically segmenting 3-D surfaces representing boundarie...

LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception

There is a recent trend in the LiDAR perception field towards unifying m...

MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization

Generalization capabilities of learning-based medical image segmentation...

Topical Segmentation of Spoken Narratives: A Test Case on Holocaust Survivor Testimonies

The task of topical segmentation is well studied, but previous work has ...

Please sign up or login with your details

Forgot password? Click here to reset