1
|
Dunenova G, Kalmataeva Z, Kaidarova D, Dauletbaev N, Semenova Y, Mansurova M, Grjibovski A, Kassymbekova F, Sarsembayev A, Semenov D, Glushkova N. The Performance and Clinical Applicability of HER2 Digital Image Analysis in Breast Cancer: A Systematic Review. Cancers (Basel) 2024; 16:2761. [PMID: 39123488 PMCID: PMC11311684 DOI: 10.3390/cancers16152761] [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: 06/06/2024] [Revised: 07/28/2024] [Accepted: 07/30/2024] [Indexed: 08/12/2024] Open
Abstract
This systematic review aims to address the research gap in the performance of computational algorithms for the digital image analysis of HER2 images in clinical settings. While numerous studies have explored various aspects of these algorithms, there is a lack of comprehensive evaluation regarding their effectiveness in real-world clinical applications. We conducted a search of the Web of Science and PubMed databases for studies published from 31 December 2013 to 30 June 2024, focusing on performance effectiveness and components such as dataset size, diversity and source, ground truth, annotation, and validation methods. The study was registered with PROSPERO (CRD42024525404). Key questions guiding this review include the following: How effective are current computational algorithms at detecting HER2 status in digital images? What are the common validation methods and dataset characteristics used in these studies? Is there standardization of algorithm evaluations of clinical applications that can improve the clinical utility and reliability of computational tools for HER2 detection in digital image analysis? We identified 6833 publications, with 25 meeting the inclusion criteria. The accuracy rate with clinical datasets varied from 84.19% to 97.9%. The highest accuracy was achieved on the publicly available Warwick dataset at 98.8% in synthesized datasets. Only 12% of studies used separate datasets for external validation; 64% of studies used a combination of accuracy, precision, recall, and F1 as a set of performance measures. Despite the high accuracy rates reported in these studies, there is a notable absence of direct evidence supporting their clinical application. To facilitate the integration of these technologies into clinical practice, there is an urgent need to address real-world challenges and overreliance on internal validation. Standardizing study designs on real clinical datasets can enhance the reliability and clinical applicability of computational algorithms in improving the detection of HER2 cancer.
Collapse
Affiliation(s)
- Gauhar Dunenova
- Department of Epidemiology, Biostatistics and Evidence-Based Medicine, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan
| | - Zhanna Kalmataeva
- Rector Office, Asfendiyarov Kazakh National Medical University, Almaty 050000, Kazakhstan;
| | - Dilyara Kaidarova
- Kazakh Research Institute of Oncology and Radiology, Almaty 050022, Kazakhstan;
| | - Nurlan Dauletbaev
- Department of Internal, Respiratory and Critical Care Medicine, Philipps University of Marburg, 35037 Marburg, Germany;
- Department of Pediatrics, Faculty of Medicine and Health Sciences, McGill University, Montreal, QC H4A 3J1, Canada
- Faculty of Medicine and Health Care, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan
| | - Yuliya Semenova
- School of Medicine, Nazarbayev University, Astana 010000, Kazakhstan;
| | - Madina Mansurova
- Department of Artificial Intelligence and Big Data, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan;
| | - Andrej Grjibovski
- Central Scientific Research Laboratory, Northern State Medical University, Arkhangelsk 163000, Russia;
- Department of Epidemiology and Modern Vaccination Technologies, I.M. Sechenov First Moscow State Medical University, Moscow 105064, Russia
- Department of Biology, Ecology and Biotechnology, Northern (Arctic) Federal University, Arkhangelsk 163000, Russia
- Department of Health Policy and Management, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan
| | - Fatima Kassymbekova
- Department of Public Health and Social Sciences, Kazakhstan Medical University “KSPH”, Almaty 050060, Kazakhstan;
| | - Aidos Sarsembayev
- School of Digital Technologies, Almaty Management University, Almaty 050060, Kazakhstan;
- Health Research Institute, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan;
| | - Daniil Semenov
- Computer Science and Engineering Program, Astana IT University, Astana 020000, Kazakhstan;
| | - Natalya Glushkova
- Department of Epidemiology, Biostatistics and Evidence-Based Medicine, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan
- Health Research Institute, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan;
| |
Collapse
|
2
|
Geiersbach KB, Sill DR, Del Rosario KM, Meyer RG, Spears GM, Yuhas JA, Sukov WR, Jenkins RB, Ocal IT, Mounajjed T, Chen B. Detailed Reanalysis of 500 Breast Cancers With Equivocal HER2 Immunohistochemistry and Borderline ERBB2 Fluorescence In Situ Hybridization Results. Am J Clin Pathol 2021; 156:886-894. [PMID: 33942843 DOI: 10.1093/ajcp/aqab042] [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: 11/14/2022] Open
Abstract
OBJECTIVES We investigated the impact of our laboratory's reflex testing process for resolving ERBB2 (HER2) status on breast cancer samples that require additional workup after fluorescence in situ hybridization (FISH), per guideline recommendations published in 2018 by the American Society of Clinical Oncology (ASCO) and the College of American Pathologists (CAP). METHODS In total, 500 breast cancer specimens with ERBB2 FISH results in groups 2 through 4 (all reported as immunohistochemistry [IHC] equivocal [2+] at external laboratories) were resubmitted for IHC testing in our laboratory. Per the ASCO/CAP guideline, FISH was rescored when internal IHC was also equivocal (2+), targeted to tumor areas demonstrating more intense IHC staining, if observed. RESULTS Reflex IHC/FISH testing changed the final reported ERBB2 status in 185 of 500 (37.0%) samples. Result changes included discordant IHC (n = 4 score 0, n = 132 score 1+, and n = 16 score 3+) and discordant FISH (n = 33). Numerical differences in FISH scores were comparable for targeted vs nontargeted FISH rescoring (P = .086 for ERBB2 copy number; P = .49 for ERBB2 ratio). Two cases showed larger differences in FISH scores, suggesting heterogeneity. CONCLUSIONS Retesting of breast cancer samples with equivocal IHC frequently changes IHC results, but targeted reanalysis of borderline FISH results rarely identifies significant differences in ERBB2 copy number or ratio.
Collapse
Affiliation(s)
| | - Daniel R Sill
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | | | - Reid G Meyer
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | - Grant M Spears
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | - Jason A Yuhas
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | - William R Sukov
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | - Robert B Jenkins
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | - Idris T Ocal
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Scottsdale, AZ, USA
| | - Taofic Mounajjed
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | - Beiyun Chen
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| |
Collapse
|
3
|
Kay C, Martínez-Pérez C, Meehan J, Gray M, Webber V, Dixon JM, Turnbull AK. Current trends in the treatment of HR+/HER2+ breast cancer. Future Oncol 2021; 17:1665-1681. [PMID: 33726508 DOI: 10.2217/fon-2020-0504] [Citation(s) in RCA: 24] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/03/2023] Open
Abstract
Treatment for HR+/HER2+ patients has been debated, as some tumors within this luminal HER2+ subtype behave like luminal A cancers, whereas others behave like non-luminal HER2+ breast cancers. Recent research and clinical trials have revealed that a combination of hormone and targeted anti-HER2 approaches without chemotherapy provides long-term disease control for at least some HR+/HER2+ patients. Novel anti-HER2 therapies, including neratinib and trastuzumab emtansine, and new agents that are effective in HR+ cancers, including the next generation of oral selective estrogen receptor downregulators/degraders and CDK4/6 inhibitors such as palbociclib, are now being evaluated in combination. This review discusses current trials and results from previous studies that will provide the basis for current recommendations on how to treat newly diagnosed patients with HR+/HER2+ disease.
Collapse
Affiliation(s)
- Charlene Kay
- Translational Oncology Research Group, MRC Institute of Genetics & Molecular Medicine, Western General Hospital, University of Edinburgh, Edinburgh, EH4 2XU, UK.,Breast Cancer Now Edinburgh Research Team, MRC Institute of Genetics & Molecular Medicine, Western General Hospital, University of Edinburgh, Edinburgh, EH4 2XU, UK
| | - Carlos Martínez-Pérez
- Translational Oncology Research Group, MRC Institute of Genetics & Molecular Medicine, Western General Hospital, University of Edinburgh, Edinburgh, EH4 2XU, UK.,Breast Cancer Now Edinburgh Research Team, MRC Institute of Genetics & Molecular Medicine, Western General Hospital, University of Edinburgh, Edinburgh, EH4 2XU, UK
| | - James Meehan
- Translational Oncology Research Group, MRC Institute of Genetics & Molecular Medicine, Western General Hospital, University of Edinburgh, Edinburgh, EH4 2XU, UK
| | - Mark Gray
- The Royal (Dick) School of Veterinary Studies & Roslin Institute, University of Edinburgh, Edinburgh, EH25 9RG, UK
| | - Victoria Webber
- Edinburgh Breast Unit, Western General Hospital, NHS Lothian, Edinburgh, EH4 2XU, UK
| | - J Michael Dixon
- Breast Cancer Now Edinburgh Research Team, MRC Institute of Genetics & Molecular Medicine, Western General Hospital, University of Edinburgh, Edinburgh, EH4 2XU, UK.,Edinburgh Breast Unit, Western General Hospital, NHS Lothian, Edinburgh, EH4 2XU, UK
| | - Arran K Turnbull
- Translational Oncology Research Group, MRC Institute of Genetics & Molecular Medicine, Western General Hospital, University of Edinburgh, Edinburgh, EH4 2XU, UK.,Breast Cancer Now Edinburgh Research Team, MRC Institute of Genetics & Molecular Medicine, Western General Hospital, University of Edinburgh, Edinburgh, EH4 2XU, UK
| |
Collapse
|
4
|
De Jesus J, Rosa M. Suboptimal concordance in testing and retesting results of triple-negative breast carcinoma cases among laboratories: one institution experience. Cancer Cell Int 2019; 19:263. [PMID: 31632197 PMCID: PMC6788018 DOI: 10.1186/s12935-019-0987-7] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2019] [Accepted: 10/01/2019] [Indexed: 12/31/2022] Open
Abstract
Background Triple-negative breast carcinoma (TNBC) patients do not benefit from hormone- or human epidermal growth factor receptor 2- (HER2-) targeted therapies. Accurate testing is pivotal for these patients. Methods TNBC cases that were retested at our institution during a 3-year period were evaluated for concordance rates in estrogen (ER) and progesterone (PR) receptor and HER2 results. Results We found 19 (22%) discrepancies (13 major/6 minor) among 86 cases. Minor discrepancies were in HER2 changes by immunohistochemistry, and all cases were demonstrated to be negative by and dual in situ hybridization. All major discrepancies were in ER/PR expression changes. In only 2 cases the treatment changed based on repeated results and/or patient history. Conclusions Discrepancies in prognostic/predictive testing continue to be frequent despite rigorous regulations. However, since for the majority of patients in our setting, the treatment plan did not change, reflex retesting for TNBC has been deemed unnecessary in our institution.
Collapse
Affiliation(s)
- Jose De Jesus
- Department of Anatomic Pathology, H. Lee Moffitt Cancer Center and Research Institute, 12902 Magnolia Drive, Tampa, FL 33612 USA
| | - Marilin Rosa
- Department of Anatomic Pathology, H. Lee Moffitt Cancer Center and Research Institute, 12902 Magnolia Drive, Tampa, FL 33612 USA
| |
Collapse
|
5
|
Hormone- and HER2-receptor assessment in 33,046 breast cancer patients: a nationwide comparison of positivity rates between pathology laboratories in the Netherlands. Breast Cancer Res Treat 2019; 175:487-497. [PMID: 30825048 PMCID: PMC6533417 DOI: 10.1007/s10549-019-05180-5] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2019] [Accepted: 02/19/2019] [Indexed: 01/13/2023]
Abstract
Purpose Patient management of invasive breast cancer (IBC) is to a large extent based on hormone- and HER2-receptor assessment. High-quality, reliable receptor assessment is of key importance as false results may lead to under- or overtreatment of patients. Surveillance of case-mix adjusted positivity rates has been suggested as a tool to identify laboratories with insufficient testing assays, as this covers the whole process of receptor assessment and enables laboratories to benchmark their positivity rates against other laboratories. We studied laboratory-specific variation in hormone- and HER2 positivity rates of 33,046 breast cancer patients using real-life nationwide data. Methods All synoptic pathology reports of IBC resection-specimens, obtained between 2013 and 2016, were retrieved from the nationwide Dutch pathology registry (PALGA). Absolute and case-mix adjusted receptor positivity rates were compared to the mean national proportion and presented in funnel plots in separate analyses for estrogen (ER), progesterone (PR) and HER2. Case-mix adjustment was performed by multivariable logistic regression. Results 33,794 IBC lesions from 33,046 patients of 39 pathology laboratories were included. After case-mix adjustment, mean positivity rates were 87.2% for ER (range 80.4–94.3), 71.3% for PR (62.5–77.5%), and 9.9% for HER2 (5.5–12.7%). Overall, 14 (35.9%), 17 (43.6%) and 11 (28.2%) laboratories showed positivity rates outside the 95% confidence interval for ER, PR and HER2, respectively. Conclusion This nationwide study shows that absolute variation in hormone- and HER2-receptor positivity rates between Dutch pathology laboratories is limited. Yet, the considerable number of outlying laboratories shows that there is still need for improvement. Continuous monitoring and benchmarking of positivity rates may help to realize this.
Collapse
|
6
|
Bogen SA. A Root Cause Analysis Into the High Error Rate in Clinical Immunohistochemistry. Appl Immunohistochem Mol Morphol 2019; 27:329-338. [PMID: 30807309 PMCID: PMC6706333 DOI: 10.1097/pai.0000000000000750] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
The field of Clinical Immunohistochemistry (IHC) is beset with a high error rate, an order of magnitude higher than in other types of clinical laboratory testing. Despite the many improvements in the field, these errors have persisted over the last 2 decades. The improvements over the years include an extensive literature describing the potential causes of errors and how to avoid them. More stringent regulatory guidelines have also been implemented. These measures reflect the standard view is that fixing the broad confluence of causes of error will address the problem. This review takes a different tack. To understand the high error rates, this review compares Clinical IHC laboratory practice to practices of other clinical laboratory disciplines. What aspects of laboratory testing that minimize errors in other clinical laboratory disciplines are not found in Clinical IHC? In this review, we seek to identify causal factors and underlying root causes that are unique to the field of Clinical IHC in comparison to other laboratory testing disciplines. The most important underlying root cause is the absence of traceable units of measure, international standards, calibrators that are traceable to standards, and quantitative monitoring of controls. These tools and practices (in other clinical laboratory disciplines) provide regular accurate feedback to laboratory personnel on analytic test performance.
Collapse
Affiliation(s)
- Steven A Bogen
- Department of Pathology & Laboratory Medicine, Tufts Medical Center and MDP LLC, Boston, MA
| |
Collapse
|