LegoNet: Alternating Model Blocks for Medical Image Segmentation
Since the emergence of convolutional neural networks (CNNs), and later vision transformers (ViTs), the common paradigm for model development has always been using a set of identical block types with varying parameters/hyper-parameters. To leverage the benefits of different architectural designs (e.g. CNNs and ViTs), we propose to alternate structurally different types of blocks to generate a new architecture, mimicking how Lego blocks can be assembled together. Using two CNN-based and one SwinViT-based blocks, we investigate three variations to the so-called LegoNet that applies the new concept of block alternation for the segmentation task in medical imaging. We also study a new clinical problem which has not been investigated before, namely the right internal mammary artery (RIMA) and perivascular space segmentation from computed tomography angiography (CTA) which has demonstrated a prognostic value to major cardiovascular outcomes. We compare the model performance against popular CNN and ViT architectures using two large datasets (e.g. achieving 0.749 dice similarity coefficient (DSC) on the larger dataset). We evaluate the performance of the model on three external testing cohorts as well, where an expert clinician made corrections to the model segmented results (DSC>0.90 for the three cohorts). To assess our proposed model for suitability in clinical use, we perform intra- and inter-observer variability analysis. Finally, we investigate a joint self-supervised learning approach to assess its impact on model performance. The code and the pretrained model weights will be available upon acceptance.
View on arXiv@article{sobirov2025_2306.03494,
title={ Structurally Different Neural Network Blocks for the Segmentation of Atrial and Aortic Perivascular Adipose Tissue in Multi-centre CT Angiography Scans },
author={ Ikboljon Sobirov and Cheng Xie and Muhammad Siddique and Parijat Patel and Kenneth Chan and Thomas Halborg and Christos P. Kotanidis and Zarqaish Fatima and Henry West and Sheena Thomas and Maria Lyasheva and Donna Alexander and David Adlam and Praveen Rao and Das Indrajeet and Aparna Deshpande and Amrita Bajaj and Jonathan C L Rodrigues and Benjamin J Hudson and Vivek Srivastava and George Krasopoulos and Rana Sayeed and Qiang Zhang and Pete Tomlins and Cheerag Shirodaria and Keith M. Channon and Stefan Neubauer and Charalambos Antoniades and Mohammad Yaqub },
journal={arXiv preprint arXiv:2306.03494},
year={ 2025 }
}