Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade
Background: Evaluating histologic grade for breast cancer diagnosis is standard and associated with prognostic outcomes. Current challenges include the time required for manual microscopic evaluation and interobserver variability. This study proposes a computer-aided diagnostic (CAD) pipeline for gr...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Current Oncology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1718-7729/28/6/366 |
| _version_ | 1797505633058029568 |
|---|---|
| author | Andrew Lagree Audrey Shiner Marie Angeli Alera Lauren Fleshner Ethan Law Brianna Law Fang-I Lu David Dodington Sonal Gandhi Elzbieta A. Slodkowska Alex Shenfield Katarzyna J. Jerzak Ali Sadeghi-Naini William T. Tran |
| author_facet | Andrew Lagree Audrey Shiner Marie Angeli Alera Lauren Fleshner Ethan Law Brianna Law Fang-I Lu David Dodington Sonal Gandhi Elzbieta A. Slodkowska Alex Shenfield Katarzyna J. Jerzak Ali Sadeghi-Naini William T. Tran |
| author_sort | Andrew Lagree |
| collection | DOAJ |
| description | Background: Evaluating histologic grade for breast cancer diagnosis is standard and associated with prognostic outcomes. Current challenges include the time required for manual microscopic evaluation and interobserver variability. This study proposes a computer-aided diagnostic (CAD) pipeline for grading tumors using artificial intelligence. Methods: There were 138 patients included in this retrospective study. Breast core biopsy slides were prepared using standard laboratory techniques, digitized, and pre-processed for analysis. Deep convolutional neural networks (CNNs) were developed to identify the regions of interest containing malignant cells and to segment tumor nuclei. Imaging-based features associated with spatial parameters were extracted from the segmented regions of interest (ROIs). Clinical datasets and pathologic biomarkers (estrogen receptor, progesterone receptor, and human epidermal growth factor 2) were collected from all study subjects. Pathologic, clinical, and imaging-based features were input into machine learning (ML) models to classify histologic grade, and model performances were tested against ground-truth labels at the patient-level. Classification performances were evaluated using receiver-operating characteristic (ROC) analysis. Results: Multiparametric feature sets, containing both clinical and imaging-based features, demonstrated high classification performance. Using imaging-derived markers alone, the classification performance demonstrated an area under the curve (AUC) of 0.745, while modeling these features with other pathologic biomarkers yielded an AUC of 0.836. Conclusion: These results demonstrate an association between tumor nuclear spatial features and tumor grade. If further validated, these systems may be implemented into pathology CADs and can assist pathologists to expeditiously grade tumors at the time of diagnosis and to help guide clinical decisions. |
| first_indexed | 2024-03-10T04:21:24Z |
| format | Article |
| id | doaj.art-e432955289cb4ecdacbc77ecf0a36083 |
| institution | Directory Open Access Journal |
| issn | 1198-0052 1718-7729 |
| language | English |
| last_indexed | 2024-03-10T04:21:24Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Current Oncology |
| spelling | doaj.art-e432955289cb4ecdacbc77ecf0a360832023-11-23T07:50:04ZengMDPI AGCurrent Oncology1198-00521718-77292021-10-012864298431610.3390/curroncol28060366Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic GradeAndrew Lagree0Audrey Shiner1Marie Angeli Alera2Lauren Fleshner3Ethan Law4Brianna Law5Fang-I Lu6David Dodington7Sonal Gandhi8Elzbieta A. Slodkowska9Alex Shenfield10Katarzyna J. Jerzak11Ali Sadeghi-Naini12William T. Tran13Department of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaDepartment of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaDepartment of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaDepartment of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaDepartment of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaDepartment of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaRadiogenomics Laboratory, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaDepartment of Laboratory Medicine and Molecular Diagnostics, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaRadiogenomics Laboratory, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaDepartment of Laboratory Medicine and Molecular Diagnostics, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaDepartment of Engineering and Mathematics, Sheffield Hallam University, Howard St, Sheffield S1 1WB, UKDivision of Medical Oncology, Department of Medicine, University of Toronto, Toronto, ON M5S 3H2, CanadaDepartment of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaDepartment of Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, CanadaBackground: Evaluating histologic grade for breast cancer diagnosis is standard and associated with prognostic outcomes. Current challenges include the time required for manual microscopic evaluation and interobserver variability. This study proposes a computer-aided diagnostic (CAD) pipeline for grading tumors using artificial intelligence. Methods: There were 138 patients included in this retrospective study. Breast core biopsy slides were prepared using standard laboratory techniques, digitized, and pre-processed for analysis. Deep convolutional neural networks (CNNs) were developed to identify the regions of interest containing malignant cells and to segment tumor nuclei. Imaging-based features associated with spatial parameters were extracted from the segmented regions of interest (ROIs). Clinical datasets and pathologic biomarkers (estrogen receptor, progesterone receptor, and human epidermal growth factor 2) were collected from all study subjects. Pathologic, clinical, and imaging-based features were input into machine learning (ML) models to classify histologic grade, and model performances were tested against ground-truth labels at the patient-level. Classification performances were evaluated using receiver-operating characteristic (ROC) analysis. Results: Multiparametric feature sets, containing both clinical and imaging-based features, demonstrated high classification performance. Using imaging-derived markers alone, the classification performance demonstrated an area under the curve (AUC) of 0.745, while modeling these features with other pathologic biomarkers yielded an AUC of 0.836. Conclusion: These results demonstrate an association between tumor nuclear spatial features and tumor grade. If further validated, these systems may be implemented into pathology CADs and can assist pathologists to expeditiously grade tumors at the time of diagnosis and to help guide clinical decisions.https://www.mdpi.com/1718-7729/28/6/366breast cancerNottingham gradetumorbiopsyimaging biomarkerscomputational oncology |
| spellingShingle | Andrew Lagree Audrey Shiner Marie Angeli Alera Lauren Fleshner Ethan Law Brianna Law Fang-I Lu David Dodington Sonal Gandhi Elzbieta A. Slodkowska Alex Shenfield Katarzyna J. Jerzak Ali Sadeghi-Naini William T. Tran Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade Current Oncology breast cancer Nottingham grade tumor biopsy imaging biomarkers computational oncology |
| title | Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade |
| title_full | Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade |
| title_fullStr | Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade |
| title_full_unstemmed | Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade |
| title_short | Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade |
| title_sort | assessment of digital pathology imaging biomarkers associated with breast cancer histologic grade |
| topic | breast cancer Nottingham grade tumor biopsy imaging biomarkers computational oncology |
| url | https://www.mdpi.com/1718-7729/28/6/366 |
| work_keys_str_mv | AT andrewlagree assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT audreyshiner assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT marieangelialera assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT laurenfleshner assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT ethanlaw assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT briannalaw assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT fangilu assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT daviddodington assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT sonalgandhi assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT elzbietaaslodkowska assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT alexshenfield assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT katarzynajjerzak assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT alisadeghinaini assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade AT williamttran assessmentofdigitalpathologyimagingbiomarkersassociatedwithbreastcancerhistologicgrade |