Abstract #2263

A Densely Connected Neural Network with Frequency Balancing Loss for Adipose Tissue Segmentation in Children using Free-Breathing Abdominal MRI

Sevgi Gokce Kafali^1,2, Shu-Fu Shih^1,2, Xinzhou Li^1,2, Tess Armstrong¹, Kelsey Kuwahara³, Sparsha Govardhan⁴, Karrie V Ly⁴, Shahnaz Ghahremani¹, Kara L Calkins⁴, and Holden H Wu^1,2

¹Radiological Sciences, University of California, Los Angeles, Los Angeles, CA, United States, ²Bioengineering, University of California, Los Angeles, Los Angeles, CA, United States, ³Cognitive Science, University of California, Los Angeles, Los Angeles, CA, United States, ⁴Pediatrics, University of California, Los Angeles, Los Angeles, CA, United States

Obese children have larger amounts of subcutaneous and visceral adipose tissue (SAT, VAT) and are at high risk for cardiometabolic disease. The reference standard to analyze SAT/VAT uses breath-held (BH) abdominal MRI for manual annotation of SAT/VAT. In children, the BH requirement and spatially varying VAT distribution are major challenges for body composition analysis. This work proposed a densely connected neural network with a class frequency balancing, boundary emphasizing loss to segment SAT/VAT using free breathing abdominal MRI in children.

This abstract and the presentation materials are available to members only; a login is required.

Join Here