Deep Learning and Transfer Learning for Automatic Cell Counting in Microscope Images of Human Cancer Cell Lines
Open Access
- 27 May 2021
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 11 (11) , 4912
Abstract
In biology and medicine, cell counting is one of the most important elements of cytometry, with applications to research and clinical practice. For instance, the complete cell count could help to determine conditions for which cancer cells could grow or not. However, cell counting is a laborious and time-consuming process, and its automatization is highly demanded. Here, we propose use of a Convolutional Neural Network-based regressor, a regression model trained end-to-end, to provide the cell count. First, unlike most of the related work, we formulate the problem of cell counting as the regression task rather than the classification task. This allows not only to reduce the required annotation information (i.e., the number of cells instead of pixel-level annotations) but also to reduce the burden of segmenting potential cells and then classifying them. Second, we propose use of xResNet, a successful convolutional architecture with residual connection, together with transfer learning (using a pretrained model) to achieve human-level performance. We demonstrate the performance of our approach to real-life data of two cell lines, human osteosarcoma and human leukemia, collected at the University of Amsterdam (133 training images, and 32 test images). We show that the proposed method (deep learning and transfer learning) outperforms currently used machine learning methods. It achieves the test mean absolute error equal 12 (±15) against 32 (±33) obtained by the deep learning without transfer learning, and 41 (±37) of the best-performing machine learning pipeline (Random Forest Regression with the Histogram of Gradients features).Keywords
Funding Information
- Polish Ministry of Science and Higher Education (1639/MOB/V/2017/0)
This publication has 62 references indexed in Scilit:
- A systematic RNAi synthetic interaction screen reveals a link between p53 and snoRNP assemblyNature Cell Biology, 2011
- The microbial content of unexpired pasteurized milk from selected supermarkets in a developing countryAsian Pacific Journal of Tropical Biomedicine, 2011
- Eyes Wide Open: A Critical Review of Sphere-Formation as an Assay for Stem CellsCell Stem Cell, 2011
- Neural-Colony Forming Cell Assay: An Assay To Discriminate Bona Fide Neural Stem Cells from Neural Progenitor CellsJournal of Visualized Experiments, 2011
- Preferential tumour accumulation of gold nanoparticles, visualised by magnetic resonance imaging: Radiosensitisation studies in vivo and in vitroInternational Journal of Radiation Biology, 2010
- In vitro evaluation of cellular responses induced by stable fullerene C60 medium dispersionThe Journal of Biochemistry, 2010
- Tocotrienols induce apoptosis in breast cancer cell lines via an endoplasmic reticulum stress-dependent increase in extrinsic death receptor signalingBreast Cancer Research and Treatment, 2010
- Greedy function approximation: A gradient boosting machine.The Annals of Statistics, 2001
- Spontaneous megakaryocyte colony formation in myeloproliferative disorders is not neutralizable by antibodies against IL3, IL6 and GM‐CSFBritish Journal of Haematology, 1994
- Ridge Regression: Biased Estimation for Nonorthogonal ProblemsTechnometrics, 1970