Imaging-Based Machine Learning Analysis of Patient-Derived Tumor Organoid Drug Response

Abstract

Three-quarters of compounds that enter clinical trials fail to make it to market due to safety or efficacy concerns. This statistic strongly suggests a need for better screening methods that result in improved translatability of compounds during the preclinical testing period. Patient-derived organoids have been touted as a promising 3D preclinical model system to impact the drug discovery pipeline, particularly in oncology. However, assessing drug efficacy in such models poses its own set of challenges, and traditional cell viability readouts fail to leverage some of the advantages that the organoid systems provide. Consequently, phenotypically evaluating complex 3D cell culture models remains difficult due to intra- and inter-patient organoid size differences, cellular heterogeneities, and temporal response dynamics. Here, we present an image-based high-content assay that provides object level information on 3D patient-derived tumor organoids without the need for vital dyes. Leveraging computer vision, we segment and define organoids as independent regions of interest and obtain morphometric and textural information per organoid. By acquiring brightfield images at different timepoints in a robust, non-destructive manner, we can track the dynamic response of individual organoids to various drugs. Furthermore, to simplify the analysis of the resulting large, complex data files, we developed a web-based data visualization tool, the Organoizer, that is available for public use. Our work demonstrates the feasibility and utility of using imaging, computer vision and machine learning to determine the vital status of individual patient-derived organoids without relying upon vital dyes, thus taking advantage of the characteristics offered by this preclinical model system.

Keywords: drug response; high content imaging; label-free analysis; machine learning; patient-derived organoids (PDO).

Figure 1

Workflow schematic (A) At day -4 organoids were digested to single cells and seeded at 5,000 cells/well in Basement Membrane Extract. Plates were incubated for 4 days allowing organoids to reform. Baseline images were taken at day 0 prior to the initiation of treatment. After initial treatment, plates were re-imaged at days 1, 3, and 7. Media and treatment are refreshed post imaging on day 3, with final measurements taken at day 7. (B) Using 96 well plates, multiple patients and/or treatments can be performed with a single assay. Images were obtained in z-stack then combined into a single maximum projection image upon which all further processing and analysis was performed. A textural algorithm was used to identify organoid regions of interest, with a segmenting algorithm applied to split organoids in near proximity to each other. A training set was created by identifying live/dead organoids across untreated and treated samples from each patient. This supervised machine learning algorithm was then applied to experimental data. (C) Classification data was compiled into spreadsheets then uploaded to a web-based app for data processing and visualization.

Figure 2

PDOs display distinct texture and morphology features related to viability. (A) Heatmap illustrating 25 morphology and texture features (z-score normalized) across 6 different PDOs in the untreated (media only) condition on Day 3. Columns represent replicates for each PDO. (B) Features discriminating between live and dead PDOs are listed in order of relevance as indicated by the linear coefficient. (C) Representative PDO images of selected morphology and texture features that discriminate between live and dead classification. Scale bar is 50 μm. (D) The signal to noise ratio is displayed as goodness of live (blue) versus dead (orange) PDOs manually classified in the training set. Filled circles denote PDOs included in the training set and open circles are classified by the algorithm.

Figure 3

Comparison of live and dead classification by ML and vital dye. (A) Classification of 18 different organoid images as either live or dead was determined using three independent methods: tissue culture experts, ML, and DRAQ7, and then compared to determine level of concordance. (B) PDOs treated with staurosporine or untreated controls stained with DRAQ7 and classified by ML. Scale bar is 50µm. (C) The normalized proportion of live/total organoids (PDO 12620) for the control and staurosporine treated group as determined by both ML and DRAQ7 was plotted over the course of 7 days (error bars: SD of 3 replicate wells per group per timepoint). When classified by ML the difference in response between the treated and untreated groups are seen starting on day 1, whereas VD classification does not start to show separation until after day 3. (D) Percentage agreement of ML and DRAQ7 live/dead classification for untreated and staurosporine treated organoids (PDO 12620; error bars are SD of 3 replicate wells each). (E) Tracking the vital status of individual organoids (PDO 13154) over 7 days treatment with staurosporine as assessed by our ML classification (N=114 organoids).

Figure 4

PDO-specific drug responses over time. (A) Heat maps of dead PDO features under drug perturbations. Z-score normalized averaged feature values are shown with treatment and time on the x-axis, with features on the y-axis. (B) Boxplots of the feature “region threshold compactness 60%” generated using the Organoizer show the variation between the classified live/dead groups. (C) Fractions of live/total organoids from untreated media control, irinotecan-treated and oxaliplatin-treated groups are plotted over time to generate dose response curves. Points indicate the mean and bars show the SD.