1
|
Eloy C, Marques A, Pinto J, Pinheiro J, Campelos S, Curado M, Vale J, Polónia A. Artificial intelligence-assisted cancer diagnosis improves the efficiency of pathologists in prostatic biopsies. Virchows Arch 2023; 482:595-604. [PMID: 36809483 PMCID: PMC10033575 DOI: 10.1007/s00428-023-03518-5] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2023] [Revised: 02/07/2023] [Accepted: 02/09/2023] [Indexed: 02/23/2023]
Abstract
Paige Prostate is a clinical-grade artificial intelligence tool designed to assist the pathologist in detecting, grading, and quantifying prostate cancer. In this work, a cohort of 105 prostate core needle biopsies (CNBs) was evaluated through digital pathology. Then, we compared the diagnostic performance of four pathologists diagnosing prostatic CNB unaided and, in a second phase, assisted by Paige Prostate. In phase 1, pathologists had a diagnostic accuracy for prostate cancer of 95.00%, maintaining their performance in phase 2 (93.81%), with an intraobserver concordance rate between phases of 98.81%. In phase 2, pathologists reported atypical small acinar proliferation (ASAP) less often (about 30% less). Additionally, they requested significantly fewer immunohistochemistry (IHC) studies (about 20% less) and second opinions (about 40% less). The median time required for reading and reporting each slide was about 20% lower in phase 2, in both negative and cancer cases. Lastly, the average total agreement with the software performance was observed in about 70% of the cases, being significantly higher in negative cases (about 90%) than in cancer cases (about 30%). Most of the diagnostic discordances occurred in distinguishing negative cases with ASAP from small foci of well-differentiated (less than 1.5 mm) acinar adenocarcinoma. In conclusion, the synergic usage of Paige Prostate contributes to a significant decrease in IHC studies, second opinion requests, and time for reporting while maintaining highly accurate diagnostic standards.
Collapse
Affiliation(s)
- Catarina Eloy
- Pathology Laboratory, Institute of Molecular Pathology and Immunology of the University of Porto (Ipatimup), Porto, Portugal
- i3S - Instituto de Investigação E Inovação Em Saúde, Porto, Portugal
- Faculty of Medicine, University of Porto, Porto, Portugal
| | - Ana Marques
- Pathology Laboratory, Institute of Molecular Pathology and Immunology of the University of Porto (Ipatimup), Porto, Portugal
- Serviço de Anatomia Patológica, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - João Pinto
- Pathology Laboratory, Institute of Molecular Pathology and Immunology of the University of Porto (Ipatimup), Porto, Portugal
- Serviço de Anatomia Patológica, Hospital Pedro Hispano - Unidade Local de Saúde de Matosinhos, Matosinhos, Portugal
| | - Jorge Pinheiro
- Pathology Laboratory, Institute of Molecular Pathology and Immunology of the University of Porto (Ipatimup), Porto, Portugal
- Serviço de Anatomia Patológica, Centro Hospitalar Universitário de São João, Porto, Portugal
| | - Sofia Campelos
- Pathology Laboratory, Institute of Molecular Pathology and Immunology of the University of Porto (Ipatimup), Porto, Portugal
| | - Mónica Curado
- Pathology Laboratory, Institute of Molecular Pathology and Immunology of the University of Porto (Ipatimup), Porto, Portugal
| | - João Vale
- Pathology Laboratory, Institute of Molecular Pathology and Immunology of the University of Porto (Ipatimup), Porto, Portugal
| | - António Polónia
- Pathology Laboratory, Institute of Molecular Pathology and Immunology of the University of Porto (Ipatimup), Porto, Portugal.
- i3S - Instituto de Investigação E Inovação Em Saúde, Porto, Portugal.
| |
Collapse
|
2
|
Yoder A, Inge LJ, Chen CC, Marati VR, Nguyen TK, Zuiderveld K, Martin J, Gladden S, Miri MS, Venugopal R, Lopez B, Ranger-Moore J, Guetter C. Computer-Aided Scoring Of () Gene Amplification Status In Breast Cancer. J Pathol Inform 2022; 13:100116. [PMID: 36268099 PMCID: PMC9577051 DOI: 10.1016/j.jpi.2022.100116] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2022] [Revised: 06/05/2022] [Accepted: 06/24/2022] [Indexed: 11/30/2022] Open
Abstract
Background Identification of HER2 protein overexpression and/or amplification of the HER2 gene are required to qualify breast cancer patients for HER2 targeted therapies. In situ hybridization (ISH) assays that identify HER2 gene amplification function as a stand-alone test for determination of HER2 status and rely on the manual quantification of the number of HER2 genes and copies of chromosome 17 to determine HER2 amplification. Methods To assist pathologists, we have developed the uPath HER2 Dual ISH Image Analysis for Breast (uPath HER2 DISH IA) algorithm, as an adjunctive aid in the determination of HER2 gene status in breast cancer specimens. The objective of this study was to compare uPath HER2 DISH image analysis vs manual read scoring of VENTANA HER2 DISH-stained breast carcinoma specimens with ground truth (GT) gene status as the reference. Three reader pathologists reviewed 220, formalin-fixed, paraffin-embedded (FFPE) breast cancer cases by both manual and uPath HER2 DISH IA methods. Scoring results from manual read (MR) and computer-assisted scores (image analysis, IA) were compared against the GT gene status generated by consensus of a panel of pathologists. The differences in agreement rates of HER2 gene status between manual, computer-assisted, and GT gene status were determined. Results The positive percent agreement (PPA) and negative percent agreement (NPA) rates for image analysis (IA) vs GT were 97.2% (95% confidence interval [CI]: 95.0, 99.3) and 94.3% (95% CI: 90.8, 97.3) respectively. Comparison of agreement rates showed that the lower bounds of the 95% CIs for the difference of PPA and NPA for IA vs MR were –0.9% and –6.2%, respectively. Further, inter- and intra-reader agreement rates in the IA method were observed with point estimates of at least 96.7%. Conclusions Overall, our data show that the uPath HER2 DISH IA is non-inferior to manual scoring and supports its use as an aid for pathologists in routine diagnosis of breast cancer. Image analysis algorithm for HER2 amplification using Bright-field ISH in Breast. Automated tumor cell selection and quantitation within pathologist defined ROI. The image analysis algorithm is non-inferior to manual scoring. Integrated solution to support pathologists in determining HER2 gene status.
Collapse
|
3
|
Polónia A, Caramelo A. HER2 in situ hybridization test in breast cancer: quantifying margins of error and genetic heterogeneity. Mod Pathol 2021; 34:1478-1486. [PMID: 33980971 DOI: 10.1038/s41379-021-00813-x] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2021] [Revised: 03/27/2021] [Accepted: 03/29/2021] [Indexed: 11/09/2022]
Abstract
The aim of the present study was to evaluate the effect of counting increasing number of invasive cancer cells in the result of the HER2 in situ hybridization (ISH) test in breast cancer as well as to compare two different approaches of measuring genomic heterogeneity (single cell and population based). A cohort of 100 consecutive breast cancer cases (primary and metastatic) were evaluated for HER2 gene amplification with bright-field ISH. The evaluation of the samples included scoring 20 nuclei, in five different areas, measuring the margins of error for each case. Genomic heterogeneity (GH) was defined by the 2018 ASCO/CAP guideline as a discrete population of tumor cells with HER2 amplification. We also evaluated GH as single tumor cells with HER2 amplification. The stabilization of the coefficient of variation of HER2/CEP17 ratio requires about 60 invasive cancer cells. The average margin of error of HER2/CEP17 ratio and of HER2 copy number was 0.40 and 0.53, respectively, when counting 20 cells, decreasing to 0.20 and 0.26 when counting 100 cells. Population GH was observed in 1% of the cases, while single cell GH was observed in 27% of the cases, reaching its maximum value in cases near the thresholds of positivity. Therefore, margins of error in HER2 ISH test are high, and the minimal cell number recommended in current guidelines should be raised to at least 60 cells. Population GH is a rare event and single cell GH is maximal in cases near the thresholds.
Collapse
Affiliation(s)
- António Polónia
- Department of Pathology, Ipatimup Diagnostics, Institute of Molecular Pathology and Immunology, University of Porto, Porto, Portugal. .,I3S - Instituto de Investigação e Inovação em Saúde, University of Porto, Porto, Portugal.
| | - Ana Caramelo
- Department of Pathology, Ipatimup Diagnostics, Institute of Molecular Pathology and Immunology, University of Porto, Porto, Portugal.,I3S - Instituto de Investigação e Inovação em Saúde, University of Porto, Porto, Portugal
| |
Collapse
|
4
|
Curado M, Caramelo AS, Eloy C, Polónia A. What to expect from the 2018 ASCO/CAP HER2 guideline in the reflex in situ hybridization test of immunohistochemically equivocal 2+ cases? Virchows Arch 2019; 475:303-311. [PMID: 30953146 DOI: 10.1007/s00428-019-02567-z] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2019] [Revised: 03/22/2019] [Accepted: 03/25/2019] [Indexed: 01/12/2023]
Abstract
To evaluate the effect of the 2018 ASCO/CAP guideline in the identification of HER2-positive breast carcinomas (BC) in reflex in situ hybridization (ISH) test. A total of 592 primary invasive BC cases from before and after the publication of the updated ASCO/CAP guideline were evaluated for HER2 amplification by silver ISH according to the 2013 and 2018 guidelines. Cases were mostly (95%) HER2 equivocal by immunohistochemistry (IHC), not centrally reviewed. Other reasons for referring cases were IHC confirmation, IHC discordancy (either between needle-core-biopsy (NCB) and surgical excision specimen (SES) or between different laboratories) and IHC result unexpected for histopathologic features. Cases evaluated with the 2013 guideline (1st cohort) were 14.6% HER2-positive, decreasing significantly after the reclassification with the 2018 guideline due to the exclusion of group 2 cases without HER2 protein overexpression. Cases studied after the implementation of the 2018 guideline (2nd cohort) were 8.7% HER2-positive, a frequency that was not significantly different from the reclassification of the 1st cohort with the 2018 guideline. All cases referred for IHC confirmation had the expected ISH result. Cases with IHC discordancy between NCB and SES were ISH concordant. Only one out of 14 cases with an IHC score 3+ and classified as histological grade 1 or with a Ki67 below 10% was classified as ISH HER2-positive. The 2018 ASCO/CAP guideline resulted in a decrease of HER2-positive cases in reflex ISH test, selecting less patients for anti-HER2-targeted therapy.
Collapse
Affiliation(s)
- Mónica Curado
- Department of Pathology, Ipatimup Diagnostics, Institute of Molecular Pathology and Immunology, University of Porto, Rua Júlio Amaral de Carvalho, 45, 4200-135, Porto, Portugal.,I3S-Instituto de Investigação e Inovação em Saúde, University of Porto, Rua Júlio Amaral de Carvalho, 45, 4200-135, Porto, Portugal
| | - Ana Sofia Caramelo
- Department of Pathology, Ipatimup Diagnostics, Institute of Molecular Pathology and Immunology, University of Porto, Rua Júlio Amaral de Carvalho, 45, 4200-135, Porto, Portugal.,I3S-Instituto de Investigação e Inovação em Saúde, University of Porto, Rua Júlio Amaral de Carvalho, 45, 4200-135, Porto, Portugal
| | - Catarina Eloy
- Department of Pathology, Ipatimup Diagnostics, Institute of Molecular Pathology and Immunology, University of Porto, Rua Júlio Amaral de Carvalho, 45, 4200-135, Porto, Portugal.,I3S-Instituto de Investigação e Inovação em Saúde, University of Porto, Rua Júlio Amaral de Carvalho, 45, 4200-135, Porto, Portugal.,Faculty of Medicine, University of Porto, Al. Prof. Hernâni Monteiro, 4200-319, Porto, Portugal
| | - António Polónia
- Department of Pathology, Ipatimup Diagnostics, Institute of Molecular Pathology and Immunology, University of Porto, Rua Júlio Amaral de Carvalho, 45, 4200-135, Porto, Portugal. .,I3S-Instituto de Investigação e Inovação em Saúde, University of Porto, Rua Júlio Amaral de Carvalho, 45, 4200-135, Porto, Portugal.
| |
Collapse
|
5
|
Polónia A, Oliveira G, Schmitt F. Characterization of HER2 gene amplification heterogeneity in invasive and in situ breast cancer using bright-field in situ hybridization. Virchows Arch 2017; 471:589-598. [PMID: 28702778 DOI: 10.1007/s00428-017-2189-9] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2017] [Revised: 05/30/2017] [Accepted: 06/28/2017] [Indexed: 10/19/2022]
Abstract
The aims of this study were to evaluate and compare the HER2 gene amplification status in invasive and adjacent in situ breast carcinoma, using bright-field in situ hybridization, and to document the possible presence of HER2 genetic heterogeneity (HER2-GH) in both components. A cohort of 100 primary invasive carcinomas (IC) associated with carcinoma in situ (CIS) were evaluated for HER2 gene amplification by SISH according to the 2013 ASCO/CAP HER2 guideline. A second cohort of all the cases with HER2-GH since the introduction of the updated ASCO/CAP HER2 guideline was also characterized, and an evaluation of the HER2 gene amplification in the CIS component, if present, was also done. In the first cohort, the HER2 amplification in the IC was negative in 87% of the cases and positive in 13% of the cases, without the presence of HER2-GH. All the cases had an associated CIS with the same HER2 status as IC, with four cases of CIS presenting HER2-GH. In the CIS, we observed a significant relationship of HER2 gene amplification with high nuclear grade. In the four cases with HER2-GH in CIS, two cases presented HER2 gene amplification in the IC. The second cohort included 12 cases with HER2-GH in a total of 1243 IC cases (0.97%). Additionally, we identified two cases associated with non-amplified CIS. HER2-GH is a rare event in IC and can already be present in CIS, not being an important step in the acquisition of invasive features.
Collapse
Affiliation(s)
- António Polónia
- Department of Pathology, Ipatimup Diagnostics, Ipatimup-Institute of Molecular Pathology and Immunology of the University of Porto, Rua Júlio Amaral de Carvalho 45, 4200-135, Porto, Portugal.,Faculty of Medicine, University of Porto, Alameda Professor Hernâni Monteiro, 4200-319, Porto, Portugal
| | - Guilherme Oliveira
- Department of Pathology, Ipatimup Diagnostics, Ipatimup-Institute of Molecular Pathology and Immunology of the University of Porto, Rua Júlio Amaral de Carvalho 45, 4200-135, Porto, Portugal
| | - Fernando Schmitt
- Department of Pathology, Ipatimup Diagnostics, Ipatimup-Institute of Molecular Pathology and Immunology of the University of Porto, Rua Júlio Amaral de Carvalho 45, 4200-135, Porto, Portugal. .,Faculty of Medicine, University of Porto, Alameda Professor Hernâni Monteiro, 4200-319, Porto, Portugal. .,Laboratoire national de santé, 1, rue Louis Rech, 3555, Dudelange, Luxembourg.
| |
Collapse
|