학술논문
Analytical Validation of the PreciseDx Digital Prognostic Breast Cancer Test in Early-Stage Breast Cancer.
Document Type
Academic Journal
Author
Fernandez G; PreciseDx, New York, NY; Icahn School of Medicine at Mount Sinai, New York, NY.; Zeineh J; PreciseDx, New York, NY.; Prastawa M; PreciseDx, New York, NY.; Scott R; PreciseDx, New York, NY.; Madduri AS; PreciseDx, New York, NY; Icahn School of Medicine at Mount Sinai, New York, NY.; Shtabsky A; PreciseDx, New York, NY.; Jaffer S; Lenox Hill Hospital, New York, NY.; Feliz A; PreciseDx, New York, NY.; Veremis B; PreciseDx, New York, NY; Icahn School of Medicine at Mount Sinai, New York, NY.; Mejias JC; PreciseDx, New York, NY.; Charytonowicz E; PreciseDx, New York, NY; Icahn School of Medicine at Mount Sinai, New York, NY.; Gladoun N; PreciseDx, New York, NY; Icahn School of Medicine at Mount Sinai, New York, NY.; Koll G; PreciseDx, New York, NY.; Cruz K; PreciseDx, New York, NY.; Malinowski D; PreciseDx, New York, NY.; Donovan MJ; PreciseDx, New York, NY; Icahn School of Medicine at Mount Sinai, New York, NY; University of Miami, Pathology, Miami, FL. Electronic address: mdonovan@precisedx.ai.
Source
Publisher: Elsevier Country of Publication: United States NLM ID: 100898731 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1938-0666 (Electronic) Linking ISSN: 15268209 NLM ISO Abbreviation: Clin Breast Cancer Subsets: MEDLINE
Subject
Language
English
Abstract
Background: PreciseDx Breast (PDxBr) is a digital test that predicts early-stage breast cancer recurrence within 6-years of diagnosis.
Materials and Methods: Using hematoxylin and eosin-stained whole slide images of invasive breast cancer (IBC) and artificial intelligence-enabled morphology feature array, microanatomic features are generated. Morphometric attributes in combination with patient's age, tumor size, stage, and lymph node status predict disease free survival using a proprietary algorithm. Here, analytical validation of the automated annotation process and extracted histologic digital features of the PDxBr test, including impact of methodologic variability on the composite risk score is presented. Studies of precision, repeatability, reproducibility and interference were performed on morphology feature array-derived features. The final risk score was assessed over 20-days with 2-operators, 2-runs/day, and 2-replicates across 8-patients, allowing for calculation of within-run repeatability, between-run and within-laboratory reproducibility.
Results: Analytical validation of features derived from whole slide images demonstrated a high degree of precision for tumor segmentation (0.98, 0.98), lymphocyte detection (0.91, 0.93), and mitotic figures (0.85, 0.84). Correlation of variation of the assay risk score for both reproducibility and repeatability were less than 2%, and interference from variation in hematoxylin and eosin staining or tumor thickness was not observed demonstrating assay robustness across standard histopathology preparations.
Conclusion: In summary, the analytical validation of the digital IBC risk assessment test demonstrated a strong performance across all features in the model and complimented the clinical validation of the assay previously shown to accurately predict recurrence within 6-years in early-stage invasive breast cancer patients.
Competing Interests: Disclosure This study was funded by PDxBr and the authors have the following disclosures: GF, JZ, MP, RS, ASM, AS, AF, JCM, GK, DM, and KC are employees of PDxBr; BV, EC, and N are Mount Sinai employees; MJD and SJ are consultants to PDxBr.
(Copyright © 2023 The Authors. Published by Elsevier Inc. All rights reserved.)
Materials and Methods: Using hematoxylin and eosin-stained whole slide images of invasive breast cancer (IBC) and artificial intelligence-enabled morphology feature array, microanatomic features are generated. Morphometric attributes in combination with patient's age, tumor size, stage, and lymph node status predict disease free survival using a proprietary algorithm. Here, analytical validation of the automated annotation process and extracted histologic digital features of the PDxBr test, including impact of methodologic variability on the composite risk score is presented. Studies of precision, repeatability, reproducibility and interference were performed on morphology feature array-derived features. The final risk score was assessed over 20-days with 2-operators, 2-runs/day, and 2-replicates across 8-patients, allowing for calculation of within-run repeatability, between-run and within-laboratory reproducibility.
Results: Analytical validation of features derived from whole slide images demonstrated a high degree of precision for tumor segmentation (0.98, 0.98), lymphocyte detection (0.91, 0.93), and mitotic figures (0.85, 0.84). Correlation of variation of the assay risk score for both reproducibility and repeatability were less than 2%, and interference from variation in hematoxylin and eosin staining or tumor thickness was not observed demonstrating assay robustness across standard histopathology preparations.
Conclusion: In summary, the analytical validation of the digital IBC risk assessment test demonstrated a strong performance across all features in the model and complimented the clinical validation of the assay previously shown to accurately predict recurrence within 6-years in early-stage invasive breast cancer patients.
Competing Interests: Disclosure This study was funded by PDxBr and the authors have the following disclosures: GF, JZ, MP, RS, ASM, AS, AF, JCM, GK, DM, and KC are employees of PDxBr; BV, EC, and N are Mount Sinai employees; MJD and SJ are consultants to PDxBr.
(Copyright © 2023 The Authors. Published by Elsevier Inc. All rights reserved.)