1
|
Saygin C, Zhang P, Stauber J, Aldoss I, Sperling AS, Weeks LD, Luskin MR, Knepper TC, Wanjari P, Wang P, Lager AM, Fitzpatrick C, Segal JP, Gharghabi M, Gurbuxani S, Venkataraman G, Cheng JX, Eisfelder BJ, Bohorquez O, Patel AA, Umesh Nagalakshmi S, Jayaram S, Odenike OM, Larson RA, Godley LA, Arber DA, Gibson CJ, Munshi NC, Marcucci G, Ebert BL, Greally JM, Steidl U, Lapalombella R, Shah BD, Stock W. Acute Lymphoblastic Leukemia with Myeloid Mutations Is a High-Risk Disease Associated with Clonal Hematopoiesis. Blood Cancer Discov 2024; 5:164-179. [PMID: 38150184 PMCID: PMC11061587 DOI: 10.1158/2643-3230.bcd-23-0106] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [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] [Received: 06/23/2023] [Revised: 10/05/2023] [Accepted: 12/19/2023] [Indexed: 12/28/2023] Open
Abstract
Myeloid neoplasms arise from preexisting clonal hematopoiesis (CH); however, the role of CH in the pathogenesis of acute lymphoblastic leukemia (ALL) is unknown. We found that 18% of adult ALL cases harbored TP53, and 16% had myeloid CH-associated gene mutations. ALL with myeloid mutations (MyM) had distinct genetic and clinical characteristics, associated with inferior survival. By using single-cell proteogenomic analysis, we demonstrated that myeloid mutations were present years before the diagnosis of ALL, and a subset of these clones expanded over time to manifest as dominant clones in ALL. Single-cell RNA sequencing revealed upregulation of genes associated with cell survival and resistance to apoptosis in B-ALL with MyM, which responds better to newer immunotherapeutic approaches. These findings define ALL with MyM as a high-risk disease that can arise from antecedent CH and offer new mechanistic insights to develop better therapeutic and preventative strategies. SIGNIFICANCE CH is a precursor lesion for lymphoblastic leukemogenesis. ALL with MyM has distinct genetic and clinical characteristics, associated with adverse survival outcomes after chemotherapy. CH can precede ALL years before diagnosis, and ALL with MyM is enriched with activated T cells that respond to immunotherapies such as blinatumomab. See related commentary by Iacobucci, p. 142.
Collapse
Affiliation(s)
- Caner Saygin
- Section of Hematology/Oncology, University of Chicago, Chicago, Illinois
| | - Pu Zhang
- Division of Hematology, The Ohio State University, Columbus, Ohio
| | - Jacob Stauber
- Albert Einstein College of Medicine–Montefiore Health System, New York, New York
| | - Ibrahim Aldoss
- Department of Hematology and Hematopoietic Cell Transplantation, City of Hope, Duarte, California
| | - Adam S. Sperling
- Dana-Farber Cancer Institute, Boston, Massachusetts
- Division of Hematology, Brigham and Women's Hospital, Boston, Massachusetts
| | | | | | | | - Pankhuri Wanjari
- Department of Pathology, University of Chicago, Chicago, Illinois
| | - Peng Wang
- Department of Pathology, University of Chicago, Chicago, Illinois
| | - Angela M. Lager
- Department of Pathology, University of Chicago, Chicago, Illinois
| | | | - Jeremy P. Segal
- Department of Pathology, University of Chicago, Chicago, Illinois
| | - Mehdi Gharghabi
- Division of Hematology, The Ohio State University, Columbus, Ohio
| | | | | | - Jason X. Cheng
- Department of Pathology, University of Chicago, Chicago, Illinois
| | - Bart J. Eisfelder
- Section of Hematology/Oncology, University of Chicago, Chicago, Illinois
| | - Oliver Bohorquez
- Albert Einstein College of Medicine–Montefiore Health System, New York, New York
| | - Anand A. Patel
- Section of Hematology/Oncology, University of Chicago, Chicago, Illinois
| | | | | | | | - Richard A. Larson
- Section of Hematology/Oncology, University of Chicago, Chicago, Illinois
| | - Lucy A. Godley
- Section of Hematology/Oncology, University of Chicago, Chicago, Illinois
| | - Daniel A. Arber
- Department of Pathology, University of Chicago, Chicago, Illinois
| | | | | | - Guido Marcucci
- Department of Hematology and Hematopoietic Cell Transplantation, City of Hope, Duarte, California
| | | | - John M. Greally
- Albert Einstein College of Medicine–Montefiore Health System, New York, New York
| | - Ulrich Steidl
- Albert Einstein College of Medicine–Montefiore Health System, New York, New York
| | | | | | - Wendy Stock
- Section of Hematology/Oncology, University of Chicago, Chicago, Illinois
| |
Collapse
|
2
|
Storrs EP, Chati P, Usmani A, Sloan I, Krasnick BA, Babbra R, Harris PK, Sachs CM, Qaium F, Chatterjee D, Wetzel C, Goedegebuure SP, Hollander T, Anthony H, Ponce J, Khaliq AM, Badiyan S, Kim H, Denardo DG, Lang GD, Cosgrove ND, Kushnir VM, Early DS, Masood A, Lim KH, Hawkins WG, Ding L, Fields RC, Das KK, Chaudhuri AA. High-dimensional deconstruction of pancreatic cancer identifies tumor microenvironmental and developmental stemness features that predict survival. NPJ Precis Oncol 2023; 7:105. [PMID: 37857854 PMCID: PMC10587349 DOI: 10.1038/s41698-023-00455-z] [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: 04/06/2023] [Accepted: 09/26/2023] [Indexed: 10/21/2023] Open
Abstract
Numerous cell states are known to comprise the pancreatic ductal adenocarcinoma (PDAC) tumor microenvironment (TME). However, the developmental stemness and co-occurrence of these cell states remain poorly defined. Here, we performed single-cell RNA sequencing (scRNA-seq) on a cohort of treatment-naive PDAC time-of-diagnosis endoscopic ultrasound-guided fine needle biopsy (EUS-FNB) samples (n = 25). We then combined these samples with surgical resection (n = 6) and publicly available samples to increase statistical power (n = 80). Following annotation into 25 distinct cell states, cells were scored for developmental stemness, and a customized version of the Ecotyper tool was used to identify communities of co-occurring cell states in bulk RNA-seq samples (n = 268). We discovered a tumor microenvironmental community comprised of aggressive basal-like malignant cells, tumor-promoting SPP1+ macrophages, and myofibroblastic cancer-associated fibroblasts associated with especially poor prognosis. We also found a developmental stemness continuum with implications for survival that is present in both malignant cells and cancer-associated fibroblasts (CAFs). We further demonstrated that high-dimensional analyses predictive of survival are feasible using standard-of-care, time-of-diagnosis EUS-FNB specimens. In summary, we identified tumor microenvironmental and developmental stemness characteristics from a high-dimensional gene expression analysis of PDAC using human tissue specimens, including time-of-diagnosis EUS-FNB samples. These reveal new connections between tumor microenvironmental composition, CAF and malignant cell stemness, and patient survival that could lead to better upfront risk stratification and more personalized upfront clinical decision-making.
Collapse
Affiliation(s)
- Erik P Storrs
- Department of Genetics, Washington University School of Medicine, St. Louis, MO, USA
- Division of Biology and Biomedical Sciences, Washington University School of Medicine, St. Louis, MO, USA
| | - Prathamesh Chati
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA
| | - Abul Usmani
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA
| | - Ian Sloan
- Division of Gastroenterology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA
| | - Bradley A Krasnick
- Department of Surgery, Washington University School of Medicine, St. Louis, MO, USA
| | - Ramandeep Babbra
- Division of Hematology & Oncology, Department of Medicine, University of Rochester Medical Center, Rochester, NY, USA
| | - Peter K Harris
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA
| | - Chloe M Sachs
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA
| | - Faridi Qaium
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA
| | - Deyali Chatterjee
- Division of Laboratory Medicine, Department of Pathology, MD Anderson Cancer Center, Houston, TX, USA
| | - Chris Wetzel
- Department of Surgery, Washington University School of Medicine, St. Louis, MO, USA
| | - S Peter Goedegebuure
- Department of Surgery, Washington University School of Medicine, St. Louis, MO, USA
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA
| | - Thomas Hollander
- Division of Gastroenterology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA
| | - Hephzibah Anthony
- Division of Gastroenterology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA
| | - Jennifer Ponce
- McDonnell Genome Institute, Washington University School of Medicine, St. Louis, MO, USA
| | - Ateeq M Khaliq
- Division of Hematology/Oncology, Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Shahed Badiyan
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA
| | - Hyun Kim
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA
| | - David G Denardo
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA
- Department of Pathology and Immunology, Washington University School of Medicine, St. Louis, MO, USA
- Division of Oncology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA
| | - Gabriel D Lang
- Division of Gastroenterology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA
| | - Natalie D Cosgrove
- Division of Gastroenterology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA
| | - Vladimir M Kushnir
- Division of Gastroenterology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA
| | - Dayna S Early
- Division of Gastroenterology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA
| | - Ashiq Masood
- Division of Hematology/Oncology, Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Kian-Huat Lim
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA
- Division of Oncology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA
| | - William G Hawkins
- Department of Surgery, Washington University School of Medicine, St. Louis, MO, USA
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA
| | - Li Ding
- Department of Genetics, Washington University School of Medicine, St. Louis, MO, USA
- Division of Biology and Biomedical Sciences, Washington University School of Medicine, St. Louis, MO, USA
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA
- McDonnell Genome Institute, Washington University School of Medicine, St. Louis, MO, USA
- Division of Oncology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA
| | - Ryan C Fields
- Division of Biology and Biomedical Sciences, Washington University School of Medicine, St. Louis, MO, USA
- Department of Surgery, Washington University School of Medicine, St. Louis, MO, USA
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA
| | - Koushik K Das
- Division of Gastroenterology, Department of Medicine, Washington University School of Medicine, St. Louis, MO, USA.
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA.
| | - Aadel A Chaudhuri
- Department of Genetics, Washington University School of Medicine, St. Louis, MO, USA.
- Division of Biology and Biomedical Sciences, Washington University School of Medicine, St. Louis, MO, USA.
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA.
- Siteman Cancer Center, Washington University School of Medicine, St. Louis, MO, USA.
- Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, MO, USA.
- Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, MO, USA.
| |
Collapse
|
3
|
Aasted MK, Groen AC, Keane JT, Dabelsteen S, Tan E, Schnabel J, Liu F, Lewis HGS, Theodoropulos C, Posey AD, Wandall HH. Targeting Solid Cancers with a Cancer-Specific Monoclonal Antibody to Surface Expressed Aberrantly O-glycosylated Proteins. Mol Cancer Ther 2023; 22:1204-1214. [PMID: 37451822 PMCID: PMC10543972 DOI: 10.1158/1535-7163.mct-23-0221] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [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] [Received: 04/11/2023] [Revised: 06/14/2023] [Accepted: 07/10/2023] [Indexed: 07/18/2023]
Abstract
The lack of antibodies with sufficient cancer selectivity is currently limiting the treatment of solid tumors by immunotherapies. Most current immunotherapeutic targets are tumor-associated antigens that are also found in healthy tissues and often do not display sufficient cancer selectivity to be used as targets for potent antibody-based immunotherapeutic treatments, such as chimeric antigen receptor (CAR) T cells. Many solid tumors, however, display aberrant glycosylation that results in expression of tumor-associated carbohydrate antigens that are distinct from healthy tissues. Targeting aberrantly glycosylated glycopeptide epitopes within existing or novel glycoprotein targets may provide the cancer selectivity needed for immunotherapy of solid tumors. However, to date only a few such glycopeptide epitopes have been targeted. Here, we used O-glycoproteomics data from multiple cell lines to identify a glycopeptide epitope in CD44v6, a cancer-associated CD44 isoform, and developed a cancer-specific mAb, 4C8, through a glycopeptide immunization strategy. 4C8 selectively binds to Tn-glycosylated CD44v6 in a site-specific manner with low nanomolar affinity. 4C8 was shown to be highly cancer specific by IHC of sections from multiple healthy and cancerous tissues. 4C8 CAR T cells demonstrated target-specific cytotoxicity in vitro and significant tumor regression and increased survival in vivo. Importantly, 4C8 CAR T cells were able to selectively kill target cells in a mixed organotypic skin cancer model having abundant CD44v6 expression without affecting healthy keratinocytes, indicating tolerability and safety.
Collapse
Affiliation(s)
- Mikkel K.M. Aasted
- Department of Cellular and Molecular Medicine, Copenhagen Center for Glycomics, University of Copenhagen, Copenhagen, Denmark
| | | | - John T. Keane
- Department of Systems Pharmacology and Translational Therapeutics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Sally Dabelsteen
- Department of Oral Pathology, School of Dentistry, University of Copenhagen, Copenhagen, Denmark
| | - Edwin Tan
- GO-Therapeutics, One Broadway, Cambridge, Massachusetts
| | | | - Fang Liu
- Department of Systems Pharmacology and Translational Therapeutics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
| | - Hyeon-Gyu S. Lewis
- Department of Systems Pharmacology and Translational Therapeutics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
| | | | - Avery D. Posey
- Department of Systems Pharmacology and Translational Therapeutics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania
- Corporal Michael J. Crescenz VA Medical Center, Philadelphia, Pennsylvania
| | - Hans H. Wandall
- Department of Cellular and Molecular Medicine, Copenhagen Center for Glycomics, University of Copenhagen, Copenhagen, Denmark
- GO-Therapeutics, One Broadway, Cambridge, Massachusetts
| |
Collapse
|
4
|
Saygin C, Giordano G, Shimamoto K, Eisfelder B, Thomas-Toth A, Venkataraman G, Ananthanarayanan V, Vincent TL, DuVall A, Patel AA, Chen Y, Tan F, Anthony SP, Chen Y, Shen Y, Odenike O, Teachey DT, Kee BL, LaBelle J, Stock W. Dual Targeting of Apoptotic and Signaling Pathways in T-Lineage Acute Lymphoblastic Leukemia. Clin Cancer Res 2023; 29:3151-3161. [PMID: 37363966 PMCID: PMC10425730 DOI: 10.1158/1078-0432.ccr-23-0415] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [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] [Received: 02/10/2023] [Revised: 05/08/2023] [Accepted: 06/20/2023] [Indexed: 06/28/2023]
Abstract
PURPOSE Relapsed T-acute lymphoblastic leukemia (T-ALL) has limited treatment options. We investigated mechanisms of resistance to BH3 mimetics in T-ALL to develop rational combination strategies. We also looked at the preclinical efficacy of NWP-0476, a novel BCL-2/BCL-xL inhibitor, as single agent and combination therapy in T-ALL. EXPERIMENTAL DESIGN We used BH3 profiling as a predictive tool for BH3 mimetic response in T-ALL. Using isogenic control, venetoclax-resistant (ven-R) and NWP-0476-resistant (NWP-R) cells, phosphokinase array was performed to identify differentially regulated signaling pathways. RESULTS Typical T-ALL cells had increased dependence on BCL-xL, whereas early T-precursor (ETP)-ALL cells had higher BCL-2 dependence for survival. BCL-2/BCL-xL dual inhibitors were effective against both subtypes of T-lineage ALL. A 71-protein human phosphokinase array showed increased LCK activity in ven-R cells, and increased ACK1 activity in ven-R and NWP-R cells. We hypothesized that pre-TCR and ACK1 signaling pathways are drivers of resistance to BCL-2 and BCL-xL inhibition, respectively. First, we silenced LCK gene in T-ALL cell lines, which resulted in increased sensitivity to BCL-2 inhibition. Mechanistically, LCK activated NF-κB pathway and the expression of BCL-xL. Silencing ACK1 gene resulted in increased sensitivity to both BCL-2 and BCL-xL inhibitors. ACK1 signaling upregulated AKT pathway, which inhibited the pro-apoptotic function of BAD. In a T-ALL patient-derived xenograft model, combination of NWP-0476 and dasatinib demonstrated synergy without major organ toxicity. CONCLUSIONS LCK and ACK1 signaling pathways are critical regulators of BH3 mimetic resistance in T-ALL. Combination of BH3 mimetics with tyrosine kinase inhibitors might be effective against relapsed T-ALL.
Collapse
Affiliation(s)
- Caner Saygin
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, Illinois
| | - Giorgia Giordano
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, Illinois
| | - Kathryn Shimamoto
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, Illinois
| | - Bart Eisfelder
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, Illinois
| | | | | | | | - Tiffaney L. Vincent
- The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania
- University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania
| | - Adam DuVall
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, Illinois
| | - Anand A. Patel
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, Illinois
| | - Yi Chen
- Newave Pharmaceutical Inc., Pleasanton, California
| | - Fenlai Tan
- Newave Pharmaceutical Inc., Pleasanton, California
| | | | - Yu Chen
- Newave Pharmaceutical Inc., Pleasanton, California
| | - Yue Shen
- Newave Pharmaceutical Inc., Pleasanton, California
| | - Olatoyosi Odenike
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, Illinois
| | - David T. Teachey
- The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania
- University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania
| | - Barbara L. Kee
- Department of Pathology, University of Chicago, Chicago, Illinois
| | - James LaBelle
- Department of Pediatrics, University of Chicago, Chicago, Illinois
| | - Wendy Stock
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, Illinois
| |
Collapse
|
5
|
Dolezal JM, Srisuwananukorn A, Karpeyev D, Ramesh S, Kochanny S, Cody B, Mansfield AS, Rakshit S, Bansal R, Bois MC, Bungum AO, Schulte JJ, Vokes EE, Garassino MC, Husain AN, Pearson AT. Uncertainty-informed deep learning models enable high-confidence predictions for digital histopathology. Nat Commun 2022; 13:6572. [PMID: 36323656 PMCID: PMC9630455 DOI: 10.1038/s41467-022-34025-x] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [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: 05/05/2022] [Accepted: 10/07/2022] [Indexed: 11/06/2022] Open
Abstract
A model's ability to express its own predictive uncertainty is an essential attribute for maintaining clinical user confidence as computational biomarkers are deployed into real-world medical settings. In the domain of cancer digital histopathology, we describe a clinically-oriented approach to uncertainty quantification for whole-slide images, estimating uncertainty using dropout and calculating thresholds on training data to establish cutoffs for low- and high-confidence predictions. We train models to identify lung adenocarcinoma vs. squamous cell carcinoma and show that high-confidence predictions outperform predictions without uncertainty, in both cross-validation and testing on two large external datasets spanning multiple institutions. Our testing strategy closely approximates real-world application, with predictions generated on unsupervised, unannotated slides using predetermined thresholds. Furthermore, we show that uncertainty thresholding remains reliable in the setting of domain shift, with accurate high-confidence predictions of adenocarcinoma vs. squamous cell carcinoma for out-of-distribution, non-lung cancer cohorts.
Collapse
Affiliation(s)
- James M Dolezal
- Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA
| | | | | | - Siddhi Ramesh
- Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA
| | - Sara Kochanny
- Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA
| | - Brittany Cody
- Department of Pathology, University of Chicago, Chicago, IL, USA
| | | | - Sagar Rakshit
- Division of Medical Oncology, Mayo Clinic, Rochester, MN, USA
| | - Radhika Bansal
- Division of Medical Oncology, Mayo Clinic, Rochester, MN, USA
| | - Melanie C Bois
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA
| | - Aaron O Bungum
- Divisions of Pulmonary Medicine and Critical Care, Mayo Clinic, Rochester, MN, USA
| | - Jefree J Schulte
- Department of Pathology and Laboratory Medicine, University of Wisconsin at Madison, Madison, WN, USA
| | - Everett E Vokes
- Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA
| | - Marina Chiara Garassino
- Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA
| | - Aliya N Husain
- Department of Pathology, University of Chicago, Chicago, IL, USA
| | - Alexander T Pearson
- Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA.
| |
Collapse
|
6
|
Howard FM, Dolezal J, Kochanny S, Schulte J, Chen H, Heij L, Huo D, Nanda R, Olopade OI, Kather JN, Cipriani N, Grossman RL, Pearson AT. The impact of site-specific digital histology signatures on deep learning model accuracy and bias. Nat Commun 2021; 12:4423. [PMID: 34285218 PMCID: PMC8292530 DOI: 10.1038/s41467-021-24698-1] [Citation(s) in RCA: 34] [Impact Index Per Article: 11.3] [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: 12/09/2020] [Accepted: 07/01/2021] [Indexed: 12/20/2022] Open
Abstract
The Cancer Genome Atlas (TCGA) is one of the largest biorepositories of digital histology. Deep learning (DL) models have been trained on TCGA to predict numerous features directly from histology, including survival, gene expression patterns, and driver mutations. However, we demonstrate that these features vary substantially across tissue submitting sites in TCGA for over 3,000 patients with six cancer subtypes. Additionally, we show that histologic image differences between submitting sites can easily be identified with DL. Site detection remains possible despite commonly used color normalization and augmentation methods, and we quantify the image characteristics constituting this site-specific digital histology signature. We demonstrate that these site-specific signatures lead to biased accuracy for prediction of features including survival, genomic mutations, and tumor stage. Furthermore, ethnicity can also be inferred from site-specific signatures, which must be accounted for to ensure equitable application of DL. These site-specific signatures can lead to overoptimistic estimates of model performance, and we propose a quadratic programming method that abrogates this bias by ensuring models are not trained and validated on samples from the same site.
Collapse
Affiliation(s)
- Frederick M Howard
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA
| | - James Dolezal
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA
| | - Sara Kochanny
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA
| | - Jefree Schulte
- Department of Pathology, University of Chicago, Chicago, IL, USA
| | - Heather Chen
- Department of Pathology, University of Chicago, Chicago, IL, USA
| | - Lara Heij
- Department of Surgery and Transplantation, University Hospital RWTH Aachen, Aachen, Germany
- Institute of Pathology, University Hospital RWTH Aachen, Aachen, Germany
| | - Dezheng Huo
- Department of Public Health Sciences, University of Chicago, Chicago, IL, USA
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA
| | - Rita Nanda
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA
| | - Olufunmilayo I Olopade
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA
| | - Jakob N Kather
- Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany
- Pathology and Data Analytics, Leeds Institute of Medical Research at St James's, University of Leeds, Leeds, UK
- Medical Oncology, National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany
| | - Nicole Cipriani
- Department of Pathology, University of Chicago, Chicago, IL, USA
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA
| | - Robert L Grossman
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA.
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA.
| | - Alexander T Pearson
- Section of Hematology/Oncology, Department of Medicine, University of Chicago, Chicago, IL, USA.
- University of Chicago Comprehensive Cancer Center, Chicago, IL, USA.
| |
Collapse
|