Ki-67 evaluation using deep-learning model-assisted digital image analysis in breast cancer

被引:0
作者
Matsumoto, Hirofumi [1 ]
Miyata, Ryota [2 ]
Tsuruta, Yuma [1 ]
Nakada, Norihiro [1 ]
Koki, Ayako [3 ]
Unesoko, Mikiko [3 ]
Abe, Norie [3 ]
Zaha, Hisamitsu [3 ]
机构
[1] Nakagami Hosp, Dept Pathol, 610 Noborikawa, Okinawa, Okinawa 9042195, Japan
[2] Univ Ryukyus, Fac Engn, Okinawa, Japan
[3] Nakagami Hosp, Dept Breast Surg, Okinawa, Japan
关键词
breast cancer; deep learning; digital image analysis; Ki-67; INTERNATIONAL KI67; AMERICAN SOCIETY; PROGNOSTIC VALUE; WOMEN; RECOMMENDATIONS; CONSENSUS; THERAPY;
D O I
10.1111/his.15356
中图分类号
Q2 [细胞生物学];
学科分类号
071009 ; 090102 ;
摘要
AimsTo test the efficacy of artificial intelligence (AI)-assisted Ki-67 digital image analysis in invasive breast carcinoma (IBC) with quantitative assessment of AI model performance.Methods and ResultsThis study used 494 cases of Ki-67 slide images of IBC core needle biopsies. The methods were divided into two steps: (i) construction of a deep-learning model (DL); and (ii) DL implementation for Ki-67 analysis. First, a DL tissue classifier model (DL-TC) and a DL nuclear detection model (DL-ND) were constructed using HALO AI DenseNet V2 algorithm with 31,924 annotations in 300 Ki-67 digital slide images. Whether the class predicted by DL-TC in the test set was correct compared with the annotation of ground truth at the pixel level was evaluated. Second, DL-TC- and DL-ND-assisted digital image analysis (DL-DIA) was performed in the other 194 luminal-type cases and correlations with manual counting and clinical outcome were investigated to confirm the accuracy and prognostic potential of DL-DIA. The performance of DL-TC was excellent and invasive carcinoma nests were well segmented from other elements (average precision: 0.851; recall: 0.878; F1-score: 0.858). Ki-67 index data and the number of nuclei from DL-DIA were positively correlated with data from manual counting (rho = 0.961, and 0.928, respectively). High Ki-67 index (cutoff 20%) cases showed significantly worse recurrence-free survival and breast cancer-specific survival (P = 0.024, and 0.032, respectively).ConclusionThe performances of DL-TC and DL-ND were excellent. DL-DIA demonstrated a high degree of concordance with manual counting of Ki-67 and the results of this approach have prognostic potential.
引用
收藏
页码:460 / 471
页数:12
相关论文
共 23 条
[1]   Noninferiority of Artificial IntelligenceeAssisted Analysis of Ki-67 and Estrogen/Progesterone Receptor in Breast Cancer Routine Diagnostics [J].
Abele, Niklas ;
Tiemann, Katharina ;
Krech, Till ;
Wellmann, Axel ;
Schaaf, Christian ;
Laenger, Florian ;
Peters, Anja ;
Donner, Andreas ;
Keil, Felix ;
Daifalla, Khalid ;
Mackens, Marina ;
Mamilos, Andreas ;
Minin, Evgeny ;
Kruemmelbein, Michel ;
Krause, Linda ;
Stark, Maria ;
Zapf, Antonia ;
Paepper, Marc ;
Hartmann, Arndt ;
Lang, Tobias .
MODERN PATHOLOGY, 2023, 36 (03)
[2]   Prognostic value of automated KI67 scoring in breast cancer: a centralised evaluation of 8088 patients from 10 study groups [J].
Abubakar, Mustapha ;
Orr, Nick ;
Daley, Frances ;
Coulson, Penny ;
Ali, H. Raza ;
Blows, Fiona ;
Benitez, Javier ;
Milne, Roger ;
Brenner, Herman ;
Stegmaier, Christa ;
Mannermaa, Arto ;
Chang-Claude, Jenny ;
Rudolph, Anja ;
Sinn, Peter ;
Couch, Fergus J. ;
Devilee, Peter ;
Tollenaar, Rob A. E. M. ;
Seynaeve, Caroline ;
Figueroa, Jonine ;
Sherman, Mark E. ;
Lissowska, Jolanta ;
Hewitt, Stephen ;
Eccles, Diana ;
Hooning, Maartje J. ;
Hollestelle, Antoinette ;
Martens, John W. M. ;
van Deurzen, Carolien H. M. ;
Bolla, Manjeet K. ;
Wang, Qin ;
Jones, Michael ;
Schoemaker, Minouk ;
Wesseling, Jelle ;
van Leeuwen, Flora E. ;
Van 't Veer, Laura ;
Easton, Douglas ;
Swerdlow, Anthony J. ;
Dowsett, Mitch ;
Pharoah, Paul D. ;
Schmidt, Marjanka K. ;
Garcia-Closas, Montserrat .
BREAST CANCER RESEARCH, 2016, 18
[3]   Ki67 reproducibility using digital image analysis: an inter-platform and inter-operator study [J].
Acs, Balazs ;
Pelekanou, Vasiliki ;
Bai, Yalai ;
Martinez-Morilla, Sandra ;
Toki, Maria ;
Leung, Samuel C. Y. ;
Nielsen, Torsten O. ;
Rimm, David L. .
LABORATORY INVESTIGATION, 2019, 99 (01) :107-117
[4]   The human-in-the-loop: an evaluation of pathologists' interaction with artificial intelligence in clinical practice [J].
Boden, Anna C. S. ;
Molin, Jesper ;
Garvin, Stina ;
West, Rebecca A. ;
Lundstrom, Claes ;
Treanor, Darren .
HISTOPATHOLOGY, 2021, 79 (02) :210-218
[5]   Artificial intelligence and computational pathology [J].
Cui, Miao ;
Zhang, David Y. .
LABORATORY INVESTIGATION, 2021, 101 (04) :412-422
[6]   Assessment of Ki67 in Breast Cancer: Recommendations from the International Ki67 in Breast Cancer Working Group [J].
Dowsett, Mitch ;
Nielsen, Torsten O. ;
A'Hern, Roger ;
Bartlett, John ;
Coombes, R. Charles ;
Cuzick, Jack ;
Ellis, Matthew ;
Henry, N. Lynn ;
Hugh, Judith C. ;
Lively, Tracy ;
McShane, Lisa ;
Paik, Soon ;
Penault-Llorca, Frederique ;
Prudkin, Ljudmila ;
Regan, Meredith ;
Salter, Janine ;
Sotiriou, Christos ;
Smith, Ian E. ;
Viale, Giuseppe ;
Zujewski, Jo Anne ;
Hayes, Daniel F. .
JNCI-JOURNAL OF THE NATIONAL CANCER INSTITUTE, 2011, 103 (22) :1656-1664
[7]   Personalizing the treatment of women with early breast cancer: highlights of the St Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2013 [J].
Goldhirsch, A. ;
Winer, E. P. ;
Coates, A. S. ;
Gelber, R. D. ;
Piccart-Gebhart, M. ;
Thuerlimann, B. ;
Senn, H. -J. .
ANNALS OF ONCOLOGY, 2013, 24 (09) :2206-2223
[8]   Use of Biomarkers to Guide Decisions on Adjuvant Systemic Therapy for Women With Early-Stage Invasive Breast Cancer: American Society of Clinical Oncology Clinical Practice Guideline [J].
Harris, Lyndsay N. ;
Ismaila, Nofisat ;
McShane, Lisa M. ;
Andre, Fabrice ;
Collyar, Deborah E. ;
Gonzalez-Angulo, Ana M. ;
Hammond, Elizabeth H. ;
Kuderer, Nicole M. ;
Liu, Minetta C. ;
Mennel, Robert G. ;
Van Poznak, Catherine ;
Bast, Robert C. ;
Hayes, Daniel F. .
JOURNAL OF CLINICAL ONCOLOGY, 2016, 34 (10) :1134-+
[9]   Automated assessment of Ki-67 in breast cancer: the utility of digital image analysis using virtual triple staining and whole slide imaging [J].
Hida, Akira, I ;
Omanovic, Dzenita ;
Pedersen, Lars ;
Oshiro, Yumi ;
Ogura, Takashi ;
Nomura, Tsunehisa ;
Kurebayashi, Junichi ;
Kanomata, Naoki ;
Moriya, Takuya .
HISTOPATHOLOGY, 2020, 77 (03) :471-480
[10]   Investigation of the freely available easy-to-use software 'EZR' for medical statistics [J].
Kanda, Y. .
BONE MARROW TRANSPLANTATION, 2013, 48 (03) :452-458