Domain-specific transfer learning in the automated scoring of tumor-stroma ratio from histopathological images of colorectal cancer
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
Published inPLoS ONE
DisciplineComputing, Information Technology and MathematicsTietotekniikkaHuman and Machine based Intelligence in LearningSolu- ja molekyylibiologiaLaskennallinen tiedeHyvinvoinnin tutkimuksen yhteisöComputing, Information Technology and MathematicsMathematical Information TechnologyHuman and Machine based Intelligence in LearningCell and Molecular BiologyComputational ScienceSchool of Wellbeing
© 2023 Petäinen et al.
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. ...
PublisherPublic Library of Science (PLoS)
Dataset(s) related to the publication10.17632/37t2d6xmy2.1
Publication in research information system
MetadataShow full item record
Related funder(s)Council of Tampere Region
Funding program(s)ERDF European Regional Development Fund, React-EU
Additional information about fundingThis study is one part of AI Hub Central Finland project that has received funding from the Council of Tampere Region (https://www. pirkanmaa.fi/en/) (Decision number: A75000) and Leverage from the EU 2014–2020, funded by European Regional Development Fund (ERDF) (https://ec.europa.eu/regional_policy/funding/erdf_ en).
Showing items with similar title or keywords.
The potential of convolutional neural network in the evaluation of tumor-stroma ratio from colorectal cancer histopathological images Petäinen, Liisa (2022)Tässä Pro gradu-työssä tutkitaan konvoluutioneuroverkkojen käyttömahdollisuuksia histopatologisista kuvista tehtävässä kasvain-strooma suhdeluvun arvioinnissa. Tarkoituksena on selvittää, mikä on siirto-opettamisen vaikutus, ...
Domain‐specific neural networks improve automated bird sound recognition already with small amount of local data Lauha, Patrik; Somervuo, Panu; Lehikoinen, Petteri; Geres, Lisa; Richter, Tobias; Seibold, Sebastian; Ovaskainen, Otso (Wiley-Blackwell, 2022)An automatic bird sound recognition system is a useful tool for collecting data of different bird species for ecological analysis. Together with autonomous recording units (ARUs), such a system provides a possibility to ...
Differentiating Malignant from Benign for Melanocytic and Non-melanocytic Skin Tumors : A Pilot Study on Hyperspectral Imaging and Convolutional Neural Networks Lindholm, Vivian; Raita-Hakola, Anna-Maria; Annala, Leevi; Salmivuori, Mari; Jeskanen, Leila; Koskenmies, Sari; Pitkänen, Sari; Saari, Heikki; Pölönen, Ilkka; Isoherranen, Kirsi; Ranki, Annamari (Society for Publication of Acta Dermato-Venereologica, 2022)
Differentiating Malignant from Benign Pigmented or Non-Pigmented Skin Tumours : A Pilot Study on 3D Hyperspectral Imaging of Complex Skin Surfaces and Convolutional Neural Networks Lindholm, Vivian; Raita-Hakola, Anna-Maria; Annala, Leevi; Salmivuori, Mari; Jeskanen, Leila; Saari, Heikki; Koskenmies, Sari; Pitkänen, Sari; Pölönen, Ilkka; Isoherranen, Kirsi; Ranki, Annamari (MDPI AG, 2022)Several optical imaging techniques have been developed to ease the burden of skin cancer disease on our health care system. Hyperspectral images can be used to identify biological tissues by their diffuse reflected spectra. ...
Pölönen, Ilkka; Rahkonen, Samuli; Annala, Leevi; Neittaanmäki, Noora (SPIE, The International Society for Optical Engineering, 2019)Skin cancers are world wide deathly health problem, where significant life and cost savings could be achieved if detection of cancer can be done in early phase. Hypespectral imaging is prominent tool for non-invasive ...