# Segmentation of 3D High-frequency Ultrasound Images of Human Lymph Nodes Using Graph Cut with Energy Functional Adapted to Local Intensity Distribution

## TL;DR

This paper introduces a novel graph cut segmentation method with locally adaptive energy for 3D high-frequency ultrasound images of human lymph nodes, effectively handling spatially varying intensity distributions due to acoustic attenuation.

## Contribution

It presents a new graph cut approach that adapts to local intensity variations, improving segmentation accuracy in challenging ultrasound images of lymph nodes.

## Key findings

- Achieved Dice similarity coefficient of 0.937+/-0.035.
- Effectively distinguished lymph node parenchyma from fat.
- Outperformed previous segmentation methods.

## Abstract

Previous studies by our group have shown that three-dimensional high-frequency quantitative ultrasound methods have the potential to differentiate metastatic lymph nodes from cancer-free lymph nodes dissected from human cancer patients. To successfully perform these methods inside the lymph node parenchyma, an automatic segmentation method is highly desired to exclude the surrounding thin layer of fat from quantitative ultrasound processing and accurately correct for ultrasound attenuation. In high-frequency ultrasound images of lymph nodes, the intensity distribution of lymph node parenchyma and fat varies spatially because of acoustic attenuation and focusing effects. Thus, the intensity contrast between two object regions (e.g., lymph node parenchyma and fat) is also spatially varying. In our previous work, nested graph cut demonstrated its ability to simultaneously segment lymph node parenchyma, fat, and the outer phosphate-buffered saline bath even when some boundaries are lost because of acoustic attenuation and focusing effects. This paper describes a novel approach called graph cut with locally adaptive energy to further deal with spatially varying distributions of lymph node parenchyma and fat caused by inhomogeneous acoustic attenuation. The proposed method achieved Dice similarity coefficients of 0.937+-0.035 when compared to expert manual segmentation on a representative dataset consisting of 115 three-dimensional lymph node images obtained from colorectal cancer patients.