Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study

Zhou, Boyang; Wang, Lifan; Yin, Haohao; Wu, Tingfan; Ren, Tiantian; Peng, Chuan; Li, De-Xuan; Shi, Hui; Sun, Liping; Zhao, Chong‐Ke; Xu, Hui‐Xiong

doi:10.1016/j.ebiom.2021.103684

Cited by 32 publications

(29 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 224×224, 320×320 and 448×448 pixels were adopted in this study because these three REZs are commonly used in engineering ( 18 , 22 , 37 ). They are both obtained after scaling on the original size, and the different REZs react to the same model affecting the size of the convolutional kernel field of perception ( 38 ).…”

Section: Discussionmentioning

confidence: 99%

“…Currently, more breast AI experiments of US with targeted and multimodal have been designed to address some problems on a smaller scale. They may become a more achievable goal in the short term, such as the prediction of lymph node metastasis, molecular subtypes and pathological types of breast cancer ( 18 – 22 ).…”

Section: Discussionmentioning

confidence: 99%

“…Breast US Artificial Intelligence (AI) can accurately identify breast masses in relation to the volume of masses ( 14 – 16 ). In addition, it can improve the diagnosis of early breast cancer, providing a reference for early diagnosis of non-mass lesions ( 17 ), determining the molecular subtypes ( 18 , 19 ), pathological types ( 20 ), status of axillary lymph node metastasis ( 21 , 22 ) and prognosis ( 23 , 24 ). However, by analyzing and summarizing the current studies on intelligent discrimination based on breast US data, relationship of model_REZ and diagnose performance is not deeply explored.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Comparative Study of Multiple Deep Learning Models Based on Multi-Input Resolution for Breast Ultrasound Images

Jiang³

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

PurposeThe purpose of this study was to explore the performance of different parameter combinations of deep learning (DL) models (Xception, DenseNet121, MobileNet, ResNet50 and EfficientNetB0) and input image resolutions (REZs) (224 × 224, 320 × 320 and 488 × 488 pixels) for breast cancer diagnosis.MethodsThis multicenter study retrospectively studied gray-scale ultrasound breast images enrolled from two Chinese hospitals. The data are divided into training, validation, internal testing and external testing set. Three-hundreds images were randomly selected for the physician-AI comparison. The Wilcoxon test was used to compare the diagnose error of physicians and models under P=0.05 and 0.10 significance level. The specificity, sensitivity, accuracy, area under the curve (AUC) were used as primary evaluation metrics.ResultsA total of 13,684 images of 3447 female patients are finally included. In external test the 224 and 320 REZ achieve the best performance in MobileNet and EfficientNetB0 respectively (AUC: 0.893 and 0.907). Meanwhile, 448 REZ achieve the best performance in Xception, DenseNet121 and ResNet50 (AUC: 0.900, 0.883 and 0.871 respectively). In physician-AI test set, the 320 REZ for EfficientNetB0 (AUC: 0.896, P < 0.1) is better than senior physicians. Besides, the 224 REZ for MobileNet (AUC: 0.878, P < 0.1), 448 REZ for Xception (AUC: 0.895, P < 0.1) are better than junior physicians. While the 448 REZ for DenseNet121 (AUC: 0.880, P < 0.05) and ResNet50 (AUC: 0.838, P < 0.05) are only better than entry physicians.ConclusionBased on the gray-scale ultrasound breast images, we obtained the best DL combination which was better than the physicians.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of Multiple Deep Learning Models Based on Multi-Input Resolution for Breast Ultrasound Images

Jiang³

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…Variation in individual gene expression does not localize to specific cell types and cellular regulatory mechanisms. Although multiple studies reveal the molecular subtypes and pathogenesis of breast cancer based on bulk RNA-seq [ 16 , 17 , 18 ], high-resolution exploration of molecular mechanisms is lacking.…”

Section: Introductionmentioning

confidence: 99%

Intercellular Communication Reveals Therapeutic Potential of Epithelial-Mesenchymal Transition in Triple-Negative Breast Cancer

Liu

Bao

et al. 2022

Biomolecules

View full text Add to dashboard Cite

(1) Background: Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer with high intra-tumoral heterogeneity. The epithelial-mesenchymal transition (EMT) is one of the inducers of cancer metastasis and migration. However, the description of the EMT process in TNBC using single-cell RNA sequencing (scRNA-seq) remains unclear. (2) Methods: In this study, we analyzed 8938 cellular gene expression profiles from five TNBC patients. We first scored each malignant cell based on functional pathways to determine its EMT characteristics. Then, a pseudo-time trajectory analysis was employed to characterize the cell trajectories. Furthermore, CellChat was used to identify the cellular communications. (3) Results: We identified 888 epithelium-like and 846 mesenchyme-like malignant cells, respectively. A further pseudo-time trajectory analysis indicated the transition trends from epithelium-like to mesenchyme-like in malignant cells. To characterize the potential regulators of the EMT process, we identified 10 dysregulated transcription factors (TFs) between epithelium-like and mesenchyme-like malignant cells, in which overexpressed forkhead box protein A1 (FOXA1) was recognized as a poor prognosis marker of TNBC. Furthermore, we dissected the cell-cell communications via ligand-receptor (L-R) interactions. We observed that tumor-associated macrophages (TAMs) may support the invasion of malignant epithelial cells, based on CXCL-CXCR2 signaling. The tumor necrosis factor (TNF) signaling pathway secreted by TAMs was identified as an outgoing communication pattern, mediating the communications between monocytes/TAMs and malignant epithelial cells. Alternatively, the TNF-related ligand-receptor (L-R) pairs showed promising clinical implications. Some immunotherapy and anti-neoplastic drugs could interact with the L-R pairs as a potential strategy for the treatment of TNBC. In summary, this study enhances the understanding of the EMT process in the TNBC microenvironment, and dissections of EMT-related cell communications also provided us with potential treatment targets.

show abstract

“…The related studies also confirmed that this technology undoubtedly has a broad prospects in the field of US. For example, with a prospective and multicenter study design, we ( 6 ) developed an assembled convolutional neural network model for identifying molecular subtypes of breast cancer that could contribute to the clinical management of patients with breast disease. And the adoption of tele-US could improve the quality of breast US examinations for inexperienced US doctors ( 7 ).…”

mentioning

confidence: 99%

Editorial: Ultrasound in Oncology: Application of Big Data and Artificial Intelligence

Shen

Yue²,

Xu³

2021

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

Decoding the molecular subtypes of breast cancer seen on multimodal ultrasound images using an assembled convolutional neural network model: A prospective and multicentre study

Cited by 32 publications

References 53 publications

A Comparative Study of Multiple Deep Learning Models Based on Multi-Input Resolution for Breast Ultrasound Images

A Comparative Study of Multiple Deep Learning Models Based on Multi-Input Resolution for Breast Ultrasound Images

Intercellular Communication Reveals Therapeutic Potential of Epithelial-Mesenchymal Transition in Triple-Negative Breast Cancer

Editorial: Ultrasound in Oncology: Application of Big Data and Artificial Intelligence

Contact Info

Product

Resources

About