Search

• We propose deep learning models for classification of cancer cells belonging to different organs on holographic images. • We present self-supervised pretraining and hyperparameter tuning for efficient training on biomedical holographic datasets. • Perform extensive experiments with self-supervised frameworks and compared self-supervised learning with supervised learning and proved the effectiveness of the former for holographic images classification. • Proposed work can be an effective tool for the automatic classification of cancer cells for medical diagnosis using self-supervised learning. Image-based stain-free elliptical cancer cell classification is challenging, due to the inter-class morphological similarity. In this paper, we address the classification of different types of cancer cell lines (lung, breast, bladder, and skin) by utilizing self-supervised learning, and compare it with supervised learning based on convolutional neural network. Digital holography in a microscopic configuration was used to obtain stain-free quantitative phase images representing the intracellular content and morphology of cells. The performance of self-supervised learning in natural images shows promising results, and consistently closes the gap between self-supervised and supervised learning. The ability of self-supervised learning to effectively utilize unlabeled data for training is instrumental in the biomedical domain, where labeled data is scarce. Our goal is to study different self-supervised frameworks of biomedical holographic data, and determine how they can be utilized to advance liquid biopsy for the detection of cancer cells. After extensive experimentation, we conclude that self-supervised learning improves the classification performance on cancer cell datasets, and outperforms supervised learning when training data is limited, which is mostly the case in biomedical imaging. [ABSTRACT FROM AUTHOR]

Worldwide, the second-highest mortality rate is caused by breast cancer (BC). The most studied BC cell line is MCF-7 because it exhibits strong consistency with clinical cases and is a good system for analyzing tumors with functional estrogen receptors (ER-positive cancers). In this paper, we introduce the first theoretical method for describing PTEN-loss-induced cellular senescence (PICS), which is an increase in cellular senescence caused by PTEN knockout, utilizing a logical model of the G2/M checkpoint. We predict that PTEN expression acts as a switch between cell phenotypes associated with senescence and apoptosis. We show that PICS is induced by the activity of the positive feedback between AKT and mTORC2, and that overexpression of PTEN will disrupt the feedback, abrogating senescence and only leading to arrest or apoptosis. Furthermore, we demonstrate that miR-21 can be used as a target against proliferation control because its knockout is equivalent to PTEN overexpression. We think the findings can be used to motivate new strategies for MCF-7 strain proliferation control. [ABSTRACT FROM AUTHOR]