EUVIMEDEUVIMED entdecken
Crossref

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

Hirofumi Matsumoto iD, Ryota Miyata, Yuma Tsuruta, Norihiro Nakada, Ayako Koki, Mikiko Unesoko, Norie Abe, Hisamitsu Zaha

Histopathology · 2025

DOI: 10.1111/his.15356 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Histopathology, 2025. Verfasst von Hirofumi Matsumoto und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, Nakagami Hospital, Okinawa, Japan. Hauptthemen laut MEDLINE: Breast Neoplasms, Ki-67 Antigen, Deep Learning. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 22 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

To 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 Results This 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 ( ρ = 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).

Conclusion

The 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsKi-67 AntigenDeep LearningHumansFemaleMiddle AgedAgedAdultBiomarkers, TumorImage Processing, Computer-AssistedImage Interpretation, Computer-AssistedBiopsy, Large-Core NeedleAged, 80 and over

Stichwörter der Autor:innen

Ki‐67breast cancerdeep learningdigital image analysis

Substanzen

Ki-67 AntigenBiomarkers, Tumor

Autor:innen und Institutionen

  • Department of Pathology, Nakagami Hospital, Okinawa, Japan.
  • Faculty of Engineering, University of the Ryukyus, Okinawa, Japan.
  • Department of Breast Surgery, Nakagami Hospital, Okinawa, Japan.

ORCID-Profile: Hirofumi Matsumoto

Zitieren

APA

Matsumoto, H., Miyata, R., Tsuruta, Y., Nakada, N., Koki, A., Unesoko, M., Abe, N., & Zaha, H. (2025). Ki‐67 evaluation using deep‐learning model‐assisted digital image analysis in breast cancer. Histopathology. https://doi.org/10.1111/his.15356

Vancouver

Matsumoto H, Miyata R, Tsuruta Y, Nakada N, Koki A, Unesoko M, et al. Ki‐67 evaluation using deep‐learning model‐assisted digital image analysis in breast cancer. Histopathology. 2025. doi:10.1111/his.15356

BibTeX
@article{Matsumoto2025,
  author = {Matsumoto, Hirofumi and Miyata, Ryota and Tsuruta, Yuma and Nakada, Norihiro and Koki, Ayako and Unesoko, Mikiko and Abe, Norie and Zaha, Hisamitsu},
  title = {Ki‐67 evaluation using deep‐learning model‐assisted digital image analysis in breast cancer},
  journal = {Histopathology},
  year = {2025},
  doi = {10.1111/his.15356}
}
Kostenlos starten →