Predicting Breast Tumor Malignancy Using Deep ConvNeXt Radiomics and Quality-Based Score Pooling in Ultrasound Sequences

Abstract

Breast cancer needs to be detected early to reduce mortality rate. Ultrasound imaging (US) could significantly enhance diagnosing cases with dense breasts. Most of the existing computer-aided diagnosis (CAD) systems employ a single ultrasound image for the breast tumor to extract features to classify it as benign or malignant. However, the accuracy of such CAD system is limited due to the large tumor size and shape variation, irregular and ambiguous tumor boundaries, and low signal-to-noise ratio in ultrasound images due to their noisy nature and the significant similarity between normal and abnormal tissues. To handle these issues, we propose a deep-learning-based radiomics method based on breast US sequences in this paper. The proposed approach involves three main components: radiomic features extraction based on a deep learning network, so-called ConvNeXt, a malignancy score pooling mechanism, and visual interpretations. Specifically, we employ the ConvNeXt network, a deep convolutional neural network (CNN) trained using the vision transformer style. We also propose an efficient pooling mechanism to fuse the malignancy scores of each breast US sequence frame based on image-quality statistics. The ablation study and experimental results demonstrate that our method achieves competitive results compared to other CNN-based methods.

Overview of Artificial Intelligence in Breast Cancer Medical Imaging

“…Hassanien et al presented a new DL-based radiomics method called ConvNeXt to endow the CAD to predict the malignancy score of a breast lesion. By using a vision transformer style, the ConvNeXt system is able to perform the malignant score analysis of breast ultrasound sequences and present visual interpretations for its decision [ 65 ]. Jabeen and colleagues optimized feature extraction and improved breast cancer categorization accuracy to 99.1% by modifying and retraining the deep model named DarkNet53.…”

Image segmentation of gastroscopy based on ConvNeXt 2.5D UNet

“…Path enhancement structure is used to mine multi-scale features in fine segmentation. In Paper [3], a deep learning-based radiomics method for breast ultrasound sequences was mainly introduced.…”

Cerebral stroke classification based on fusion model of 3D EmbedConvNext and 3D Bi‐LSTM network

“…ConvNeXt also has many applications in medicine. The study proposes to use ConvNeXt to predict the malignant degree of breast tumors 21 . The study offers to use 3D ConvNeXt to detect COVID and predict its severity 22 .…”

“…The study proposes to use ConvNeXt to predict the malignant degree of breast tumors. 21 The study offers to use 3D ConvNeXt to detect COVID and predict its severity. 22 The study uses variants of ConvNeXt to classify colorectal polyps from histopathological images.…”