1
|
Qian N, Jiang W, Wu X, Zhang N, Yu H, Guo Y. Lesion attention guided neural network for contrast-enhanced mammography-based biomarker status prediction in breast cancer. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 250:108194. [PMID: 38678959 DOI: 10.1016/j.cmpb.2024.108194] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/06/2023] [Revised: 04/13/2024] [Accepted: 04/21/2024] [Indexed: 05/01/2024]
Abstract
BACKGROUND AND OBJECTIVE Accurate identification of molecular biomarker statuses is crucial in cancer diagnosis, treatment, and prognosis. Studies have demonstrated that medical images could be utilized for non-invasive prediction of biomarker statues. The biomarker status-associated features extracted from medical images are essential in developing medical image-based non-invasive prediction models. Contrast-enhanced mammography (CEM) is a promising imaging technique for breast cancer diagnosis. This study aims to develop a neural network-based method to extract biomarker-related image features from CEM images and evaluate the potential of CEM in non-invasive biomarker status prediction. METHODS An end-to-end learning convolutional neural network with the whole breast images as inputs was proposed to extract CEM features for biomarker status prediction in breast cancer. The network focused on lesion regions and flexibly extracted image features from lesion and peri‑tumor regions by employing supervised learning with a smooth L1-based consistency constraint. An image-level weakly supervised segmentation network based on Vision Transformer with cross attention to contrast images of breasts with lesions against the contralateral breast images was developed for automatic lesion segmentation. Finally, prediction models were developed following further selection of significant features and the implementation of random forest-based classification. Results were reported using the area under the curve (AUC), accuracy, sensitivity, and specificity. RESULTS A dataset from 1203 breast cancer patients was utilized to develop and evaluate the proposed method. Compared to the method without lesion attention and with only lesion regions as inputs, the proposed method performed better at biomarker status prediction. Specifically, it achieved an AUC of 0.71 (95 % confidence interval [CI]: 0.65, 0.77) for Ki-67 and 0.73 (95 % CI: 0.65, 0.80) for human epidermal growth factor receptor 2 (HER2). CONCLUSIONS A lesion attention-guided neural network was proposed in this work to extract CEM image features for biomarker status prediction in breast cancer. The promising results demonstrated the potential of CEM in non-invasively predicting the biomarker statuses in breast cancer.
Collapse
Affiliation(s)
- Nini Qian
- Department of Biomedical Engineering, Medical School, Tianjin University, Tianjin 300072, China; State Key Laboratory of Advanced Medical Materials and Devices, Tianjin University, Tianjin, China
| | - Wei Jiang
- Department of Biomedical Engineering, Medical School, Tianjin University, Tianjin 300072, China; State Key Laboratory of Advanced Medical Materials and Devices, Tianjin University, Tianjin, China; Department of Radiotherapy, Yantai Yuhuangding Hospital, Shandong 264000, China
| | - Xiaoqian Wu
- Department of Radiation Oncology, The Affiliated Hospital of Qingdao University, Qingdao 266071, China
| | - Ning Zhang
- Department of Biomedical Engineering, Medical School, Tianjin University, Tianjin 300072, China; State Key Laboratory of Advanced Medical Materials and Devices, Tianjin University, Tianjin, China
| | - Hui Yu
- Department of Biomedical Engineering, Medical School, Tianjin University, Tianjin 300072, China; State Key Laboratory of Advanced Medical Materials and Devices, Tianjin University, Tianjin, China
| | - Yu Guo
- Department of Biomedical Engineering, Medical School, Tianjin University, Tianjin 300072, China; State Key Laboratory of Advanced Medical Materials and Devices, Tianjin University, Tianjin, China.
| |
Collapse
|
2
|
Guo Y, Zhang H, Yuan L, Chen W, Zhao H, Yu QQ, Shi W. Machine learning and new insights for breast cancer diagnosis. J Int Med Res 2024; 52:3000605241237867. [PMID: 38663911 PMCID: PMC11047257 DOI: 10.1177/03000605241237867] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2023] [Accepted: 02/21/2024] [Indexed: 04/28/2024] Open
Abstract
Breast cancer (BC) is the most prominent form of cancer among females all over the world. The current methods of BC detection include X-ray mammography, ultrasound, computed tomography, magnetic resonance imaging, positron emission tomography and breast thermographic techniques. More recently, machine learning (ML) tools have been increasingly employed in diagnostic medicine for its high efficiency in detection and intervention. The subsequent imaging features and mathematical analyses can then be used to generate ML models, which stratify, differentiate and detect benign and malignant breast lesions. Given its marked advantages, radiomics is a frequently used tool in recent research and clinics. Artificial neural networks and deep learning (DL) are novel forms of ML that evaluate data using computer simulation of the human brain. DL directly processes unstructured information, such as images, sounds and language, and performs precise clinical image stratification, medical record analyses and tumour diagnosis. Herein, this review thoroughly summarizes prior investigations on the application of medical images for the detection and intervention of BC using radiomics, namely DL and ML. The aim was to provide guidance to scientists regarding the use of artificial intelligence and ML in research and the clinic.
Collapse
Affiliation(s)
- Ya Guo
- Department of Oncology, Jining No.1 People’s Hospital, Shandong First Medical University, Jining, Shandong Province, China
| | - Heng Zhang
- Department of Laboratory Medicine, Shandong Daizhuang Hospital, Jining, Shandong Province, China
| | - Leilei Yuan
- Department of Oncology, Jining No.1 People’s Hospital, Shandong First Medical University, Jining, Shandong Province, China
| | - Weidong Chen
- Department of Oncology, Jining No.1 People’s Hospital, Shandong First Medical University, Jining, Shandong Province, China
| | - Haibo Zhao
- Department of Oncology, Jining No.1 People’s Hospital, Shandong First Medical University, Jining, Shandong Province, China
| | - Qing-Qing Yu
- Phase I Clinical Research Centre, Jining No.1 People’s Hospital, Shandong First Medical University, Jining, Shandong Province, China
| | - Wenjie Shi
- Molecular and Experimental Surgery, University Clinic for General-, Visceral-, Vascular- and Trans-Plantation Surgery, Medical Faculty University Hospital Magdeburg, Otto-von Guericke University, Magdeburg, Germany
| |
Collapse
|
3
|
Ayana G, Lee E, Choe SW. Vision Transformers for Breast Cancer Human Epidermal Growth Factor Receptor 2 Expression Staging without Immunohistochemical Staining. THE AMERICAN JOURNAL OF PATHOLOGY 2024; 194:402-414. [PMID: 38096984 DOI: 10.1016/j.ajpath.2023.11.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/03/2023] [Revised: 10/10/2023] [Accepted: 11/20/2023] [Indexed: 12/31/2023]
Abstract
Accurate staging of human epidermal growth factor receptor 2 (HER2) expression is vital for evaluating breast cancer treatment efficacy. However, it typically involves costly and complex immunohistochemical staining, along with hematoxylin and eosin staining. This work presents customized vision transformers for staging HER2 expression in breast cancer using only hematoxylin and eosin-stained images. The proposed algorithm comprised three modules: a localization module for weakly localizing critical image features using spatial transformers, an attention module for global learning via vision transformers, and a loss module to determine proximity to a HER2 expression level based on input images by calculating ordinal loss. Results, reported with 95% CIs, reveal the proposed approach's success in HER2 expression staging: area under the receiver operating characteristic curve, 0.9202 ± 0.01; precision, 0.922 ± 0.01; sensitivity, 0.876 ± 0.01; and specificity, 0.959 ± 0.02 over fivefold cross-validation. Comparatively, this approach significantly outperformed conventional vision transformer models and state-of-the-art convolutional neural network models (P < 0.001). Furthermore, it surpassed existing methods when evaluated on an independent test data set. This work holds great importance, aiding HER2 expression staging in breast cancer treatment while circumventing the costly and time-consuming immunohistochemical staining procedure, thereby addressing diagnostic disparities in low-resource settings and low-income countries.
Collapse
Affiliation(s)
- Gelan Ayana
- Department of Medical IT Convergence Engineering, Kumoh National Institute of Technology, Gumi, Republic of Korea; School of Biomedical Engineering, Jimma University, Jimma, Ethiopia
| | - Eonjin Lee
- Department of Medical IT Convergence Engineering, Kumoh National Institute of Technology, Gumi, Republic of Korea
| | - Se-Woon Choe
- Department of Medical IT Convergence Engineering, Kumoh National Institute of Technology, Gumi, Republic of Korea; Department of IT Convergence Engineering, Kumoh National Institute of Technology, Gumi, Republic of Korea.
| |
Collapse
|
4
|
S S, Dharani Devi G, V R, Jeyalakshmi J. Privacy-Preserving Breast Cancer Classification: A Federated Transfer Learning Approach. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01035-8. [PMID: 38424280 DOI: 10.1007/s10278-024-01035-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/17/2023] [Revised: 01/11/2024] [Accepted: 01/30/2024] [Indexed: 03/02/2024]
Abstract
Breast cancer is deadly cancer causing a considerable number of fatalities among women in worldwide. To enhance patient outcomes as well as survival rates, early and accurate detection is crucial. Machine learning techniques, particularly deep learning, have demonstrated impressive success in various image recognition tasks, including breast cancer classification. However, the reliance on large labeled datasets poses challenges in the medical domain due to privacy issues and data silos. This study proposes a novel transfer learning approach integrated into a federated learning framework to solve the limitations of limited labeled data and data privacy in collaborative healthcare settings. For breast cancer classification, the mammography and MRO images were gathered from three different medical centers. Federated learning, an emerging privacy-preserving paradigm, empowers multiple medical institutions to jointly train the global model while maintaining data decentralization. Our proposed methodology capitalizes on the power of pre-trained ResNet, a deep neural network architecture, as a feature extractor. By fine-tuning the higher layers of ResNet using breast cancer datasets from diverse medical centers, we enable the model to learn specialized features relevant to different domains while leveraging the comprehensive image representations acquired from large-scale datasets like ImageNet. To overcome domain shift challenges caused by variations in data distributions across medical centers, we introduce domain adversarial training. The model learns to minimize the domain discrepancy while maximizing classification accuracy, facilitating the acquisition of domain-invariant features. We conducted extensive experiments on diverse breast cancer datasets obtained from multiple medical centers. Comparative analysis was performed to evaluate the proposed approach against traditional standalone training and federated learning without domain adaptation. When compared with traditional models, our proposed model showed a classification accuracy of 98.8% and a computational time of 12.22 s. The results showcase promising enhancements in classification accuracy and model generalization, underscoring the potential of our method in improving breast cancer classification performance while upholding data privacy in a federated healthcare environment.
Collapse
Affiliation(s)
- Selvakanmani S
- Department of Information Technology, R.M.K Engineering College, Chennai, Tamil Nadu, India.
| | - G Dharani Devi
- Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai, Tamil Nadu, India
| | - Rekha V
- Department of Artificial Intelligence and Data Science, Panimalar Engineering College, Chennai, Tamil Nadu, India
| | - J Jeyalakshmi
- Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidhyapeetham, Chennai, India
| |
Collapse
|
5
|
Li X, Lv X, Li H, Zhang G, Long Y, Li K, Fan Y, Jin D, Zhou F, Liu H. Undifferentially Expressed CXXC5 as a Transcriptionally Regulatory Biomarker of Breast Cancer. Adv Biol (Weinh) 2023; 7:e2300189. [PMID: 37423953 DOI: 10.1002/adbi.202300189] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2023] [Revised: 06/17/2023] [Indexed: 07/11/2023]
Abstract
This work hypothesizes that some genes undergo radically changed transcription regulations (TRs) in breast cancer (BC), but don't show differential expressions for unknown reasons. The TR of a gene is quantitatively formulated by a regression model between the expression of this gene and multiple transcription factors (TFs). The difference between the predicted and real expression levels of a gene in a query sample is defined as the mqTrans value of this gene, which quantitatively reflects its regulatory changes. This work systematically screens the undifferentially expressed genes with differentially expressed mqTrans values in 1036 samples across five datasets and three ethnic groups. This study calls the 25 genes satisfying the above hypothesis in at least four datasets as dark biomarkers, and the strong dark biomarker gene CXXC5 (CXXC Finger Protein 5) is even supported by all the five independent BC datasets. Although CXXC5 does not show differential expressions in BC, its transcription regulations show quantitative associations with BCs in diversified cohorts. The overlapping long noncoding RNAs (lncRNAs) may have contributed their transcripts to the expression miscalculations of dark biomarkers. The mqTrans analysis serves as a complementary view of the transcriptome-based detections of biomarkers that are ignored by many existing studies.
Collapse
Affiliation(s)
- Xue Li
- School of Public Health, the Key Laboratory of Environmental Pollution Monitoring and Disease Control, Ministry of Education, Guizhou Medical University, Guiyang, 550025, China
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, China
- Engineering Research Center of Medical Biotechnology, Guizhou Medical University, Guiyang, Guizhou, 550025, China
| | - Xiaoying Lv
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, China
- Engineering Research Center of Medical Biotechnology, Guizhou Medical University, Guiyang, Guizhou, 550025, China
| | - Haijun Li
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, China
- Engineering Research Center of Medical Biotechnology, Guizhou Medical University, Guiyang, Guizhou, 550025, China
| | - Gongyou Zhang
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, China
- Engineering Research Center of Medical Biotechnology, Guizhou Medical University, Guiyang, Guizhou, 550025, China
| | - Yaohang Long
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, China
- Engineering Research Center of Medical Biotechnology, Guizhou Medical University, Guiyang, Guizhou, 550025, China
| | - Kewei Li
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China
- College of Computer Science and Technology, Jilin University, Changchun, 130012, China
| | - Yusi Fan
- College of Software, Jilin University, Changchun, 130012, China
| | - Dawei Jin
- Research Institute of Guizhou Huada Life Big Data, Guiyang, Guizhou, 550025, China
| | - Fengfeng Zhou
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China
- College of Computer Science and Technology, Jilin University, Changchun, 130012, China
| | - Hongmei Liu
- School of Biology and Engineering, Guizhou Medical University, Guiyang, 550025, China
- Engineering Research Center of Medical Biotechnology, Guizhou Medical University, Guiyang, Guizhou, 550025, China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China
| |
Collapse
|
6
|
Gu Y, Huang H, Tong Q, Cao M, Ming W, Zhang R, Zhu W, Wang Y, Sun X. Multi-View Radiomics Feature Fusion Reveals Distinct Immuno-Oncological Characteristics and Clinical Prognoses in Hepatocellular Carcinoma. Cancers (Basel) 2023; 15:cancers15082338. [PMID: 37190266 DOI: 10.3390/cancers15082338] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2023] [Revised: 04/13/2023] [Accepted: 04/15/2023] [Indexed: 05/17/2023] Open
Abstract
Hepatocellular carcinoma (HCC) is one of the most prevalent malignancies worldwide, and the pronounced intra- and inter-tumor heterogeneity restricts clinical benefits. Dissecting molecular heterogeneity in HCC is commonly explored by endoscopic biopsy or surgical forceps, but invasive tissue sampling and possible complications limit the broadeer adoption. The radiomics framework is a promising non-invasive strategy for tumor heterogeneity decoding, and the linkage between radiomics and immuno-oncological characteristics is worth further in-depth study. In this study, we extracted multi-view imaging features from contrast-enhanced CT (CE-CT) scans of HCC patients, followed by developing a fused imaging feature subtyping (FIFS) model to identify two distinct radiomics subtypes. We observed two subtypes of patients with distinct texture-dominated radiomics profiles and prognostic outcomes, and the radiomics subtype identified by FIFS model was an independent prognostic factor. The heterogeneity was mainly attributed to inflammatory pathway activity and the tumor immune microenvironment. The predominant radiogenomics association was identified between texture-related features and immune-related pathways by integrating network analysis, and was validated in two independent cohorts. Collectively, this work described the close connections between multi-view radiomics features and immuno-oncological characteristics in HCC, and our integrative radiogenomics analysis strategy may provide clues to non-invasive inflammation-based risk stratification.
Collapse
Affiliation(s)
- Yu Gu
- State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, China
| | - Hao Huang
- State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, China
| | - Qi Tong
- Department of Radiology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing 210008, China
| | - Meng Cao
- Department of General Surgery, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing 210008, China
| | - Wenlong Ming
- State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, China
| | - Rongxin Zhang
- State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, China
| | - Wenyong Zhu
- State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, China
| | - Yuqi Wang
- State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, China
| | - Xiao Sun
- State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, China
| |
Collapse
|
7
|
Identifying Associations between DCE-MRI Radiomic Features and Expression Heterogeneity of Hallmark Pathways in Breast Cancer: A Multi-Center Radiogenomic Study. Genes (Basel) 2022; 14:genes14010028. [PMID: 36672769 PMCID: PMC9858814 DOI: 10.3390/genes14010028] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2022] [Revised: 12/12/2022] [Accepted: 12/20/2022] [Indexed: 12/25/2022] Open
Abstract
BACKGROUND To investigate the relationship between dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomic features and the expression activity of hallmark pathways and to develop prediction models of pathway-level heterogeneity for breast cancer (BC) patients. METHODS Two radiogenomic cohorts were analyzed (n = 246). Tumor regions were segmented semiautomatically, and 174 imaging features were extracted. Gene set enrichment analysis (GSEA) and gene set variation analysis (GSVA) were performed to identify significant imaging-pathway associations. Random forest regression was used to predict pathway enrichment scores. Five-fold cross-validation and grid search were used to determine the optimal preprocessing operation and hyperparameters. RESULTS We identified 43 pathways, and 101 radiomic features were significantly related in the discovery cohort (p-value < 0.05). The imaging features of the tumor shape and mid-to-late post-contrast stages showed more transcriptional connections. Ten pathways relevant to functions such as cell cycle showed a high correlation with imaging in both cohorts. The prediction model for the mTORC1 signaling pathway achieved the best performance with the mean absolute errors (MAEs) of 27.29 and 28.61% in internal and external test sets, respectively. CONCLUSIONS The DCE-MRI features were associated with hallmark activities and may improve individualized medicine for BC by noninvasively predicting pathway-level heterogeneity.
Collapse
|