Artificial Intelligence-Based Mitosis Scoring in Breast Cancer: Clinical Application

被引：9

作者：

Ibrahim, Asmaa ^{[1
,2
]}

Jahanifar, Mostafa ^{[3
]}

Wahab, Noorul ^{[3
]}

Toss, Michael S. ^{[1
,4
]}

Makhlouf, Shorouk ^{[1
]}

Atallah, Nehal ^{[1
]}

Lashen, Ayat G. ^{[1
]}

Katayama, Ayaka ^{[1
]}

Graham, Simon ^{[3
]}

Bilal, Mohsin ^{[3
]}

Bhalerao, Abhir ^{[3
]}

Raza, Shan E. Ahmed ^{[3
]}

Snead, David ^{[5
,6
]}

Minhas, Fayyaz ^{[3
]}

Rajpoot, Nasir ^{[3
]}

Rakha, Emad ^{[1
,7
,8
]}

机构：

[1] Univ Nottingham, Sch Med, Acad Unit Translat Med Sci, Nottingham, England

[2] Suez Canal Univ, Fac Med, Dept Pathol, Ismailia, Egypt

[3] Univ Warwick, Tissue Image Analyt Ctr, Coventry, England

[4] Royal Hallamshire Hosp, Sheffield Teaching Hosp, NHS Fdn Trust, Histopathol Dept, Sheffield, England

[5] Univ Hosp Coventry, Cellular Pathol, Coventry, England

[6] Warwickshire NHS Trust, Bedworth, England

[7] Nottingham Univ Hosp NHS Trust, Nottingham, England

[8] Hamad Med Corp, Pathol Dept, Doha, Qatar

来源：

MODERN PATHOLOGY | 2024年 / 37卷 / 03期

关键词：

algorithm; artificial intelligence; mitosis; MITOTIC-ACTIVITY; PROGNOSTIC-SIGNIFICANCE; GENOME BROWSER; PROLIFERATION; TISSUE; EXPRESSION; TUMORS; CANINE; COUNT;

D O I：

10.1016/j.modpat.2023.100416

中图分类号：

R36 [病理学];

学科分类号：

100104 ;

摘要：

In recent years, artificial intelligence (AI) has demonstrated exceptional performance in mitosis identification and quantification. However, the implementation of AI in clinical practice needs to be evaluated against the existing methods. This study is aimed at assessing the optimal method of using AI-based mitotic figure scoring in breast cancer (BC). We utilized whole slide images from a large cohort of BC with extended follow-up comprising a discovery (n = 1715) and a validation (n = 859) set (Nottingham cohort). The Cancer Genome Atlas of breast invasive carcinoma (TCGA-BRCA) cohort (n = 757) was used as an external test set. Employing automated mitosis detection, the mitotic count was assessed using 3 different methods, the mitotic count per tumor area (MCT; calculated by dividing the number of mitotic figures by the total tumor area), the mitotic index (MI; defined as the average number of mitotic figures per 1000 malignant cells), and the mitotic activity index (MAI; defined as the number of mitotic figures in 3 mm(2) area within the mitotic hotspot). These automated metrics were evaluated and compared based on their correlation with the wellestablished visual scoring method of the Nottingham grading system and Ki67 score, clinicopathologic parameters, and patient outcomes. AI-based mitotic scores derived from the 3 methods (MCT, MI, and MAI) were significantly correlated with the clinicopathologic characteristics and patient survival (P < .001). However, the mitotic counts and the derived cutoffs varied significantly between the 3 methods. Only MAI and MCT were positively correlated with the gold standard visual scoring method used in Nottingham grading system (r = 0.8 and r = 0.7, respectively) and Ki67 scores (r = 0.69 and r = 0.55, respectively), and MAI was the only independent predictor of survival (P < .05) in multivariate Cox regression analysis. For clinical applications, the optimum method of scoring mitosis using AI needs to be considered. MAI can provide reliable and reproducible results and can accurately quantify mitotic figures in BC. (c) 2023 THE AUTHORS. Published by Elsevier Inc. on behalf of the United States & Canadian Academy of Pathology.

引用

页数：12

共 56 条

[11]

Davenport Thomas, 2019, Future Healthc J, V6, P94, DOI [10.2139/ssrn.3525037, 10.7861/futurehosp.6-2-94, 10.7861/futurehosp.6-2-94]

[12] Strategies for subtypes-dealing with the diversity of breast cancer: highlights of the St Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2011 [J].