1
|
Majumdar A, Lad J, Tumanova K, Serra S, Quereshy F, Khorasani M, Vitkin A. Machine learning based local recurrence prediction in colorectal cancer using polarized light imaging. JOURNAL OF BIOMEDICAL OPTICS 2024; 29:052915. [PMID: 38077502 PMCID: PMC10704263 DOI: 10.1117/1.jbo.29.5.052915] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Revised: 11/03/2023] [Accepted: 11/09/2023] [Indexed: 12/18/2023]
Abstract
Significance Current treatment for stage III colorectal cancer (CRC) patients involves surgery that may not be sufficient in many cases, requiring additional adjuvant systemic therapy. Identification of this latter cohort that is likely to recur following surgery is key to better personalized therapy selection, but there is a lack of proper quantitative assessment tools for potential clinical adoption. Aim The purpose of this study is to employ Mueller matrix (MM) polarized light microscopy in combination with supervised machine learning (ML) to quantitatively analyze the prognostic value of peri-tumoral collagen in CRC in relation to 5-year local recurrence (LR). Approach A simple MM microscope setup was used to image surgical resection samples acquired from stage III CRC patients. Various potential biomarkers of LR were derived from MM elements via decomposition and transformation operations. These were used as features by different supervised ML models to distinguish samples from patients that locally recurred 5 years later from those that did not. Results Using the top five most prognostic polarimetric biomarkers ranked by their relevant feature importances, the best-performing XGBoost model achieved a patient-level accuracy of 86%. When the patient pool was further stratified, 96% accuracy was achieved within a tumor-stage-III sub-cohort. Conclusions ML-aided polarimetric analysis of collagenous stroma may provide prognostic value toward improving the clinical management of CRC patients.
Collapse
Affiliation(s)
- Anamitra Majumdar
- University of Toronto, Department of Medical Biophysics, Toronto, Ontario, Canada
| | - Jigar Lad
- McMaster University, Department of Physics and Astronomy, Hamilton, Ontario, Canada
| | - Kseniia Tumanova
- University of Toronto, Department of Medical Biophysics, Toronto, Ontario, Canada
| | - Stefano Serra
- University of Toronto, Department of Laboratory Medicine and Pathobiology, Toronto, Ontario, Canada
| | - Fayez Quereshy
- University of Toronto, Department of Laboratory Medicine and Pathobiology, Toronto, Ontario, Canada
| | - Mohammadali Khorasani
- University of British Columbia, Department of Surgery, Victoria, British Columbia, Canada
| | - Alex Vitkin
- University of Toronto, Department of Medical Biophysics, Toronto, Ontario, Canada
- University of Toronto, Department of Radiation Oncology, Toronto, Ontario, Canada
| |
Collapse
|
2
|
Tumanova K, Serra S, Majumdar A, Lad J, Quereshy F, Khorasani M, Vitkin A. Mueller matrix polarization parameters correlate with local recurrence in patients with stage III colorectal cancer. Sci Rep 2023; 13:13424. [PMID: 37591987 PMCID: PMC10435541 DOI: 10.1038/s41598-023-40480-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2023] [Accepted: 08/10/2023] [Indexed: 08/19/2023] Open
Abstract
The peri-tumoural stroma has been explored as a useful source of prognostic information in colorectal cancer. Using Mueller matrix (MM) polarized light microscopy for quantification of unstained histology slides, the current study assesses the prognostic potential of polarimetric characteristics of peri-tumoural collagenous stroma architecture in 38 human stage III colorectal cancer (CRC) patient samples. Specifically, Mueller matrix transformation and polar decomposition parameters were tested for association with 5-year patient local recurrence outcomes. The results show that some of these polarimetric parameters were significantly different (p value < 0.05) for the recurrence versus the no-recurrence patient cohorts (Mann-Whitney U test). MM parameters may thus be prognostically valuable towards improving clinical management/treatment stratification in CRC patients.
Collapse
Affiliation(s)
- Kseniia Tumanova
- Department of Medical Biophysics, University of Toronto, Toronto, Canada.
| | - Stefano Serra
- Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, Canada
| | - Anamitra Majumdar
- Department of Medical Biophysics, University of Toronto, Toronto, Canada
| | - Jigar Lad
- Department of Medical Biophysics, University of Toronto, Toronto, Canada
| | - Fayez Quereshy
- Department of Surgery, University of Toronto, Toronto, Canada
| | | | - Alex Vitkin
- Department of Medical Biophysics, University of Toronto, Toronto, Canada
- Division of Biophysics and Bioimaging, Princess Margaret Cancer Centre, University Health Network, Toronto, Canada
- Department of Radiation Oncology, University of Toronto, Toronto, Canada
| |
Collapse
|
3
|
Polarimetric biomarkers of peri-tumoral stroma can correlate with 5-year survival in patients with left-sided colorectal cancer. Sci Rep 2022; 12:12652. [PMID: 35879367 PMCID: PMC9314438 DOI: 10.1038/s41598-022-16178-3] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2022] [Accepted: 07/06/2022] [Indexed: 12/24/2022] Open
Abstract
Using a novel variant of polarized light microscopy for high-contrast imaging and quantification of unstained histology slides, the current study assesses the prognostic potential of peri-tumoral collagenous stroma architecture in 32 human stage III colorectal cancer (CRC) patient samples. We analyze three distinct polarimetrically-derived images and their associated texture features, explore different unsupervised clustering algorithm models to group the data, and compare the resultant groupings with patient survival. The results demonstrate an appreciable total accuracy of ~ 78% with significant separation (p < 0.05) across all approaches for the binary classification of 5-year patient survival outcomes. Surviving patients preferentially belonged to Cluster 1 irrespective of model approach, suggesting similar stromal microstructural characteristics in this sub-population. The results suggest that polarimetrically-derived stromal biomarkers may possess prognostic value that could improve clinical management/treatment stratification in CRC patients.
Collapse
|
4
|
Sprenger J, Murray C, Lad J, Jones B, Thomas G, Nofech-Mozes S, Khorasani M, Vitkin A. Toward a quantitative method for estimating tumour-stroma ratio in breast cancer using polarized light microscopy. BIOMEDICAL OPTICS EXPRESS 2021; 12:3241-3252. [PMID: 34221657 PMCID: PMC8221948 DOI: 10.1364/boe.422452] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/09/2021] [Revised: 04/28/2021] [Accepted: 05/01/2021] [Indexed: 05/10/2023]
Abstract
The tumour-stroma ratio (TSR) has been explored as a useful source of prognostic information in various cancers, including colorectal, breast, and gastric. Despite research showing potential prognostic utility, its uptake into the clinic has been limited, in part due to challenges associated with subjectivity, reproducibility, and quantification. We have recently proposed a simple, robust, and quantifiable high-contrast method of imaging intra- and peri-tumoural stroma based on polarized light microscopy. Here we report on its use to quantify TSR in human breast cancer using unstained slides from 40 patient samples of invasive ductal carcinoma (IDC). Polarimetric results based on a stromal abundance metric correlated well with pathology designations, showing a statistically significant difference between high- and low-stroma samples as scored by two clinical pathologists. The described polarized light imaging methodology shows promise for use as a quantitative, automatic, and standardizable tool for quantifying TSR, potentially addressing some of the challenges associated with its current estimation.
Collapse
Affiliation(s)
- Jillian Sprenger
- Department of Medical Biophysics, University of Toronto, Toronto, Canada
| | - Ciara Murray
- Laboratory Medicine Program, University Health Network, Ontario, Canada
| | - Jigar Lad
- Department of Medical Biophysics, University of Toronto, Toronto, Canada
| | - Blake Jones
- Department of Medical Biophysics, University of Toronto, Toronto, Canada
| | - Georgia Thomas
- Department of Medical Biophysics, University of Toronto, Toronto, Canada
| | - Sharon Nofech-Mozes
- Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, Canada
| | - Mohammadali Khorasani
- Department of Surgery, University of British Columbia, Victoria, Canada
- Co-senior authors
| | - Alex Vitkin
- Department of Medical Biophysics, University of Toronto, Toronto, Canada
- Division of Biophysics and Bioimaging, Princess Margaret Cancer Centre, University Health Network, Toronto, Canada
- Department of Radiation Oncology, University of Toronto, Toronto, Canada
- Co-senior authors
| |
Collapse
|
5
|
Liu Y, Dong Y, Si L, Meng R, Dong Y, Ma H. Comparison between image texture and polarization features in histopathology. BIOMEDICAL OPTICS EXPRESS 2021; 12:1593-1608. [PMID: 33796375 PMCID: PMC7984792 DOI: 10.1364/boe.416382] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/01/2020] [Revised: 02/08/2021] [Accepted: 02/08/2021] [Indexed: 05/08/2023]
Abstract
Digital pathology has shown great importance for diagnostic purposes in the digital age by integrating basic image features into multi-modality information. We quantify the degree of correlation between the multiple texture features from H&E images and polarization parameter sets derived from Mueller matrix images of the same sample to provide more microstructural information for assisting diagnosis. The experimental result shows the correlations between texture feature and polarization parameter via Pearson coefficients. Polarization parameters t1 , DL and the depolarization parameter Δ correlated with image texture features Tamura_Fcon and Tamura_Frgh, and can be used as powerful tools to quantitatively characterize cell nuclei related with tumor progression in breast pathological tissues. Polarization parameters δ and rL associated with the image texture feature Tamura_Flin have great potential for the quantitative characterization of proliferative fibers produced by inflammation. Furthermore, polarization parameters have the advantages of stable recognition in low resolution images. This work validates the associations between image texture features and polarization parameters and the merit of polarization imaging methods in low-resolution situations.
Collapse
Affiliation(s)
- Yudi Liu
- Center for Precision Medicine and Healthcare, Tsinghua-Berkeley Shenzhen Institute, Shenzhen 518055, China
- These authors contributed equally to this work
| | - Yang Dong
- Center for Precision Medicine and Healthcare, Tsinghua-Berkeley Shenzhen Institute, Shenzhen 518055, China
- These authors contributed equally to this work
| | - Lu Si
- Center for Precision Medicine and Healthcare, Tsinghua-Berkeley Shenzhen Institute, Shenzhen 518055, China
| | - Ruoyu Meng
- Shenzhen Key Laboratory for Minimal Invasive Medical Technologies, Institute of Optical Imaging and Sensing, Graduate School at Shenzhen Tsinghua University, Shenzhen 518055, China
| | - Yanmin Dong
- Shenzhen Hospital of Traditional Chinese Medicine, Shenzhen 518034, China
| | - Hui Ma
- Center for Precision Medicine and Healthcare, Tsinghua-Berkeley Shenzhen Institute, Shenzhen 518055, China
- Shenzhen Key Laboratory for Minimal Invasive Medical Technologies, Institute of Optical Imaging and Sensing, Graduate School at Shenzhen Tsinghua University, Shenzhen 518055, China
- Department of Physics, Tsinghua University, Beijing 100084, China
| |
Collapse
|