1
|
Tong Y, Hu Z, Wang H, Huang J, Zhan Y, Chai W, Deng Y, Yuan Y, Shen K, Wang Y, Chen X, Yu J. Anti-HER2 therapy response assessment for guiding treatment (de-)escalation in early HER2-positive breast cancer using a novel deep learning radiomics model. Eur Radiol 2024:10.1007/s00330-024-10609-7. [PMID: 38329503 DOI: 10.1007/s00330-024-10609-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2023] [Revised: 11/24/2023] [Accepted: 01/01/2024] [Indexed: 02/09/2024]
Abstract
OBJECTIVES Anti-HER2 targeted therapy significantly reduces risk of relapse in HER2 + breast cancer. New measures are needed for a precise risk stratification to guide (de-)escalation of anti-HER2 strategy. METHODS A total of 726 HER2 + cases who received no/single/dual anti-HER2 targeted therapies were split into three respective cohorts. A deep learning model (DeepTEPP) based on preoperative breast magnetic resonance (MR) was developed. Patients were scored and categorized into low-, moderate-, and high-risk groups. Recurrence-free survival (RFS) was compared in patients with different risk groups according to the anti-HER2 treatment they received, to validate the value of DeepTEPP in predicting treatment efficacy and guiding anti-HER2 strategy. RESULTS DeepTEPP was capable of risk stratification and guiding anti-HER2 treatment strategy: DeepTEPP-Low patients (60.5%) did not derive significant RFS benefit from trastuzumab (p = 0.144), proposing an anti-HER2 de-escalation. DeepTEPP-Moderate patients (19.8%) significantly benefited from trastuzumab (p = 0.048), but did not obtain additional improvements from pertuzumab (p = 0.125). DeepTEPP-High patients (19.7%) significantly benefited from dual HER2 blockade (p = 0.045), suggesting an anti-HER2 escalation. CONCLUSIONS DeepTEPP represents a pioneering MR-based deep learning model that enables the non-invasive prediction of adjuvant anti-HER2 effectiveness, thereby providing valuable guidance for anti-HER2 (de-)escalation strategies. DeepTEPP provides an important reference for choosing the appropriate individualized treatment in HER2 + breast cancer patients, warranting prospective validation. CLINICAL RELEVANCE STATEMENT We built an MR-based deep learning model DeepTEPP, which enables the non-invasive prediction of adjuvant anti-HER2 effectiveness, thus guiding anti-HER2 (de-)escalation strategies in early HER2-positive breast cancer patients. KEY POINTS • DeepTEPP is able to predict anti-HER2 effectiveness and to guide treatment (de-)escalation. • DeepTEPP demonstrated an impressive prognostic efficacy for recurrence-free survival and overall survival. • To our knowledge, this is one of the very few, also the largest study to test the efficacy of a deep learning model extracted from breast MR images on HER2-positive breast cancer survival and anti-HER2 therapy effectiveness prediction.
Collapse
Affiliation(s)
- Yiwei Tong
- Department of General Surgery, Comprehensive Breast Health Center, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, 197 Ruijin Er Road, Shanghai, 200025, China
| | - Zhaoyu Hu
- School of Information Science and Technology, Fudan University, No. 220, Handan Road, Yangpu District, Shanghai, 200433, China
| | - Haoyu Wang
- Department of General Surgery, Comprehensive Breast Health Center, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, 197 Ruijin Er Road, Shanghai, 200025, China
| | - Jiahui Huang
- Department of General Surgery, Comprehensive Breast Health Center, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, 197 Ruijin Er Road, Shanghai, 200025, China
| | - Ying Zhan
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Weimin Chai
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Yinhui Deng
- School of Information Science and Technology, Fudan University, No. 220, Handan Road, Yangpu District, Shanghai, 200433, China
| | - Ying Yuan
- Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China
| | - Kunwei Shen
- Department of General Surgery, Comprehensive Breast Health Center, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, 197 Ruijin Er Road, Shanghai, 200025, China
| | - Yuanyuan Wang
- School of Information Science and Technology, Fudan University, No. 220, Handan Road, Yangpu District, Shanghai, 200433, China
| | - Xiaosong Chen
- Department of General Surgery, Comprehensive Breast Health Center, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, 197 Ruijin Er Road, Shanghai, 200025, China.
| | - Jinhua Yu
- School of Information Science and Technology, Fudan University, No. 220, Handan Road, Yangpu District, Shanghai, 200433, China.
| |
Collapse
|
2
|
Abstract
Several articles in the literature have demonstrated a promising role for breast MRI techniques that are more economic in total exam time than others when used as supplement to mammography for detection and diagnosis of breast cancer. There are many technical factors that must be considered in the shortened breast MRI protocols to cut down time of standard ones, including using optimal fat suppression, gadolinium-chelates intravascular contrast administrations for dynamic imaging with post processing subtractions and maximum intensity projections (MIP) high spatial and temporal resolution among others. Multiparametric breast MRI that includes both gadolinium-dependent, i.e., dynamic contrast-enhanced (DCE-MRI) and gadolinium-free techniques, i.e., diffusion-weighted/diffusion-tensor magnetic resonance imaging (DWI/DTI) are shown by several investigators that can provide extremely high sensitivity and specificity for detection of breast cancer. This article provides an overview of the proven indications for breast MRI including breast cancer screening for higher than average risk, determining chemotherapy induced tumor response, detecting residual tumor after incomplete surgical excision, detecting occult cancer in patients presenting with axillary node metastasis, detecting residual tumor after incomplete breast cancer surgical excision, detecting cancer when results of conventional imaging are equivocal, as well patients suspicious of having breast implant rupture. Despite having the highest sensitivity for breast cancer detection, there are pitfalls, however, secondary to false positive and false negative contrast enhancement and contrast-free MRI techniques. Awareness of the strengths and limitations of different approaches to obtain state of the art MR images of the breast will facilitate the work-up of patients with suspicious breast lesions.
Collapse
Affiliation(s)
- Anabel M Scaranelo
- Medical Imaging Department, 12366University of Toronto, Ontario, Canada.,Breast Imaging Division, Joint Department of Medical Imaging, University of Health Network, Sinai Health and Women's College Hospital, Toronto, Ontario, Canada
| |
Collapse
|
3
|
Healy NA, Benson JR, Sinnatamby R. Role of early post-operative breast MRI: how helpful is it in deciding the next step for women who may have residual disease? BJR Open 2021; 3:20210024. [PMID: 34381952 PMCID: PMC8327930 DOI: 10.1259/bjro.20210024] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2021] [Revised: 07/04/2021] [Accepted: 07/06/2021] [Indexed: 02/03/2023] Open
Abstract
Objectives Positive resection margins following breast conserving surgery are a risk factor for local disease recurrence. Subsequent management of patients is often not straightforward, with post-operative breast MRI increasingly used to aid decision-making. Interpretation of MRI after surgery can prove challenging due to local inflammatory enhancement. We reviewed our experience of post-operative breast MRIs to determine their ability to detect residual disease and to evaluate how they changed initial patient management from re-excision to an alternative. Methods: A search of breast MRIs performed from August 2014 to December 2019 was undertaken, to identify those performed post-operatively within 4 months of breast conserving surgery. Electronic patient records and imaging were evaluated to determine additional work-up, pathology and surgical outcomes. Results: Of the 2274 breast MRIs during the study period, 44 (2%) were performed post-operatively to evaluate 47 breasts. MRI was normal in 20 cases (43%), suspicious findings at surgical cavity only in 13 (28%), suspicious ipsilateral distant breast findings only in 6 (13%), and both cavity and distant findings in 7 cases (15%). Contralateral abnormalities were identified in 3 cases. Following MRI, mastectomy was performed in 11 cases, re-excision in 25, with 2 subsequent mastectomies, and multidisciplinary team accepted margins in 11 cases, 10 of whom underwent post-operative radiotherapy. MRI altered initial patient management from re-excision to an alternative in 25 cases (45%). Conclusion: Post-operative breast MRI, although potentially challenging to interpret, can prove useful in planning the next step in patient management, particularly in its ability to evaluate the whole breast. Advances in knowledge Post-operative breast MRI is increasingly requested at multidisciplinary team following breast conserving surgery with positive surgical margins on histology, however interpretation is challenging. The value of these studies lie in assessment of the distant breast rather than the surgical resection cavity and can alter patient management guiding the most appropriate next step for definitive treatment.
Collapse
Affiliation(s)
- Nuala A Healy
- Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Addenbrookes' Hospital, Hills Road, Cambridge, UK
| | - John R Benson
- Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Addenbrookes' Hospital, Hills Road, Cambridge, UK
| | - Ruchi Sinnatamby
- Cambridge Breast Unit, Cambridge University Hospitals NHS Foundation Trust, Addenbrookes' Hospital, Hills Road, Cambridge, UK
| |
Collapse
|
4
|
Zheng S, Qi L, Guang-Qiang Z, Ming-Ming S, Chun-Hong X. Role of Magnetic Resonance Imaging in Predicting Residual Breast Cancer After Vacuum-Assisted Breast Biopsy. Am Surg 2020; 87:885-891. [PMID: 33284052 DOI: 10.1177/0003134820952430] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
PURPOSE This study aims to evaluate the effectiveness of breast magnetic resonance imaging (MRI) in detecting residual breast cancer in patients after vacuum-assisted breast biopsy (VABB). METHODS Between 2012 and 2019, 26 patients with breast cancer who underwent VABB were enrolled. Breast MRI was conducted after VABB. Imaging findings were then compared with the histopathological results. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were calculated. RESULTS Residual cancer was confirmed histologically in 8 of the 26 patients after VABB. The overall sensitivity, specificity, PPV, NPV, and accuracy of MRI for diagnosing residual cancer were 79.9%, 73.0%, 87.1%, 61.3%, and 77.8%, respectively. The sensitivity and NPV improved to 100%, when the number of biopsy specimens was larger than five. CONCLUSION Breast MRI showed high sensitivity and NPV in detecting residual breast tumor after VABB.
Collapse
Affiliation(s)
- Sun Zheng
- Department of Thyroid and Breast Surgery, Weifang Hospital of Traditional Chinese Medicine, China
| | - Liu Qi
- Department of Thyroid and Breast Surgery, Weifang Hospital of Traditional Chinese Medicine, China
| | - Zhang Guang-Qiang
- Department of Thyroid and Breast Surgery, Weifang Hospital of Traditional Chinese Medicine, China
| | - Shi Ming-Ming
- Department of Thyroid and Breast Surgery, Weifang Hospital of Traditional Chinese Medicine, China
| | - Xu Chun-Hong
- Department of Thyroid and Breast Surgery, Weifang Hospital of Traditional Chinese Medicine, China
| |
Collapse
|
5
|
Ruiz-Flores L, Whitman GJ, Le-Petross HTC, Hess KR, Parikh JR. Variation in Technical Quality of Breast MRI. Acad Radiol 2020; 27:468-475. [PMID: 31371208 DOI: 10.1016/j.acra.2019.07.002] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2019] [Revised: 06/20/2019] [Accepted: 07/04/2019] [Indexed: 02/03/2023]
Abstract
PURPOSE Breast magnetic resonance imaging (MRI) quality may vary across the United States. Our aim was to investigate the quality of outside breast MRIs presenting for second opinion at a tertiary cancer center following implementation of the American College of Radiology (ACR) Breast MRI Accreditation Program. MATERIALS AND METHODS We retrospectively reviewed the technical quality of the MRI studies of 100 consecutive cases submitted for second opinion in 2013. The image quality was blindly reviewed per ACR Breast MRI Accreditation Program by three fellowship-trained breast radiologists and one breast imaging fellow. RESULTS In total, 88 of the 100 cases were referred from facilities in the United States. Sixty (68%) of the 88 cases had at least one technical deficiency. In 10 cases (11%), more than five different technical deficiencies occurred. The most frequently encountered deficiencies were related to artifacts (74%), with shimming (N = 17) and motion (N = 16) being the most common. In total, 38% of cases (N = 33) had a deficient T2-weighted sequence, mostly due to low signal to noise ratio (N = 25). A total of 27% cases (N = 24) had deficiencies in the delayed phase postcontrast T1-weighted sequence, mainly due to low signal to noise ratio (N = 21) and 23% had deficiencies in the early phase postcontrast T1-weighted sequence, predominantly due to low signal to noise ratio as well. (N = 19). CONCLUSION Our study demonstrates variability of breast MRI quality across the United States. Radiologists should become familiar with the requirements of the ACR breast MRI accreditation program and strive to meet the expected standards in order to enhance patient quality and safety.
Collapse
Affiliation(s)
- Lorell Ruiz-Flores
- Section of Breast Imaging, Department of Diagnostic Radiology, The University of Texas MD Anderson Cancer Center, 1155 Pressler St., Unit 1350, CPB 5.3208, Houston, TX 77030.
| | - Gary J Whitman
- Section of Breast Imaging, Department of Diagnostic Radiology, The University of Texas MD Anderson Cancer Center, 1155 Pressler St., Unit 1350, CPB 5.3208, Houston, TX 77030
| | - H T Carissa Le-Petross
- Section of Breast Imaging, Department of Diagnostic Radiology, The University of Texas MD Anderson Cancer Center, 1155 Pressler St., Unit 1350, CPB 5.3208, Houston, TX 77030
| | - Kenneth R Hess
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, Texas
| | - Jay R Parikh
- Section of Breast Imaging, Department of Diagnostic Radiology, The University of Texas MD Anderson Cancer Center, 1155 Pressler St., Unit 1350, CPB 5.3208, Houston, TX 77030
| |
Collapse
|
6
|
Park G, Bae K, Hwang IY, Kim JS, Kwon WJ, Bang M. Prediction of Residual Malignancy After Excisional Biopsy for Breast Cancer With Suspicious Microcalcifications: Comparison of Mammography and Magnetic Resonance Imaging. Clin Breast Cancer 2019; 19:e753-e758. [DOI: 10.1016/j.clbc.2019.05.003] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2019] [Accepted: 05/05/2019] [Indexed: 11/26/2022]
|
7
|
Schoub PK. Understanding indications and defining guidelines for breast magnetic resonance imaging. SA J Radiol 2018; 22:1353. [PMID: 31754513 PMCID: PMC6837823 DOI: 10.4102/sajr.v22i2.1353] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2018] [Accepted: 08/07/2018] [Indexed: 12/29/2022] Open
Abstract
Magnetic resonance imaging (MRI) of the breast is the most sensitive imaging modality for detecting cancer. With improved scan resolution and correctly applied clinical indications, the specificity of breast MRI has markedly improved in recent years. Current literature indicates an overall sensitivity for breast MRI of 98% - 100% and specificity of 88%. By comparison, the sensitivity and specificity for mammography is in the region of 71% and 98%, respectively. In particular, the very high negative predictive value (NPV) of breast MRI, which approaches 100%, is hugely useful in establishing absence of disease. Furthermore, the ability to accurately delineate viable cancer by way of combining both morphological and functional (contrast enhancement) capabilities means that MRI is the best tool we have in terms of local cancer staging and identifying residual or recurrent disease. The high NPV also means that breast MRI is uniquely capable of ruling out cancer or high-grade ductal carcinoma in situ in appropriate circumstances. I hope that the following guidelines that are based on those of the American College of Radiology and the European Society of Breast Imaging in addition to multiple review articles will provide some assistance to radiologists in terms of the correct indications for breast MRI. There are few formal guidelines in South Africa for the usage of breast MRI. In fact, there is a general paucity of guidelines in the international radiology world. The role of breast MRI in high-risk screening and identification of the primary in occult breast cancer is universally accepted. Thereafter, there is little consensus. By using some general guidelines, and bringing MRI into the discussion of multidisciplinary breast cancer management, good clinical practice and consistent decision-making can be established.
Collapse
Affiliation(s)
- Peter K Schoub
- Department of Radiology, Parklane Radiology, Johannesburg, South Africa
| |
Collapse
|