1
|
Yi M, Lin Y, Lin Z, Xu Z, Li L, Huang R, Huang W, Wang N, Zuo Y, Li N, Ni D, Zhang Y, Li Y. Biopsy or Follow-up: AI Improves the Clinical Strategy of US BI-RADS 4A Breast Nodules Using a Convolutional Neural Network. Clin Breast Cancer 2024:S1526-8209(24)00041-7. [PMID: 38494415 DOI: 10.1016/j.clbc.2024.02.003] [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: 08/15/2023] [Revised: 02/04/2024] [Accepted: 02/06/2024] [Indexed: 03/19/2024]
Abstract
OBJECTIVES To develop predictive nomograms based on clinical and ultrasound features and to improve the clinical strategy for US BI-RADS 4A lesions. METHODS Patients with US BI-RADS 4A lesions from 3 hospitals between January 2016 and June 2020 were retrospectively included. Clinical and ultrasound features were extracted to establish nomograms CE (based on clinical experience) and DL (based on deep-learning algorithm). The performances of nomograms were evaluated by receiver operator characteristic curves, calibration curves and decision curves. Diagnostic performances with DL of radiologists were analyzed. RESULTS 1616 patients from 2 hospitals were randomly divided into training and internal validation cohorts at a ratio of 7:3. Hundred patients from another hospital made up external validation cohort. DL achieved more optimized AUCs than CE (internal validation: 0.916 vs. 0.863, P < .01; external validation: 0.884 vs. 0.776, P = .05). The sensitivities of DL were higher than CE (internal validation: 81.03% vs. 72.41%, P = .044; external validation: 93.75% vs. 81.25%, P = .4795) without losing specificity (internal validation: 84.91% vs. 86.47%, P = .353; external validation: 69.14% vs. 71.60%, P = .789). Decision curves indicated DL adds more clinical net benefit. With DL's assistance, both radiologists achieved higher AUCs (0.712 vs. 0.801; 0.547 vs. 0.800), improved specificities (70.93% vs. 74.42%, P < .001; 59.3% vs. 81.4%, P = .004), and decreased unnecessary biopsy rates by 6.7% and 24%. CONCLUSION DL was developed to discriminate US BI-RADS 4A lesions with a higher diagnostic power and more clinical net benefit than CE. Using DL may guide clinicians to make precise clinical decisions and avoid overtreatment of benign lesions.
Collapse
Affiliation(s)
- Mei Yi
- Department of Ultrasound, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Yue Lin
- Department of Ultrasound, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Zehui Lin
- Medical Ultrasound Image Computing (MUSIC) Lab, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China
| | - Ziting Xu
- Department of Ultrasound, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Lian Li
- Department of Ultrasound, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Ruobing Huang
- Medical Ultrasound Image Computing (MUSIC) Lab, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China
| | - Weijun Huang
- Department of Ultrasound, The First People's Hospital of Foshan, Foshan, China
| | - Nannan Wang
- Department of Ultrasound, The First People's Hospital of Foshan, Foshan, China
| | - Yanling Zuo
- Department of Ultrasound Imaging, Affiliated Cancer Hospital & Institute of Guangzhou Medical University, Guangzhou, China
| | - Nuo Li
- Department of Ultrasound, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Dong Ni
- Medical Ultrasound Image Computing (MUSIC) Lab, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China
| | - Yanyan Zhang
- Department of Ultrasound, Nanfang Hospital, Southern Medical University, Guangzhou, China.
| | - Yingjia Li
- Department of Ultrasound, Nanfang Hospital, Southern Medical University, Guangzhou, China.
| |
Collapse
|
2
|
Sundar PM, Shanmugasundaram S, Nagappan E. The role of the IAC Yokohama System for Reporting Breast Fine Needle Aspiration Biopsy and the ACR Breast Imaging-Reporting and Data System in the evaluation of breast lesions. Cytopathology 2021; 33:185-195. [PMID: 34866246 DOI: 10.1111/cyt.13085] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2021] [Revised: 12/01/2021] [Accepted: 12/03/2021] [Indexed: 01/15/2023]
Abstract
BACKGROUND Stratification of breast lesions for appropriate management is achieved through an integration of clinical examination, imaging, and fine needle aspiration biopsy (FNAB). The current study aimed to evaluate the combined effectiveness of the widely used Breast Imaging-Reporting and Data System (BI-RADS) with the recently proposed International Academy of Cytology (IAC) Yokohama System for Reporting Breast Fine Needle Aspiration Biopsy Cytopathology. METHODS A retrospective analysis was done on all breast FNABs from 2016 through 2020. The cases were categorised according to the IAC Yokohama System. Histopathological correlation of the BI-RADS and IAC Yokohama System was performed. The rate of malignancy (ROM) for each category of the BI-RADS and IAC Yokohama System was calculated. RESULTS The ROM values for categories I to V were 38%, 0.6%, 21.9%, 100%, and 97%, respectively. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of FNAB with category III assumed as malignant were 98.9%, 85%, 76.1%, 99.3%, and 89.5%, respectively. With category III assumed as benign, these indices were 90.8%, 98.9%, 97.5%, 95.7%, and 96.2%, respectively. The sensitivity, specificity, PPV, NPV and accuracy of BI-RADS were 91.5%, 81.9%, 72%, 95%, and 85.1%, respectively. CONCLUSIONS FNAB is still an indispensable test in the evaluation of breast lesions. The utilisation of the IAC Yokohama reporting system for breast cytology in conjunction with ACR BI-RADS aids in better stratification of lesions.
Collapse
Affiliation(s)
| | | | - Elango Nagappan
- Department of Radiology, PSG Institute of Medical Sciences and Research, Coimbatore, India
| |
Collapse
|
3
|
Rehman S, Niazi IK, Naveed MA, Javaid A, Rehman B. Sonographic Evaluation of Incidental Synchronous Masses in Patients with Breast Cancer: Clinical Significance and Diagnostic Workup. Eur J Breast Health 2020; 17:28-35. [PMID: 33796828 DOI: 10.4274/ejbh.2020.5858] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2020] [Accepted: 08/29/2020] [Indexed: 12/01/2022]
Abstract
Objective This study aimed to evaluate the diagnostic accuracy of breast ultrasonography in classifying incidental satellite masses as benign or malignant in patients with breast cancer and to assess its effect on their surgical management. Materials and Methods Ultrasound-guided fine needle aspiration/biopsy was performed in 288 satellite masses of 225 patients with breast cancer. Two radiologists retrospectively reviewed the sonograms of these masses and classified them as benign or malignant and compared this feature with the results of the histopathological examination. The location of the satellite mass and type of surgery were also documented. Results Of the 288 satellite masses, 139 were located in the same quadrant, 95 in different quadrants, while 54 were in the contralateral breast. Of the 123 sonographically benign masses, 106 showed benign pathological outcome, and from 165 sonographically malignant masses, 127 were found malignant on histopathology/cytology. McNemar's chi-square was 7.27 (p-value=0.007), showing statistically significant association between sonographic features and pathological outcome of satellite masses. The sensitivity, specificity, positive and negative predictive values, and accuracy were 88.2%, 73.6%, 77%, 86.1%, and 80.9% respectively. Based on these findings, 61 patients underwent lumpectomy limited to a single tumor, 52 underwent extended resection, 78 underwent mastectomy, four underwent lumpectomy for the contralateral breast, and bilateral mastectomies were performed in another four patients. Surgery was not performed in 26 patients. Conclusion Although ultrasound is an effective tool for the detection and characterization of incidental satellite masses in patients with breast cancer, biopsy is imperative to ascertain the pathological diagnosis and, therefore, select the most appropriate surgical plan.
Collapse
Affiliation(s)
- Sara Rehman
- Department of Radiology, Shaukat Khanum Memorial Cancer Hospital and Research Centre, Lahore, Pakistan
| | - Imran Khalid Niazi
- Department of Radiology, Shaukat Khanum Memorial Cancer Hospital and Research Centre, Lahore, Pakistan
| | - Muhammad Atif Naveed
- Department of Radiology, Shaukat Khanum Memorial Cancer Hospital and Research Centre, Lahore, Pakistan
| | - Ainy Javaid
- Department of Radiology, Shaukat Khanum Memorial Cancer Hospital and Research Centre, Lahore, Pakistan
| | - Bushra Rehman
- Department of Breast Surgery, Shaukat Khanum Memorial Cancer Hospital and Research Centre, Lahore, Pakistan
| |
Collapse
|
4
|
Lee S, Jung Y, Bae Y. Synchronous BI-RADS Category 3 Lesions on Preoperative Ultrasonography in Patients with Breast Cancer: Is Short-Term Follow-Up Appropriate? J Breast Cancer 2015; 18:181-6. [PMID: 26155295 PMCID: PMC4490268 DOI: 10.4048/jbc.2015.18.2.181] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2015] [Accepted: 05/20/2015] [Indexed: 12/27/2022] Open
Abstract
Purpose Breast ultrasonography (US) has been widely used in the preoperative examination of patients with breast cancer. Breast Imaging Reporting and Data System (BI-RADS) category 3 (C3) lesions (probably benign) are regarded as having a low probability of malignancy (≤2%). The purposes of this study were to verify the malignancy rates for synchronous BI-RADS C3 lesions in patients with breast cancer and consider appropriate management strategies for these lesions. Methods Between January 2010 and January 2013, a total of 161 patients underwent surgery in our institute for breast cancer and synchronous BI-RADS C3 lesions. In the US reports, we found records of 219 synchronous BI-RADS C3 nodules in 161 patients. They were excised during surgery for breast cancer management. Stepwise logistic regression analysis was used to identify predictors of malignancy for synchronous BI-RADS C3 lesions. Results The rate of malignancy among the 219 BI-RADS C3 lesions was 9.6%. In simple logistic regression analysis, the size of the primary tumor (p<0.001), pathologic T (pT) stage (p=0.002), and progesterone receptor (PR) status of the primary tumor (p=0.029) were significant predictive factors. In multiple logistic regression analysis, the pT stage and PR status of the primary tumor remained significant predictors (p=0.004 and p=0.003, respectively), and human epidermal growth factor receptor 2 (HER2) was identified as another significant factor (p=0.006). Conclusion In patients with breast cancer who are scheduled for surgery, needle biopsy or excision should be considered for synchronous BI-RADS C3 lesions identified on preoperative US when the primary tumor has the following risk factors: large size, high PR expression, and HER2 positivity.
Collapse
Affiliation(s)
- Seokwon Lee
- Department of Surgery, Biomedical Research Institute, Pusan National University Hospital, Busan, Korea
| | - Younglae Jung
- Department of Surgery, Biomedical Research Institute, Pusan National University Hospital, Busan, Korea
| | - Youngtae Bae
- Department of Surgery, Biomedical Research Institute, Pusan National University Hospital, Busan, Korea
| |
Collapse
|
5
|
Shi XQ, Li JL, Wan WB, Huang Y. A set of shear wave elastography quantitative parameters combined with ultrasound BI-RADS to assess benign and malignant breast lesions. ULTRASOUND IN MEDICINE & BIOLOGY 2015; 41:960-966. [PMID: 25701532 DOI: 10.1016/j.ultrasmedbio.2014.11.014] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/13/2014] [Revised: 11/13/2014] [Accepted: 11/20/2014] [Indexed: 06/04/2023]
Abstract
The goal of this study was to determine whether a combination of shear wave elastography (SWE) quantitative parameters could improve the accuracy of ultrasonography in the differentiation of benign and malignant breast lesions. Two hundred seventy-nine breast lesions in 251 women were evaluated with ultrasonography and SWE; pathologic results of all lesions were available. Each lesion was classified according to the Breast Imaging Reporting and Data System (BI-RADS) for ultrasound. SWE quantitative parameters, including maximum elastic value (Emax), mean elastic value (E mean), standard deviation (SD) and ratio of E mean of the lesion to E mean of the surrounding parenchyma (E ratio), were recorded. A receiver operating characteristic curve was used to determine their cutoff values. When any of the four parameters was equal to or higher than the cutoff value, the set of SWE parameters was counted as positive. When both BI-RADS and the set were positive, lesions were evaluated as positive for malignancy. We compared the performance of this combination with use of BI-RADS, Emax, E mean, SD or E ratio alone and also with the combination of BI-RADS and Emax for benign/malignant differentiation. The combination of Emax, E mean, SD, or E ratio with BI-RADS had a sensitivity, specificity, positive predictive value, negative predictive value, accuracy and Youden index of 0.967, 0.912, 0.908, 0.969, 0.938 and 0.879, respectively. The accuracy was the highest (p < 0.01) without loss of sensitivity. Combining a set of SWE quantitative parameters (E max, E mean, SD and E ratio) could improve the accuracy of ultrasonography in differentiation of benign from malignant breast lesions, without loss of sensitivity.
Collapse
Affiliation(s)
- Xian Quan Shi
- Department of Ultrasound, Chinese People's Liberation Army General Hospital, Beijing, China
| | - Jun Lai Li
- Department of Ultrasound, Chinese People's Liberation Army General Hospital, Beijing, China.
| | - Wen Bo Wan
- Department of Ultrasound, Chinese People's Liberation Army General Hospital, Beijing, China
| | - Yan Huang
- Department of Ultrasound, China-Japan Friendship Hospital, Beijing, China
| |
Collapse
|
6
|
André M, Wiskin J, Borup D, Johnson S, Ojeda-Fournier H, Olson L. Quantitative volumetric breast imaging with 3D inverse scatter computed tomography. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2013; 2012:1110-3. [PMID: 23366090 DOI: 10.1109/embc.2012.6346129] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
A method was developed to map tissue properties of the entire breast including sound speed and attenuation using fully 3D nonlinear inverse-scattering tomography. Clinical measurements suggest that in breast tissue benign and cancerous lesions may be identified in part by these inherent acoustic parameters. Sound speed accuracy and linearity are very high over a wide range (1325-1700 m/sec) with ~1.5 mm resolution at 2 MHz in transmission mode. Attenuation tomograms provide image contrast over a wide range (0-4 dB/cm/MHz) and assist classification of masses. High resolution 0.6 mm volumetric reflection tomograms are acquired with bandwidth 2-8 MHz, are refraction-corrected with the transmission tissue data and are precisely registered in 3D with the transmission volumes. USCT promises an automated whole-breast scan providing a global view of the entire breast in 3D, facilitating comparison to prior exams in a reproducible geometry. Scanner design, automated operation and results of our trial with over 125 subjects with confirmed breast masses will be presented with detailed comparison to conventional sonography and MRI.
Collapse
Affiliation(s)
- Michael André
- Departments of Radiology, University of California and Veterans Affairs Medical Center, San Diego, CA 92093, USA.
| | | | | | | | | | | |
Collapse
|
7
|
Kim MJ, Park BW, Kim SI, Youk JH, Kwak JY, Moon HJ, Kim EK. Long-term follow-up results for ultrasound-guided vacuum-assisted removal of benign palpable breast mass. Am J Surg 2010; 199:1-7. [DOI: 10.1016/j.amjsurg.2008.11.037] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2008] [Revised: 11/10/2008] [Accepted: 11/10/2008] [Indexed: 10/20/2022]
|
8
|
Abstract
A lump in the breast is a cause of great concern. High frequency, high-resolution USG helps in its evaluation. This is exemplified in women with dense breast tissue where USG is useful in detecting small breast cancers that are not seen on mammography. Several studies in the past have addressed the issue of differentiating benign from malignant lesions in the breast. The American College of Radiology has also brought out a BIRADS-US classification system for categorizing focal breast lesions.
Collapse
|
9
|
Application of sonographic BI-RADS to synchronous breast nodules detected in patients with breast cancer. AJR Am J Roentgenol 2008; 191:653-8. [PMID: 18716090 DOI: 10.2214/ajr.07.2861] [Citation(s) in RCA: 25] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
OBJECTIVE The purpose of this study was to evaluate the applicability of the current BI-RADS for sonography to the assessment of synchronous breast nodules other than the primary malignant tumor in patients with breast cancer. MATERIALS AND METHODS One hundred eighty-nine synchronous nodules in 147 breast cancer patients were surgically excised after localization, and 412 synchronous nodules in 191 patients were observed or biopsied or excised without localization. Among a total of 601 synchronous nodules, 372 nodules were ipsilateral and 229 were contralateral to a primary malignant tumor. Two radiologists retrospectively reviewed sonograms of these nodules and determined the sonographic BI-RADS category without clinical information or pathologic results. For each nodule, the preoperative BI-RADS category and pathologic or follow-up results were compared. RESULTS Four hundred eighty-two nodules were classified category 3; 112 nodules, category 4; and seven nodules, category 5. Fifty-five (11.4%) of the category 3 nodules and 57 (47.9%) of the category 4 and 5 nodules were confirmed malignant. Thirty-six (21.2%) of 170 category 3 synchronous nodules in the same quadrant as the primary tumor were confirmed malignant, as were 12 (9.8%) of 122 nodules in a different quadrant and eight (4.2%) of 190 nodules in the contralateral breast. CONCLUSION For assessment of synchronous nodules in breast cancer patients, application of conventional screening sonographic BI-RADS categories may not account for possible increased risk of malignancy in synchronous nodules, especially those in the same quadrant of the breast as the index malignant tumor.
Collapse
|
10
|
Affiliation(s)
- Edward A Sickles
- University of California San Francisco School of Medicine, San Francisco, California, USA.
| |
Collapse
|