Automated Breast Ultrasound Lesions Segmentation

Abstract

Breast ultrasound images have a complicated structure, which is difficult to be segmented due to the fact that it has low signal and affected by noise ratio. In order to reduce chances of human error, stages of processing in breast ultrasound images is essential, and might be different from one another. This thesis proposes novel methods for ultrasound lesion detection and segmentation. Recent research concentrated on the Region of Interest (ROI) labeling and ROI segmentation. Using ROI of breast ultrasound images, we propose a new image filtering method for breast ultrasound, namely Altered Phase Preserving Dynamic Range Compression (APPDRC). Focusing on the filtering stage, a comparison between the proposed method APPDRC Filter and previous approaches is validated on a dataset of 306 images, namely Inverted Median filter, Multifractal Filter, Hybrid Filter, SRAD filter, and PPDRC. Further, a summary of the work to date on the effect of filtering on lesion segmentation in ultrasound breast images is reported. Jaccard Similarity Index (JSI) is used for evaluation, in which the automated segmentation result is compared with the experienced radiologist’s manual delineation. The results revealed that making the choice of filtering algorithm affects the final segmentation results. Considering JSI, Dice and MCC metrics, the proposed APPDRC Filter achieved the best performance, and outperformed the five evaluated filtering methods. For lesion segmentation of breast ultrasound images, using full BUS images, we propose a new segmentation approach called Adjusted Quick Shift Phase Preserving Dynamic Range Compression (AQS-APPDRC). AQS-APPDRC consists of three steps: preprocessing step by applying APPDRC Filter and Frost Filter, followed by proposed Adjusted Quick Shift segmentation for superpixel extraction, and a post processing step of Binary Thresholding for blob selection. The results of proposed AQSAPPDRC segmentation is compared with other two conventional segmentation methods namely: QS-FR, and QS-PPDRC. In addition, this thesis considers two state-of-the-art Convolutional Neural Networks (CNNs), i.e. U-Net and FCNs (FCN-AlexNet, FCN-32s and FCN-16s) for comparison. The segmentation results are evaluated on two small breast ultrasound datasets, where Dataset A with 306 images and Dataset B with 163 images. The proposed AQS-APPDRC approach achieved the best performance amongst two conventional methods and the CNNs in terms of Dice, Specificity, and MCC, when evaluated on Dataset A. For Dataset B, FCN-16s showed the best Dice, Specificity, and MCC, but the proposed AQS-APPDRC achieved comparable results. For Sensitivity, FCN-32s showed the best result for both datasets. The results revealed that, for CNNs, the size of dataset is always the key indicator for its performance. The conventional methods produce comparable results on small dataset.