1
|
Kazemi A, Rasouli-Saravani A, Gharib M, Albuquerque T, Eslami S, Schüffler PJ. A systematic review of machine learning-based tumor-infiltrating lymphocytes analysis in colorectal cancer: Overview of techniques, performance metrics, and clinical outcomes. Comput Biol Med 2024; 173:108306. [PMID: 38554659 DOI: 10.1016/j.compbiomed.2024.108306] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2023] [Revised: 03/04/2024] [Accepted: 03/12/2024] [Indexed: 04/02/2024]
Abstract
The incidence of colorectal cancer (CRC), one of the deadliest cancers around the world, is increasing. Tissue microenvironment (TME) features such as tumor-infiltrating lymphocytes (TILs) can have a crucial impact on diagnosis or decision-making for treating patients with CRC. While clinical studies showed that TILs improve the host immune response, leading to a better prognosis, inter-observer agreement for quantifying TILs is not perfect. Incorporating machine learning (ML) based applications in clinical routine may promote diagnosis reliability. Recently, ML has shown potential for making progress in routine clinical procedures. We aim to systematically review the TILs analysis based on ML in CRC histological images. Deep learning (DL) and non-DL techniques can aid pathologists in identifying TILs, and automated TILs are associated with patient outcomes. However, a large multi-institutional CRC dataset with a diverse and multi-ethnic population is necessary to generalize ML methods.
Collapse
Affiliation(s)
- Azar Kazemi
- Department of Medical Informatics, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran; Institute of General and Surgical Pathology, Technical University of Munich, Munich, Germany.
| | - Ashkan Rasouli-Saravani
- Student Research Committee, Department of Immunology, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
| | - Masoumeh Gharib
- Department of Pathology, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran.
| | | | - Saeid Eslami
- Department of Medical Informatics, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran; Pharmaceutical Sciences Research Center, Institute of Pharmaceutical Technology, Mashhad University of Medical Sciences, Mashhad, Iran; Department of Medical Informatics, University of Amsterdam, Amsterdam, the Netherlands.
| | - Peter J Schüffler
- Institute of General and Surgical Pathology, Technical University of Munich, Munich, Germany; TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany; Munich Center for Machine Learning, Munich, Germany; Munich Data Science Institute, Munich, Germany.
| |
Collapse
|
2
|
Iwuajoku V, Haas A, Ekici K, Khan MZ, Stögbauer F, Steiger K, Mogler C, Schüffler PJ. [Digital transformation of a routine histopathology lab : Dos and don'ts!]. Pathologie (Heidelb) 2024; 45:98-105. [PMID: 38189845 PMCID: PMC10902067 DOI: 10.1007/s00292-023-01291-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Accepted: 11/15/2023] [Indexed: 01/09/2024]
Abstract
The implementation of digital histopathology in the laboratory marks a crucial milestone in the overall digital transformation of pathology. This shift offers a range of new possibilities, including access to extensive datasets for AI-assisted analyses, the flexibility of remote work and home office arrangements for specialists, and the expedited and simplified sharing of images and data for research, conferences, and tumor boards. However, the transition to a fully digital workflow involves significant technological and personnel-related efforts. It necessitates careful and adaptable change management to minimize disruptions, particularly in the personnel domain, and to prevent the loss of valuable potential from employees who may be resistant to change. This article consolidates our institute's experiences, highlighting technical and personnel-related challenges encountered during the transition to digital pathology. It also presents a comprehensive overview of potential difficulties at various interfaces when converting routine operations to a digital workflow.
Collapse
Affiliation(s)
- Viola Iwuajoku
- Institut für Pathologie, TUM School of Medicine and Health, Technische Universität München, Trogerstraße 18, 81675, München, Deutschland
| | - Anette Haas
- Institut für Pathologie, TUM School of Medicine and Health, Technische Universität München, Trogerstraße 18, 81675, München, Deutschland
| | - Kübra Ekici
- Institut für Pathologie, TUM School of Medicine and Health, Technische Universität München, Trogerstraße 18, 81675, München, Deutschland
| | - Mohammad Zaid Khan
- Institut für Pathologie, TUM School of Medicine and Health, Technische Universität München, Trogerstraße 18, 81675, München, Deutschland
| | - Fabian Stögbauer
- Institut für Pathologie, TUM School of Medicine and Health, Technische Universität München, Trogerstraße 18, 81675, München, Deutschland
| | - Katja Steiger
- Institut für Pathologie, TUM School of Medicine and Health, Technische Universität München, Trogerstraße 18, 81675, München, Deutschland
| | - Carolin Mogler
- Institut für Pathologie, TUM School of Medicine and Health, Technische Universität München, Trogerstraße 18, 81675, München, Deutschland
| | - Peter J Schüffler
- Institut für Pathologie, TUM School of Medicine and Health, Technische Universität München, Trogerstraße 18, 81675, München, Deutschland.
- TUM School of Computational Information and Technology, Technische Universität München, München, Deutschland.
| |
Collapse
|
3
|
Raciti P, Sue J, Retamero JA, Ceballos R, Godrich R, Kunz JD, Casson A, Thiagarajan D, Ebrahimzadeh Z, Viret J, Lee D, Schüffler PJ, DeMuth G, Gulturk E, Kanan C, Rothrock B, Reis-Filho J, Klimstra DS, Reuter V, Fuchs TJ. Clinical Validation of Artificial Intelligence-Augmented Pathology Diagnosis Demonstrates Significant Gains in Diagnostic Accuracy in Prostate Cancer Detection. Arch Pathol Lab Med 2023; 147:1178-1185. [PMID: 36538386 DOI: 10.5858/arpa.2022-0066-oa] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/28/2022] [Indexed: 09/29/2023]
Abstract
CONTEXT.— Prostate cancer diagnosis rests on accurate assessment of tissue by a pathologist. The application of artificial intelligence (AI) to digitized whole slide images (WSIs) can aid pathologists in cancer diagnosis, but robust, diverse evidence in a simulated clinical setting is lacking. OBJECTIVE.— To compare the diagnostic accuracy of pathologists reading WSIs of prostatic biopsy specimens with and without AI assistance. DESIGN.— Eighteen pathologists, 2 of whom were genitourinary subspecialists, evaluated 610 prostate needle core biopsy WSIs prepared at 218 institutions, with the option for deferral. Two evaluations were performed sequentially for each WSI: initially without assistance, and immediately thereafter aided by Paige Prostate (PaPr), a deep learning-based system that provides a WSI-level binary classification of suspicious for cancer or benign and pinpoints the location that has the greatest probability of harboring cancer on suspicious WSIs. Pathologists' changes in sensitivity and specificity between the assisted and unassisted modalities were assessed, together with the impact of PaPr output on the assisted reads. RESULTS.— Using PaPr, pathologists improved their sensitivity and specificity across all histologic grades and tumor sizes. Accuracy gains on both benign and cancerous WSIs could be attributed to PaPr, which correctly classified 100% of the WSIs showing corrected diagnoses in the PaPr-assisted phase. CONCLUSIONS.— This study demonstrates the effectiveness and safety of an AI tool for pathologists in simulated diagnostic practice, bridging the gap between computational pathology research and its clinical application, and resulted in the first US Food and Drug Administration authorization of an AI system in pathology.
Collapse
Affiliation(s)
- Patricia Raciti
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Jillian Sue
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Juan A Retamero
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Rodrigo Ceballos
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Ran Godrich
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Jeremy D Kunz
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Adam Casson
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Dilip Thiagarajan
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Zahra Ebrahimzadeh
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Julian Viret
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Donghun Lee
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Peter J Schüffler
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | | | - Emre Gulturk
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Christopher Kanan
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Brandon Rothrock
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Jorge Reis-Filho
- The Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center, New York, New York (Reis-Filho, Reuter)
| | - David S Klimstra
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| | - Victor Reuter
- The Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center, New York, New York (Reis-Filho, Reuter)
| | - Thomas J Fuchs
- From Paige (Raciti, Sue, Retamero, Ceballos, Godrich, Kunz, Casson, Thiagarajan, Ebrahimzadeh, Viret, Lee, Schüffler, Gulturk, Kanan, Rothrock, Klimstra, Fuchs), New York, New York
| |
Collapse
|
4
|
Kazemi A, Gharib M, Mohamadian Roshan N, Taraz Jamshidi S, Stögbauer F, Eslami S, Schüffler PJ. Assessment of the Tumor-Stroma Ratio and Tumor-Infiltrating Lymphocytes in Colorectal Cancer: Inter-Observer Agreement Evaluation. Diagnostics (Basel) 2023; 13:2339. [PMID: 37510083 PMCID: PMC10378655 DOI: 10.3390/diagnostics13142339] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2023] [Revised: 07/04/2023] [Accepted: 07/06/2023] [Indexed: 07/30/2023] Open
Abstract
BACKGROUND To implement the new marker in clinical practice, reliability assessment, validation, and standardization of utilization must be applied. This study evaluated the reliability of tumor-infiltrating lymphocytes (TILs) and tumor-stroma ratio (TSR) assessment through conventional microscopy by comparing observers' estimations. METHODS Intratumoral and tumor-front stromal TILs, and TSR, were assessed by three pathologists using 86 CRC HE slides. TSR and TILs were categorized using one and four different proposed cutoff systems, respectively, and agreement was assessed using the intraclass coefficient (ICC) and Cohen's kappa statistics. Pairwise evaluation of agreement was performed using the Fleiss kappa statistic and the concordance rate and it was visualized by Bland-Altman plots. To investigate the association between biomarkers and patient data, Pearson's correlation analysis was applied. RESULTS For the evaluation of intratumoral stromal TILs, ICC of 0.505 (95% CI: 0.35-0.64) was obtained, kappa values were in the range of 0.21 to 0.38, and concordance rates in the range of 0.61 to 0.72. For the evaluation of tumor-front TILs, ICC was 0.52 (95% CI: 0.32-0.67), the overall kappa value ranged from 0.24 to 0.30, and the concordance rate ranged from 0.66 to 0.72. For estimating the TSR, the ICC was 0.48 (95% CI: 0.35-0.60), the kappa value was 0.49 and the concordance rate was 0.76. We observed a significant correlation between tumor grade and the median of TSR (0.29 (95% CI: 0.032-0.51), p-value = 0.03). CONCLUSIONS The agreement between pathologists in estimating these markers corresponds to poor-to-moderate agreement; implementing immune scores in daily practice requires more concentration in inter-observer agreements.
Collapse
Affiliation(s)
- Azar Kazemi
- Institute of General and Surgical Pathology, Technical University of Munich, 81675 Munich, Germany
- Department of Medical Informatics, School of Medicine, Mashhad University of Medical Sciences, Mashhad 9177948564, Iran
| | - Masoumeh Gharib
- Department of Pathology, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad 9137913316, Iran
| | - Nema Mohamadian Roshan
- Department of Pathology, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad 9137913316, Iran
| | - Shirin Taraz Jamshidi
- Department of Pathology, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad 9137913316, Iran
| | - Fabian Stögbauer
- Institute of General and Surgical Pathology, Technical University of Munich, 81675 Munich, Germany
| | - Saeid Eslami
- Department of Medical Informatics, School of Medicine, Mashhad University of Medical Sciences, Mashhad 9177948564, Iran
- Pharmaceutical Sciences Research Center, Institute of Pharmaceutical Technology, Mashhad University of Medical Sciences, Mashhad 9177948954, Iran
- Department of Medical Informatics, University of Amsterdam, 1105 AZ Amsterdam, The Netherlands
| | - Peter J Schüffler
- Institute of General and Surgical Pathology, Technical University of Munich, 81675 Munich, Germany
| |
Collapse
|
5
|
Schüffler PJ, Stamelos E, Ahmed I, Yarlagadda DVK, Ardon O, Hanna MG, Reuter VE, Klimstra DS, Hameed M. Efficient Visualization of Whole Slide Images in Web-based Viewers for Digital Pathology. Arch Pathol Lab Med 2022; 146:1273-1280. [PMID: 34979569 PMCID: PMC10060618 DOI: 10.5858/arpa.2021-0197-oa] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 09/07/2021] [Indexed: 11/06/2022]
Abstract
CONTEXT.— Wide adoption of digital pathology requires efficient visualization and navigation in Web-based digital slide viewers, which is poorly defined. OBJECTIVE.— To define and quantify relevant performance metrics for efficient visualization of cases and slides in digital slide viewers. DESIGN.— With a universal slide viewer used in clinical routine diagnostics, we evaluated the impact of slide caching, compression type, tile, and block size of whole slide images generated from Philips, Leica, and 3DHistech scanners on streaming performance on case, slide, and field of view levels. RESULTS.— Two hundred thirty-nine pathologists routinely reviewed 60 080 whole slide images over 3 months. The median time to open a case's slides from the laboratory information system was less than 4 seconds, the time to change to a slide within the case was less than 1 second, and the time to render the adjacent field of view when navigating the slide was less than one-quarter of a second. A whole slide image's block size and a viewer tile size of 1024 pixels showed best performance to display a field of view and was preferrable over smaller tiles due to fewer mosaic effects. For Philips, fastest median slide streaming pace was 238 ms per field of view and for 3DHistech, 125 ms. For Leica, the fastest pace of 108 ms per field of view was established with block serving without decompression. CONCLUSIONS.— This is the first study to systematically assess user-centric slide visualization performance metrics for digital viewers, including time to open a case, time to change a slide, and time to change a field of view. These metrics help to improve the viewer's configuration, leading to an efficient visualization baseline that is widely accepted among pathologists using routine digital pathology.
Collapse
Affiliation(s)
- Peter J Schüffler
- From the Institute of Pathology, Technical University of Munich, Munich, Germany (Schüffler)
| | - Evangelos Stamelos
- From the Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, New York (Schüffler, Stamelos, Ahmed, Yarlagadda, Ardon, Hanna, Reuter, Klimstra, Hameed)
| | - Ishtiaque Ahmed
- From the Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, New York (Schüffler, Stamelos, Ahmed, Yarlagadda, Ardon, Hanna, Reuter, Klimstra, Hameed)
| | - D Vijay K Yarlagadda
- From the Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, New York (Schüffler, Stamelos, Ahmed, Yarlagadda, Ardon, Hanna, Reuter, Klimstra, Hameed)
| | - Orly Ardon
- From the Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, New York (Schüffler, Stamelos, Ahmed, Yarlagadda, Ardon, Hanna, Reuter, Klimstra, Hameed)
| | - Matthew G Hanna
- From the Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, New York (Schüffler, Stamelos, Ahmed, Yarlagadda, Ardon, Hanna, Reuter, Klimstra, Hameed)
| | - Victor E Reuter
- From the Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, New York (Schüffler, Stamelos, Ahmed, Yarlagadda, Ardon, Hanna, Reuter, Klimstra, Hameed)
| | - David S Klimstra
- From the Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, New York (Schüffler, Stamelos, Ahmed, Yarlagadda, Ardon, Hanna, Reuter, Klimstra, Hameed)
| | - Meera Hameed
- From the Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, New York (Schüffler, Stamelos, Ahmed, Yarlagadda, Ardon, Hanna, Reuter, Klimstra, Hameed)
| |
Collapse
|
6
|
Richter C, Mezger E, Schüffler PJ, Sommer W, Fusco F, Hauner K, Schmid SC, Gschwend JE, Weichert W, Schwamborn K, Pförringer D, Schlitter AM. Pathological Reporting of Radical Prostatectomy Specimens Following ICCR Recommendation: Impact of Electronic Reporting Tool Implementation on Quality and Interdisciplinary Communication in a Large University Hospital. Curr Oncol 2022; 29:7245-7256. [PMID: 36290848 PMCID: PMC9600383 DOI: 10.3390/curroncol29100571] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2022] [Revised: 09/21/2022] [Accepted: 09/27/2022] [Indexed: 01/13/2023] Open
Abstract
Prostate cancer represents one of the most common malignant tumors in male patients in Germany. The pathological reporting of radical prostatectomy specimens following a structured process constitutes an excellent prototype for the introduction of software-based standardized structured reporting in pathology. This can lead to reports of higher quality and could create a fundamental improvement for future AI applications. A software-based reporting template was used to generate standardized structured pathological reports of radical prostatectomy specimens of patients treated at the University Hospital Klinikum rechts der Isar of Technische Universität München, Germany. Narrative reports (NR) and standardized structured reports (SSR) were analyzed with regard to completeness, and clinicians' satisfaction with each report type was evaluated. SSR show considerably higher completeness than NR. A total of 10 categories out of 32 were significantly more complete in SSR than in NR (p < 0.05). Clinicians awarded overall high scores in NR and SSR reports. One rater acknowledged a significantly higher level of clarity and time saving when comparing SSR to NR. Our findings highlight that the standardized structured reporting of radical prostatectomy specimens, qualifying as level 5 reports, significantly increases objectively measured content quality and the level of completeness. The implementation of nationwide SSR in Germany, particularly in oncologic pathology, can serve pathologists, clinicians, and patients.
Collapse
Affiliation(s)
- Caroline Richter
- Institute of General and Surgical Pathology, Technische Universität München, Trogerstr. 18, 81675 Munich, Germany
| | - Eva Mezger
- Smart Reporting GmbH, 80538 Munich, Germany
| | - Peter J. Schüffler
- Institute of General and Surgical Pathology, Technische Universität München, Trogerstr. 18, 81675 Munich, Germany
| | - Wieland Sommer
- Smart Reporting GmbH, 80538 Munich, Germany
- Department of Radiology, LMU University Hospital, 81377 Munich, Germany
| | - Federico Fusco
- Institute of General and Surgical Pathology, Technische Universität München, Trogerstr. 18, 81675 Munich, Germany
| | - Katharina Hauner
- Department of Urology, Klinikum Rechts der Isar, Technische Universität München, 81675 Munich, Germany
| | - Sebastian C. Schmid
- Department of Urology, Klinikum Rechts der Isar, Technische Universität München, 81675 Munich, Germany
| | - Jürgen E. Gschwend
- Department of Urology, Klinikum Rechts der Isar, Technische Universität München, 81675 Munich, Germany
| | - Wilko Weichert
- Institute of General and Surgical Pathology, Technische Universität München, Trogerstr. 18, 81675 Munich, Germany
| | - Kristina Schwamborn
- Institute of General and Surgical Pathology, Technische Universität München, Trogerstr. 18, 81675 Munich, Germany
| | - Dominik Pförringer
- Clinic and Policlinic for Trauma Surgery, Klinikum Rechts der Isar, Technische Universität München, Ismaninger Straße 22, 81675 Munich, Germany
| | - Anna Melissa Schlitter
- Institute of General and Surgical Pathology, Technische Universität München, Trogerstr. 18, 81675 Munich, Germany
- Correspondence:
| |
Collapse
|
7
|
Schüffler PJ, Ozcan GG, Al-Ahmadie H, Fuchs TJ. FlexTileSource: An OpenSeadragon Extension for Efficient Whole-Slide Image Visualization. J Pathol Inform 2021; 12:31. [PMID: 34760328 PMCID: PMC8529343 DOI: 10.4103/jpi.jpi_13_21] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2021] [Revised: 05/03/2021] [Accepted: 07/01/2021] [Indexed: 11/08/2022] Open
Abstract
BACKGROUND Web-based digital slide viewers for pathology commonly use OpenSlide and OpenSeadragon (OSD) to access, visualize, and navigate whole-slide images (WSI). Their standard settings represent WSI as deep zoom images (DZI), a generic image pyramid structure that differs from the proprietary pyramid structure in the WSI files. The transformation from WSI to DZI is an additional, time-consuming step when rendering digital slides in the viewer, and inefficiency of digital slide viewers is a major criticism for digital pathology. AIMS To increase efficiency of digital slide visualization by serving tiles directly from the native WSI pyramid, making the transformation from WSI to DZI obsolete. METHODS We implemented a new flexible tile source for OSD that accepts arbitrary native pyramid structures instead of DZI levels. We measured its performance on a data set of 8104 WSI reviewed by 207 pathologists over 40 days in a web-based digital slide viewer used for routine diagnostics. RESULTS The new FlexTileSource accelerates the display of a field of view in general by 67 ms and even by 117 ms if the block size of the WSI and the tile size of the viewer is increased to 1024 px. We provide the code of our open-source library freely on https://github.com/schuefflerlab/openseadragon. CONCLUSIONS This is the first study to quantify visualization performance on a web-based slide viewer at scale, taking block size and tile size of digital slides into account. Quantifying performance will enable to compare and improve web-based viewers and therewith facilitate the adoption of digital pathology.
Collapse
Affiliation(s)
- Peter J. Schüffler
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, NY, USA
- TUM School of Medicine, Technical University of Munich, Munich, Germany
| | - Gamze Gokturk Ozcan
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, NY, USA
| | - Hikmat Al-Ahmadie
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, NY, USA
| | - Thomas J. Fuchs
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, NY, USA
- Department of Pathology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| |
Collapse
|
8
|
Schüffler PJ, Geneslaw L, Yarlagadda DVK, Hanna MG, Samboy J, Stamelos E, Vanderbilt C, Philip J, Jean MH, Corsale L, Manzo A, Paramasivam NHG, Ziegler JS, Gao J, Perin JC, Kim YS, Bhanot UK, Roehrl MHA, Ardon O, Chiang S, Giri DD, Sigel CS, Tan LK, Murray M, Virgo C, England C, Yagi Y, Sirintrapun SJ, Klimstra D, Hameed M, Reuter VE, Fuchs TJ. Integrated digital pathology at scale: A solution for clinical diagnostics and cancer research at a large academic medical center. J Am Med Inform Assoc 2021; 28:1874-1884. [PMID: 34260720 PMCID: PMC8344580 DOI: 10.1093/jamia/ocab085] [Citation(s) in RCA: 25] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2020] [Revised: 03/25/2021] [Accepted: 05/04/2021] [Indexed: 02/07/2023] Open
Abstract
OBJECTIVE Broad adoption of digital pathology (DP) is still lacking, and examples for DP connecting diagnostic, research, and educational use cases are missing. We blueprint a holistic DP solution at a large academic medical center ubiquitously integrated into clinical workflows; researchapplications including molecular, genetic, and tissue databases; and educational processes. MATERIALS AND METHODS We built a vendor-agnostic, integrated viewer for reviewing, annotating, sharing, and quality assurance of digital slides in a clinical or research context. It is the first homegrown viewer cleared by New York State provisional approval in 2020 for primary diagnosis and remote sign-out during the COVID-19 (coronavirus disease 2019) pandemic. We further introduce an interconnected Honest Broker for BioInformatics Technology (HoBBIT) to systematically compile and share large-scale DP research datasets including anonymized images, redacted pathology reports, and clinical data of patients with consent. RESULTS The solution has been operationally used over 3 years by 926 pathologists and researchers evaluating 288 903 digital slides. A total of 51% of these were reviewed within 1 month after scanning. Seamless integration of the viewer into 4 hospital systems clearly increases the adoption of DP. HoBBIT directly impacts the translation of knowledge in pathology into effective new health measures, including artificial intelligence-driven detection models for prostate cancer, basal cell carcinoma, and breast cancer metastases, developed and validated on thousands of cases. CONCLUSIONS We highlight major challenges and lessons learned when going digital to provide orientation for other pathologists. Building interconnected solutions will not only increase adoption of DP, but also facilitate next-generation computational pathology at scale for enhanced cancer research.
Collapse
Affiliation(s)
- Peter J Schüffler
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
- Institute of Pathology, Technical University of Munich, Munich, Germany
| | - Luke Geneslaw
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - D Vijay K Yarlagadda
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Matthew G Hanna
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Jennifer Samboy
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Evangelos Stamelos
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Chad Vanderbilt
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - John Philip
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
- Department of Health Informatics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Marc-Henri Jean
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Lorraine Corsale
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Allyne Manzo
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Neeraj H G Paramasivam
- Department of Information Systems, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - John S Ziegler
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Jianjiong Gao
- Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Juan C Perin
- Department of Information Systems, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Young Suk Kim
- School of Medicine, Stanford University, Stanford, California, USA
| | - Umeshkumar K Bhanot
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Michael H A Roehrl
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
- Human Oncology and Pathogenesis Program, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Orly Ardon
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Sarah Chiang
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Dilip D Giri
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Carlie S Sigel
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Lee K Tan
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Melissa Murray
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Christina Virgo
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Christine England
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Yukako Yagi
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - S Joseph Sirintrapun
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - David Klimstra
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Meera Hameed
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Victor E Reuter
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Thomas J Fuchs
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York, USA
- Department of Pathology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| |
Collapse
|
9
|
Schüffler PJ, Yarlagadda DVK, Vanderbilt C, Fuchs TJ. Overcoming an Annotation Hurdle: Digitizing Pen Annotations from Whole Slide Images. J Pathol Inform 2021; 12:9. [PMID: 34012713 PMCID: PMC8112348 DOI: 10.4103/jpi.jpi_85_20] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2020] [Revised: 11/24/2020] [Accepted: 12/20/2020] [Indexed: 01/01/2023] Open
Abstract
Background: The development of artificial intelligence (AI) in pathology frequently relies on digitally annotated whole slide images (WSI). The creation of these annotations – manually drawn by pathologists in digital slide viewers – is time consuming and expensive. At the same time, pathologists routinely annotate glass slides with a pen to outline cancerous regions, for example, for molecular assessment of the tissue. These pen annotations are currently considered artifacts and excluded from computational modeling. Methods: We propose a novel method to segment and fill hand-drawn pen annotations and convert them into a digital format to make them accessible for computational models. Our method is implemented in Python as an open source, publicly available software tool. Results: Our method is able to extract pen annotations from WSI and save them as annotation masks. On a data set of 319 WSI with pen markers, we validate our algorithm segmenting the annotations with an overall Dice metric of 0.942, Precision of 0.955, and Recall of 0.943. Processing all images takes 15 min in contrast to 5 h manual digital annotation time. Further, the approach is robust against text annotations. Conclusions: We envision that our method can take advantage of already pen-annotated slides in scenarios in which the annotations would be helpful for training computational models. We conclude that, considering the large archives of many pathology departments that are currently being digitized, our method will help to collect large numbers of training samples from those data.
Collapse
Affiliation(s)
- Peter J Schüffler
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, NY, USA
| | | | - Chad Vanderbilt
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, NY, USA
| | - Thomas J Fuchs
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York City, NY, USA
| |
Collapse
|
10
|
Ho DJ, Agaram NP, Schüffler PJ, Vanderbilt CM, Jean MH, Hameed MR, Fuchs TJ. Deep Interactive Learning: An Efficient Labeling Approach for Deep Learning-Based Osteosarcoma Treatment Response Assessment. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020 2020. [DOI: 10.1007/978-3-030-59722-1_52] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
|
11
|
Puylaert CAJ, Tielbeek JAW, Schüffler PJ, Nio CY, Horsthuis K, Mearadji B, Ponsioen CY, Vos FM, Stoker J. Comparison of contrast-enhanced and diffusion-weighted MRI in assessment of the terminal ileum in Crohn's disease patients. Abdom Radiol (NY) 2019; 44:398-405. [PMID: 30109377 DOI: 10.1007/s00261-018-1734-6] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/08/2023]
Abstract
PURPOSE The purpose of the study was to compare the performance of contrast-enhanced (CE)-MRI and diffusion-weighted imaging (DW)-MRI in grading Crohn's disease activity of the terminal ileum. METHODS Three readers evaluated CE-MRI, DW-MRI, and their combinations (CE/DW-MRI and DW/CE-MRI, depending on which protocol was used at the start of evaluation). Disease severity grading scores were correlated to the Crohn's Disease Endoscopic Index of Severity (CDEIS). Diagnostic accuracy, severity grading, and levels of confidence were compared between imaging protocols and interobserver agreement was calculated. RESULTS Sixty-one patients were included (30 female, median age 36). Diagnostic accuracy for active disease for CE-MRI, DW-MRI, CE/DW-MRI, and DW/CE-MRI ranged between 0.82 and 0.85, 0.75 and 0.83, 0.79 and 0.84, and 0.74 and 0.82, respectively. Severity grading correlation to CDEIS ranged between 0.70 and 0.74, 0.66 and 0.70, 0.69 and 0.75, and 0.67 and 0.74, respectively. For each reader, CE-MRI values were consistently higher than DW-MRI, albeit not significantly. Confidence levels for all readers were significantly higher for CE-MRI compared to DW-MRI (P < 0.001). Further increased confidence was seen when using combined imaging protocols. CONCLUSIONS There was no significant difference of CE-MRI and DW-MRI in determining disease activity, but the higher confidence levels may favor CE-MRI. DW-MRI is a good alternative in cases with relative contraindications for the use of intravenous contrast medium.
Collapse
|
12
|
Puylaert CAJ, Schüffler PJ, Naziroglu RE, Tielbeek JAW, Li Z, Makanyanga JC, Tutein Nolthenius CJ, Nio CY, Pendsé DA, Menys A, Ponsioen CY, Atkinson D, Forbes A, Buhmann JM, Fuchs TJ, Hatzakis H, van Vliet LJ, Stoker J, Taylor SA, Vos FM. Semiautomatic Assessment of the Terminal Ileum and Colon in Patients with Crohn Disease Using MRI (the VIGOR++ Project). Acad Radiol 2018; 25:1038-1045. [PMID: 29428210 DOI: 10.1016/j.acra.2017.12.024] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2017] [Revised: 12/20/2017] [Accepted: 12/25/2017] [Indexed: 01/18/2023]
Abstract
RATIONALE AND OBJECTIVES The objective of this study was to develop and validate a predictive magnetic resonance imaging (MRI) activity score for ileocolonic Crohn disease activity based on both subjective and semiautomatic MRI features. MATERIALS AND METHODS An MRI activity score (the "virtual gastrointestinal tract [VIGOR]" score) was developed from 27 validated magnetic resonance enterography datasets, including subjective radiologist observation of mural T2 signal and semiautomatic measurements of bowel wall thickness, excess volume, and dynamic contrast enhancement (initial slope of increase). A second subjective score was developed based on only radiologist observations. For validation, two observers applied both scores and three existing scores to a prospective dataset of 106 patients (59 women, median age 33) with known Crohn disease, using the endoscopic Crohn's Disease Endoscopic Index of Severity (CDEIS) as a reference standard. RESULTS The VIGOR score (17.1 × initial slope of increase + 0.2 × excess volume + 2.3 × mural T2) and other activity scores all had comparable correlation to the CDEIS scores (observer 1: r = 0.58 and 0.59, and observer 2: r = 0.34-0.40 and 0.43-0.51, respectively). The VIGOR score, however, improved interobserver agreement compared to the other activity scores (intraclass correlation coefficient = 0.81 vs 0.44-0.59). A diagnostic accuracy of 80%-81% was seen for the VIGOR score, similar to the other scores. CONCLUSIONS The VIGOR score achieves comparable accuracy to conventional MRI activity scores, but with significantly improved reproducibility, favoring its use for disease monitoring and therapy evaluation.
Collapse
Affiliation(s)
- Carl A J Puylaert
- Department of Radiology and Nuclear Medicine, Academic Medical Centre, Meibergdreef 9, P.O 22660, 1100DD, Amsterdam, The Netherlands.
| | - Peter J Schüffler
- Department of Computer Sciences, Eidgenössische Technische Hochschule Zurich, Zurich, Switzerland; Department of Medical Physics, Memorial Sloan-Kettering Cancer Center, New York, New York
| | - Robiel E Naziroglu
- Department of Imaging Physics, Delft University of Technology, Delft, The Netherlands
| | - Jeroen A W Tielbeek
- Department of Radiology and Nuclear Medicine, Academic Medical Centre, Meibergdreef 9, P.O 22660, 1100DD, Amsterdam, The Netherlands
| | - Zhang Li
- Department of Imaging Physics, Delft University of Technology, Delft, The Netherlands; College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China
| | - Jesica C Makanyanga
- Center for Medical Imaging, University College London Hospitals National Health Service Foundation Trust, London, UK
| | - Charlotte J Tutein Nolthenius
- Department of Radiology and Nuclear Medicine, Academic Medical Centre, Meibergdreef 9, P.O 22660, 1100DD, Amsterdam, The Netherlands
| | - C Yung Nio
- Department of Radiology and Nuclear Medicine, Academic Medical Centre, Meibergdreef 9, P.O 22660, 1100DD, Amsterdam, The Netherlands
| | - Douglas A Pendsé
- Center for Medical Imaging, University College London Hospitals National Health Service Foundation Trust, London, UK
| | - Alex Menys
- Center for Medical Imaging, University College London Hospitals National Health Service Foundation Trust, London, UK
| | - Cyriel Y Ponsioen
- Department of Gastroenterology, Academic Medical Centre, Amsterdam, The Netherlands
| | - David Atkinson
- Center for Medical Imaging, University College London Hospitals National Health Service Foundation Trust, London, UK
| | - Alastair Forbes
- Norwich Medical School, University of East Anglia, Norwich, UK
| | - Joachim M Buhmann
- Department of Computer Sciences, Eidgenössische Technische Hochschule Zurich, Zurich, Switzerland
| | - Thomas J Fuchs
- Department of Medical Physics, Memorial Sloan-Kettering Cancer Center, New York, New York
| | | | - Lucas J van Vliet
- Department of Imaging Physics, Delft University of Technology, Delft, The Netherlands
| | - Jaap Stoker
- Department of Radiology and Nuclear Medicine, Academic Medical Centre, Meibergdreef 9, P.O 22660, 1100DD, Amsterdam, The Netherlands
| | - Stuart A Taylor
- Center for Medical Imaging, University College London Hospitals National Health Service Foundation Trust, London, UK
| | - Frans M Vos
- Department of Radiology and Nuclear Medicine, Academic Medical Centre, Meibergdreef 9, P.O 22660, 1100DD, Amsterdam, The Netherlands; Department of Imaging Physics, Delft University of Technology, Delft, The Netherlands
| |
Collapse
|
13
|
Fankhauser CD, Schüffler PJ, Gillessen S, Omlin A, Rupp NJ, Rueschoff JH, Hermanns T, Poyet C, Sulser T, Moch H, Wild PJ. Comprehensive immunohistochemical analysis of PD-L1 shows scarce expression in castration-resistant prostate cancer. Oncotarget 2018; 9:10284-10293. [PMID: 29535806 PMCID: PMC5828186 DOI: 10.18632/oncotarget.22888] [Citation(s) in RCA: 39] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2016] [Accepted: 11/15/2017] [Indexed: 12/20/2022] Open
Abstract
BACKGROUND We aimed to analyze the frequency and distribution of PD-L1 expression in specimens from prostate cancer (PC) patients using two different anti-PD-L1 antibodies (E1L3N, SP263). MATERIALS AND METHODS PD-L1 immunohistochemistry was performed in a tissue microarray consisting of 82 castration-resistant prostate cancer (CRPC) specimens, 70 benign prostate hyperplasia (BPH) specimens, 96 localized PC cases, and 3 PC cell lines, using two different antibodies (clones E1L3N, and SP263). Staining images for CD4, CD8, PD-L1, and PanCK of a single PD-L1 positive case were compared, using a newly developed dot-wise correlation method for digital images to objectively test for co-expression. RESULTS Depending on the antibody used, in tumor cells (TC) only five (E1L3N: 6%) and three (SP263: 3.7%) samples were positive. In infiltrating immune cells (IC) 12 (SP263: 14.6%) and 8 (E1L3N: 9.9%) specimens showed PD-L1 expression. Two PC cell lines (PC3, LnCaP) also displayed membranous immunoreactivity. All localized PCs or BPH samples tested were negative. Dot-wise digital correlation of expression patterns revealed a moderate positive correlation between PD-L1 and PanCK expression, whereas both PanCK and PD-L1 showed a weak negative Pearson correlation coefficient between CD4 and CD8. CONCLUSIONS PD-L1 was not expressed in localized PC or BPH, and was only found in a minority of CRPC tumors and infiltrating immune cells. Protein expression maps and systematic dot-wise comparison could be a useful objective way to describe the relationship between immuno- and tumor-related proteins in the future, without the need to develop multiplex staining methods.
Collapse
Affiliation(s)
- Christian D. Fankhauser
- Department of Urology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Peter J. Schüffler
- Department of Computer Science, ETH Zurich, Zurich, Switzerland
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Silke Gillessen
- Department of Medical Oncology and Hematology, Cantonal Hospital, St. Gallen, Switzerland
| | - Aurelius Omlin
- Department of Medical Oncology and Hematology, Cantonal Hospital, St. Gallen, Switzerland
| | - Niels J. Rupp
- Department of Pathology and Molecular Pathology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Jan H. Rueschoff
- Department of Pathology and Molecular Pathology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Thomas Hermanns
- Department of Urology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Cedric Poyet
- Department of Urology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Tullio Sulser
- Department of Urology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Holger Moch
- Department of Pathology and Molecular Pathology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Peter J. Wild
- Department of Pathology and Molecular Pathology, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| |
Collapse
|
14
|
Schaumberg AJ, Sirintrapun SJ, Al-Ahmadie HA, Schüffler PJ, Fuchs TJ. DeepScope: Nonintrusive Whole Slide Saliency Annotation and Prediction from Pathologists at the Microscope. Comput Intell Methods Bioinform Biostat (2016) 2017; 10477:42-58. [PMID: 29601065 DOI: 10.1007/978-3-319-67834-4_4] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/03/2023]
Abstract
Modern digital pathology departments have grown to produce whole-slide image data at petabyte scale, an unprecedented treasure chest for medical machine learning tasks. Unfortunately, most digital slides are not annotated at the image level, hindering large-scale application of supervised learning. Manual labeling is prohibitive, requiring pathologists with decades of training and outstanding clinical service responsibilities. This problem is further aggravated by the United States Food and Drug Administration's ruling that primary diagnosis must come from a glass slide rather than a digital image. We present the first end-to-end framework to overcome this problem, gathering annotations in a nonintrusive manner during a pathologist's routine clinical work: (i) microscope-specific 3D-printed commodity camera mounts are used to video record the glass-slide-based clinical diagnosis process; (ii) after routine scanning of the whole slide, the video frames are registered to the digital slide; (iii) motion and observation time are estimated to generate a spatial and temporal saliency map of the whole slide. Demonstrating the utility of these annotations, we train a convolutional neural network that detects diagnosis-relevant salient regions, then report accuracy of 85.15% in bladder and 91.40% in prostate, with 75.00% accuracy when training on prostate but predicting in bladder, despite different pathologists examining the different tissues. When training on one patient but testing on another, AUROC in bladder is 0.79±0.11 and in prostate is 0.96±0.04. Our tool is available at https://bitbucket.org/aschaumberg/deepscope.
Collapse
Affiliation(s)
- Andrew J Schaumberg
- Memorial Sloan Kettering Cancer Center and the Tri-Institutional Training Program in Computational Biology and Medicine, New York, NY, USA.,Weill Cornell Graduate School of Medical Sciences, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - S Joseph Sirintrapun
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Hikmat A Al-Ahmadie
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Peter J Schüffler
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Thomas J Fuchs
- Weill Cornell Graduate School of Medical Sciences, Memorial Sloan Kettering Cancer Center, New York, NY, USA.,Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA.,Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| |
Collapse
|
15
|
Surinova S, Choi M, Tao S, Schüffler PJ, Chang CY, Clough T, Vysloužil K, Khoylou M, Srovnal J, Liu Y, Matondo M, Hüttenhain R, Weisser H, Buhmann JM, Hajdúch M, Brenner H, Vitek O, Aebersold R. Prediction of colorectal cancer diagnosis based on circulating plasma proteins. EMBO Mol Med 2016; 7:1166-78. [PMID: 26253081 PMCID: PMC4568950 DOI: 10.15252/emmm.201404873] [Citation(s) in RCA: 68] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022] Open
Abstract
Non-invasive detection of colorectal cancer with blood-based markers is a critical clinical need. Here we describe a phased mass spectrometry-based approach for the discovery, screening, and validation of circulating protein biomarkers with diagnostic value. Initially, we profiled human primary tumor tissue epithelia and characterized about 300 secreted and cell surface candidate glycoproteins. These candidates were then screened in patient systemic circulation to identify detectable candidates in blood plasma. An 88-plex targeting method was established to systematically monitor these proteins in two large and independent cohorts of plasma samples, which generated quantitative clinical datasets at an unprecedented scale. The data were deployed to develop and evaluate a five-protein biomarker signature for colorectal cancer detection.
Collapse
Affiliation(s)
- Silvia Surinova
- Department of Biology, Institute of Molecular Systems Biology, ETH Zurich, Zurich, Switzerland
| | - Meena Choi
- Department of Statistics, Purdue University, West Lafayette, IN, USA
| | - Sha Tao
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Peter J Schüffler
- Department of Computer Science, Institute for Machine Learning, ETH Zurich, Zurich, Switzerland
| | - Ching-Yun Chang
- Department of Statistics, Purdue University, West Lafayette, IN, USA
| | - Timothy Clough
- Department of Statistics, Purdue University, West Lafayette, IN, USA
| | - Kamil Vysloužil
- Department of Surgery, University Hospital in Olomouc, Olomouc, Czech Republic
| | - Marta Khoylou
- Institute of Molecular and Translational Medicine, Faculty of Medicine and Dentistry, Palacký University, Olomouc, Czech Republic
| | - Josef Srovnal
- Institute of Molecular and Translational Medicine, Faculty of Medicine and Dentistry, Palacký University, Olomouc, Czech Republic
| | - Yansheng Liu
- Department of Biology, Institute of Molecular Systems Biology, ETH Zurich, Zurich, Switzerland
| | - Mariette Matondo
- Department of Biology, Institute of Molecular Systems Biology, ETH Zurich, Zurich, Switzerland
| | - Ruth Hüttenhain
- Department of Biology, Institute of Molecular Systems Biology, ETH Zurich, Zurich, Switzerland
| | - Hendrik Weisser
- Department of Biology, Institute of Molecular Systems Biology, ETH Zurich, Zurich, Switzerland
| | - Joachim M Buhmann
- Department of Computer Science, Institute for Machine Learning, ETH Zurich, Zurich, Switzerland
| | - Marián Hajdúch
- Institute of Molecular and Translational Medicine, Faculty of Medicine and Dentistry, Palacký University, Olomouc, Czech Republic
| | - Hermann Brenner
- Division of Clinical Epidemiology and Aging Research, German Cancer Research Center (DKFZ), Heidelberg, Germany German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Olga Vitek
- Department of Statistics, Purdue University, West Lafayette, IN, USA Department of Computer Science, Purdue University, West Lafayette, IN, USA College of Science and College of Computer and Information Science, Northeastern University, Boston, MA, USA
| | - Ruedi Aebersold
- Department of Biology, Institute of Molecular Systems Biology, ETH Zurich, Zurich, Switzerland Faculty of Science, University of Zurich, Zurich, Switzerland
| |
Collapse
|
16
|
Zhong Q, Rüschoff JH, Guo T, Gabrani M, Schüffler PJ, Rechsteiner M, Liu Y, Fuchs TJ, Rupp NJ, Fankhauser C, Buhmann JM, Perner S, Poyet C, Blattner M, Soldini D, Moch H, Rubin MA, Noske A, Rüschoff J, Haffner MC, Jochum W, Wild PJ. Image-based computational quantification and visualization of genetic alterations and tumour heterogeneity. Sci Rep 2016; 6:24146. [PMID: 27052161 PMCID: PMC4823793 DOI: 10.1038/srep24146] [Citation(s) in RCA: 22] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2016] [Accepted: 03/22/2016] [Indexed: 12/31/2022] Open
Abstract
Recent large-scale genome analyses of human tissue samples have uncovered a high degree of genetic alterations and tumour heterogeneity in most tumour entities, independent of morphological phenotypes and histopathological characteristics. Assessment of genetic copy-number variation (CNV) and tumour heterogeneity by fluorescence in situ hybridization (ISH) provides additional tissue morphology at single-cell resolution, but it is labour intensive with limited throughput and high inter-observer variability. We present an integrative method combining bright-field dual-colour chromogenic and silver ISH assays with an image-based computational workflow (ISHProfiler), for accurate detection of molecular signals, high-throughput evaluation of CNV, expressive visualization of multi-level heterogeneity (cellular, inter- and intra-tumour heterogeneity), and objective quantification of heterogeneous genetic deletions (PTEN) and amplifications (19q12, HER2) in diverse human tumours (prostate, endometrial, ovarian and gastric), using various tissue sizes and different scanners, with unprecedented throughput and reproducibility.
Collapse
Affiliation(s)
- Qing Zhong
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | - Jan H Rüschoff
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | - Tiannan Guo
- Institute of Molecular Systems Biology, ETH, Zurich, Switzerland
| | - Maria Gabrani
- Zurich Labouratory, IBM Research-Zurich, Rueschlikon, Switzerland
| | | | - Markus Rechsteiner
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | - Yansheng Liu
- Institute of Molecular Systems Biology, ETH, Zurich, Switzerland
| | - Thomas J Fuchs
- Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Niels J Rupp
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | - Christian Fankhauser
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | | | - Sven Perner
- Department of Prostate Cancer Research, Institute of Pathology, University Hospital of Bonn, Bonn, Germany
| | - Cédric Poyet
- Department of Urology, University Hospital Zurich, Zurich, Switzerland
| | - Miriam Blattner
- Institute for Precision Medicine and Department of Pathology and Laboratory Medicine, Weill Medical College of Cornell University and New York-Presbyterian Hospital, New York, NY, USA
| | - Davide Soldini
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | - Holger Moch
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | - Mark A Rubin
- Institute for Precision Medicine and Department of Pathology and Laboratory Medicine, Weill Medical College of Cornell University and New York-Presbyterian Hospital, New York, NY, USA
| | - Aurelia Noske
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | - Josef Rüschoff
- Targos Molecular Pathology, Pathology Nordhessen, Kassel, Germany
| | - Michael C Haffner
- Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University, Baltimore, Maryland, USA
| | - Wolfram Jochum
- Institute of Pathology, Cantonal Hospital St. Gallen, St. Gallen, Switzerland
| | - Peter J Wild
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| |
Collapse
|
17
|
Rupp NJ, Schüffler PJ, Zhong Q, Falkner F, Rechsteiner M, Rüschoff JH, Fankhauser C, Drach M, Largo R, Tremp M, Poyet C, Sulser T, Kristiansen G, Moch H, Buhmann J, Müntener M, Wild PJ. Oxygen supply maps for hypoxic microenvironment visualization in prostate cancer. J Pathol Inform 2016; 7:3. [PMID: 26955501 PMCID: PMC4763504 DOI: 10.4103/2153-3539.175376] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2015] [Accepted: 10/26/2015] [Indexed: 12/04/2022] Open
Abstract
Background: Intratumoral hypoxia plays an important role with regard to tumor biology and susceptibility to radio- and chemotherapy. For further investigation of hypoxia-related changes, areas of certain hypoxia must be reliably detected within cancer tissues. Pimonidazole, a 2-nitroimindazole, accumulates in hypoxic tissue and can be easily visualized using immunohistochemistry. Materials and Methods: To improve detection of highly hypoxic versus normoxic areas in prostate cancer, immunoreactivity of pimonidazole and a combination of known hypoxia-related proteins was used to create computational oxygen supply maps of prostate cancer. Pimonidazole was intravenously administered before radical prostatectomy in n = 15 patients, using the da Vinci robot-assisted surgical system. Prostatectomy specimens were immediately transferred into buffered formaldehyde, fixed overnight, and completely embedded in paraffin. Pimonidazole accumulation and hypoxia-related protein expression were visualized by immunohistochemistry. Oxygen supply maps were created using the normalized information from pimonidazole and hypoxia-related proteins. Results: Based on pimonidazole staining and other hypoxia.related proteins (osteopontin, hypoxia-inducible factor 1-alpha, and glucose transporter member 1) oxygen supply maps in prostate cancer were created. Overall, oxygen supply maps consisting of information from all hypoxia-related proteins showed high correlation and mutual information to the golden standard of pimonidazole. Here, we describe an improved computer-based ex vivo model for an accurate detection of oxygen supply in human prostate cancer tissue. Conclusions: This platform can be used for precise colocalization of novel candidate hypoxia-related proteins in a representative number of prostate cancer cases, and improve issues of single marker correlations. Furthermore, this study provides a source for further in situ tests and biochemical investigations
Collapse
Affiliation(s)
- Niels J Rupp
- Institute of Surgical Pathology, University Hospital Zurich, Schmelzbergstrasse 12, 8091 Zurich, Switzerland
| | - Peter J Schüffler
- Department of Computer Science, ETH Zurich, Universitaetstr 6, 8092 Zurich, Switzerland
| | - Qing Zhong
- Institute of Surgical Pathology, University Hospital Zurich, Schmelzbergstrasse 12, 8091 Zurich, Switzerland
| | - Florian Falkner
- Institute of Pathology, Cantonal Hospital Winterthur, Brauerstrasse 15, 8401 Winterthur, Switzerland
| | - Markus Rechsteiner
- Institute of Surgical Pathology, University Hospital Zurich, Schmelzbergstrasse 12, 8091 Zurich, Switzerland
| | - Jan H Rüschoff
- Institute of Surgical Pathology, University Hospital Zurich, Schmelzbergstrasse 12, 8091 Zurich, Switzerland
| | - Christian Fankhauser
- Institute of Surgical Pathology, University Hospital Zurich, Schmelzbergstrasse 12, 8091 Zurich, Switzerland
| | - Matthias Drach
- Institute of Surgical Pathology, University Hospital Zurich, Schmelzbergstrasse 12, 8091 Zurich, Switzerland
| | - Remo Largo
- Department of Urology, University Hospital Zurich, Rämistrasse 100, 8091 Zurich, Switzerland
| | - Mathias Tremp
- Department of Plastic, Reconstructive and Aesthetic Surgery, University Hospital Basel, Spitalstrasse 21, 4031 Basel, Switzerland
| | - Cedric Poyet
- Department of Urology, University Hospital Zurich, Rämistrasse 100, 8091 Zurich, Switzerland
| | - Tullio Sulser
- Department of Urology, University Hospital Zurich, Rämistrasse 100, 8091 Zurich, Switzerland
| | - Glen Kristiansen
- Institute of Pathology, University Hospital Bonn, Sigmund-Freud-Strasse 25, 53127 Bonn, Germany
| | - Holger Moch
- Institute of Surgical Pathology, University Hospital Zurich, Schmelzbergstrasse 12, 8091 Zurich, Switzerland
| | - Joachim Buhmann
- Department of Computer Science, ETH Zurich, Universitaetstr 6, 8092 Zurich, Switzerland
| | - Michael Müntener
- Department of Urology, City Hospital Triemli, Birmensdorferstrasse 497, 8063 Zurich, Switzerland
| | - Peter J Wild
- Institute of Surgical Pathology, University Hospital Zurich, Schmelzbergstrasse 12, 8091 Zurich, Switzerland
| |
Collapse
|
18
|
Schüffler PJ, Schapiro D, Giesen C, Wang HAO, Bodenmiller B, Buhmann JM. Automatic single cell segmentation on highly multiplexed tissue images. Cytometry A 2015; 87:936-42. [DOI: 10.1002/cyto.a.22702] [Citation(s) in RCA: 47] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2014] [Revised: 04/14/2015] [Accepted: 05/14/2015] [Indexed: 11/12/2022]
Affiliation(s)
- Peter J. Schüffler
- Department of Computer Science; ETH Zurich; Zurich 8092 Switzerland
- Life Science Zurich Graduate School, ETH Zurich and University of Zurich; Zurich Switzerland
| | - Denis Schapiro
- Life Science Zurich Graduate School, ETH Zurich and University of Zurich; Zurich Switzerland
- Institute of Molecular Life Sciences, University of Zurich; Zurich 8057 Switzerland
| | - Charlotte Giesen
- Institute of Molecular Life Sciences, University of Zurich; Zurich 8057 Switzerland
| | - Hao A. O. Wang
- Department of Chemistry; ETH Zurich; Zurich 8093 Switzerland
| | - Bernd Bodenmiller
- Institute of Molecular Life Sciences, University of Zurich; Zurich 8057 Switzerland
| | | |
Collapse
|
19
|
Brandt S, Montagna C, Georgis A, Schüffler PJ, Bühler MM, Seifert B, Thiesler T, Curioni-Fontecedro A, Hegyi I, Dehler S, Martin V, Tinguely M, Soldini D. The combined expression of the stromal markers fibronectin and SPARC improves the prediction of survival in diffuse large B-cell lymphoma. Exp Hematol Oncol 2013; 2:27. [PMID: 24499539 PMCID: PMC3852975 DOI: 10.1186/2162-3619-2-27] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2013] [Accepted: 09/30/2013] [Indexed: 01/01/2023] Open
Abstract
Background In diffuse large B-cell lymphomas, gene expression profiling studies attributed a major biologic role to non-neoplastic cells of the tumour microenvironment as its composition and characteristics were shown to predict survival. In particular, the expression of selected genes encoding components of the extracellular matrix was reported to be associated with clinical outcome. Nevertheless, the translation of these data into robust, routinely applicable immunohistochemical markers is still warranted. Therefore, in this study, we analysed the combination of the expression of the extracellular matrix components Fibronectin and SPARC on formalin-fixed paraffin embedded tissue derived from 173 patients with DLBCL in order to recapitulate gene expression profiling data. Results The expression of Fibronectin and SPARC was detected in 77/173 (44.5%) and 125/173 (72.3%) cases, respectively, and 55/173 (31.8%) cases were double positive. Patients with lymphomas expressing Fibronectin showed significantly longer overall survival when compared to negative ones (6.3 versus 3.6 years). Moreover, patients with double positive lymphomas also presented with significantly longer overall survival when compared with the remaining cases (11.6 versus 3.6 years) and this combined expression of both markers results in a better association with overall survival data than the expression of SPARC or Fibronectin taken separately (Hazard ratio 0.41, 95% confidence interval 0.17 to 0.95, p = 0.037). Finally, neither Fibronectin nor SPARC expression was associated with any of the collected clinico-pathological parameters. Conclusions The combined immunohistochemical assessment of Fibronectin and SPARC, two components of the extracellular matrix, represents an important tool for the prediction of survival in diffuse large B-cell lymphomas. Our study suggests that translation of gene expression profiling data on tumour microenvironment into routinely applicable immunohistochemical markers is a useful approach for a further characterization of this heterogeneous type of lymphoma.
Collapse
Affiliation(s)
- Simone Brandt
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | - Chiara Montagna
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | - Antoin Georgis
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | | | - Marco M Bühler
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | - Burkhardt Seifert
- Division of Biostatistics, Institute for Social and Preventive Medicine, University of Zurich, Zurich, Switzerland
| | - Thore Thiesler
- Institute of Pathology, University of Bonn, Bonn, Germany
| | | | - Ivan Hegyi
- Institute of Pathology, Locarno, Switzerland
| | - Silvia Dehler
- Cancer Registry, Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| | | | - Marianne Tinguely
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland.,Kempf and Pfaltz, Histologische Diagnostik, Zurich 8042, Switzerland
| | - Davide Soldini
- Institute of Surgical Pathology, University Hospital Zurich, Zurich, Switzerland
| |
Collapse
|
20
|
Schüffler PJ, Fuchs TJ, Ong CS, Wild PJ, Rupp NJ, Buhmann JM. TMARKER: A free software toolkit for histopathological cell counting and staining estimation. J Pathol Inform 2013; 4:S2. [PMID: 23766938 PMCID: PMC3678753 DOI: 10.4103/2153-3539.109804] [Citation(s) in RCA: 45] [Impact Index Per Article: 4.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2012] [Accepted: 01/21/2013] [Indexed: 11/04/2022] Open
Abstract
BACKGROUND Histological tissue analysis often involves manual cell counting and staining estimation of cancerous cells. These assessments are extremely time consuming, highly subjective and prone to error, since immunohistochemically stained cancer tissues usually show high variability in cell sizes, morphological structures and staining quality. To facilitate reproducible analysis in clinical practice as well as for cancer research, objective computer assisted staining estimation is highly desirable. METHODS We employ machine learning algorithms as randomized decision trees and support vector machines for nucleus detection and classification. Superpixels as segmentation over the tissue image are classified into foreground and background and thereafter into malignant and benign, learning from the user's feedback. As a fast alternative without nucleus classification, the existing color deconvolution method is incorporated. RESULTS Our program TMARKER connects already available workflows for computational pathology and immunohistochemical tissue rating with modern active learning algorithms from machine learning and computer vision. On a test dataset of human renal clear cell carcinoma and prostate carcinoma, the performance of the used algorithms is equivalent to two independent pathologists for nucleus detection and classification. CONCLUSION We present a novel, free and operating system independent software package for computational cell counting and staining estimation, supporting IHC stained tissue analysis in clinic and for research. Proprietary toolboxes for similar tasks are expensive, bound to specific commercial hardware (e.g. a microscope) and mostly not quantitatively validated in terms of performance and reproducibility. We are confident that the presented software package will proof valuable for the scientific community and we anticipate a broader application domain due to the possibility to interactively learn models for new image types.
Collapse
Affiliation(s)
- Peter J. Schüffler
- Institute for Computational Science, ETH Zurich, Switzerland
- Competence Center for Systems Physiology and Metabolic Diseases, ETH Zurich, Switzerland
| | | | - Cheng Soon Ong
- NICTA, The University of Melbourne, Parkville VIC 3010, Australia
| | - Peter J. Wild
- Institute of Pathology, University Hospital Zurich, Switzerland
| | - Niels J. Rupp
- Institute of Pathology, University Hospital Zurich, Switzerland
| | - Joachim M. Buhmann
- Institute for Computational Science, ETH Zurich, Switzerland
- Competence Center for Systems Physiology and Metabolic Diseases, ETH Zurich, Switzerland
| |
Collapse
|
21
|
Veeck J, Wild PJ, Fuchs T, Schüffler PJ, Hartmann A, Knüchel R, Dahl E. Prognostic relevance of Wnt-inhibitory factor-1 (WIF1) and Dickkopf-3 (DKK3) promoter methylation in human breast cancer. BMC Cancer 2009; 9:217. [PMID: 19570204 PMCID: PMC2717119 DOI: 10.1186/1471-2407-9-217] [Citation(s) in RCA: 72] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2008] [Accepted: 07/01/2009] [Indexed: 01/12/2023] Open
Abstract
BACKGROUND Secreted Wnt signaling antagonists have recently been described as frequent targets of epigenetic inactivation in human tumor entities. Since gene silencing of certain Wnt antagonists was found to be correlated with adverse patient survival in cancer, we aimed at investigating a potential prognostic impact of the two Wnt antagonizing molecules WIF1 and DKK3 in breast cancer, which are frequently silenced by promoter methylation in this disease. METHODS WIF1 and DKK3 promoter methylation were assessed by methylation-specific PCR with bisulfite-converted DNA from 19 normal breast tissues and 150 primary breast carcinomas. Promoter methylation was interpreted in a qualitative, binary fashion. Statistical evaluations included two-sided Fisher's exact tests, univariate log-rank tests of Kaplan-Meier curves as well as multivariate Cox regression analyses. RESULTS WIF1 and DKK3 promoter methylation were detected in 63.3% (95/150) and 61.3% (92/150) of breast carcinoma samples, respectively. In normal breast tissues, WIF1 methylation was present in 0% (0/19) and DKK3 methylation in 5.3% (1/19) of samples. In breast carcinomas, WIF1 methylation was significantly associated with methylation of DKK3 (p = 0.009). Methylation of either gene was not associated with clinicopathological parameters, except for DKK3 methylation being associated with patient age (p = 0.007). In univariate analysis, WIF1 methylation was not associated with clinical patient outcome. In contrast, DKK3 methylation was a prognostic factor in patient overall survival (OS) and disease-free survival (DFS). Estimated OS rates after 10 years were 54% for patients with DKK3-methylated tumors, in contrast to patients without DKK3 methylation in the tumor, who had a favorable 97% OS after 10 years (p < 0.001). Likewise, DFS at 10 years for patients harboring DKK3 methylation in the tumor was 58%, compared with 78% for patients with unmethylated DKK3 (p = 0.037). Multivariate analyses revealed that DKK3 methylation was an independent prognostic factor predicting poor OS (hazard ratio (HR): 14.4; 95% confidence interval (CI): 1.9-111.6; p = 0.011), and short DFS (HR: 2.5; 95% CI: 1.0-6.0; p = 0.047) in breast cancer. CONCLUSION Although the Wnt antagonist genes WIF1 and DKK3 show a very similar frequency of promoter methylation in human breast cancer, only DKK3 methylation proves as a novel prognostic marker potentially useful in the clinical management of this disease.
Collapse
Affiliation(s)
- Jürgen Veeck
- Molecular Oncology Group, Institute of Pathology, University Hospital of the RWTH Aachen, Pauwelsstrasse 30, D-52074 Aachen, Germany.
| | | | | | | | | | | | | |
Collapse
|