Tumor detection from breast ultrasound images using mammary gland attentive U-Net

Yang, Kaiwen; Suzuki, Asobu; Ye, Jiaxing; Nosato, Hirokazu; Izumori, Ayumi; Sakanashi, Hidenori

doi:10.1117/12.2590073

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the BUS image segmentation task, fully convolutional networks [22] and U-Net [23] are the primary backbone models that can favorably characterize local and global information for lesion region segmentation. More recent studies have focused on devising U-Net variants that can further boost the segmentation performance [24][25][26][27].…”

Section: Bus Image Analysis Using Cascade Approachmentioning

confidence: 99%

See 1 more Smart Citation

CTG-Net: Cross-task guided network for breast ultrasound diagnosis

Yang

Suzuki

et al. 2022

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Deep learning techniques have achieved remarkable success in lesion segmentation and classification between benign and malignant tumors in breast ultrasound images. However, existing studies are predominantly focused on devising efficient neural network-based learning structures to tackle specific tasks individually. By contrast, in clinical practice, sonographers perform segmentation and classification as a whole; they investigate the border contours of the tissue while detecting abnormal masses and performing diagnostic analysis. Performing multiple cognitive tasks simultaneously in this manner facilitates exploitation of the commonalities and differences between tasks. Inspired by this unified recognition process, this study proposes a novel learning scheme, called the cross-task guided network (CTG-Net), for efficient ultrasound breast image understanding. CTG-Net integrates the two most significant tasks in computerized breast lesion pattern investigation: lesion segmentation and tumor classification. Further, it enables the learning of efficient feature representations across tasks from ultrasound images and the task-specific discriminative features that can greatly facilitate lesion detection. This is achieved using task-specific attention models to share the prediction results between tasks. Then, following the guidance of task-specific attention soft masks, the joint feature responses are efficiently calibrated through iterative model training. Finally, a simple feature fusion scheme is used to aggregate the attention-guided features for efficient ultrasound pattern analysis. We performed extensive experimental comparisons on multiple ultrasound datasets. Compared to state-of-the-art multi-task learning approaches, the proposed approach can improve the Dice’s coefficient, true-positive rate of segmentation, AUC, and sensitivity of classification by 11%, 17%, 2%, and 6%, respectively. The results demonstrate that the proposed cross-task guided feature learning framework can effectively fuse the complementary information of ultrasound image segmentation and classification tasks to achieve accurate tumor localization. Thus, it can aid sonographers to detect and diagnose breast cancer.

show abstract

Section: Bus Image Analysis Using Cascade Approachmentioning

confidence: 99%

“…1) Discrimination between normal tissues and lesions. For the segmentation task, we compared CTG-Net with the widely used BUS image segmentation methods U-Net [23], Attention U-Net [45], Nested U-Net [49], and MAU-Net [25]. The results of the comparison are listed in Table 1(A).…”

Section: Plos Onementioning

confidence: 99%