Technical note on the validation of a semi-automated image analysis software application for estrogen and progesterone receptor detection in breast cancer

Krecsák, László; Micsik, Tamás; Kiszler, Gábor; Krenács, Tibor; Szabó, Dániel; Jónás, Viktor; Császár, Gergely; Czúni, László; Gurzó, Péter; Ficsor, Levente; Molnár, Béla

doi:10.1186/1746-1596-6-6

Cited by 31 publications

(29 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study differs from previous studies with the use of an automated image analysis of MHCI expression rather than the commonly used semiquantitative scoring system conducted by a pathologist [10,14]. Automated image analysis allows for rapid high-content slide analysis, providing a more objective and robust approach to data analysis [18]. Quantitative image analysis also allows for the potential identification of a numeric MHCI score, which could be used in statistical models to predict outcome for patients following nephrectomy.…”

Section: Discussioncontrasting

confidence: 38%

High Expression of Major Histocompatibility Complex Class I in Clear Cell Renal Cell Carcinoma Is Associated with Improved Prognosis

Holzman

Calle²,

Osunkoya³

et al. 2015

Urol Int

View full text Add to dashboard Cite

Introduction: In this study we analyzed major histocompatibility complex class I (MHCI) expression as a potential prognostic immune marker for patients with clear cell renal cell carcinoma (ccRCC). Patients and Methods: 34 patients with localized ccRCC (pT1-pT3) who had undergone nephrectomy and had at least 4 years of clinical follow-up data were included in the study. Immunohistochemical staining for MHCI was performed on tumor sections. An automated image analysis algorithm was applied to representative tumor areas to quantitate the proportion of stained pixels (positivity score = positive pixels/total pixels) on scanned digital slides. Results: At the end of the study, the patients who were alive had increased MHCI expression (mean positivity score 0.80) compared to those who died of the disease (mean positivity score 0.53; p < 0.0001, t test). Patients who were alive with recurrence had increased MHCI expression (positivity score 0.81) compared to those who succumbed to their disease recurrence (positivity score 0.53; p < 0.0001, t test). Survival was higher among patients with high MHCI expression compared to patients with low MHCI expression (p < 0.0001, Mantel-Cox). Conclusions: With an automated high-throughput image analysis technique, this study shows that higher tumor cell MHCI expression promotes increased survival and reduced incidence of recurrence compared to patients with lower tumor cell MHCI expression.

show abstract

Section: Discussioncontrasting

confidence: 38%

High Expression of Major Histocompatibility Complex Class I in Clear Cell Renal Cell Carcinoma Is Associated with Improved Prognosis

Holzman

Calle²,

Osunkoya³

et al. 2015

Urol Int

View full text Add to dashboard Cite

show abstract

“…However, defining parameters prior to analysis is very susceptible towards morphologic variability typical of many tumors or technical variation and therefore requires constant adjustment. Other approaches for automated immunohistology evaluation such as, for instance, described or applied in (11,24,25) rely on training of certain cell and tissue features, a procedure that is usually time consuming and often requires retraining of the method before analyzing new images. Our approach is capable of providing reliable results without any training, calibration, or interaction performed by the user, because we combine very generic assumptions on cell features with automated adaptive threshold search to detect Ki67-positive and negative cells.…”

Section: Discussionmentioning

confidence: 99%

Standardized Ki67 Diagnostics Using Automated Scoring—Clinical Validation in the GeparTrio Breast Cancer Study

Klauschen

Wienert

Schmitt

et al. 2015

Clinical Cancer Research

View full text Add to dashboard Cite

Purpose: Scoring proliferation through Ki67 immunohistochemistry is an important component in predicting therapy response to chemotherapy in patients with breast cancer. However, recent studies have cast doubt on the reliability of "visual" Ki67 scoring in the multicenter setting, particularly in the lower, yet clinically important, proliferation range. Therefore, an accurate and standardized Ki67 scoring is pivotal both in routine diagnostics and larger multicenter studies.Experimental Design: We validated a novel fully automated Ki67 scoring approach that relies on only minimal a priori knowledge on cell properties and requires no training data for calibration. We applied our approach to 1,082 breast cancer samples from the neoadjuvant GeparTrio trial and compared the performance of automated and manual Ki67 scoring.Results: The three groups of autoKi67 as defined by low ( 15%), medium (15.1%-35%), and high (>35%) automated scores showed pCR rates of 5.8%, 16.9%, and 29.5%, respectively. AutoKi67 was significantly linked to prognosis with overall and progression-free survival P values P OS < 0.0001 and P PFS < 0.0002, compared with P OS < 0.0005 and P PFS < 0.0001 for manual Ki67 scoring. Moreover, automated Ki67 scoring was an independent prognosticator in the multivariate analysis with P OS ¼ 0.002, P PFS ¼ 0.009 (autoKi67) versus P OS ¼ 0.007, P PFS ¼ 0.004 (manual Ki67).Conclusions: The computer-assisted Ki67 scoring approach presented here offers a standardized means of tumor cell proliferation assessment in breast cancer that correlated with clinical endpoints and is deployable in routine diagnostics. It may thus help to solve recently reported reliability concerns in Ki67 diagnostics.

show abstract

“…We started with an earlier work in mind; that work was a case study of a clinical validation [6]. The categorizing approach of [7] was of great help to widen our field of view in this area.…”

Section: Related Literaturementioning

confidence: 99%

Semi-Automated Quantitative Validation Tool for Medical Image Processing Algorithm Development

Jónás

Kozlovszky

Molnár

2015

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Abstract. Cancer research and diagnostics is an important frontier to apply the power of computers. Researchers use image processing techniques for a few years now, but diagnostics only start to explore its possibilities. Pathologists specialized in this area usually diagnose by visual inspection, typically through a microscope, or more recently on a computer screen. They examine at tissue specimen or a sample consisting of a population cells extracted from it. The latter area is the area of cytometry that researchers started to support by creating image processing algorithms. The validation of an image processing approach like that is an expensive task both financially and time-wise. This paper aims to show a semi-automatized method to simplify this task, by reducing the amount of human interaction necessary.

show abstract

Technical note on the validation of a semi-automated image analysis software application for estrogen and progesterone receptor detection in breast cancer

Cited by 31 publications

References 19 publications

High Expression of Major Histocompatibility Complex Class I in Clear Cell Renal Cell Carcinoma Is Associated with Improved Prognosis

High Expression of Major Histocompatibility Complex Class I in Clear Cell Renal Cell Carcinoma Is Associated with Improved Prognosis

Standardized Ki67 Diagnostics Using Automated Scoring—Clinical Validation in the GeparTrio Breast Cancer Study

Semi-Automated Quantitative Validation Tool for Medical Image Processing Algorithm Development

Contact Info

Product

Resources

About