1
|
Jurgas A, Wodzinski M, D'Amato M, van der Laak J, Atzori M, Müller H. Improving quality control of whole slide images by explicit artifact augmentation. Sci Rep 2024; 14:17847. [PMID: 39090284 PMCID: PMC11294620 DOI: 10.1038/s41598-024-68667-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2024] [Accepted: 07/26/2024] [Indexed: 08/04/2024] Open
Abstract
The problem of artifacts in whole slide image acquisition, prevalent in both clinical workflows and research-oriented settings, necessitates human intervention and re-scanning. Overcoming this challenge requires developing quality control algorithms, that are hindered by the limited availability of relevant annotated data in histopathology. The manual annotation of ground-truth for artifact detection methods is expensive and time-consuming. This work addresses the issue by proposing a method dedicated to augmenting whole slide images with artifacts. The tool seamlessly generates and blends artifacts from an external library to a given histopathology dataset. The augmented datasets are then utilized to train artifact classification methods. The evaluation shows their usefulness in classification of the artifacts, where they show an improvement from 0.10 to 0.01 AUROC depending on the artifact type. The framework, model, weights, and ground-truth annotations are freely released to facilitate open science and reproducible research.
Collapse
Affiliation(s)
- Artur Jurgas
- AGH University of Krakow, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, 30059, Krakow, Poland.
- University of Applied Sciences Western Switzerland (HES-SO), Institute of Informatics, 3960, Sierre, Switzerland.
| | - Marek Wodzinski
- AGH University of Krakow, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, 30059, Krakow, Poland
- University of Applied Sciences Western Switzerland (HES-SO), Institute of Informatics, 3960, Sierre, Switzerland
| | - Marina D'Amato
- Radboud University Medical Center, Nijmegen, The Netherlands
| | | | - Manfredo Atzori
- University of Applied Sciences Western Switzerland (HES-SO), Institute of Informatics, 3960, Sierre, Switzerland
- Department of Neuroscience, University of Padova, Padua, Italy
| | - Henning Müller
- University of Applied Sciences Western Switzerland (HES-SO), Institute of Informatics, 3960, Sierre, Switzerland
- Medical Faculty, University of Geneva, Geneva, Switzerland
| |
Collapse
|
2
|
Fan F, Liu Q, Zee J, Ozeki T, Demeke D, Yang Y, Farris AB, Wang B, Shah M, Jacobs J, Mariani L, Lafata K, Rubin J, Chen Y, Holzman L, Hodgin JB, Madabhushi A, Barisoni L, Janowczyk A. Clinical Relevance of Computationally Derived Tubular Features: Spatial Relationships and the Development of Tubulointerstitial Scarring in MCD/FSGS. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2024.07.19.24310619. [PMID: 39072032 PMCID: PMC11275675 DOI: 10.1101/2024.07.19.24310619] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/30/2024]
Abstract
Background Visual scoring of tubular damage has limitations in capturing the full spectrum of structural changes and prognostic potential. We investigate if computationally quantified tubular features can enhance prognostication and reveal spatial relationships with interstitial fibrosis. Methods Deep-learning and image-processing-based segmentations were employed in N=254/266 PAS-WSIs from the NEPTUNE/CureGN datasets (135/153 focal segmental glomerulosclerosis and 119/113 minimal change disease) for: cortex, tubular lumen (TL), epithelium (TE), nuclei (TN), and basement membrane (TBM). N=104 pathomic features were extracted from these segmented tubular substructures and summarized at the patient level using summary statistics. The tubular features were quantified across the biopsy and in manually segmented regions of mature interstitial fibrosis and tubular atrophy (IFTA), pre-IFTA and non-IFTA in the NEPTUNE dataset. Minimum Redundancy Maximum Relevance was used in the NEPTUNE dataset to select features most associated with disease progression and proteinuria remission. Ridge-penalized Cox models evaluated their predictive discrimination compared to clinical/demographic data and visual-assessment. Models were evaluated in the CureGN dataset. Results N=9 features were predictive of disease progression and/or proteinuria remission. Models with tubular features had high prognostic accuracy in both NEPTUNE and CureGN datasets and increased prognostic accuracy for both outcomes (5.6%-7.7% and 1.6%-4.6% increase for disease progression and proteinuria remission, respectively) compared to conventional parameters alone in the NEPTUNE dataset. TBM thickness/area and TE simplification progressively increased from non- to pre- and mature IFTA. Conclusions Previously under-recognized, quantifiable, and clinically relevant tubular features in the kidney parenchyma can enhance understanding of mechanisms of disease progression and risk stratification.
Collapse
Affiliation(s)
- Fan Fan
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
| | - Qian Liu
- Children's Hospital of Philadelphia Research Institute, Philadelphia, PA
| | - Jarcy Zee
- Children's Hospital of Philadelphia Research Institute, Philadelphia, PA
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA
| | - Takaya Ozeki
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI, United States
| | - Dawit Demeke
- Department of Pathology, University of Michigan, Ann Arbor, MI, United States
| | - Yingbao Yang
- Department of Pathology, University of Michigan, Ann Arbor, MI, United States
| | - Alton B Farris
- Department of Pathology and Laboratory Medicine, Emory University, Atlanta, GA, USA
| | - Bangcheng Wang
- Department of Pathology, Division of AI & Computational Pathology, Duke University, Durham, NC, United States
| | - Manav Shah
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
| | - Jackson Jacobs
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
| | - Laura Mariani
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI, United States
| | - Kyle Lafata
- Department of Radiation Oncology, Duke University, Durham, NC, United States
| | - Jeremy Rubin
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA
| | - Yijiang Chen
- Department of Radiation Oncology, School of Medicine, Stanford University, Stanford, CA, USA
| | - Lawrence Holzman
- Department of Medicine, Division of Nephrology and Hypertension, University of Pennsylvania, Philadelphia, PA, United States
| | - Jeffrey B Hodgin
- Department of Pathology, University of Michigan, Ann Arbor, MI, United States
| | - Anant Madabhushi
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
- Atlanta Veterans Administration Medical Center, Atlanta, GA, USA
| | - Laura Barisoni
- Department of Pathology, Division of AI & Computational Pathology, Duke University, Durham, NC, United States
- Department of Medicine, Division of Nephrology, Duke University, Durham, NC, USA
| | - Andrew Janowczyk
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
- Department of Oncology, Division of Precision Oncology, University Hospital of Geneva, Geneva, Switzerland
- Department of Diagnostics, Division of Clinical Pathology, University Hospital of Geneva, Geneva, Switzerland
| |
Collapse
|
3
|
Fan F, Martinez G, DeSilvio T, Shin J, Chen Y, Jacobs J, Wang B, Ozeki T, Lafarge MW, Koelzer VH, Barisoni L, Madabhushi A, Viswanath SE, Janowczyk A. CohortFinder: an open-source tool for data-driven partitioning of digital pathology and imaging cohorts to yield robust machine-learning models. NPJ IMAGING 2024; 2:15. [PMID: 38962496 PMCID: PMC11216973 DOI: 10.1038/s44303-024-00018-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Accepted: 04/26/2024] [Indexed: 07/05/2024]
Abstract
Batch effects (BEs) refer to systematic technical differences in data collection unrelated to biological variations whose noise is shown to negatively impact machine learning (ML) model generalizability. Here we release CohortFinder (http://cohortfinder.com), an open-source tool aimed at mitigating BEs via data-driven cohort partitioning. We demonstrate CohortFinder improves ML model performance in downstream digital pathology and medical image processing tasks. CohortFinder is freely available for download at cohortfinder.com.
Collapse
Grants
- National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) / National Institute of Health (NIH)
- NephCure Kidney and the Henry E. Haller, Jr. Foundation
- Nephrotic Syndrome Study Network
- Rare Diseases Clinical Research Network
- National Center for Advancing Translational Sciences
- RDCRN Data Management and Coordinating Center (DMCC), United States
- National Institute of Neurological Disorders and Stroke
- NCATS and the NIDDK
- University of Michigan, NephCure Kidney International, Alport Syndrome Foundation, and the Halpin Foundation
- National Cancer Institute, United States
- National Heart, Lung, and Blood Institute
- National Institute of Biomedical Imaging and Bioengineering
- VA Merit Review Award
- U.S. Department of Veterans Affairs
- Development Service the Office of the Assistant Secretary of Defense for Health Affairs
- Kidney Precision Medicine Project (KPMP) Glue Grant and sponsored research agreements from Bristol Myers-Squibb, Boehringer-Ingelheim, Eli-Lilly and Astrazeneca
- National Institute of Nursing Research
- NIBIB through the CWRU Interdisciplinary Biomedical Imaging Training Program Fellowship
- DOD Peer Reviewed Cancer Research Program
- Wen Ko APT Summer Internship Program, the Ohio Third Frontier Technology Validation Fund, and the Wallace H. Coulter Foundation Program in the Department of Biomedical Engineering at Case Western Reserve University and sponsored research funding from Pfizer
- High-Performance Computing Resource in the Core Facility for Advanced Research Computing at Case Western Reserve University
Collapse
Affiliation(s)
- Fan Fan
- Emory University and Georgia Institute of Technology, Department of Biomedical Engineering, Atlanta, GA USA
| | - Georgia Martinez
- Case Western Reserve University, Department of Biomedical Engineering, Cleveland, OH USA
| | - Thomas DeSilvio
- Case Western Reserve University, Department of Biomedical Engineering, Cleveland, OH USA
| | - John Shin
- Case Western Reserve University, Department of Biomedical Engineering, Cleveland, OH USA
| | - Yijiang Chen
- Case Western Reserve University, Department of Biomedical Engineering, Cleveland, OH USA
| | - Jackson Jacobs
- Emory University and Georgia Institute of Technology, Department of Biomedical Engineering, Atlanta, GA USA
| | - Bangchen Wang
- Duke University, Department of Pathology, Division of AI & Computational Pathology, Durham, NC USA
| | - Takaya Ozeki
- University of Michigan, Department of Internal Medicine, Division of Nephrology, Ann Arbor, MI USA
| | - Maxime W. Lafarge
- University Hospital of Zurich, University of Zurich, Department of Pathology and Molecular Pathology, Zurich, Switzerland
| | - Viktor H. Koelzer
- University Hospital of Zurich, University of Zurich, Department of Pathology and Molecular Pathology, Zurich, Switzerland
| | - Laura Barisoni
- Duke University, Department of Pathology, Division of AI & Computational Pathology, Durham, NC USA
- Duke University, Department of Medicine, Division of Nephrology, Durham, NC USA
| | - Anant Madabhushi
- Emory University and Georgia Institute of Technology, Department of Biomedical Engineering, Atlanta, GA USA
- Atlanta Veterans Administration Medical Center, Atlanta, GA USA
| | - Satish E. Viswanath
- Case Western Reserve University, Department of Biomedical Engineering, Cleveland, OH USA
| | - Andrew Janowczyk
- Emory University and Georgia Institute of Technology, Department of Biomedical Engineering, Atlanta, GA USA
- University Hospital of Geneva, Department of Oncology, Division of Precision Oncology, Geneva, Switzerland
- University Hospital of Geneva, Department of Clinical Pathology, Division of Clinical Pathology, Geneva, Switzerland
| |
Collapse
|
4
|
Goodman K, Sarullo K, Swamidass SJ, Gaut JP, Jain S. Role of Artificial Intelligence in Kidney Pathology: Promises and Pitfalls. KIDNEY360 2024; 5:1044-1046. [PMID: 39254464 PMCID: PMC11296536 DOI: 10.34067/kid.0000000000000482] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/11/2024]
Affiliation(s)
- Kyle Goodman
- Department of Pathology and Immunology, Washington University School of Medicine in St. Louis, St. Louis, Missouri
| | - Kathryn Sarullo
- Department of Pathology and Immunology, Washington University School of Medicine in St. Louis, St. Louis, Missouri
| | - S. Joshua Swamidass
- Department of Pathology and Immunology, Washington University School of Medicine in St. Louis, St. Louis, Missouri
| | - Joseph P. Gaut
- Department of Pathology and Immunology, Washington University School of Medicine in St. Louis, St. Louis, Missouri
- Department of Medicine (Nephrology), Washington University School of Medicine in St. Louis, St. Louis, Missouri
| | - Sanjay Jain
- Department of Pathology and Immunology, Washington University School of Medicine in St. Louis, St. Louis, Missouri
- Department of Medicine (Nephrology), Washington University School of Medicine in St. Louis, St. Louis, Missouri
- Department of Pediatrics, Washington University School of Medicine in St. Louis, St. Louis, Missouri
| |
Collapse
|
5
|
Poalelungi DG, Neagu AI, Fulga A, Neagu M, Tutunaru D, Nechita A, Fulga I. Revolutionizing Pathology with Artificial Intelligence: Innovations in Immunohistochemistry. J Pers Med 2024; 14:693. [PMID: 39063947 PMCID: PMC11278211 DOI: 10.3390/jpm14070693] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2024] [Revised: 06/25/2024] [Accepted: 06/26/2024] [Indexed: 07/28/2024] Open
Abstract
Artificial intelligence (AI) is a reality of our times, and it has been successfully implemented in all fields, including medicine. As a relatively new domain, all efforts are directed towards creating algorithms applicable in most medical specialties. Pathology, as one of the most important areas of interest for precision medicine, has received significant attention in the development and implementation of AI algorithms. This focus is especially important for achieving accurate diagnoses. Moreover, immunohistochemistry (IHC) serves as a complementary diagnostic tool in pathology. It can be further augmented through the application of deep learning (DL) and machine learning (ML) algorithms for assessing and analyzing immunohistochemical markers. Such advancements can aid in delineating targeted therapeutic approaches and prognostic stratification. This article explores the applications and integration of various AI software programs and platforms used in immunohistochemical analysis. It concludes by highlighting the application of these technologies to pathologies such as breast, prostate, lung, melanocytic proliferations, and hematologic conditions. Additionally, it underscores the necessity for further innovative diagnostic algorithms to assist physicians in the diagnostic process.
Collapse
Affiliation(s)
- Diana Gina Poalelungi
- Faculty of Medicine and Pharmacy, Dunarea de Jos University of Galati, 35 AI Cuza St., 800010 Galati, Romania; (D.G.P.); (M.N.); (D.T.); (A.N.); (I.F.)
- Saint Apostle Andrew Emergency County Clinical Hospital, 177 Brailei St., 800578 Galati, Romania
| | - Anca Iulia Neagu
- Faculty of Medicine and Pharmacy, Dunarea de Jos University of Galati, 35 AI Cuza St., 800010 Galati, Romania; (D.G.P.); (M.N.); (D.T.); (A.N.); (I.F.)
- Saint John Clinical Emergency Hospital for Children, 800487 Galati, Romania
| | - Ana Fulga
- Faculty of Medicine and Pharmacy, Dunarea de Jos University of Galati, 35 AI Cuza St., 800010 Galati, Romania; (D.G.P.); (M.N.); (D.T.); (A.N.); (I.F.)
- Saint Apostle Andrew Emergency County Clinical Hospital, 177 Brailei St., 800578 Galati, Romania
| | - Marius Neagu
- Faculty of Medicine and Pharmacy, Dunarea de Jos University of Galati, 35 AI Cuza St., 800010 Galati, Romania; (D.G.P.); (M.N.); (D.T.); (A.N.); (I.F.)
- Saint Apostle Andrew Emergency County Clinical Hospital, 177 Brailei St., 800578 Galati, Romania
| | - Dana Tutunaru
- Faculty of Medicine and Pharmacy, Dunarea de Jos University of Galati, 35 AI Cuza St., 800010 Galati, Romania; (D.G.P.); (M.N.); (D.T.); (A.N.); (I.F.)
- Saint Apostle Andrew Emergency County Clinical Hospital, 177 Brailei St., 800578 Galati, Romania
| | - Aurel Nechita
- Faculty of Medicine and Pharmacy, Dunarea de Jos University of Galati, 35 AI Cuza St., 800010 Galati, Romania; (D.G.P.); (M.N.); (D.T.); (A.N.); (I.F.)
- Saint John Clinical Emergency Hospital for Children, 800487 Galati, Romania
| | - Iuliu Fulga
- Faculty of Medicine and Pharmacy, Dunarea de Jos University of Galati, 35 AI Cuza St., 800010 Galati, Romania; (D.G.P.); (M.N.); (D.T.); (A.N.); (I.F.)
- Saint Apostle Andrew Emergency County Clinical Hospital, 177 Brailei St., 800578 Galati, Romania
| |
Collapse
|
6
|
Browning L, Jesus C, Malacrino S, Guan Y, White K, Puddle A, Alham NK, Haghighat M, Colling R, Birks J, Rittscher J, Verrill C. Artificial Intelligence-Based Quality Assessment of Histopathology Whole-Slide Images within a Clinical Workflow: Assessment of 'PathProfiler' in a Diagnostic Pathology Setting. Diagnostics (Basel) 2024; 14:990. [PMID: 38786288 PMCID: PMC11120465 DOI: 10.3390/diagnostics14100990] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2024] [Revised: 04/17/2024] [Accepted: 04/28/2024] [Indexed: 05/25/2024] Open
Abstract
Digital pathology continues to gain momentum, with the promise of artificial intelligence to aid diagnosis and for assessment of features which may impact prognosis and clinical management. Successful adoption of these technologies depends upon the quality of digitised whole-slide images (WSI); however, current quality control largely depends upon manual assessment, which is inefficient and subjective. We previously developed PathProfiler, an automated image quality assessment tool, and in this feasibility study we investigate its potential for incorporation into a diagnostic clinical pathology setting in real-time. A total of 1254 genitourinary WSI were analysed by PathProfiler. PathProfiler was developed and trained on prostate tissue and, of the prostate biopsy WSI, representing 46% of the WSI analysed, 4.5% were flagged as potentially being of suboptimal quality for diagnosis. All had concordant subjective issues, mainly focus-related, 54% severe enough to warrant remedial action which resulted in improved image quality. PathProfiler was less reliable in assessment of non-prostate surgical resection-type cases, on which it had not been trained. PathProfiler shows potential for incorporation into a digitised clinical pathology workflow, with opportunity for image quality improvement. Whilst its reliability in the current form appears greatest for assessment of prostate specimens, other specimen types, particularly biopsies, also showed benefit.
Collapse
Affiliation(s)
- Lisa Browning
- Department of Cellular Pathology, John Radcliffe Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
| | - Christine Jesus
- Department of Cellular Pathology, John Radcliffe Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
| | - Stefano Malacrino
- Nuffield Department of Surgical Sciences, University of Oxford, Oxford OX3 9DU, UK
| | - Yue Guan
- Department of Cellular Pathology, Royal Berkshire Hospital, Royal Berkshire NHS Foundation Trust, Reading RG1 5AN, UK
| | - Kieron White
- Department of Cellular Pathology, John Radcliffe Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
| | - Alison Puddle
- Department of Cellular Pathology, John Radcliffe Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
| | | | - Maryam Haghighat
- School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, QLD 4000, Australia
| | - Richard Colling
- Department of Cellular Pathology, John Radcliffe Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
- Nuffield Department of Surgical Sciences, University of Oxford, Oxford OX3 9DU, UK
| | - Jacqueline Birks
- Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford OX3 7LD, UK
| | - Jens Rittscher
- Department of Engineering Science, University of Oxford, Oxford OX1 3PJ, UK
- NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
| | - Clare Verrill
- Department of Cellular Pathology, John Radcliffe Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
- Nuffield Department of Surgical Sciences, University of Oxford, Oxford OX3 9DU, UK
- NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
| |
Collapse
|
7
|
Feng X, Shu W, Li M, Li J, Xu J, He M. Pathogenomics for accurate diagnosis, treatment, prognosis of oncology: a cutting edge overview. J Transl Med 2024; 22:131. [PMID: 38310237 PMCID: PMC10837897 DOI: 10.1186/s12967-024-04915-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Accepted: 01/20/2024] [Indexed: 02/05/2024] Open
Abstract
The capability to gather heterogeneous data, alongside the increasing power of artificial intelligence to examine it, leading a revolution in harnessing multimodal data in the life sciences. However, most approaches are limited to unimodal data, leaving integrated approaches across modalities relatively underdeveloped in computational pathology. Pathogenomics, as an invasive method to integrate advanced molecular diagnostics from genomic data, morphological information from histopathological imaging, and codified clinical data enable the discovery of new multimodal cancer biomarkers to propel the field of precision oncology in the coming decade. In this perspective, we offer our opinions on synthesizing complementary modalities of data with emerging multimodal artificial intelligence methods in pathogenomics. It includes correlation between the pathological and genomic profile of cancer, fusion of histology, and genomics profile of cancer. We also present challenges, opportunities, and avenues for future work.
Collapse
Affiliation(s)
- Xiaobing Feng
- College of Electrical and Information Engineering, Hunan University, Changsha, China
- Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Wen Shu
- College of Electrical and Information Engineering, Hunan University, Changsha, China
- Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Mingya Li
- College of Electrical and Information Engineering, Hunan University, Changsha, China
- Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Junyu Li
- College of Electrical and Information Engineering, Hunan University, Changsha, China
- Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Junyao Xu
- Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China
| | - Min He
- College of Electrical and Information Engineering, Hunan University, Changsha, China.
- Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, 310022, Zhejiang, China.
| |
Collapse
|
8
|
L'Imperio V, Casati G, Cazzaniga G, Tarabini A, Bolognesi MM, Gibilisco F, Fraggetta F, Pagni F. Improvements in digital pathology equipment for renal biopsies: updating the standard model. J Nephrol 2024; 37:221-229. [PMID: 36786977 DOI: 10.1007/s40620-023-01568-1] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2022] [Accepted: 01/01/2023] [Indexed: 02/15/2023]
Abstract
INTRODUCTION Digital pathology can improve the technical and interpretative workflows in nephropathology by creating hub-spoke networks and virtuous collaboration projects among centers in different geographical regions. New high-resolution fast-scanning instruments combined with currently existing equipment were tested in a nephropathology hub to evaluate possible upgrading in the routine processing phases. METHODS The scanning performance of two different instruments (Aperio vs hybrid MIDI II) was evaluated and a comparative quality control check was performed on obtained whole slide images. RESULTS Both with default and custom settings for light microscopy, MIDI II proved to be faster, with only slightly more time required to prepare the scan and larger final file size as compared to Aperio (p < 0.001). No differences were noted in the number of out-of-focus slides per case (p = 0.75). Regarding immunofluorescence, the new scanner required longer preparation time (p = 0.001) with comparable scanning times and final file size (p = 0.169 and p = 0.177, respectively). Quality control showed differences in 3 quality features related to white background and blurriness (p < 0.001). No major discordances in the final diagnosis were recorded after comparing the report obtained with slides scanned using the two instruments, with only one case (4%) showing minor disagreement. CONCLUSION The present report describes the experience of a hub nephropathology center adopting next generation digital pathology tools for the routine assessment of renal biopsies, highlighting the need for a complementary approach towards a philosophy of interoperability.
Collapse
Affiliation(s)
- Vincenzo L'Imperio
- Department of Medicine and Surgery, Pathology, University of Milano-Bicocca, IRCCS Fondazione San Gerardo dei Tintori, Monza, Italy
| | - Gabriele Casati
- Department of Medicine and Surgery, Pathology, University of Milano-Bicocca, IRCCS Fondazione San Gerardo dei Tintori, Monza, Italy
| | - Giorgio Cazzaniga
- Department of Medicine and Surgery, Pathology, University of Milano-Bicocca, IRCCS Fondazione San Gerardo dei Tintori, Monza, Italy
| | - Andrea Tarabini
- Department of Medicine and Surgery, Pathology, University of Milano-Bicocca, IRCCS Fondazione San Gerardo dei Tintori, Monza, Italy
| | - Maddalena Maria Bolognesi
- Department of Medicine and Surgery, Pathology, University of Milano-Bicocca, IRCCS Fondazione San Gerardo dei Tintori, Monza, Italy
| | - Fabio Gibilisco
- Pathology Unit, ASP Catania, "Gravina" Hospital, Caltagirone, Italy
| | | | - Fabio Pagni
- Department of Medicine and Surgery, Pathology, University of Milano-Bicocca, IRCCS Fondazione San Gerardo dei Tintori, Monza, Italy.
| |
Collapse
|
9
|
Farris AB, Alexander MP, Balis UGJ, Barisoni L, Boor P, Bülow RD, Cornell LD, Demetris AJ, Farkash E, Hermsen M, Hogan J, Kain R, Kers J, Kong J, Levenson RM, Loupy A, Naesens M, Sarder P, Tomaszewski JE, van der Laak J, van Midden D, Yagi Y, Solez K. Banff Digital Pathology Working Group: Image Bank, Artificial Intelligence Algorithm, and Challenge Trial Developments. Transpl Int 2023; 36:11783. [PMID: 37908675 PMCID: PMC10614670 DOI: 10.3389/ti.2023.11783] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2023] [Accepted: 09/22/2023] [Indexed: 11/02/2023]
Abstract
The Banff Digital Pathology Working Group (DPWG) was established with the goal to establish a digital pathology repository; develop, validate, and share models for image analysis; and foster collaborations using regular videoconferencing. During the calls, a variety of artificial intelligence (AI)-based support systems for transplantation pathology were presented. Potential collaborations in a competition/trial on AI applied to kidney transplant specimens, including the DIAGGRAFT challenge (staining of biopsies at multiple institutions, pathologists' visual assessment, and development and validation of new and pre-existing Banff scoring algorithms), were also discussed. To determine the next steps, a survey was conducted, primarily focusing on the feasibility of establishing a digital pathology repository and identifying potential hosts. Sixteen of the 35 respondents (46%) had access to a server hosting a digital pathology repository, with 2 respondents that could serve as a potential host at no cost to the DPWG. The 16 digital pathology repositories collected specimens from various organs, with the largest constituent being kidney (n = 12,870 specimens). A DPWG pilot digital pathology repository was established, and there are plans for a competition/trial with the DIAGGRAFT project. Utilizing existing resources and previously established models, the Banff DPWG is establishing new resources for the Banff community.
Collapse
Affiliation(s)
- Alton B. Farris
- Department of Pathology and Laboratory Medicine, Emory University, Atlanta, GE, United States
| | - Mariam P. Alexander
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, United States
| | - Ulysses G. J. Balis
- Department of Pathology, University of Michigan, Ann Arbor, MI, United States
| | - Laura Barisoni
- Department of Pathology and Medicine, Duke University, Durham, NC, United States
| | - Peter Boor
- Institute of Pathology, Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen University Clinic, Aachen, Germany
- Department of Nephrology and Immunology, RWTH Aachen University Clinic, Aachen, Germany
| | - Roman D. Bülow
- Institute of Pathology, Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen University Clinic, Aachen, Germany
| | - Lynn D. Cornell
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, United States
| | - Anthony J. Demetris
- Department of Pathology, University of Pittsburgh, Pittsburgh, PA, United States
| | - Evan Farkash
- Department of Pathology, University of Michigan, Ann Arbor, MI, United States
| | - Meyke Hermsen
- Department of Pathology, Radboud University Medical Center, Nijmegen, Netherlands
| | - Julien Hogan
- Department of Pathology and Laboratory Medicine, Emory University, Atlanta, GE, United States
- Nephrology Service, Robert Debré Hospital, University of Paris, Paris, France
| | - Renate Kain
- Department of Pathology, Medical University of Vienna, Vienna, Austria
| | - Jesper Kers
- Department of Pathology, Amsterdam University Medical Centers, Amsterdam, Netherlands
- Department of Pathology, Leiden University Medical Center, Leiden, Netherlands
| | - Jun Kong
- Georgia State University, Atlanta, GA, United States
- Emory University, Atlanta, GA, United States
| | - Richard M. Levenson
- Department of Pathology, University of California Davis Health System, Sacramento, CA, United States
| | - Alexandre Loupy
- Institut National de la Santé et de la Recherche Médicale, UMR 970, Paris Translational Research Centre for Organ Transplantation, and Kidney Transplant Department, Hôpital Necker, Assistance Publique-Hôpitaux de Paris, University of Paris, Paris, France
| | - Maarten Naesens
- Department of Microbiology, Immunology and Transplantation, KU Leuven, Leuven, Belgium
| | - Pinaki Sarder
- Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, Intelligent Critical Care Center, College of Medicine, University of Florida at Gainesville, Gainesville, FL, United States
| | - John E. Tomaszewski
- Department of Pathology, The State University of New York at Buffalo, Buffalo, NY, United States
| | - Jeroen van der Laak
- Department of Pathology, Radboud University Medical Center, Nijmegen, Netherlands
- Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden
| | - Dominique van Midden
- Department of Pathology, Radboud University Medical Center, Nijmegen, Netherlands
| | - Yukako Yagi
- Memorial Sloan Kettering Cancer Center, New York, NY, United States
| | - Kim Solez
- Department of Pathology, University of Alberta, Edmonton, AB, Canada
| |
Collapse
|
10
|
Broecker V, Brännström M, Bösmüller H, Sticová E, Malušková J, Chiesa-Vottero A, Mölne J. Reproducibility of Rejection Grading in Uterus Transplantation: A Multicenter Study. Transplant Direct 2023; 9:e1535. [PMID: 37745947 PMCID: PMC10513355 DOI: 10.1097/txd.0000000000001535] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Revised: 07/27/2023] [Accepted: 08/09/2023] [Indexed: 09/26/2023] Open
Abstract
Background Diagnosis of rejection after uterus transplantation is based on histopathological examination of ectocervical biopsies. Inflammation at the stromal-epithelial interface is the backbone of the histopathological classification proposed by our group in 2017. However, the reproducibility of this grading scheme has not been tested, and it is unclear whether it covers the full morphological spectrum of rejection. Methods We present a multicenter study in which 5 pathologists from 4 uterus transplantation centers performed 2 rounds of grading on 145 and 48 cervical biopsies, respectively. Three of the centers provided biopsies. Additionally, the presence of perivascular stromal inflammation was recorded. During discussions after the first round, further histological lesions (venous endothelial inflammation and apoptosis) were identified for closer evaluation and added to the panel of lesions to score in the second round. All participants completed a questionnaire to explore current practices in handling and reporting uterus transplant biopsies. Results Cervical biopsies were commonly performed in all centers to monitor rejection. Intraobserver reproducibility of rejection grading (performed by 1 rater) was excellent, whereas interobserver reproducibility was moderate and did not improve in the second round. Reproducibility of perivascular stromal inflammation was moderate but unsatisfactory for venous endothelial inflammation and apoptosis. All lesions were more frequent in, but not restricted to, biopsies with rejection patterns. Conclusions Grading of rejection in cervical biopsies is reproducible and applicable to biopsies from different centers. Diagnosis of rejection may be improved by adding further histological lesions to the grading system; however, lesions require rigorous consensus definition.
Collapse
Affiliation(s)
- Verena Broecker
- Department of Clinical Pathology, Sahlgrenska University Hospital, Region Västra Götaland, Gothenburg, Sweden
- Department of Obstetrics and Gynecology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Mats Brännström
- Department of Obstetrics and Gynecology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Hans Bösmüller
- Institute of Pathology and Neuropathology, University Hospital Tübingen, Tübingen, Germany
| | - Eva Sticová
- Clinical and Transplant Pathology Department, Institute for Clinical and Experimental Medicine (IKEM), Prague, Czech Republic
| | - Jana Malušková
- Clinical and Transplant Pathology Department, Institute for Clinical and Experimental Medicine (IKEM), Prague, Czech Republic
| | | | - Johan Mölne
- Department of Clinical Pathology, Sahlgrenska University Hospital, Region Västra Götaland, Gothenburg, Sweden
- Department of Laboratory Medicine, Institute of Biomedicine, Sahlgrenska Academy, University of Gothenburg, Sweden
| |
Collapse
|
11
|
Liu Y, Han D, Parwani AV, Li Z. Applications of Artificial Intelligence in Breast Pathology. Arch Pathol Lab Med 2023; 147:1003-1013. [PMID: 36800539 DOI: 10.5858/arpa.2022-0457-ra] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/15/2022] [Indexed: 02/19/2023]
Abstract
CONTEXT.— Increasing implementation of whole slide imaging together with digital workflow and advances in computing capacity enable the use of artificial intelligence (AI) in pathology, including breast pathology. Breast pathologists often face a significant workload, with diagnosis complexity, tedious repetitive tasks, and semiquantitative evaluation of biomarkers. Recent advances in developing AI algorithms have provided promising approaches to meet the demand in breast pathology. OBJECTIVE.— To provide an updated review of AI in breast pathology. We examined the success and challenges of current and potential AI applications in diagnosing and grading breast carcinomas and other pathologic changes, detecting lymph node metastasis, quantifying breast cancer biomarkers, predicting prognosis and therapy response, and predicting potential molecular changes. DATA SOURCES.— We obtained data and information by searching and reviewing literature on AI in breast pathology from PubMed and based our own experience. CONCLUSIONS.— With the increasing application in breast pathology, AI not only assists in pathology diagnosis to improve accuracy and reduce pathologists' workload, but also provides new information in predicting prognosis and therapy response.
Collapse
Affiliation(s)
- Yueping Liu
- From the Department of Pathology, The Fourth Hospital of Hebei Medical University, Shijiazhuang, China (Liu, Han)
| | - Dandan Han
- From the Department of Pathology, The Fourth Hospital of Hebei Medical University, Shijiazhuang, China (Liu, Han)
| | - Anil V Parwani
- The Department of Pathology, The Ohio State University, Columbus (Parwani, Li)
| | - Zaibo Li
- From the Department of Pathology, The Fourth Hospital of Hebei Medical University, Shijiazhuang, China (Liu, Han)
| |
Collapse
|
12
|
Jurgas A, Wodzinski M, Celniak W, Atzori M, Muller H. Artifact Augmentation for Learning-based Quality Control of Whole Slide Images. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023; 2023:1-4. [PMID: 38082977 DOI: 10.1109/embc40787.2023.10340997] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/18/2023]
Abstract
The acquisition of whole slide images is prone to artifacts that can require human control and re-scanning, both in clinical workflows and in research-oriented settings. Quality control algorithms are a first step to overcome this challenge, as they limit the use of low quality images. Developing quality control systems in histopathology is not straightforward, also due to the limited availability of data related to this topic. We address the problem by proposing a tool to augment data with artifacts. The proposed method seamlessly generates and blends artifacts from an external library to a given histopathology dataset. The datasets augmented by the blended artifacts are then used to train an artifact detection network in a supervised way. We use the YOLOv5 model for the artifact detection with a slightly modified training pipeline. The proposed tool can be extended into a complete framework for the quality assessment of whole slide images.Clinical relevance- The proposed method may be useful for the initial quality screening of whole slide images. Each year, millions of whole slide images are acquired and digitized worldwide. Numerous of them contain artifacts affecting the following AI-oriented analysis. Therefore, a tool operating at the acquisition phase and improving the initial quality assessment is crucial to increase the performance of digital pathology algorithms, e.g., early cancer diagnosis.
Collapse
|
13
|
Lucarelli N, Yun D, Han D, Ginley B, Moon KC, Rosenberg AZ, Tomaszewski JE, Zee J, Jen KY, Han SS, Sarder P. Discovery of Novel Digital Biomarkers for Type 2 Diabetic Nephropathy Classification via Integration of Urinary Proteomics and Pathology. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.04.28.23289272. [PMID: 37205413 PMCID: PMC10187347 DOI: 10.1101/2023.04.28.23289272] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/21/2023]
Abstract
Background The heterogeneous phenotype of diabetic nephropathy (DN) from type 2 diabetes complicates appropriate treatment approaches and outcome prediction. Kidney histology helps diagnose DN and predict its outcomes, and an artificial intelligence (AI)-based approach will maximize clinical utility of histopathological evaluation. Herein, we addressed whether AI-based integration of urine proteomics and image features improves DN classification and its outcome prediction, altogether augmenting and advancing pathology practice. Methods We studied whole slide images (WSIs) of periodic acid-Schiff-stained kidney biopsies from 56 DN patients with associated urinary proteomics data. We identified urinary proteins differentially expressed in patients who developed end-stage kidney disease (ESKD) within two years of biopsy. Extending our previously published human-AI-loop pipeline, six renal sub-compartments were computationally segmented from each WSI. Hand-engineered image features for glomeruli and tubules, and urinary protein measurements, were used as inputs to deep-learning frameworks to predict ESKD outcome. Differential expression was correlated with digital image features using the Spearman rank sum coefficient. Results A total of 45 urinary proteins were differentially detected in progressors, which was most predictive of ESKD (AUC=0.95), while tubular and glomerular features were less predictive (AUC=0.71 and AUC=0.63, respectively). Accordingly, a correlation map between canonical cell-type proteins, such as epidermal growth factor and secreted phosphoprotein 1, and AI-based image features was obtained, which supports previous pathobiological results. Conclusions Computational method-based integration of urinary and image biomarkers may improve the pathophysiological understanding of DN progression as well as carry clinical implications in histopathological evaluation.
Collapse
Affiliation(s)
- Nicholas Lucarelli
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA
| | - Donghwan Yun
- Department of Biomedical Sciences, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Dohyun Han
- Proteomics Core Facility, Biomedical Research Institute, Seoul National University Hospital, Seoul, Republic of Korea
| | - Brandon Ginley
- The Janssen Pharmaceutical Companies of Johnson & Johnson, Raritan NJ, USA
| | - Kyung Chul Moon
- Department of Pathology, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Avi Z. Rosenberg
- Department of Pathology, Johns Hopkins University, Baltimore, MD, USA
| | - John E. Tomaszewski
- Department of Pathology and Anatomical Sciences, University at Buffalo – The State University of New York
| | - Jarcy Zee
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania and Children’s Hospital of Philadelphia, PA, USA
| | - Kuang-Yu Jen
- Department of Pathology and Laboratory Medicine, University of California, Davis Medical Center, CA, USA
| | - Seung Seok Han
- Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Pinaki Sarder
- Department of Medicine-Quantitative Health, University of Florida College of Medicine, Gainesville, FL, USA
- Department of Electrical and Computer Engineering, University of Florida College of Engineering, Gainesville, FL, USA
| |
Collapse
|
14
|
Chen Y, Zee J, Janowczyk AR, Rubin J, Toro P, Lafata KJ, Mariani LH, Holzman LB, Hodgin JB, Madabhushi A, Barisoni L. Clinical Relevance of Computationally Derived Attributes of Peritubular Capillaries from Kidney Biopsies. KIDNEY360 2023; 4:648-658. [PMID: 37016482 PMCID: PMC10278770 DOI: 10.34067/kid.0000000000000116] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/14/2022] [Accepted: 02/13/2023] [Indexed: 04/06/2023]
Abstract
Key Points Computational image analysis allows for the extraction of new information from whole-slide images with potential clinical relevance. Peritubular capillary (PTC) density is decreased in areas of interstitial fibrosis and tubular atrophy when measured in interstitial fractional space. PTC shape (aspect ratio) is associated with clinical outcome in glomerular diseases. Background The association between peritubular capillary (PTC) density and disease progression has been studied in a variety of kidney diseases using immunohistochemistry. However, other PTC attributes, such as PTC shape, have not been explored yet. The recent development of computer vision techniques provides the opportunity for the quantification of PTC attributes using conventional stains and whole-slide images. Methods To explore the relationship between PTC characteristics and clinical outcome, n =280 periodic acid–Schiff-stained kidney biopsies (88 minimal change disease, 109 focal segmental glomerulosclerosis, 46 membranous nephropathy, and 37 IgA nephropathy) from the Nephrotic Syndrome Study Network digital pathology repository were computationally analyzed. A previously validated deep learning model was applied to segment cortical PTCs. Average PTC aspect ratio (PTC major to minor axis ratio), size (PTC pixels per PTC segmentation), and density (PTC pixels per unit cortical area) were computed for each biopsy. Cox proportional hazards models were used to assess associations between these PTC parameters and outcome (40% eGFR decline or kidney failure). Cortical PTC characteristics and interstitial fractional space PTC density were compared between areas of interstitial fibrosis and tubular atrophy (IFTA) and areas without IFTA. Results When normalized PTC aspect ratio was below 0.6, a 0.1, increase in normalized PTC aspect ratio was significantly associated with disease progression, with a hazard ratio (95% confidence interval) of 1.28 (1.04 to 1.59) (P = 0.019), while PTC density and size were not significantly associated with outcome. Interstitial fractional space PTC density was lower in areas of IFTA compared with non-IFTA areas. Conclusions Computational image analysis enables quantification of the status of the kidney microvasculature and the discovery of a previously unrecognized PTC biomarker (aspect ratio) of clinical outcome.
Collapse
Affiliation(s)
- Yijiang Chen
- Center for Computational Imaging and Personalized Diagnostics, Case Western Reserve University, Cleveland, Ohio
| | - Jarcy Zee
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania
- Children's Hospital of Philadelphia, Philadelphia, Pennsylvania
| | - Andrew R. Janowczyk
- Geneva University Hospitals, Pathology and Oncology Departments, Geneva, Switzerland
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia
| | - Jeremy Rubin
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Paula Toro
- Department of Pathology, Cleveland Clinic, Cleveland, Ohio
| | - Kyle J. Lafata
- Department of Radiology, Duke University, Durham, North Carolina
- Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina
- Department of Radiation Oncology, Duke University, Durham, North Carolina
| | - Laura H. Mariani
- Department of Internal Medicine, Division of Nephrology, University of Michigan, Ann Arbor, Michigan
| | - Lawrence B. Holzman
- Department of Medicine, Renal-Electrolyte and Hypertension Division, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Jeffrey B. Hodgin
- Department of Pathology, University of Michigan, Ann Arbor, Michigan
| | - Anant Madabhushi
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia
- Atlanta Veterans Affairs Medical Center, Atlanta, Georgia
| | - Laura Barisoni
- Department of Pathology, Division of AI and Computational Pathology, Duke University, Durham, North Carolina
- Department of Medicine, Division of Nephrology, Duke University, Durham, North Carolina
| |
Collapse
|
15
|
Blocker SJ, Morrison S, Everitt JI, Cook J, Luo S, Watts TL, Mowery YM. Whole-Slide Cytometric Feature Mapping for Distinguishing Tumor Genomic Subtypes in Head and Neck Squamous Cell Carcinoma Whole-Slide Images. THE AMERICAN JOURNAL OF PATHOLOGY 2023; 193:182-190. [PMID: 36414086 PMCID: PMC9885294 DOI: 10.1016/j.ajpath.2022.11.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Revised: 10/24/2022] [Accepted: 11/03/2022] [Indexed: 11/21/2022]
Abstract
Head and neck squamous cell carcinoma (HNSCC) is a heterogeneous disease where, in advanced stages, clinical and pathologic stages do not correlate with outcome. Molecular and genomic biomarkers for HNSCC classification have shown promise for prognostic and therapeutic applications. This study utilized automated image analysis techniques in whole-slide images of HNSCC tumors to identify relationships between cytometric features and genomic phenotypes. Hematoxylin and eosin-stained slides of HNSCC tumors (N = 49) were obtained from The Cancer Imaging Archive, along with accompanying clinical, pathologic, genomic, and proteomic reports. Automated nuclear detection was performed across the entirety of slides, and cytometric feature maps were generated. Forty-one cytometric features were evaluated for associations with tumor grade, tumor stage, tumor subsite, and integrated genomic subtype. Thirty-two features demonstrated significant association with integrated genomic subtype when corrected for multiple comparisons. In particular, the basal subtype was visually distinguishable from the chromosomal instability and immune subtypes based on cytometric feature measurements. No features were significantly associated with tumor grade, stage, or subsite. This study provides preliminary evidence that features derived from tissue pathology slides could provide insights into genomic phenotypes of HNSCC.
Collapse
Affiliation(s)
- Stephanie J Blocker
- Center for In Vivo Microscopy, Department of Radiology, Duke University School of Medicine, Durham, North Carolina.
| | - Samantha Morrison
- Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, North Carolina
| | - Jeffrey I Everitt
- Department of Pathology, Duke University School of Medicine, Durham, North Carolina
| | - James Cook
- Center for In Vivo Microscopy, Department of Radiology, Duke University School of Medicine, Durham, North Carolina
| | - Sheng Luo
- Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, North Carolina
| | - Tammara L Watts
- Department of Head and Neck Surgery and Communication Sciences, Duke University School of Medicine, Durham, North Carolina
| | - Yvonne M Mowery
- Department of Head and Neck Surgery and Communication Sciences, Duke University School of Medicine, Durham, North Carolina; Department of Radiation Oncology, Duke University School of Medicine, Durham, North Carolina
| |
Collapse
|
16
|
Patil A, Diwakar H, Sawant J, Kurian NC, Yadav S, Rane S, Bameta T, Sethi A. Efficient quality control of whole slide pathology images with human-in-the-loop training. J Pathol Inform 2023; 14:100306. [PMID: 37089617 PMCID: PMC10113897 DOI: 10.1016/j.jpi.2023.100306] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2023] [Revised: 03/11/2023] [Accepted: 03/13/2023] [Indexed: 04/25/2023] Open
Abstract
Histopathology whole slide images (WSIs) are being widely used to develop deep learning-based diagnostic solutions, especially for precision oncology. Most of these diagnostic softwares are vulnerable to biases and impurities in the training and test data which can lead to inaccurate diagnoses. For instance, WSIs contain multiple types of tissue regions, at least some of which might not be relevant to the diagnosis. We introduce HistoROI, a robust yet lightweight deep learning-based classifier to segregate WSI into 6 broad tissue regions-epithelium, stroma, lymphocytes, adipose, artifacts, and miscellaneous. HistoROI is trained using a novel human in-the-loop and active learning paradigm that ensures variations in training data for labeling efficient generalization. HistoROI consistently performs well across multiple organs, despite being trained on only a single dataset, demonstrating strong generalization. Further, we have examined the utility of HistoROI in improving the performance of downstream deep learning-based tasks using the CAMELYON breast cancer lymph node and TCGA lung cancer datasets. For the former dataset, the area under the receiver operating characteristic curve (AUC) for metastasis versus normal tissue of a neural network trained using weakly supervised learning increased from 0.88 to 0.92 by filtering the data using HistoROI. Similarly, the AUC increased from 0.88 to 0.93 for the classification between adenocarcinoma and squamous cell carcinoma on the lung cancer dataset. We also found that the performance of the HistoROI improves upon HistoQC for artifact detection on a test dataset of 93 annotated WSIs. The limitations of the proposed model are analyzed, and potential extensions are also discussed.
Collapse
Affiliation(s)
| | - Harsh Diwakar
- Indian Institute of Technology, Bombay, Mumbai, India
| | - Jay Sawant
- Indian Institute of Technology, Bombay, Mumbai, India
| | | | - Subhash Yadav
- Tata Memorial Centre - ACTREC, HBNI, Navi Mumbai, India
| | - Swapnil Rane
- Tata Memorial Centre - ACTREC, HBNI, Navi Mumbai, India
| | - Tripti Bameta
- Tata Memorial Centre - ACTREC, HBNI, Navi Mumbai, India
| | - Amit Sethi
- Indian Institute of Technology, Bombay, Mumbai, India
| |
Collapse
|
17
|
dos-Santos WLC, de Freitas LAR, Duarte AA, Angelo MF, Oliveira LR. Computational pathology, new horizons and challenges for anatomical pathology. SURGICAL AND EXPERIMENTAL PATHOLOGY 2022. [DOI: 10.1186/s42047-022-00113-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022] Open
Abstract
AbstractThe emergence of digital pathology environments and the application of computer vision to the analysis of histological sections has given rise to a new area of Anatomical Pathology, termed Computational Pathology. Advances in Computational Pathology may substantially change the routine of Anatomical Pathology laboratories and the work profile of the pathologist.
Collapse
|
18
|
Homeyer A, Geißler C, Schwen LO, Zakrzewski F, Evans T, Strohmenger K, Westphal M, Bülow RD, Kargl M, Karjauv A, Munné-Bertran I, Retzlaff CO, Romero-López A, Sołtysiński T, Plass M, Carvalho R, Steinbach P, Lan YC, Bouteldja N, Haber D, Rojas-Carulla M, Vafaei Sadr A, Kraft M, Krüger D, Fick R, Lang T, Boor P, Müller H, Hufnagl P, Zerbe N. Recommendations on compiling test datasets for evaluating artificial intelligence solutions in pathology. Mod Pathol 2022; 35:1759-1769. [PMID: 36088478 PMCID: PMC9708586 DOI: 10.1038/s41379-022-01147-y] [Citation(s) in RCA: 24] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2022] [Revised: 07/24/2022] [Accepted: 07/25/2022] [Indexed: 12/24/2022]
Abstract
Artificial intelligence (AI) solutions that automatically extract information from digital histology images have shown great promise for improving pathological diagnosis. Prior to routine use, it is important to evaluate their predictive performance and obtain regulatory approval. This assessment requires appropriate test datasets. However, compiling such datasets is challenging and specific recommendations are missing. A committee of various stakeholders, including commercial AI developers, pathologists, and researchers, discussed key aspects and conducted extensive literature reviews on test datasets in pathology. Here, we summarize the results and derive general recommendations on compiling test datasets. We address several questions: Which and how many images are needed? How to deal with low-prevalence subsets? How can potential bias be detected? How should datasets be reported? What are the regulatory requirements in different countries? The recommendations are intended to help AI developers demonstrate the utility of their products and to help pathologists and regulatory agencies verify reported performance measures. Further research is needed to formulate criteria for sufficiently representative test datasets so that AI solutions can operate with less user intervention and better support diagnostic workflows in the future.
Collapse
Affiliation(s)
- André Homeyer
- Fraunhofer Institute for Digital Medicine MEVIS, Max-von-Laue-Straße 2, 28359, Bremen, Germany.
| | - Christian Geißler
- Technische Universität Berlin, DAI-Labor, Ernst-Reuter-Platz 7, 10587, Berlin, Germany
| | - Lars Ole Schwen
- Fraunhofer Institute for Digital Medicine MEVIS, Max-von-Laue-Straße 2, 28359, Bremen, Germany
| | - Falk Zakrzewski
- Institute of Pathology, Carl Gustav Carus University Hospital Dresden (UKD), TU Dresden (TUD), Fetscherstrasse 74, 01307, Dresden, Germany
| | - Theodore Evans
- Technische Universität Berlin, DAI-Labor, Ernst-Reuter-Platz 7, 10587, Berlin, Germany
| | - Klaus Strohmenger
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Institute of Pathology, Charitéplatz 1, 10117, Berlin, Germany
| | - Max Westphal
- Fraunhofer Institute for Digital Medicine MEVIS, Max-von-Laue-Straße 2, 28359, Bremen, Germany
| | - Roman David Bülow
- Institute of Pathology, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany
| | - Michaela Kargl
- Medical University of Graz, Diagnostic and Research Center for Molecular BioMedicine, Diagnostic & Research Institute of Pathology, Neue Stiftingtalstrasse 6, 8010, Graz, Austria
| | - Aray Karjauv
- Technische Universität Berlin, DAI-Labor, Ernst-Reuter-Platz 7, 10587, Berlin, Germany
| | - Isidre Munné-Bertran
- MoticEurope, S.L.U., C. Les Corts, 12 Poligono Industrial, 08349, Barcelona, Spain
| | - Carl Orge Retzlaff
- Technische Universität Berlin, DAI-Labor, Ernst-Reuter-Platz 7, 10587, Berlin, Germany
| | | | | | - Markus Plass
- Medical University of Graz, Diagnostic and Research Center for Molecular BioMedicine, Diagnostic & Research Institute of Pathology, Neue Stiftingtalstrasse 6, 8010, Graz, Austria
| | - Rita Carvalho
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Institute of Pathology, Charitéplatz 1, 10117, Berlin, Germany
| | - Peter Steinbach
- Helmholtz-Zentrum Dresden Rossendorf, Bautzner Landstraße 400, 01328, Dresden, Germany
| | - Yu-Chia Lan
- Institute of Pathology, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany
| | - Nassim Bouteldja
- Institute of Pathology, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany
| | - David Haber
- Lakera AI AG, Zelgstrasse 7, 8003, Zürich, Switzerland
| | | | - Alireza Vafaei Sadr
- Institute of Pathology, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany
| | | | - Daniel Krüger
- Olympus Soft Imaging Solutions GmbH, Johann-Krane-Weg 39, 48149, Münster, Germany
| | - Rutger Fick
- Tribun Health, 2 Rue du Capitaine Scott, 75015, Paris, France
| | - Tobias Lang
- Mindpeak GmbH, Zirkusweg 2, 20359, Hamburg, Germany
| | - Peter Boor
- Institute of Pathology, University Hospital RWTH Aachen, Pauwelsstraße 30, 52074, Aachen, Germany
| | - Heimo Müller
- Medical University of Graz, Diagnostic and Research Center for Molecular BioMedicine, Diagnostic & Research Institute of Pathology, Neue Stiftingtalstrasse 6, 8010, Graz, Austria
| | - Peter Hufnagl
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Institute of Pathology, Charitéplatz 1, 10117, Berlin, Germany
| | - Norman Zerbe
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Institute of Pathology, Charitéplatz 1, 10117, Berlin, Germany
| |
Collapse
|
19
|
Marciel MP, Haldar B, Hwang J, Bhalerao N, Bellis SL. Role of tumor cell sialylation in pancreatic cancer progression. Adv Cancer Res 2022; 157:123-155. [PMID: 36725107 PMCID: PMC11342334 DOI: 10.1016/bs.acr.2022.07.003] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest malignancies and is currently the third leading cause of cancer death. The aggressiveness of PDAC stems from late diagnosis, early metastasis, and poor efficacy of current chemotherapies. Thus, there is an urgent need for effective biomarkers for early detection of PDAC and development of new therapeutic strategies. It has long been known that cellular glycosylation is dysregulated in pancreatic cancer cells, however, tumor-associated glycans and their cognate glycosylating enzymes have received insufficient attention as potential clinical targets. Aberrant glycosylation affects a broad range of pathways that underpin tumor initiation, metastatic progression, and resistance to cancer treatment. One of the prevalent alterations in the cancer glycome is an enrichment in a select group of sialylated glycans including sialylated, branched N-glycans, sialyl Lewis antigens, and sialylated forms of truncated O-glycans such as the sialyl Tn antigen. These modifications affect the activity of numerous cell surface receptors, which collectively impart malignant characteristics typified by enhanced cell proliferation, migration, invasion and apoptosis-resistance. Additionally, sialic acids on tumor cells engage inhibitory Siglec receptors on immune cells to dampen anti-tumor immunity, further promoting cancer progression. The goal of this review is to summarize the predominant changes in sialylation occurring in pancreatic cancer, the biological functions of sialylated glycoproteins in cancer pathogenesis, and the emerging strategies for targeting sialoglycans and Siglec receptors in cancer therapeutics.
Collapse
Affiliation(s)
- Michael P Marciel
- Department of Cell, Developmental and Integrative Biology, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Barnita Haldar
- Department of Cell, Developmental and Integrative Biology, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Jihye Hwang
- Department of Cell, Developmental and Integrative Biology, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Nikita Bhalerao
- Department of Cell, Developmental and Integrative Biology, University of Alabama at Birmingham, Birmingham, AL, United States
| | - Susan L Bellis
- Department of Cell, Developmental and Integrative Biology, University of Alabama at Birmingham, Birmingham, AL, United States.
| |
Collapse
|
20
|
Gámez Serna C, Romero-Palomo F, Arcadu F, Funk J, Schumacher V, Janowczyk A. MMO-Net (Multi-Magnification Organ Network): A use case for Organ Identification using Multiple Magnifications in Preclinical Pathology Studies. J Pathol Inform 2022; 13:100126. [PMID: 36268069 PMCID: PMC9577048 DOI: 10.1016/j.jpi.2022.100126] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/03/2022] [Revised: 07/04/2022] [Accepted: 07/12/2022] [Indexed: 11/29/2022] Open
Abstract
Identifying organs within histology images is a fundamental and non-trivial step in toxicological digital pathology workflows as multiple organs often appear on the same whole slide image (WSI). Previous works in automated tissue classification have investigated the use of single magnifications, and demonstrated limitations when attempting to identify small and contiguous organs at low magnifications. In order to overcome these shortcomings, we present a multi-magnification convolutional neural network (CNN), called MMO-Net, which employs context and cellular detail from different magnifications to facilitate the recognition of complex organs. Across N=320 WSI from 3 contract research organization (CRO) laboratories, we demonstrate state-of-the-art organ detection and segmentation performance of 7 rat organs with and without lesions: liver, kidney, thyroid gland, parathyroid gland, urinary bladder, salivary gland, and mandibular lymph node (AUROC=0.99-1.0 for all organs, Dice≥0.9 except parathyroid (0.73)). Evaluation takes place at both inter- and intra CRO levels, suggesting strong generalizability performance. Results are qualitatively reviewed using visualization masks to ensure separation of organs in close proximity (e.g., thyroid vs parathyroid glands). MMO-Net thus offers organ localization that serves as a potential quality control tool to validate WSI metadata and as a preprocessing step for subsequent organ-specific artificial intelligence (AI) use cases. To facilitate research in this area, all associated WSI and metadata used for this study are being made freely available, forming a first of its kind dataset for public use.
Collapse
Affiliation(s)
- Citlalli Gámez Serna
- Roche Pharma Research and Early Development (pRED), Oncology, Roche Innovation Center Basel, Basel, Switzerland
| | - Fernando Romero-Palomo
- Roche Pharma Research and Early Development (pRED), Pharmaceutical Sciences, Roche Innovation Center Basel, Basel, Switzerland
| | - Filippo Arcadu
- Roche Pharma Research and Early Development Informatics (pREDi), Safety Development Informatics, Roche Innovation Center Basel, Basel, Switzerland
| | - Jürgen Funk
- Roche Pharma Research and Early Development (pRED), Pharmaceutical Sciences, Roche Innovation Center Basel, Basel, Switzerland
| | - Vanessa Schumacher
- Roche Pharma Research and Early Development (pRED), Pharmaceutical Sciences, Roche Innovation Center Basel, Basel, Switzerland
| | - Andrew Janowczyk
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA
- Precision Oncology Center, University of Lausanne, Lausanne, Switzerland
| |
Collapse
|
21
|
The fibrogenic niche in kidney fibrosis: components and mechanisms. Nat Rev Nephrol 2022; 18:545-557. [PMID: 35788561 DOI: 10.1038/s41581-022-00590-z] [Citation(s) in RCA: 103] [Impact Index Per Article: 51.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 05/24/2022] [Indexed: 02/08/2023]
Abstract
Kidney fibrosis, characterized by excessive deposition of extracellular matrix (ECM) that leads to tissue scarring, is the final common outcome of a wide variety of chronic kidney diseases. Rather than being distributed uniformly across the kidney parenchyma, renal fibrotic lesions initiate at certain focal sites in which the fibrogenic niche is formed in a spatially confined fashion. This niche provides a unique tissue microenvironment that is orchestrated by a specialized ECM network consisting of de novo-induced matricellular proteins. Other structural elements of the fibrogenic niche include kidney resident and infiltrated inflammatory cells, extracellular vesicles, soluble factors and metabolites. ECM proteins in the fibrogenic niche recruit soluble factors including WNTs and transforming growth factor-β from the extracellular milieu, creating a distinctive profibrotic microenvironment. Studies using decellularized ECM scaffolds from fibrotic kidneys show that the fibrogenic niche autonomously promotes fibroblast proliferation, tubular injury, macrophage activation and endothelial cell depletion, pathological features that recapitulate key events in the pathogenesis of chronic kidney disease. The concept of the fibrogenic niche represents a paradigm shift in understanding of the mechanism of kidney fibrosis that could lead to the development of non-invasive biomarkers and novel therapies not only for chronic kidney disease, but also for fibrotic diseases of other organs.
Collapse
|
22
|
Haghighat M, Browning L, Sirinukunwattana K, Malacrino S, Khalid Alham N, Colling R, Cui Y, Rakha E, Hamdy FC, Verrill C, Rittscher J. Automated quality assessment of large digitised histology cohorts by artificial intelligence. Sci Rep 2022; 12:5002. [PMID: 35322056 PMCID: PMC8943120 DOI: 10.1038/s41598-022-08351-5] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2021] [Accepted: 03/03/2022] [Indexed: 02/07/2023] Open
Abstract
Research using whole slide images (WSIs) of histopathology slides has increased exponentially over recent years. Glass slides from retrospective cohorts, some with patient follow-up data are digitised for the development and validation of artificial intelligence (AI) tools. Such resources, therefore, become very important, with the need to ensure that their quality is of the standard necessary for downstream AI development. However, manual quality control of large cohorts of WSIs by visual assessment is unfeasible, and whilst quality control AI algorithms exist, these focus on bespoke aspects of image quality, e.g. focus, or use traditional machine-learning methods, which are unable to classify the range of potential image artefacts that should be considered. In this study, we have trained and validated a multi-task deep neural network to automate the process of quality control of a large retrospective cohort of prostate cases from which glass slides have been scanned several years after production, to determine both the usability of the images at the diagnostic level (considered in this study to be the minimal standard for research) and the common image artefacts present. Using a two-layer approach, quality overlays of WSIs were generated from a quality assessment (QA) undertaken at patch-level at \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$5\times$$\end{document}5× magnification. From these quality overlays the slide-level quality scores were predicted and then compared to those generated by three specialist urological pathologists, with a Pearson correlation of 0.89 for overall ‘usability’ (at a diagnostic level), and 0.87 and 0.82 for focus and H&E staining quality scores respectively. To demonstrate its wider potential utility, we subsequently applied our QA pipeline to the TCGA prostate cancer cohort and to a colorectal cancer cohort, for comparison. Our model, designated as PathProfiler, indicates comparable predicted usability of images from the cohorts assessed (86–90% of WSIs predicted to be usable), and perhaps more significantly is able to predict WSIs that could benefit from an intervention such as re-scanning or re-staining for quality improvement. We have shown in this study that AI can be used to automate the process of quality control of large retrospective WSI cohorts to maximise their utility for research.
Collapse
Affiliation(s)
- Maryam Haghighat
- Department of Engineering Science, Institute of Biomedical Engineering (IBME), University of Oxford, Oxford, UK. .,CSIRO, Brisbane, QLD, Australia.
| | - Lisa Browning
- Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford, UK.,NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, Oxfordshire, UK
| | - Korsuk Sirinukunwattana
- Department of Engineering Science, Institute of Biomedical Engineering (IBME), University of Oxford, Oxford, UK
| | - Stefano Malacrino
- Nuffield Department of Surgical Sciences, University of Oxford, John Radcliffe Hospital, Oxford, UK
| | - Nasullah Khalid Alham
- Department of Engineering Science, Institute of Biomedical Engineering (IBME), University of Oxford, Oxford, UK
| | - Richard Colling
- Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford, UK.,Nuffield Department of Surgical Sciences, University of Oxford, John Radcliffe Hospital, Oxford, UK
| | - Ying Cui
- Nuffield Department of Surgical Sciences, University of Oxford, John Radcliffe Hospital, Oxford, UK
| | - Emad Rakha
- School of Medicine, University of Nottingham, Nottingham, UK
| | - Freddie C Hamdy
- NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, Oxfordshire, UK.,Nuffield Department of Surgical Sciences, University of Oxford, John Radcliffe Hospital, Oxford, UK
| | - Clare Verrill
- Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Oxford, UK.,NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, Oxfordshire, UK.,Nuffield Department of Surgical Sciences, University of Oxford, John Radcliffe Hospital, Oxford, UK
| | - Jens Rittscher
- Department of Engineering Science, Institute of Biomedical Engineering (IBME), University of Oxford, Oxford, UK. .,NIHR Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, Oxfordshire, UK.
| |
Collapse
|
23
|
Hanna MG, Ardon O, Reuter VE, Sirintrapun SJ, England C, Klimstra DS, Hameed MR. Integrating digital pathology into clinical practice. Mod Pathol 2022; 35:152-164. [PMID: 34599281 DOI: 10.1038/s41379-021-00929-0] [Citation(s) in RCA: 32] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2021] [Revised: 09/03/2021] [Accepted: 09/12/2021] [Indexed: 11/09/2022]
Abstract
The field of anatomic pathology has been evolving in the last few decades and the advancements have been largely fostered by innovative technology. Immunohistochemistry enabled a paradigm shift in discovery and diagnostic evaluation, followed by booming genomic advancements which allowed for submicroscopic pathologic characterization, and now the field of digital pathology coupled with machine learning and big data acquisition is paving the way to revolutionize the pathology medical domain. Whole slide imaging (WSI) is a disruptive technology where glass slides are digitized to produce on-screen whole slide images. Specifically, in the past decade, there have been significant advances in digital pathology systems that have allowed this technology to promote integration into clinical practice. Whole slide images (WSI), or digital slides, can be viewed and navigated comparable to glass slides on a microscope, as digital files. Whole slide imaging has increased in adoption among pathologists, pathology departments, and scientists for clinical, educational, and research initiatives. Integration of digital pathology systems requires a coordinated effort with numerous stakeholders, not only within the pathology department, but across the entire enterprise. Each pathology department has distinct needs, use cases and blueprints, however the framework components and variables for successful clinical integration can be generalized across any organization seeking to undergo a digital transformation at any scale. This article will review those components and considerations for integrating digital pathology systems into clinical practice.
Collapse
Affiliation(s)
- Matthew G Hanna
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
| | - Orly Ardon
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Victor E Reuter
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | | | - Christine England
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - David S Klimstra
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Meera R Hameed
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
| |
Collapse
|
24
|
Weis CA, Bindzus JN, Voigt J, Runz M, Hertjens S, Gaida MM, Popovic ZV, Porubsky S. Assessment of glomerular morphological patterns by deep learning algorithms. J Nephrol 2022; 35:417-427. [PMID: 34982414 PMCID: PMC8927010 DOI: 10.1007/s40620-021-01221-9] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/30/2021] [Indexed: 12/11/2022]
Abstract
Background Compilation of different morphological lesion signatures is characteristic of renal pathology. Previous studies have documented the potential value of artificial intelligence (AI) in recognizing relatively clear-cut glomerular structures and patterns, such as segmental or global sclerosis or mesangial hypercellularity. This study aimed to test the capacity of deep learning algorithms to recognize complex glomerular structural changes that reflect common diagnostic dilemmas in nephropathology. Methods For this purpose, we defined nine classes of glomerular morphological patterns and trained twelve convolutional neuronal network (CNN) models on these. The two-step training process was done on a first dataset defined by an expert nephropathologist (12,253 images) and a second consensus dataset (11,142 images) defined by three experts in the field. Results The efficacy of CNN training was evaluated using another set with 180 consensus images, showing convincingly good classification results (kappa-values 0.838–0.938). Furthermore, we elucidated the image areas decisive for CNN-based decision making by class activation maps. Finally, we demonstrated that the algorithm could decipher glomerular disease patterns coinciding in a single glomerulus (e.g. necrosis along with mesangial and endocapillary hypercellularity). Conclusions In summary, our model, focusing on glomerular lesions detectable by conventional microscopy, is the first sui generis to deploy deep learning as a reliable and promising tool in recognition of even discrete and/or overlapping morphological changes. Our results provide a stimulus for ongoing projects that integrate further input levels next to morphology (such as immunohistochemistry, electron microscopy, and clinical information) to develop a novel tool applicable for routine diagnostic nephropathology. Supplementary Information The online version contains supplementary material available at 10.1007/s40620-021-01221-9.
Collapse
Affiliation(s)
- Cleo-Aron Weis
- Institute of Pathology, University Medical Centre Mannheim, University of Heidelberg, 68167, Mannheim, Germany.
| | - Jan Niklas Bindzus
- Institute of Pathology, University Medical Centre Mannheim, University of Heidelberg, 68167, Mannheim, Germany
| | - Jonas Voigt
- Institute of Pathology, University Medical Centre Mannheim, University of Heidelberg, 68167, Mannheim, Germany
| | - Marlen Runz
- Institute of Pathology, University Medical Centre Mannheim, University of Heidelberg, 68167, Mannheim, Germany.,Mannheim Institute for Intelligent Systems in Medicine, University Medical Centre Mannheim, University of Heidelberg, Mannheim, Germany
| | - Svetlana Hertjens
- Institute of Medical Statistics and Biometry, Medical Faculty Mannheim, University of Heidelberg, Mannheim, Germany
| | - Matthias M Gaida
- Institute of Pathology, University Medical Center of the Johannes Gutenberg University Mainz, Langenbeckstrasse 1, 55131, Mainz, Germany
| | - Zoran V Popovic
- Institute of Pathology, University Medical Centre Mannheim, University of Heidelberg, 68167, Mannheim, Germany
| | - Stefan Porubsky
- Institute of Pathology, University Medical Center of the Johannes Gutenberg University Mainz, Langenbeckstrasse 1, 55131, Mainz, Germany.
| |
Collapse
|
25
|
Leo P, Janowczyk A, Elliott R, Janaki N, Bera K, Shiradkar R, Farré X, Fu P, El-Fahmawi A, Shahait M, Kim J, Lee D, Yamoah K, Rebbeck TR, Khani F, Robinson BD, Eklund L, Jambor I, Merisaari H, Ettala O, Taimen P, Aronen HJ, Boström PJ, Tewari A, Magi-Galluzzi C, Klein E, Purysko A, Nc Shih N, Feldman M, Gupta S, Lal P, Madabhushi A. Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study. NPJ Precis Oncol 2021; 5:35. [PMID: 33941830 PMCID: PMC8093226 DOI: 10.1038/s41698-021-00174-3] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2020] [Accepted: 04/05/2021] [Indexed: 01/04/2023] Open
Abstract
Existing tools for post-radical prostatectomy (RP) prostate cancer biochemical recurrence (BCR) prognosis rely on human pathologist-derived parameters such as tumor grade, with the resulting inter-reviewer variability. Genomic companion diagnostic tests such as Decipher tend to be tissue destructive, expensive, and not routinely available in most centers. We present a tissue non-destructive method for automated BCR prognosis, termed "Histotyping", that employs computational image analysis of morphologic patterns of prostate tissue from a single, routinely acquired hematoxylin and eosin slide. Patients from two institutions (n = 214) were used to train Histotyping for identifying high-risk patients based on six features of glandular morphology extracted from RP specimens. Histotyping was validated for post-RP BCR prognosis on a separate set of n = 675 patients from five institutions and compared against Decipher on n = 167 patients. Histotyping was prognostic of BCR in the validation set (p < 0.001, univariable hazard ratio [HR] = 2.83, 95% confidence interval [CI]: 2.03-3.93, concordance index [c-index] = 0.68, median years-to-BCR: 1.7). Histotyping was also prognostic in clinically stratified subsets, such as patients with Gleason grade group 3 (HR = 4.09) and negative surgical margins (HR = 3.26). Histotyping was prognostic independent of grade group, margin status, pathological stage, and preoperative prostate-specific antigen (PSA) (multivariable p < 0.001, HR = 2.09, 95% CI: 1.40-3.10, n = 648). The combination of Histotyping, grade group, and preoperative PSA outperformed Decipher (c-index = 0.75 vs. 0.70, n = 167). These results suggest that a prognostic classifier for prostate cancer based on digital images could serve as an alternative or complement to molecular-based companion diagnostic tests.
Collapse
Grants
- National Cancer Institute under award numbers 1U24CA199374-01, R01CA249992-01A1 R01CA202752-01A1 R01CA208236-01A1 R01CA216579-01A1 R01CA220581-01A1 1U01CA239055-01 1U01CA248226-01 1U54CA254566-01 National Heart, Lung and Blood Institute 1R01HL15127701A1, National Institute for Biomedical Imaging and Bioengineering 1R43EB028736-01, National Center for Research Resources 1 C06 RR12463-01, VA Merit Review Award IBX004121A from the United States Department of Veterans Affairs Biomedical Laboratory Research and Development Service, the Office of the Assistant Secretary of Defense for Health Affairs, through the Breast Cancer Research Program (W81XWH-19-1-0668), the Prostate Cancer Research Program (W81XWH-15-1-0558, W81XWH-20-1-0851), the Lung Cancer Research Program (W81XWH-18-1-0440, W81XWH-20-1-0595), the Peer Reviewed Cancer Research Program (W81XWH-18-1-0404), the Kidney Precision Medicine Project Glue Grant, the Ohio Third Frontier Technology Validation Fund, the Clinical and Translational Science Collaborative of Cleveland (UL1TR0002548) from the National Center for Advancing Translational Sciences (NCATS) component of the National Institutes of Health and NIH roadmap for Medical Research, The Wallace H. Coulter Foundation Program in the Department of Biomedical Engineering at Case Western Reserve University,
- Sigrid Jusélius Foundation The Finnish Cancer Foundation
- Department of Defense Prostate Cancer Disparity Award (W81XWH-19-1-0720),
- National Science Foundation Graduate Research Fellowship Program (CON501692)
Collapse
Affiliation(s)
- Patrick Leo
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA
| | - Andrew Janowczyk
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA
- Department of Oncology, Lausanne University Hospital and Lausanne University, Lausanne, Switzerland
| | - Robin Elliott
- Department of Pathology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA
| | - Nafiseh Janaki
- Department of Pathology, Harvard Medical School, Brigham and Women's Hospital, Boston, MA, USA
| | - Kaustav Bera
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA
| | - Rakesh Shiradkar
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA
| | - Xavier Farré
- Public Health Agency of Catalonia, Lleida, Catalonia, Spain
| | - Pingfu Fu
- Department of Population and Quantitative Health Sciences, Case Western Reserve University, Cleveland, OH, USA
| | - Ayah El-Fahmawi
- Department of Urology, Penn Presbyterian Medical Center, Philadelphia, PA, USA
| | - Mohammed Shahait
- Department of Urology, Penn Presbyterian Medical Center, Philadelphia, PA, USA
| | - Jessica Kim
- Department of Urology, Penn Presbyterian Medical Center, Philadelphia, PA, USA
| | - David Lee
- Department of Urology, Penn Presbyterian Medical Center, Philadelphia, PA, USA
| | - Kosj Yamoah
- Moffitt Cancer Center, Department of Radiation Oncology, University of South Florida, Tampa, FL, USA
| | - Timothy R Rebbeck
- T.H. Chan School of Public Health and Dana Farber Cancer Institute, Harvard University, Boston, MA, USA
| | - Francesca Khani
- Departments of Pathology and Laboratory Medicine and Urology, Weill Cornell Medicine, New York, NY, USA
| | - Brian D Robinson
- Departments of Pathology and Laboratory Medicine and Urology, Weill Cornell Medicine, New York, NY, USA
| | - Lauri Eklund
- Department of Pathology, University of Turku, Institute of Biomedicine and Turku University Hospital, Turku, Finland
| | - Ivan Jambor
- Department of Pathology, University of Turku, Institute of Biomedicine and Turku University Hospital, Turku, Finland
- Department of Diagnostic Radiology, University of Turku, Turku, Finland
| | - Harri Merisaari
- Department of Pathology, University of Turku, Institute of Biomedicine and Turku University Hospital, Turku, Finland
| | - Otto Ettala
- Department of Urology, University of Turku, Institute of Biomedicine and Turku University Hospital, Turku, Finland
| | - Pekka Taimen
- Department of Pathology, University of Turku, Institute of Biomedicine and Turku University Hospital, Turku, Finland
| | - Hannu J Aronen
- Department of Pathology, University of Turku, Institute of Biomedicine and Turku University Hospital, Turku, Finland
- Turku University Hospital, Medical Imaging Centre of Southwest Finland, Turku, Finland
| | - Peter J Boström
- Department of Urology, University of Turku and Turku University Hospital, Turku, Finland
| | - Ashutosh Tewari
- Department of Urology, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | | | - Eric Klein
- Cleveland Clinic, Glickman Urological and Kidney Institute, Cleveland, OH, USA
| | - Andrei Purysko
- Cleveland Clinic, Imaging Institute, Section of Abdominal Imaging, Cleveland, OH, USA
| | - Natalie Nc Shih
- Department of Pathology, University of Pennsylvania, Philadelphia, PA, USA
| | - Michael Feldman
- Department of Pathology, University of Pennsylvania, Philadelphia, PA, USA
| | - Sanjay Gupta
- Department of Urology, Case Western Reserve University, Cleveland, OH, USA
- Louis Stokes Cleveland Veterans Administration Medical Center, Cleveland, OH, USA
| | - Priti Lal
- Department of Pathology, University of Pennsylvania, Philadelphia, PA, USA
| | - Anant Madabhushi
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA.
- Louis Stokes Cleveland Veterans Administration Medical Center, Cleveland, OH, USA.
| |
Collapse
|