A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Domain-specific transfer learning in the automated scoring of tumor-stroma ratio from histopathological images of colorectal cancer (2023)

Petäinen, L., Väyrynen, J. P., Ruusuvuori, P., Pölönen, I., Äyrämö, S., & Kuopio, T. (2023). Domain-specific transfer learning in the automated scoring of tumor-stroma ratio from histopathological images of colorectal cancer. PLoS ONE, 18(5), Article e0286270. https://doi.org/10.1371/journal.pone.0286270

JYU-tekijät tai -toimittajat

Petäinen, Liisa
Pölönen, Ilkka
Äyrämö, Sami
Kuopio, Teijo

Julkaisun tiedot

Julkaisun kaikki tekijät tai toimittajat: Petäinen, Liisa; Väyrynen, Juha P.; Ruusuvuori, Pekka; Pölönen, Ilkka; Äyrämö, Sami; Kuopio, Teijo

Lehti tai sarja: PLoS ONE

eISSN: 1932-6203

Julkaisuvuosi: 2023

Ilmestymispäivä: 26.05.2023

Volyymi: 18

Lehden numero: 5

Artikkelinumero: e0286270

Kustantaja: Public Library of Science (PLoS)

Julkaisumaa: Yhdysvallat (USA)

Julkaisun kieli: englanti

DOI: https://doi.org/10.1371/journal.pone.0286270

Linkki tutkimusaineistoon:  10.17632/37t2d6xmy2.1

Julkaisun avoin saatavuus: Avoimesti saatavilla

Julkaisukanavan avoin saatavuus: Kokonaan avoin julkaisukanava

Julkaisu on rinnakkaistallennettu (JYX): https://jyx.jyu.fi/handle/123456789/87316

Tiivistelmä

Tumor-stroma ratio (TSR) is a prognostic factor for many types of solid tumors. In this study, we propose a method for automated estimation of TSR from histopathological images of colorectal cancer. The method is based on convolutional neural networks which were trained to classify colorectal cancer tissue in hematoxylin-eosin stained samples into three classes: stroma, tumor and other. The models were trained using a data set that consists of 1343 whole slide images. Three different training setups were applied with a transfer learning approach using domain-specific data i.e. an external colorectal cancer histopathological data set. The three most accurate models were chosen as a classifier, TSR values were predicted and the results were compared to a visual TSR estimation made by a pathologist. The results suggest that classification accuracy does not improve when domain-specific data are used in the pre-training of the convolutional neural network models in the task at hand. Classification accuracy for stroma, tumor and other reached 96.1% on an independent test set. Among the three classes the best model gained the highest accuracy (99.3%) for class tumor. When TSR was predicted with the best model, the correlation between the predicted values and values estimated by an experienced pathologist was 0.57. Further research is needed to study associations between computationally predicted TSR values and other clinicopathological factors of colorectal cancer and the overall survival of the patients.

YSO-asiasanat: koneoppiminen; suolistosyövät; syöpätaudit; neuroverkot; ennusteet

Vapaat asiasanat: colorectal cancer; machine learning; cancers and neoplasms; smooth muscles; vision; neural networks; malignant tumors; forecasting

Liittyvät organisaatiot

Hankkeet, joissa julkaisu on tehty

OKM-raportointi: Kyllä

Raportointivuosi: 2023

JUFO-taso: 1