Application and Comparison of Supervised Learning Strategies to Classify Polarity of Epithelial Cell Spheroids in 3D Culture

Patient-by-Patient Deep Transfer Learning for Drug-Response Profiling Using Confocal Fluorescence Microscopy of Pediatric Patient-Derived Tumor-Cell Spheroids

Image-based phenotypic drug profiling is receiving increasing attention in drug discovery and precision medicine. Compared to classical end-point measurements quantifying drug response, image-based profiling enables both the quantification of drug response and characterization of disease entities and drug-induced cell-death phenotypes. Here, we aim to quantify image-based drug responses in patient-derived 3D spheroid tumor cell cultures, tackling the challenges of a lack of single-cell-segmentation methods and limited patient-derived material. Therefore, we investigate deep transfer learning with patient-by-patient fine-tuning for cell-viability quantification. We fine-tune a convolutional neural network (pre-trained on ImageNet) with 210 control images specific to a single training cell line and 54 additional screen -specific assay control images. This method of image-based drug profiling is validated on 6 cell lines with known drug sensitivities, and further tested with primary patient-derived samples in a medium-throughput setting. Network outputs at different drug concentrations are used for drug-sensitivity scoring, and dense-layer activations are used in t-distributed stochastic neighbor embeddings of drugs to visualize groups of drugs with similar cell-death phenotypes. Image-based cell-line experiments show strong correlation to metabolic results ( R ≈ 0.7 ) and confirm expected hits, indicating the predictive power of deep learning to identify drug-hit candidates for individual patients. In patient-derived samples, combining drug sensitivity scoring with phenotypic analysis may provide opportunities for complementary combination treatments. Deep transfer learning with patient-by-patient fine-tuning is a promising, segmentation-free image-analysis approach for precision medicine and drug discovery.

Machine learning-based detection of label-free cancer stem-like cell fate

The detection of cancer stem-like cells (CSCs) is mainly based on molecular markers or functional tests giving a posteriori results. Therefore label-free and real-time detection of single CSCs remains a difficult challenge. The recent development of microfluidics has made it possible to perform high-throughput single cell imaging under controlled conditions and geometries. Such a throughput requires adapted image analysis pipelines while providing the necessary amount of data for the development of machine-learning algorithms. In this paper, we provide a data-driven study to assess the complexity of brightfield time-lapses to monitor the fate of isolated cancer stem-like cells in non-adherent conditions. We combined for the first time individual cell fate and cell state temporality analysis in a unique algorithm. We show that with our experimental system and on two different primary cell lines our optimized deep learning based algorithm outperforms classical computer vision and shallow learning-based algorithms in terms of accuracy while being faster than cutting-edge convolutional neural network (CNNs). With this study, we show that tailoring our deep learning-based algorithm to the image analysis problem yields better results than pre-trained models. As a result, such a rapid and accurate CNN is compatible with the rise of high-throughput data generation and opens the door to on-the-fly CSC fate analysis.

Primary URECs: a source to better understand the pathology of renal tubular epithelia in pediatric hereditary cystic kidney diseases

Background

In pediatric hereditary cystic kidney diseases, epithelial cell defects mostly result from rare, autosomal recessively inherited pathogenic variants in genes encoding proteins of the cilia-centrosome complex. Consequences of individual gene variants on epithelial function are often difficult to predict and can furthermore depend on the patient’s genetic background. Here, we studied urine-derived renal tubular epithelial cells (URECs) from genetically determined, pediatric cohorts of different hereditary cystic kidney diseases, comprising autosomal recessive polycystic kidney disease, nephronophthisis (NPH) and the Bardet Biedl syndrome (BBS). UREC characteristics and behavior in epithelial function-related 3D cell culture were compared in order to identify gene and variant-specific properties and to determine aspects of epithelial (cell) dysfunction.

Results

UREC preparations from patients (19) and healthy controls (39) were studied in a qualitative and quantitative manner using primary cells cultured for up-to 21 days. In patients with biallelic pathogenic variants in PKHD1 or NPHP genes, we were able to receive satisfactory amounts of URECs of reproducible quality. In BBS patients, UREC yield was lower and more dependent on the individual genotype. In contrast, in UREC preparations derived from healthy controls, no predictable and satisfactory outcome could be established. Considering cell proliferation, tubular origin and epithelial properties in 2D/3D culture conditions, we observed distinct and reproducible epithelial properties of URECs. In particular, the cells from patients carrying PKHD1 variants were characterized by a high incidence of defective morphogenesis of monolayered spheroids—a property proposed to be suitable for corrective intervention. Furthermore, we explored different ways to generate reference cell lines for both—patients and healthy controls—in order to eliminate restrictions in cell number and availability of primary URECs.

Conclusions

Ex vivo 3D cell culture of primary URECs represents a valuable, non-invasive source to evaluate epithelial cell function in kidney diseases and as such helps to elucidate the functional consequences of rare genetic disorders. In combination with genetically defined control cell lines to be generated in the future, the cultivation of primary URECs could become a relevant tool for testing personalized treatment of epithelial dysfunction in patients with hereditary cystic kidney disease.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13023-022-02265-1.

Modeling and Predicting the Cell Migration Properties from Scratch Wound Healing Assay on Cisplatin-Resistant Ovarian Cancer Cell Lines Using Artificial Neural Network

The study of artificial neural networks (ANN) has undergone a tremendous revolution in recent years, boosted by deep learning tools. The presence of a greater number of learning tools and their applications, in particular, favors this revolution. However, there is a significant need to deal with the issue of implementing a systematic method during the development phase of the ANN to increase its performance. A multilayer feedforward neural network (FNN) was proposed in this paper to predict the cell migration assay on cisplatin-sensitive and cisplatin-resistant (CisR) ovarian cancer (OC) cell lines via scratch wound healing assay. An FNN training algorithm model was generated using the MATLAB fitting function in a MATLAB script to accomplish this task. The input parameters were types of cell lines, times, and wound area, and outputs were relative wound area, percentage of wound closure, and wound healing speed. In addition, we tested and compared the initial accuracy of various supervised learning classifier and support vector regression (SVR) algorithms. The proposed ANN model achieved good agreement with the experimental data and minimized error between the estimated and experimental values. The conclusions drawn demonstrate that the developed ANN model is a useful, accurate, fast, and inexpensive method to predict cancerous cell migration characteristics evaluated via scratch wound healing assay.

Recent Trends and Perspectives in Cerebral Organoids Imaging and Analysis

Purpose: Since their first generation in 2013, the use of cerebral organoids has spread exponentially. Today, the amount of generated data is becoming challenging to analyze manually. This review aims to overview the current image acquisition methods and to subsequently identify the needs in image analysis tools for cerebral organoids. Methods: To address this question, we went through all recent articles published on the subject and annotated the protocols, acquisition methods, and algorithms used. Results: Over the investigated period of time, confocal microscopy and bright-field microscopy were the most used acquisition techniques. Cell counting, the most common task, is performed in 20% of the articles and area; around 12% of articles calculate morphological parameters. Image analysis on cerebral organoids is performed in majority using ImageJ software (around 52%) and Matlab language (4%). Treatments remain mostly semi-automatic. We highlight the limitations encountered in image analysis in the cerebral organoid field and suggest possible solutions and implementations to develop. Conclusions: In addition to providing an overview of cerebral organoids cultures and imaging, this work highlights the need to improve the existing image analysis methods for such images and the need for specific analysis tools. These solutions could specifically help to monitor the growth of future standardized cerebral organoids.

Deep-LUMEN assay - human lung epithelial spheroid classification from brightfield images using deep learning

Three-dimensional (3D) tissue models such as epithelial spheroids or organoids have become popular for pre-clinical drug studies. In contrast to 2D monolayer culture, the characterization of 3D tissue models from non-invasive brightfield images is a significant challenge. To address this issue, here we report a deep-learning uncovered measurement of epithelial networks (Deep-LUMEN) assay. Deep-LUMEN is an object detection algorithm that has been fine-tuned to automatically uncover subtle differences in epithelial spheroid morphology from brightfield images. This algorithm can track changes in the luminal structure of tissue spheroids and distinguish between polarized and non-polarized lung epithelial spheroids. The Deep-LUMEN assay was validated by screening for changes in spheroid epithelial architecture in response to different extracellular matrices and drug treatments. Specifically, we found the dose-dependent toxicity of cyclosporin can be underestimated if the effect of the drug on tissue morphology is not considered. Hence, Deep-LUMEN could be used to assess drug effects and capture morphological changes in 3D spheroid models in a non-invasive manner.

Fibrocystin Is Essential to Cellular Control of Adhesion and Epithelial Morphogenesis

Mutations of the Pkhd1 gene cause autosomal recessive polycystic kidney disease (ARPKD). Pkhd1 encodes fibrocystin/polyductin (FPC), a ciliary type I membrane protein of largely unknown function, suggested to affect adhesion signaling of cells. Contributions of epithelial cell adhesion and contractility to the disease process are elusive. Here, we link loss of FPC to defective epithelial morphogenesis in 3D cell culture and altered cell contact formation. We study Pkhd1-silenced Madin-Darby Canine Kidney II (MDCKII) cells using an epithelial morphogenesis assay based on micropatterned glass coverslips. The assay allows analysis of cell adhesion, polarity and lumen formation of epithelial spheroids. Pkhd1 silencing critically affects the initial phase of the morphogenesis assay, leading to a reduction of correctly polarized spheroids by two thirds. Defects are characterized by altered cell adhesion and centrosome positioning of FPC-deficient cells in their 1-/2-cell stages. When myosin II inhibitor is applied to reduce cellular tension during the critical early phase of the assay, Pkhd1 silencing no longer inhibits formation of correctly polarized epithelia. We propose that altered sensing and cell interaction of FPC-deficient epithelial cells promote progressive epithelial defects in ARPKD.