Shape Detection In 2D Ultrasound Images

TL;DR

This paper explores using Dual Path Networks combined with Fully Convolutional Networks to automatically detect and segment shapes in 2D ultrasound images of the liver, aiming for objective analysis in clinical diagnostics.

Contribution

It introduces a novel approach combining DPN and FCN architectures for shape detection in ultrasound images, especially effective with limited datasets.

Findings

DPN and FCN improve segmentation accuracy

Different denoising filters impact results

Method effective with small datasets

Abstract

Ultrasound images are one of the most widely used techniques in clinical settings to analyze and detect different organs for study or diagnoses of diseases. The dependence on subjective opinions of experts such as radiologists calls for an automatic recognition and detection system that can provide an objective analysis. Previous work done on this topic is limited and can be classified by the organ of interest. Hybrid neural networks, linear and logistic regression models, 3D reconstructed models, and various machine learning techniques have been used to solve complex problems such as detection of lesions and cancer. Our project aims to use Dual Path Networks (DPN) to segment and detect shapes in ultrasound images taken from 3D printed models of the liver. Further the DPN deep architectures could be coupled with Fully Convolutional Network (FCN) to refine the results. Data denoised with various filters would be used to gauge how they fare against each other and provide the best results. Small amount of dataset works with DPNs, and hence, that should be appropriate for us as our dataset shall be limited in size. Moreover, the ultrasound scans shall need to be taken from different orientations of the scanner with respect to the organ, such that the training dataset can accurately perform segmentation and shape detection.