Mouse-INtraDuctal (MIND): an in vivo model for studying the underlying mechanisms of DCIS malignancy

Abstract

Due to widespread adoption of screening mammography, there has been a significant increase in new diagnoses of ductal carcinoma in situ (DCIS). However, DCIS prognosis remains unclear. To address this gap, we developed an in vivo model, Mouse-INtraDuctal (MIND), in which patient-derived DCIS epithelial cells are injected intraductally and allowed to progress naturally in mice. Similar to human DCIS, the cancer cells formed in situ lesions inside the mouse mammary ducts and mimicked all histologic subtypes including micropapillary, papillary, cribriform, solid, and comedo. Among 37 patient samples injected into 202 xenografts, at median duration of 9 months, 20 samples (54%) injected into 95 xenografts showed in vivo invasive progression, while 17 (46%) samples injected into 107 xenografts remained non-invasive. Among the 20 samples that showed invasive progression, nine samples injected into 54 xenografts exhibited a mixed pattern in which some xenografts showed invasive progression while others remained non-invasive. Among the clinically relevant biomarkers, only elevated progesterone receptor expression in patient DCIS and the extent of in vivo growth in xenografts predicted an invasive outcome. The Tempus XT assay was used on 16 patient DCIS formalin-fixed, paraffin-embedded sections including eight DCISs that showed invasive progression, five DCISs that remained non-invasive, and three DCISs that showed a mixed pattern in the xenografts. Analysis of the frequency of cancer-related pathogenic mutations among the groups showed no significant differences (KW: p > 0.05). There were also no differences in the frequency of high, moderate, or low severity mutations (KW; p > 0.05). These results suggest that genetic changes in the DCIS are not the primary driver for the development of invasive disease. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Keywords: DCIS; DCIS model; Mouse-INtraDuctal (MIND); animal models; breast cancer; breast malignancy; ductal carcinoma in situ; nonmalignant breast cancers; precancer biology.

Figure 1

Mouse INtraDuctal (MIND) model. MIND involves the intraductal injection of patient‐derived DCIS epithelial cells into the mammary ducts of immunocompromised mice. (1–2) DCIS epithelial cells are obtained following an overnight digestion of patient DCIS biopsy or surgical samples. (3) DCIS cells are injected into the primary mouse mammary ducts via the nipple. (4) Engrafted epithelial cells form in situ lesions and a fraction becomes invasive by bypassing the myoepithelial layer and the basement membrane. The brown regions in the outline of the mouse are mammary gland pairs 1–5.

Figure 2

MIND supports the natural evolution of human DCIS in mice. (A) Representative images of a progressed DCIS xenograft (patient 20) and a non‐progressed DCIS xenograft (patient 14). Panel A shows whole‐gland cross‐section images (left) and magnified views (right). (B) Representative images of human‐specific CK19 immunofluorescence (red), SMA (green), and Hoechst nuclear dye (blue) demonstrating loss of the myoepithelial layer around the progressed lesions, while the SMA layer remained intact around the non‐progressed lesions. Arrows point to intraductal lesions that lost SMA.

Figure 3

DCIS MIND xenografts retain their histologic features with sequential transplantation. DCIS epithelial cells were sorted magnetically and sequentially transplanted into a second generation of mice. (A) Flow cytometry analysis showing the proportion of EpCAM‐positive cells before sorting (pre‐sort), following the exclusion of mouse cells using anti‐mouse MHC I/II (post‐sort), and in the mouse cell subpopulation positively sorted using anti‐mouse MHC I/II. The dashed lines represent an isotype control that is overlaid on the pre‐ and post‐sort graphs. One isotype control was used to overlay on both pre‐ and post‐sort graphs. (B) Representative immunofluorescence images of first generation (12 months) and second generation (3 and 12 months) following transplantation. Anti‐human CK19 (red), anti‐SMA (green), and Hoechst nuclear dye (blue).

Figure 4

Extent of PDX DCIS in vivo growth showed a significant correlation with invasive progression. Forest plot of the extent of xenografted DCIS in vivo growth for 34 patient samples (202 xenografts). Each line represents median growth and interquartile ranges (25–75%) for PDXs derived from one patient sample. Red labels represent progressed, blue non‐progressed, and purple mixed progressed and non‐progressed samples. The inset shows the results of simple linear regression analysis, comparing the extent of DCIS in vivo growth among the three groups. P = progressed; NP = non‐progressed; NP/P = mixed.

Figure 5

A side‐by‐side comparison of biomarkers and histology in patient DCISs and their corresponding xenografts. (A) H&E images demonstrated that xenografted DCISs support the formation of all five DCIS histologic features: cribriform, solid, comedo, micropapillary, and papillary. (B) Representative IHC images comparing patient lesions and their corresponding xenografts, demonstrating that a large proportion of MIND models retain biomarkers expressed in patient DCISs, including ER, PR, HER2, P53, and Ki67. (C) A pairwise comparison of biomarker expression in patient DCISs and their corresponding xenografts. NP.PT = non‐progressed patient; NP.Xeno = non‐progressed xenograft; P.PT = progressed patient; P.Xeno = progressed xenograft.

Figure 6

Heatmap of cancer‐related gene mutations and their severity in patient DCIS. Tempus XT oncology assay results on patient DCISs, comparing those that advanced to invasive lesions with those that remained non‐invasive in the MIND models. NP = non‐progressed; P = progressed; P/NP = mixed or both progressed and non‐progressed. Alterations are color‐coded as severe (3), moderate (2), mild (1), and none (0).