Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks

By Moi Hoon Yap, Gerard Pons, Joan Martí, Sergi Ganau, Melcior Sentís, Reyer Zwiggelaar, Adrian K. Davison, Robert Marti. IEEE journal of biomedical and health informatics, 2018

903 citations recorded by the source corpus.

Breast lesion detection using ultrasound imaging is considered an important step of computer-aided diagnosis systems. Over the past decade, researchers have demonstrated the possibilities to automate the initial lesion detection. However, the lack of a common dataset impedes research when comparing the performance of such algorithms. This paper proposes the use of deep learning approaches for breast ultrasound lesion detection and investigates three different methods: a Patch-based LeNet, a U-Net, and a transfer learning approach with a pretrained FCN-AlexNet. Their performance is compared against four state-of-the-art lesion detection algorithms (i.e., Radial Gradient Index, Multifractal Filtering, Rule-based Region Ranking, and Deformable Part Models). In addition, this paper compares and contrasts two conventional ultrasound image datasets acquired from two different ultrasound systems. Dataset A comprises 306 (60 malignant and 246 benign) images and Dataset B comprises 163 (53 malignant and 110 benign) images. To overcome the lack of public datasets in this domain, Dataset B will be made available for research purposes. The results demonstrate an overall improvement by the deep learning approaches when assessed on both datasets in terms of True Positive Fraction, False Positives per image, and F-measure.

Subfields: Artificial Intelligence, Molecular Biology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/96b2bc59a36fea81681d782cffe00d942a481249

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Transformers in Medical Image Analysis: A Review (2022, methodology): “[53] Breast Cancer Breast BUSI [54] Dataset B [55] apply ViT on classification of breast ultrasound images Jiang et al.”
Deep Learning in Medical Ultrasound Analysis: A Review (2019, methodology): “To perform a comprehensive comparison, Yap et al. [108] contrasted three different deep learning methods—a patch-based LeNet, a U-net, and a transfer learning approach with a pre-trained FCN-AlexNet—for breast lesion detection from two US image datasets acquired from two different US systems.”
A Review of Deep Learning on Medical Image Analysis (2020, methodology): “[69] implemented three independent deep convolutional neural networks to detect breast lesions, containing a patch-based LeNet, a UNet and an FCN-AlexNet which was pre-trained with transfer learning technology.”
Machine-Learning-Based Disease Diagnosis: A Comprehensive Review (2021, background): “CNN is widely employed in face identification, text analysis, human organ localization, and biological image detection or recognition [24].”
Federated learning for medical image analysis: A survey (2023, neutral): “[117] Breast tumor segmentation BUS [118], BUSIS [119], UDIAT [120] Ultrasound VII.”
Transformers in Medical Imaging: A Survey (2022, methodology): “[245] Accuracy AuC Pure First application of ViTs to ultrasound images classification.”
AAU-Net: An Adaptive Attention U-Net for Breast Lesions Segmentation in Ultrasound Images (2022, background): “are the first to systematically evaluate the impact of different FCN variants on breast lesions segmentation and achieve segmentation results that outperform traditional methods [18].”
A Novel Focal Tversky Loss Function With Improved Attention U-Net for Lesion Segmentation (2018, methodology): “On average, the lesions occupy 4.84% ± 5.43% and 21.4% ± 20.3% in ISIC 2018 dataset and BUS dataset B, respectively.”
Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation (2021, background): “…of tumour delineation aim to address these issues, and public datasets, such as the Breast Ultrasound 2017 (BUS2017) dataset for breast tumours (Yap et al., 2017), Kidney Tumour Segmentation 19 (KiTS19) dataset for kidney tumours (Heller et al., 2019) and Brain Tumour Segmentation 2020…”