A Novel Multistage Transfer Learning for Ultrasound Breast Cancer Image Classification

Abstract

Breast cancer diagnosis is one of the many areas that has taken advantage of artificial intelligence to achieve better performance, despite the fact that the availability of a large medical image dataset remains a challenge. Transfer learning (TL) is a phenomenon that enables deep learning algorithms to overcome the issue of shortage of training data in constructing an efficient model by transferring knowledge from a given source task to a target task. However, in most cases, ImageNet (natural images) pre-trained models that do not include medical images, are utilized for transfer learning to medical images. Considering the utilization of microscopic cancer cell line images that can be acquired in large amount, we argue that learning from both natural and medical datasets improves performance in ultrasound breast cancer image classification. The proposed multistage transfer learning (MSTL) algorithm was implemented using three pre-trained models: EfficientNetB2, InceptionV3, and ResNet50 with three optimizers: Adam, Adagrad, and stochastic gradient de-scent (SGD). Dataset sizes of 20,400 cancer cell images, 200 ultrasound images from Mendeley and 400 ultrasound images from the MT-Small-Dataset were used. ResNet50-Adagrad-based MSTL achieved a test accuracy of 99 ± 0.612% on the Mendeley dataset and 98.7 ± 1.1% on the MT-Small-Dataset, averaging over 5-fold cross validation. A p-value of 0.01191 was achieved when comparing MSTL against ImageNet based TL for the Mendeley dataset. The result is a significant improvement in the performance of artificial intelligence methods for ultrasound breast cancer classification compared to state-of-the-art methods and could remarkably improve the early diagnosis of breast cancer in young women.

Patchless Multi-Stage Transfer Learning for Improved Mammographic Breast Mass Classification

“…The strengths of this work include the use of microscopic cancer-cell-line-image features related to mammographic images that serve as an intermediate domain between the natural image (ImageNet) and the target medical image (mammogram) domain training to achieve a high-performance deep-learning algorithm. The usage of cancer cell lines as an intermediate transfer learning stage helps the model to acquire more knowledge of the medical image domain because microscopic images and other medical images share more similar features than with natural images [ 65 ]. On top of this, the cancer cell line image dataset can be generated in a larger size compared to other medical images in terms of costs and ethical issues, which makes cancer cell line images the primary candidates for the intermediate transfer learning stage.…”

Diagnostic Strategies for Breast Cancer Detection: From Image Generation to Classification Strategies Using Artificial Intelligence Algorithms

“…They found out that rank-based stochastic process is the best-suited algorithm, obtaining an accuracy, sensibility, and specificity of 94.0%, 93.4%, and 94.6%, respectively, for classifying lesions for normal or abnormal using mammograms. Similar approaches have been proposed [ 152 , 153 , 154 , 155 ]. Table 2 presents a summary of the classifiers above discussed.…”

Classification of breast lesions on DCE-MRI Data Using Fine-tuned MobileNet

“…In recent years, artificial intelligence (AI) technology has made great progress in automatically analyzing medical images for anomaly detection. In comparison with manual inspection, automated image analysis using AI reduces the time and effort needed for manual image screening, and captures valuable and relevant information more efficiently from massive image collections [6][7][8][9].…”