Deep Integrated Pipeline of Segmentation Guided Classification of Breast Cancer from Ultrasound Images

TL;DR

This paper presents an automated, end-to-end pipeline combining advanced image preprocessing, segmentation, and transfer learning models to improve the accuracy and efficiency of breast cancer diagnosis from ultrasound images.

Contribution

It introduces a novel integrated framework using SLIC, U-Net, and VGG16 for enhanced segmentation and classification of breast ultrasound images, outperforming existing methods.

Findings

SLIC preprocessing with U-Net achieved a Dice coefficient of 63.4.

The pipeline attained 73.72% accuracy and 78.92% F1-score in benign tumor classification.

The integrated approach improves diagnostic accuracy and speed for breast cancer detection.

Abstract

Breast cancer has become a symbol of tremendous concern in the modern world, as it is one of the major causes of cancer mortality worldwide. In this regard, breast ultrasonography images are frequently utilized by doctors to diagnose breast cancer at an early stage. However, the complex artifacts and heavily noised breast ultrasonography images make diagnosis a great challenge. Furthermore, the ever-increasing number of patients being screened for breast cancer necessitates the use of automated end-to-end technology for highly accurate diagnosis at a low cost and in a short time. In this concern, to develop an end-to-end integrated pipeline for breast ultrasonography image classification, we conducted an exhaustive analysis of image preprocessing methods such as K Means++ and SLIC, as well as four transfer learning models such as VGG16, VGG19, DenseNet121, and ResNet50. With a Dice-coefficient score of 63.4 in the segmentation stage and accuracy and an F1-Score (Benign) of 73.72 percent and 78.92 percent in the classification stage, the combination of SLIC, UNET, and VGG16 outperformed all other integrated combinations. Finally, we have proposed an end to end integrated automated pipelining framework which includes preprocessing with SLIC to capture super-pixel features from the complex artifact of ultrasonography images, complementing semantic segmentation with modified U-Net, leading to breast tumor classification using a transfer learning approach with a pre-trained VGG16 and a densely connected neural network. The proposed automated pipeline can be effectively implemented to assist medical practitioners in making more accurate and timely diagnoses of breast cancer.