A Three-Dimensional Organoid Culture System Derived from Human Glioblastomas Recapitulates the Hypoxic Gradients and Cancer Stem Cell Heterogeneity of Tumors Found In Vivo

Abstract

Many cancers feature cellular hierarchies that are driven by tumor-initiating cancer stem cells (CSC) and rely on complex interactions with the tumor microenvironment. Standard cell culture conditions fail to recapitulate the original tumor architecture or microenvironmental gradients and are not designed to retain the cellular heterogeneity of parental tumors. Here, we describe a three-dimensional culture system that supports the long-term growth and expansion of tumor organoids derived directly from glioblastoma specimens, including patient-derived primary cultures, xenografts, genetically engineered glioma models, or patient samples. Organoids derived from multiple regions of patient tumors retain selective tumorigenic potential. Furthermore, organoids could be established directly from brain metastases not typically amenable to in vitro culture. Once formed, tumor organoids grew for months and displayed regional heterogeneity with a rapidly dividing outer region of SOX2(+), OLIG2(+), and TLX(+) cells surrounding a hypoxic core of primarily non-stem senescent cells and diffuse, quiescent CSCs. Notably, non-stem cells within organoids were sensitive to radiotherapy, whereas adjacent CSCs were radioresistant. Orthotopic transplantation of patient-derived organoids resulted in tumors displaying histologic features, including single-cell invasiveness, that were more representative of the parental tumor compared with those formed from patient-derived sphere cultures. In conclusion, we present a new ex vivo model in which phenotypically diverse stem and non-stem glioblastoma cell populations can be simultaneously cultured to explore new facets of microenvironmental influences and CSC biology. Cancer Res; 76(8); 2465-77. ©2016 AACR.

Figure 1

Establishment of glioblastoma CSC organoids. A, Micrograph of IN528 tumorspheres, scale bar = 400 µm. B–E, Parallel IN528 tumorsphere (B, C) or organoid cultures (D, E) for 2 and 6 weeks, scale bar = 1000 µm. F, Mosaic image of multiple low-power (4×) microscope fields showing organoid growth and smaller satellite spheres. G, IN528 organoid prior to embedding and sectioning. U.S. nickel for scale. H – J, Images of 6-well plate wells containing IN528 tumorspheres (H) or organoids (I, J) at indicated time points.

Figure 2

Organoid-derived glioblastoma xenografts recapitulate the diffusive phenotype of the original patient tumor. A, Longitudinal growth of CCF3128 patient-derived recurrent glioblastoma in organoid culture. B, Limiting dilution assays of organoid, tumorsphere, or FBS-differentiated CCF3128 cells. Sphere-forming cell frequencies are indicated next to each line. C, Survival plot of mice following orthotopic injection of 50,000 dissociated CCF3128 organoid or tumorsphere cells. D–F, High power micrographs of tumorsphere or organoid frozen sections (H&E, 40×). G, Low power micrograph of biopsy sample (H&E, 1×). H, Whole mount mouse brain bearing organoid derived xenograft demonstrating effacement of ventricles and asymmetric expansion of cerebral hemispheres with no clear margins of tumor (H&E, 1×). I, Whole mount mouse brain bearing tumorsphere derived xenograft showing solid growth pattern in subarachnoid space and clear margins of tumor/brain interface. (H&E, 1×). J, Intermediate power micrograph of patient biopsy specimen exhibiting a diffuse growth pattern of tumor cells with eosinophilic cytoplasm (H&E, 10×). K, Intermediate power micrograph of organoid derived xenografted tissue showing a diffuse growth pattern of tumor cells with eosinophilic cytoplasm and irregularly shaped nuclei (H&E, 10×). L, Intermediate power micrograph of tumorsphere-derived xenograft showing solid growth pattern, sharp tumor-brain interface with tumor cells growing down a the perivascular Virchow-Robin space (H&E, 10×). M, High power micrograph of patient biopsy tissue exhibiting variable amounts of eosinophilic cytoplasm with hyperchromatic irregular nuclei and pleomorphic cytoplasmic outlines (H&E, 40×). N, High power micrograph of organoid derived xenografted tissue exhibiting individual fibrillar tumor cells infiltrating into the brain substance as single cells with variable amounts of intervening brain parenchyma between the pleomorphic tumor cells (H&E, 40×). O, High power micrograph of tumorsphere-derived xenografted tissue showing solid growth pattern of basophilic tumor cells with high nuclear to cytoplasmic ratios that exhibit a sharp tumor-brain interface with infiltration along the perivascular Virchow Robin space (H&E, 40×).

Figure 3

Patient-derived multi-region tumor samples. A, Based on preoperative MRI scans, surgical samples were selected from 3 distinct tumor regions for laboratory propagation. These regions were: CW1757_1 = Superficial Cortex ≥ 3mm from enhancing margin and also within hyperintense FLAIR; CW1757_2 = Enhancing margin of tumor; CW1757_3 = Tumor Center, Hypointense on T1 and non-enhancing (Typically associated with necrosis on IHC). B, High power micrograph of CW1757_1 patient derived biopsy tissue along the tumor-brain margin demonstrating mild increase in cellular density related to single cell infiltration of tumor cells (H&E, 40×). C, High power micrograph of CW1757_2 biopsy demonstrating markedly increased fibrillar tumor cellular density with variable amounts of intercellular eosinophilic brain parenchyma and no geographic necrosis (H&E, 40×). D, High power micrograph of CW1757_3 biopsy demonstrating regions of geographic necrosis (centrally) consistent with therapeutic effect rimmed by viable cells of unknown histology (H&E, 40×). E, CW1757_X specimens grown directly in organoid format for the indicated culture periods in 6-well plates, scale bar = 1000 µm. F, Kaplan-Meier survival analysis of mice bearing orthotopic xenografts from dissociated organoids originating from each tumor region in panel E. G, High power micrograph of organoid derived xenografted tumor tissue along the tumor-brain interface showing moderately increased cellular density and an indistinct tumor margin related to single cell infiltration of tumor cells into the surrounding brain, a feature also found in the biopsy tissue (B above) (H&E, 40×). H, High powered micrograph showing cellular density varying from moderate to high as detected by the variable amounts of basophilic nuclei and eosinophilic cytoplasm (H&E 40×). I, High power micrograph demonstrating a region of predominately high cellular density associated with hyperchromatic and pleomorphic basophilic nuclei, a region that differs markedly from the other regions of the tumor xenograft shown in G and H (H&E 40×).

Figure 4

Inverse Gradients of Stem Cell Frequency and Hypoxia in Organoids. A–C, Wide field immunofluorescence imaging of nuclear SOX2 protein in IN528 (a), 387 (b), and CCF3128 (c, mosaic) organoids. Scale bars = 400 µm. D–F, Co-immunofluorescence of SOX2 and CA-IX near the edges of IN528 organoids. Scale bars = 200 µm.

Figure 5

Spatial and phenotypic cellular heterogeneity in organoids. A, B, Immunofluorescence mosaic imaging of Ki-67 protein and SOX2 in IN528 organoids, scale bars = 400µ. Insets (A’–B”) are magnified regions of the mosaic span as indicated by dashed boxes. C–E, Immunofluorescence imaging specific to cleaved Caspase 3 protein in IN528 (C, D) and 387 (E) organoids. White arrows indicate positive cells, scale bars = 200µm. F–H, Light micrographs of X-Gal detection of Senesence-associated β-galactosidase in IN528 (F, G) and 387 (H) organoids. Scale bars = 100 µm (F), 200 µm (G), 400 µm (H).

Figure 6

Organoid rim non-CSCs are radiosensitive. A–D, Immunofluorescence imaging of cleaved Caspase 3 protein and SOX2 protein in IN528 organoids 96 hours after 3 Gy irradiation. White arrows indicate cleaved Caspase 3 positive cells. Scale bars = 200 µm (A, C) or 100 µm (B, D). E–G, Total cells and cells positive for SOX2 (E), cleaved Caspase 3 (F), and both (G) were blindly counted from 3 non-overlapping high power fields within the indicated organoid regions. Student's t-Test; *, p < 0.02; **, p < .001.

Figure 7

Partially overlapping stem cell marker expression in glioblastoma organoids. A, Immunofluorescence mosaic imaging of SOX2 and TLX protein in 387 organoids. Scale bars = 200 µm. Insets (a’–a’”) are magnified regions of the mosaic span as indicated by dashed boxes. B–D, Immunofluorescence mosaic imaging of SOX2 and OLIG2 protein expression in IN528 organoids. Insets (B’–D”) are magnified regions of the mosaic span as indicated by dashed boxes. Scale bars = 200 µm.