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
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
- AI Hub Keski-Suomi
- Äyrämö, Sami
- Pirkanmaan liitto
OKM-raportointi: Kyllä
Raportointivuosi: 2023
JUFO-taso: 1
- Laskennallinen tiede (Informaatioteknologian tiedekunta IT) LASK
- Computing, Information Technology and Mathematics (Informaatioteknologian tiedekunta IT) CITM
- Hyvinvoinnin tutkimuksen yhteisö (Jyväskylän yliopisto JYU) JYU.Well
- Human and Machine based Intelligence in Learning (Informaatioteknologian tiedekunta IT) HUMBLE
- Solu- ja molekyylibiologia (Bio- ja ympäristötieteiden laitos BIOENV) SMB