1
|
Chen J, Huang Z, Jiang Y, Wu H, Tian H, Cui C, Shi S, Tang S, Xu J, Xu D, Dong F. Diagnostic Performance of Deep Learning in Video-Based Ultrasonography for Breast Cancer: A Retrospective Multicentre Study. ULTRASOUND IN MEDICINE & BIOLOGY 2024; 50:722-728. [PMID: 38369431 DOI: 10.1016/j.ultrasmedbio.2024.01.012] [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: 11/29/2023] [Revised: 01/08/2024] [Accepted: 01/16/2024] [Indexed: 02/20/2024]
Abstract
OBJECTIVE Although ultrasound is a common tool for breast cancer screening, its accuracy is often operator-dependent. In this study, we proposed a new automated deep-learning framework that extracts video-based ultrasound data for breast cancer screening. METHODS Our framework incorporates DenseNet121, MobileNet, and Xception as backbones for both video- and image-based models. We used data from 3907 patients to train and evaluate the models, which were tested using video- and image-based methods, as well as reader studies with human experts. RESULTS This study evaluated 3907 female patients aged 22 to 86 years. The results indicated that the MobileNet video model achieved an AUROC of 0.961 in prospective data testing, surpassing the DenseNet121 video model. In real-world data testing, it demonstrated an accuracy of 92.59%, outperforming both the DenseNet121 and Xception video models, and exceeding the 76.00% to 85.60% accuracy range of human experts. Additionally, the MobileNet video model exceeded the performance of image models and other video models across all evaluation metrics, including accuracy, sensitivity, specificity, F1 score, and AUC. Its exceptional performance, particularly suitable for resource-limited clinical settings, demonstrates its potential for clinical application in breast cancer screening. CONCLUSIONS The level of expertise reached by the video models was greater than that achieved by image-based models. We have developed an artificial intelligence framework based on videos that may be able to aid breast cancer diagnosis and alleviate the shortage of experienced experts.
Collapse
Affiliation(s)
- Jing Chen
- Ultrasound Department, The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology, Shenzhen People's Hospital, Shenzhen, Guangdong, China
| | | | - Yitao Jiang
- Research and development department, Illuminate, LLC, Shenzhen, Guangdong, China
| | - Huaiyu Wu
- Ultrasound Department, The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology, Shenzhen People's Hospital, Shenzhen, Guangdong, China
| | - Hongtian Tian
- Ultrasound Department, The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology, Shenzhen People's Hospital, Shenzhen, Guangdong, China
| | - Chen Cui
- Research and development department, Illuminate, LLC, Shenzhen, Guangdong, China
| | - Siyuan Shi
- Research and development department, Illuminate, LLC, Shenzhen, Guangdong, China
| | | | - Jinfeng Xu
- Ultrasound Department, The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology, Shenzhen People's Hospital, Shenzhen, Guangdong, China
| | - Dong Xu
- Institute of Basic Medicine and Cancer (IBMC), The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Chinese Academy of Sciences, Hangzhou, Zhejiang, China
| | - Fajin Dong
- Ultrasound Department, The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology, Shenzhen People's Hospital, Shenzhen, Guangdong, China; Jinan University, Guangzhou, Guangdong, China.
| |
Collapse
|
2
|
Yang K, Ye X, Tian H, Li Q, Liu Q, Li J, Guo J, Xu J, Dong F. Development and validation of a nomogram for discriminating between benign and malignant breast masses by conventional ultrasound and dual-mode elastography: a multicenter study. Quant Imaging Med Surg 2023; 13:865-877. [PMID: 36819244 PMCID: PMC9929388 DOI: 10.21037/qims-22-237] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/12/2022] [Accepted: 12/07/2022] [Indexed: 01/15/2023]
Abstract
Background This study developed and validated an ultrasound nomogram based on conventional ultrasound and dual-mode elastography to differentiate breast masses. Methods The data of 234 patients were collected before they underwent breast mass puncture or surgery at 4 different centers between 2016 and 2021. Patients were divided into 5 datasets: internal validation and development sets from the same hospital, and external validation sets from the 3 other hospitals. In the development cohort, age and 294 different ultrasound and elastography features were obtained from ultrasound images. Univariate logistic regression and least absolute shrinkage and selection operator (LASSO) regression were used for data reduction and visualization. Multivariable logistic regression analysis was used to develop the prediction model and ultrasound nomogram. Receiver operating characteristic (ROC) curve analysis, calibration curves, integrated discrimination improvement, and the net reclassification index were used to evaluate nomogram performance; decision curve analysis (DCA) and clinical impact curves were used to estimate clinical usefulness. Results In the development cohort, margin, posterior features, shape, vascularity, (the mean shear wave elastography value of 1.5 mm surrounding tissues in a breast mass) divided by (the mean shear wave elastography value of the breast mass)-shell mean/A mean1.5(E), (the ratio of strain elastography of adipose tissue near a breast mass) divided by [the ratio of strain elastography of (the breast mass adds the 1.5 mm surrounding tissues in the breast mass)]-B/A'1.5 were selected as predictors in multivariable logistic regression analysis, comprising Model 1. Among the 5 cohorts, Model 1 performed best, with areas under the curve (AUC) of 0.92, 0.84, 0.87, 0.93, and 0.89, respectively. The AUCs were 0.90, 0.82, 0.83, 0.91, and 0.85, respectively, in Model 2 (margin + posterior features + shape + vascularity) and 0.80, 0.76, 0.77, 0.87, and 0.80, respectively, in Model 3 [shell mean/A mean1.5(E) + B/A'1.5]. Conclusions Our ultrasound nomograms facilitate exposure to the features and visualization of breast cancer. Shell mean/A mean1.5(E), B/A'1.5 integrated with margin, posterior features, shape, and vascularity are superior at identifying breast cancer, and are worthy of further clinical investigation.
Collapse
Affiliation(s)
- Keen Yang
- Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, China
| | - Xiuqin Ye
- Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, China
| | - Hongtian Tian
- Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, China
| | - Qiaoying Li
- Department of Ultrasound, Tangdu Hospital, Fourth Military Medical University, Xi’an, China
| | - Qinghua Liu
- Department of Ultrasound, Rizhao People’s Hospital, Rizhao, China
| | - Jingjing Li
- Department of Ultrasound, Rizhao People’s Hospital, Rizhao, China
| | - Jinhan Guo
- Department of Ultrasound, Longhua Branch of Shenzhen People’s Hospital, Shenzhen, China
| | - Jinfeng Xu
- Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, China
| | - Fajin Dong
- Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, China
| |
Collapse
|
3
|
Liu J, Yoon H, Emelianov SY. Noninvasive ultrasound assessment of tissue internal pressure using dual mode elasticity imaging: a phantom study. Phys Med Biol 2022; 68. [PMID: 36562591 DOI: 10.1088/1361-6560/aca9b8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2022] [Accepted: 12/07/2022] [Indexed: 12/12/2022]
Abstract
Objective.Tissue internal pressure, such as interstitial fluid pressure in solid tumors and intramuscular pressure in compartment syndrome, is closely related to the pathological state of tissues. It is of great diagnostic value to measure and/or monitor the internal pressure of targeted tissues. Because most of the current methods for measuring tissue pressure are invasive, noninvasive methods are highly desired. In this study, we developed a noninvasive method for qualitative assessment of tissue internal pressure based on a combination of two ultrasound elasticity imaging methods: strain imaging and shear wave elasticity imaging.Approach.The method was verified through experimental investigation using two tissue-mimicking phantoms each having an inclusion confined by a membrane, in which hydrostatic pressures can be applied and maintained. To examine the sensitivity of the elasticity imaging methods to pressure variation, strain ratio and shear modulus ratio (SMR) between the inclusion and background of phantom were obtained.Main results.The results first experimentally prove that pressure, in addition to elasticity, is a contrast mechanism of strain imaging, and further demonstrate that a comparative analysis of strain ratio and SMR is an effective method for noninvasive tissue internal pressure detection.Significance.This work provides a new perspective in interpreting the strain ratio data in medical diagnosis, and it also provides a noninvasive alternative for assessing tissue internal pressure, which could be valuable for the diagnosis of pressure-related diseases.
Collapse
Affiliation(s)
- Jingfei Liu
- School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30322, United States of America
| | - Heechul Yoon
- School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30322, United States of America.,School of Electronics and Electrical Engineering, Dankook University, Yongin-si 16890, Republic of Korea
| | - Stanislav Y Emelianov
- School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30322, United States of America.,Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University School of Medicine, Atlanta, GA 30322 United States of America
| |
Collapse
|
4
|
Tang L, Wang Y, Chen P, Chen M, Jiang L. Clinical use and adjustment of ultrasound elastography for breast lesions followed WFUMB guidelines and recommendations in the real world. Front Oncol 2022; 12:1022917. [PMID: 36505783 PMCID: PMC9730323 DOI: 10.3389/fonc.2022.1022917] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2022] [Accepted: 11/07/2022] [Indexed: 11/25/2022] Open
Abstract
Objective This study aimed to explore the value of strain elastography (SE) and shear wave elastography (SWE) following the World Federation of Ultrasound in Medicine and Biology (WFUMB) guidelines and recommendations in the real world in distinguishing benign and malignant breast lesions and reducing biopsy of BI-RADS (Breast Imaging Reporting and Data System) 4a lesions. Methods This prospective study included 274 breast lesions. The elastography score (ES) by the Tsukuba score, the strain ratio (SR) for SE, and Emax for SWE of the lesion(A) and the regions(A') included the lesion and the margin (0.5-5 mm) surrounding the lesion were measured. The sensitivity, specificity, and AUC were calculated and compared by the cutoff values recommended by WFUMB guidelines. Results When scores of 1 to 3 were classified as probably benign by WFUMB recommendation, the ES was significantly higher in malignant lesions compared to benign lesions (p < 0.05) in all lesions. For the cohort by size >20 mm, the sensitivity was 100%, and the specificity was 45.5%. ES had the highest AUC: 0.79(95% CI 0.72-0.86) with a sensitivity of 96.2%, and a specificity of 61.8% for the cohort by size ≤20 mm. For the Emax-A'-S2.5mm, when the high stiffness would be considered with Emax above 80 kPa in SWE, the malignant lesions were diagnosed with a sensitivity of 95.8%, a specificity of 43.3% for all lesions, a sensitivity of 88.5% for lesions with size ≤20 mm, and sensitivity of 100.0% for lesions with size >20 mm. In 84 lesions of BI-RADS category 4a, if category 4a lesions with ES of 1-3 points or Emax-A'-S2.5 less than 80 kPa could be downgraded to category 3, 52 (61.9%) lesions could be no biopsy, including two malignancies. If category 4a lesions with ES of 1-3 points and Emax-A'-S2.5 less than 80kPa could be downgraded to category 3, 23 (27.4%) lesions could be no biopsy, with no malignancy. Conclusions The elastography score for SE and Emax-A' for SWE after our modification were beneficial in the diagnosis of breast cancer. The combination of SWE and SE could effectively reduce the biopsy rate of BI-RADS category 4a lesions.
Collapse
Affiliation(s)
- Lei Tang
- Department of Ultrasound, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China,Department of Ultrasound Medicine, Tongren Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Yuqun Wang
- Department of Ultrasound Medicine, Tongren Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Pingping Chen
- Department of Ultrasound Medicine, Tongren Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Man Chen
- Department of Ultrasound Medicine, Tongren Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China,*Correspondence: Lixin Jiang, ; Man Chen,
| | - Lixin Jiang
- Department of Ultrasound, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China,*Correspondence: Lixin Jiang, ; Man Chen,
| |
Collapse
|