Improving Automatic Fetal Biometry Measurement with Swoosh Activation Function

Zhou, Shijia, Ahn, Euijoon, Wang, Hao, Quinton, Ann, Kennedy, Narelle, Sridar, Pradeeba, Nanan, Ralph, and Kim, Jinman (2023) Improving Automatic Fetal Biometry Measurement with Swoosh Activation Function. In: Lecture Notes in Computer Science (14226) pp. 283-292. From: MICCAI 2023: 26th International Conference on Medical Image Computing and Computer Assisted Intervention, 8-12 October 2023, Vancouver, Canada.

[img] PDF (Publisher Accepted Version) - Published Version
Restricted to Repository staff only

View at Publisher Website:


The measurement of fetal thalamus diameter (FTD) and fetal head circumference (FHC) are crucial in identifying abnormal fetal thalamus development as it may lead to certain neuropsychiatric disorders in later life. However, manual measurements from 2D-US images are laborious, prone to high inter-observer variability, and complicated by the high signal-to-noise ratio nature of the images. Deep learning-based landmark detection approaches have shown promise in measuring biometrics from US images, but the current state-of-the-art (SOTA) algorithm, BiometryNet, is inadequate for FTD and FHC measurement due to its inability to account for the fuzzy edges of these structures and the complex shape of the FTD structure. To address these inadequacies, we propose a novel Swoosh Activation Function (SAF) designed to enhance the regularization of heatmaps produced by landmark detection algorithms. Our SAF serves as a regularization term to enforce an optimum mean squared error (MSE) level between predicted heatmaps, reducing the dispersiveness of hotspots in predicted heatmaps. Our experimental results demonstrate that SAF significantly improves the measurement performances of FTD and FHC with higher intraclass correlation coefficient scores in FTD and lower mean difference scores in FHC measurement than those of the current SOTA algorithm BiometryNet. Moreover, our proposed SAF is highly generalizable and architecture-agnostic. The SAF’s coefficients can be configured for different tasks, making it highly customizable. Our study demonstrates that the SAF activation function is a novel method that can improve measurement accuracy in fetal biometry landmark detection. This improvement has the potential to contribute to better fetal monitoring and improved neonatal outcomes.

Item ID: 80687
Item Type: Conference Item (Research - E1)
ISBN: 978-3-031-43990-2
Copyright Information: © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023
Funders: Australian Research Council (ARC)
Projects and Grants: ARC DP200103748
Date Deposited: 11 Oct 2023 23:21
FoR Codes: 46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460299 Artificial intelligence not elsewhere classified @ 80%
32 BIOMEDICAL AND CLINICAL SCIENCES > 3213 Paediatrics > 321302 Infant and child health @ 20%
SEO Codes: 20 HEALTH > 2001 Clinical health > 200101 Diagnosis of human diseases and conditions @ 50%
22 INFORMATION AND COMMUNICATION SERVICES > 2204 Information systems, technologies and services > 220403 Artificial intelligence @ 50%
Downloads: Total: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page