Publications

Oncotopix Clinical, Publicly Sharable

In breast cancer, analysis of HER2 expression is pivotal for treatment decision. This study aimed at comparing digital, automated image analysis with manual reading using the HER2-CONNECT algorithm (Visiopharm) in order to minimize the number of equivocal 2+ scores and the need for reflex fluorescence in situ hybridization (FISH) analysis. Consecutive samples from 462 patients were included. Tissue micro arrays (TMAs) were routinely manufactured including two 2 mm cores from each patient, and each core was assessed in order to ensure the presence of invasive carcinoma. Immunohistochemical staining (IHC) was performed with Roche/Ventanaś HER2 ready-to-use kit. TMAs were scanned in a Zeiss Axio Z1 scanner, and one batch analysis of the HER2-CONNECT algorithm including all core samples was run using Visiopharmś cloud-based software. The automated reading was compared to conventional manual assessment of HER2 protein expression, together with FISH analysis of HER2 gene amplification for borderline (2+) protein expression samples. Compared to FISH analysis, manual assessment of the HER2 protein expression demonstrated a sensitivity of 85.8% and a specificity of 86.0% with 14.0% equivocal samples. With HER2-CONNECT, sensitivity increased to 100 % and specificity to 95.5% with less than 4.5% equivocal. Total agreement when comparing HER2-CONNECT with manual IHC assessment supplemented by FISH for borderline (2+) cases was 93.6%. Application of automated image analysis for HER2 protein expression instead of manual assessment decreases the need for supplementary FISH testing by 68%. In the routine diagnostic setting, this would have significant impact on cost reduction and turn-around time.

Henrik Holten-Rossing, Maj-Lis Møller Talman, Martin Kristensson, Ben Vainer

Oncotopix Clinical, Publicly Sharable

Introduction Breast cancer is one of the most common cancer diseases in women with more than 1.67 million cases diagnosed worldwide each year. In breast cancer, the sentinel lymph node (SLN) pinpoints the first lymph node(s) into which the tumor spreads and it is usually located in the ipsilateral axilla. In patients with no clinical signs of metastatic disease in the axilla, a SLN biopsy (SLNB) is performed. Assessment of metastases in the SLNB is done in a conventional microscope by manually observing a metastasis and measuring its size and/or counting the number of tumor cells. This is done essentially to categorize the type of metastases as macrometastases, micrometastases or isolated tumor cells, which is used to determine which treatment the breast cancer patient will benefit mostly from. The aim of this study was to evaluate whether digital image analysis can be applied as a screening tool for SNLB assessment without compromising the diagnostic accuracy. Materials and methods Consecutive SLNB from 135 patients with localized breast cancer receiving surgery in the period of February to August 2015 were collected and included in this study. Of the 135 patients, 35 were received at Dept. of Pathology, Rigshospitalet, Copenhagen University Hospital, 50 at Dept. of Pathology, Zealand University Hospital, and 50 at Dept. of Pathology, Odense University Hospital. Formalin-fixed and paraffin-embedded tissue sections were analyzed by immunohistochemistry (IHC) using the BenchMark ULTRA Ventana platform. Rigshospitalet used a mixture of cytokeratin CK7 and CK19, Zealand University Hospital used pancytokeratin AE1/AE3 and Odense used pancytokeratin CAM5.2 for detection of epithelial tumor cells. Slides were stained locally. SLNB sections were assessed in a conventional microscope according to national guidelines for SLNB in breast cancer patients. The IHC stained sections were scanned by a Hamamatsu NanoZoomer-XR digital whole slide scanner and the images were analyzed by Visiopharm's software using a custommade algorithm for SLNB in breast cancer. The algorithm was optimized to the cytokeratin antibodies and the local laboratory conditions, based on staining intensity and background staining. Results Conventional microscopy was used as golden standard for assessment of positive tumor cells and compared with digital image analysis (DIA). The algorithm demonstrated a sensitivity of 100% (i.e. no false negative slides were observed), including 67.2%, 19.2% and 56.1% of the slides from the three pathology departments being negative, respectively. This means that on average, the workload could have been decreased by 58.2% by using the digital SLNB algorithm as a screening tool. Discussion and conclusion The SLNB algorithm demonstrated a sensitivity of 100% regardless of the antibody used for IHC and the staining protocol. No false negative slides were observed, which proves that the SLNB algorithm is an ideal screening tool for selecting those slides not necessary for a pathologist to see. Implementation of automated digital image analysis of SLNB in breast cancer would decrease the workload in this context for examining pathologists by almost 60%. This article is protected by copyright. All rights reserved.

Henrik Holten-Rossing, Maj-Lis Møller Talman, Anne Marie Bak Jylling, Anne-Vibeke Laenkholm, Martin Kristensson, Ben Vainer

Oncotopix Clinical, Publicly Sharable

Aims During pathological examination of breast tumours, proliferative activity is routinely evaluated by a count of mitoses. Adding immunohistochemical stains of Ki67 provides extra prognostic and predictive information. However, the currently used methods for these evaluations suffer from imperfect reproducibility. It is still unclear whether analysis of Ki67 should be performed in hot spots, in the tumour periphery, or as an average of the whole tumour section. The aim of this study was to compare the clinical relevance of mitoses, Ki67 and phosphohistone H3 in two cohorts of primary breast cancer specimens (total n = 294). Methods and results Both manual and digital image analysis scores were evaluated for sensitivity and specificity for luminal B versus A subtype as defined by PAM50 gene expression assays, for high versus low transcriptomic grade, for axillary lymph node status, and for prognostic value in terms of prediction of overall and relapse‐free survival. Digital image analysis of Ki67 outperformed the other markers, especially in hot spots. Tumours with high Ki67 expression and high numbers of phosphohistone H3‐positive cells had significantly increased hazard ratios for all‐cause mortality within 10 years from diagnosis. Replacing manual mitotic counts with digital image analysis of Ki67 in hot spots increased the differences in overall survival between the highest and lowest histological grades, and added significant prognostic information. Conclusions Digital image analysis of Ki67 in hot spots is the marker of choice for routine analysis of proliferation in breast cancer.

Gustav Stålhammar, Stephanie Robertson, Lena Wedlund, Michael Lippert, Mattias Rantalainen, Jonas Bergh, Johan Hartman

Oncotopix Clinical, Publicly Sharable

Background: The Visiopharm human epidermal growth factor receptor 2 (HER2) digital imaging analysis (DIA) algorithm assesses digitized HER2 immunohistochemistry (IHC) by measuring cell membrane connectivity. We aimed to validate this algorithm for clinical use by comparing with pathologists' scoring and correlating with HER2 fluorescence in situ hybridization (FISH) results. Materials and Methods: The study cohort consisted of 612 consecutive invasive breast carcinoma specimens including 395 biopsies and 217 resections. HER2 IHC slides were scanned using Philips IntelliSite Scanners, and the digital images were analyzed using Visiopharm HER2-CONNECT App to obtain the connectivity values (0-1) and scores (0, 1+, 2+, and 3+). HER2 DIA scores were compared with Pathologists' manual scores, and HER2 connectivity values were correlated with HER2 FISH results. Results: The concordance between HER2 DIA scores and pathologists' scores was 87.3% (534/612). All discordant cases (n = 78) were only one-step discordant (negative to equivocal, equivocal to positive, or vice versa). Five cases (0.8%) showed discordant HER2 IHC DIA and HER2 FISH results, but all these cases had relatively low HER2 copy numbers (between 4 and 6). HER2 IHC connectivity showed significantly better correlation with HER2 copy number than HER2/CEP17 ratio. Conclusions: HER2 IHC DIA demonstrates excellent concordance with pathologists' scores and accurately discriminates between HER2 FISH positive and negative cases. HER2 IHC connectivity has better correlation with HER2 copy number than HER2/CEP17 ratio, suggesting HER2 copy number may be more important in predicting HER2 protein expression, and response to anti-HER2-targeted therapy.

Ramon Hartage, Aidan Li, Scott Hammond, Anil Parwani

Oncotopix Clinical, Publicly Sharable

Purpose: Patients with HER2-positive breast cancer commonly receive anti-HER2 neoadjuvant chemotherapy and pathologic complete response (pCR) can be achieved in up to half of the patients. HER2 protein expression detected by immunohistochemistry (IHC) can be quantified using digital imaging analysis (DIA) as a value of membranous connectivity. We aimed to investigate the association HER2 IHC DIA quantitative results with response to anti-HER2 neoadjuvant chemotherapy. Methods: Digitized HER2 IHC whole slide images were analyzed using Visiopharm HER2-CONNECT to obtain quantitative HER2 membranous connectivity from a cohort of 153 HER2+ invasive breast carcinoma cases treated with anti-HER2 neoadjuvant chemotherapy (NAC). HER2 connectivity and other factors including age, histologic grade, ER, PR, and HER2 fluorescence in situ hybridization (FISH) were analyzed for association with the response to anti-HER2 NAC. Results: Eighty-three cases (54.2%) had pCR, while 70 (45.8%) showed residual tumor. Younger age, negative ER/PR, higher HER2 DIA connectivity, higher HER2 FISH ratio and copy number were significantly associated with pCR in univariate analysis. Multivariate analysis demonstrated only age, HER2 DIA connectivity, PR negativity, and HER2 copy number was significantly associated with pCR, whereas HER2 DIA connectivity had the strongest association. Conclusions: HER2 IHC DIA connectivity is the most important factor predicting pCR to anti-HER2 neoadjuvant chemotherapy in patients with HER2-positive breast cancer.

Aidan C. Li, Jing Zhao, Chao Zhao, Zhongliang Ma, Ramon Hartage, Yunxiang Zhang, Xiaoxian Li, Anil V. Parwani

Oncotopix Clinical, Publicly Sharable

Aims: Precise evaluation of proliferative activity is essential for the stratified treatment of luminal-type breast cancer (BC). Immunohistochemical staining of Ki-67 has been widely used to determine proliferative activity and is recognised to be a useful prognostic marker. However, there remains discussion concerning the methodology. We aimed to develop an automated and reliable Ki-67 assessment approach for invasive BC. Materials and results: A retrospective study was designed to include two cohorts consisting of 152 and 261 consecutive patients with luminal-type BC. Representative tissue blocks following surgery were collected, and three serial sections were stained automatically with Ki-67, pan-cytokeratin and p63. The whole slides were scanned digitally and aligned using VirtualTripleStaining – an extension to the VirtualDoubleStaining™ technique provided by Visiopharm software. The aligned files underwent automated invasive cancer detection, hot-spot identification and Ki-67 counting. The automated scores showed a significant positive correlation with the pathologists' scores (r = 0.82, P ' 0.0001). Among selected patients with curative surgery and standard adjuvant therapies (n = 130), the digitally assessed low Ki-67 group ('20%) demonstrated a significantly better prognosis (breast cancer-specific survival, P = 0.030; hazard ratio = 0.038) than the high Ki-67 group. Conclusions: Digital image analysis yielded similar results to the scores determined by experienced pathologists. The prognostic utility was verified in our cohort, and an automated process is expected to have high reproducibility. Although some pitfalls were confirmed and thus need to be monitored by laboratory staff, the application could be utilised for the assessment of BC.

Akira I. Hida, Dzenita Omanovic, Lars Pedersen, Yumi Oshiro, Takashi Ogura, Tsunehisa Nomura, Junichi Kurebayashi, Naoki Kanomata, Takuya Moriya

90159, Oncotopix Clinical, Publicly Sharable

Abstract

Identifying lymph node (LN) metastasis in invasive breast carcinoma (IBC) can be tedious and time consuming. We investigated an artificial intelligence (AI) algorithm to detect LN metastasis by screening H&E slides in a clinical digital workflow. The study included two sentinel LN (SLN) cohorts (validation cohort with 234 SLNs and consensus cohort with 102 SLNs) and one non-sentinel LN (NSLN) cohort (258 LNs enriched with lobular carcinoma and post-neoadjuvant therapy cases). All H&E slides were scanned into whole slide images (WSI) in clinical digital workflow and WSIs were automatically batch analyzed using Visiopharm (VIS) metastasis AI algorithm. For SLN validation cohort, VIS metastasis AI algorithm detected all 46 metastases including 19 macrometastases, 26 micrometastases, 1 with isolated tumor cells (ITC) with a sensitivity of 100%, specificity of 41.5%, positive predictive value (PPV) of 29.5% and negative predictive value (NPV) of 100%. The false positivity was caused by histiocytes (52.7%), crushed lymphocytes (18.2%), and others, which were readily recognized during pathologists' reviews. For SLN consensus cohort, three pathologists examined all VIS AI annotated H&E slides and cytokeratin IHC slides with similar average concordance rates (99% for both modalities). However, the average time consumed by pathologists using VIS AI annotated slides was significantly less than the time using IHC slides (0.6 vs 1.0 minute, p=0.0377). For NSLN cohort, AI algorithm detected all 81 metastases, including 23 from lobular carcinoma and 31 from post-neoadjuvant chemotherapy cases with sensitivity of 100%, specificity of 78.5%, PPV of 68.1%, and NPV of 100%. VIS AI algorithm showed perfect sensitivity and NPV in detecting LN metastasis and less time consumed, suggesting its potential utility as a screening modality in routine clinical digital pathology workflow to improve efficiency.

Bindu Challa, Maryam Tahir, Yan Hu, David Kellough, Giovani Lujan, Shaoli Sun, Anil V. Parwani, Zaibo Li

90159, Oncotopix Clinical, Publicly Sharable

Pathologists’ assessment of sentinel lymph nodes (SNs) for breast cancer (BC) metastases is a treatment-guiding yet labor-intensive and costly task because of the performance of immunohistochemistry (IHC) in morphologically negative cases. This non-randomized, single-center clinical trial (International Standard Randomized Controlled Trial Number:14323711) assessed the efficacy of an artificial intelligence (AI)-assisted workflow for detecting BC metastases in SNs while maintaining diagnostic safety standards. From September 2022 to May 2023, 190 SN specimens were consecutively enrolled and allocated biweekly to the intervention arm (n = 100) or control arm (n = 90). In both arms, digital whole-slide images of hematoxylin–eosin sections of SN specimens were assessed by an expert pathologist, who was assisted by the ‘Metastasis Detection’ app (Visiopharm) in the intervention arm. Our primary endpoint showed a significantly reduced adjusted relative risk of IHC use (0.680, 95% confidence interval: 0.347–0.878) for AI-assisted pathologists, with subsequent cost savings of ~3,000 €. Secondary endpoints showed significant time reductions and up to 30% improved sensitivity for AI-assisted pathologists. This trial demonstrates the safety and potential for cost and time savings of AI assistance. Van Dooijeweert et al. conducted a prospective study on the clinical implementation of artificial-intelligence-assisted detection of sentinel lymph node metastasis in persons with breast cancer and report on its effects, including on time and cost.

C. van Dooijeweert, R. N. Flach, N. D. ter Hoeve, C. P. H. Vreuls, R. Goldschmeding, J. E. Freund, P. Pham, T. Q. Nguyen, E. van der Wall, G. W. J. Frederix, N. Stathonikos, P. J. van Diest

Lymphnode Metastasis, Oncotopix Clinical, Publicly Sharable

The rapid introduction of digital pathology has greatly facilitated development of artificial intelligence (AI) models in pathology that have shown great promise in assisting morphological diagnostics and quantitation of therapeutic targets. We are now at a tipping point where companies have started to bring algorithms to the market, and questions arise whether the pathology community is ready to implement AI in routine workflow. However, concerns also arise about the use of AI in pathology. This article reviews the pros and cons of introducing AI in diagnostic pathology.

Paul J. van Diest, Rachel N. Flach, Carmen van Dooijeweert, Seher Makineli, Gerben E. Breimer, Nikolas Stathonikos, Paul Pham, Tri Q. Nguyen, Mitko Veta

Oncotopix Clinical, Publicly Sharable, Qu-Path

Quantification of Ki67 in breast cancer is a well-established prognostic and predictive marker, but inter-laboratory variability has hampered its clinical usefulness. This study compares the prognostic value and reproducibility of Ki67 scoring using four automated, digital image analysis (DIA) methods and two manual methods. The study cohort consisted of 367 patients diagnosed between 1990 and 2004, with hormone receptor positive, HER2 negative, lymph node negative breast cancer. Manual scoring of Ki67 was performed using predefined criteria. DIA Ki67 scoring was performed using QuPath and Visiopharm® platforms. Reproducibility was assessed by the intraclass correlation coefficient (ICC). ROC curve survival analysis identified optimal cutoff values in addition to recommendations by the International Ki67 Working Group and Norwegian Guidelines. Kaplan–Meier curves, log-rank test and Cox regression analysis assessed the association between Ki67 scoring and distant metastasis (DM) free survival. The manual hotspot and global scoring methods showed good agreement when compared to their counterpart DIA methods (ICC > 0.780), and good to excellent agreement between different DIA hotspot scoring platforms (ICC 0.781–0.906). Different Ki67 cutoffs demonstrate significant DM-free survival (p < 0.05). DIA scoring had greater prognostic value for DM-free survival using a 14% cutoff (HR 3.054–4.077) than manual scoring (HR 2.012–2.056). The use of a single cutoff for all scoring methods affected the distribution of prediction outcomes (e.g. false positives and negatives). This study demonstrates that DIA scoring of Ki67 is superior to manual methods, but further study is required to standardize automated, DIA scoring and definition of a clinical cut-off.

Emma Rewcastle, Ivar Skaland, Einar Gudlaugsson, Silja Kavlie Fykse, Jan P. A. Baak, Emiel A. M. Janssen

Oncotopix Clinical, Publicly Sharable

his review discusses the profound impact of artificial intelligence (AI) on breast cancer (BC) diagnosis and management within the field of pathology. It examines the various applications of AI across diverse aspects of BC pathology, highlighting key findings from multiple studies. Integrating AI into routine pathology practice stands to improve diagnostic accuracy, thereby contributing to reducing avoidable errors. Additionally, AI has excelled in identifying invasive breast tumors and lymph node metastasis through its capacity to process large whole-slide images adeptly. Adaptive sampling techniques and powerful convolutional neural networks mark these achievements. The evaluation of hormonal status, which is imperative for BC treatment choices, has also been enhanced by AI quantitative analysis, aiding interobserver concordance and reliability. Breast cancer grading and mitotic count evaluation also benefit from AI intervention. AI-based frameworks effectively classify breast carcinomas, even for moderately graded cases that traditional methods struggle with. Moreover, AI-assisted mitotic figures quantification surpasses manual counting in precision and sensitivity, fostering improved prognosis. The assessment of tumor-infiltrating lymphocytes in triple-negative breast cancer using AI yields insights into patient survival prognosis. Furthermore, AI-powered predictions of neoadjuvant chemotherapy response demonstrate potential for streamlining treatment strategies. Addressing limitations, such as preanalytical variables, annotation demands, and differentiation challenges, is pivotal for realizing AI’s full potential in BC pathology. Despite the existing hurdles, AI’s multifaceted contributions to BC pathology hold great promise, providing enhanced accuracy, efficiency, and standardization. Continued research and innovation are crucial for overcoming obstacles and fully harnessing AI’s transformative capabilities in breast cancer diagnosis and assessment. Graphical Abstract: (Figure presented.) HER2 ER lymph node metastasis

Amr Soliman, Zaibo Li, Anil V. Parwani