Breast Cancer Mass Detection in DCE–MRI Using Deep-Learning Features Followed by Discrimination of Infiltrative vs. In Situ Carcinoma through a Machine-Learning Approach

Abstract

Breast cancer is the leading cause of cancer deaths worldwide in women. This aggressive tumor can be categorized into two main groups—in situ and infiltrative, with the latter being the most common malignant lesions. The current use of magnetic resonance imaging (MRI) was shown to provide the highest sensitivity in the detection and discrimination between benign vs. malignant lesions, when interpreted by expert radiologists. In this article, we present the prototype of a computer-aided detection/diagnosis (CAD) system that could provide valuable assistance to radiologists for discrimination between in situ and infiltrating tumors. The system consists of two main processing levels—(1) localization of possibly tumoral regions of interest (ROIs) through an iterative procedure based on intensity values (ROI Hunter), followed by a deep-feature extraction and classification method for false-positive rejection; and (2) characterization of the selected ROIs and discrimination between in situ and invasive tumor, consisting of Radiomics feature extraction and classification through a machine-learning algorithm. The CAD system was developed and evaluated using a DCE–MRI image database, containing at least one confirmed mass per image, as diagnosed by an expert radiologist. When evaluating the accuracy of the ROI Hunter procedure with respect to the radiologist-drawn boundaries, sensitivity to mass detection was found to be 75%. The AUC of the ROC curve for discrimination between in situ and infiltrative tumors was 0.70.

An improved semantic segmentation for breast lesion from dynamic contrast enhanced MRI images using deep learning

“…The proposed DCNN‐94 demonstrated a sensitivity of 96% and a Jaccard coefficient of 0.88, outperforming IMPST, RCNN, UNet, SegNet, and Fully CNN. Conte et al used the ROI hunter method for segmentation and GoogleNet for feature extraction, detecting 41 masses out of 55 samples with an achieved AUC of 0.7 25 . In comparison, the proposed DCNN‐94 outperformed with an AUC of 0.98.…”

“…Conte et al used the ROI hunter method for segmentation and GoogleNet for feature extraction, detecting 41 masses out of 55 samples with an achieved AUC of 0.7. 25 In comparison, the proposed DCNN-94 outperformed with an AUC of 0.98.…”

“…As a result, the dice coefficient was increased by 20%. Conte et al have discussed using a region of interest hunter (ROI hunter) to segment the tumor and classify the tumor using a machine learning algorithm 25 . Guo et al have suggested an expanded UNet that included seven dropout layers in the original UNet to segment tumors from ultrasound images 26 .…”

Special Issue on Signal Processing and Machine Learning for Biomedical Data

“…De Nunzio et al [16] developed a computer-aided design (CAD), capable of analyzing breast MRI images and classified breast cancer. The system consisted of two main processing levels-the segmentation of possibly tumoral ROIs and characterization of the selected ROIs between the in situ and invasive tumor.…”

MRI radiogenomics for intelligent diagnosis of breast tumors and accurate prediction of neoadjuvant chemotherapy responses-a review

“…Several deep learning-based computer-aided detection (CAD) systems have been developed for tumor detection and segmentation. Since the first object detection systems using convolution neural networks (CNNs) were proposed in 1995, breast tumor segmentation using deep learning has been applied in many medical imaging applications [51][52][53][54]. The authors in [53] used a segmentation approach based on the U-Net architecture.…”