Loss of progesterone receptor-mediated actions induce preterm cellular and structural remodeling of the cervix and premature birth

Abstract

A decline in serum progesterone or antagonism of progesterone receptor function results in preterm labor and birth. Whether characteristics of premature remodeling of the cervix after antiprogestins or ovariectomy are similar to that at term was the focus of the present study. Groups of pregnant rats were treated with vehicle, a progesterone receptor antagonist (onapristone or mifepristone), or ovariectomized on day 17 postbreeding. As expected, controls given vehicle delivered at term while rats delivered preterm after progesterone receptor antagonist treatment or ovariectomy. Similar to the cervix before term, the preterm cervix of progesterone receptor antagonist-treated rats was characterized by reduced cell nuclei density, decreased collagen content and structure, as well as a greater presence of macrophages per unit area. Thus, loss of nuclear progesterone receptor-mediated actions promoted structural remodeling of the cervix, increased census of resident macrophages, and preterm birth much like that found in the cervix at term. In contrast to the progesterone receptor antagonist-induced advance in characteristics associated with remodeling, ovariectomy-induced loss of systemic progesterone did not affect hypertrophy, extracellular collagen, or macrophage numbers in the cervix. Thus, the structure and macrophage census in the cervix appear sufficient for premature ripening and birth to occur well before term. With progesterone receptors predominantly localized on cells other than macrophages, the findings suggest that interactions between cells may facilitate the loss of progesterone receptor-mediated actions as part of a final common mechanism that remodels the cervix in certain etiologies of preterm and with parturition at term.

Figure 1. Peripartum progesterone in circulation in preterm and term birth.

Serum progesterone concentrations (mean±SE, n = 4–6/group) on various days postbreeding in controls, and groups of pregnant rats treated with Onapristone (Ona) or RU486 or bilaterally ovariectomized on the morning of day 17 of pregnancy (Ovx). Preterm birth (PTB) occurred on day 18 postbreeding for Ona- and RU486-treated rats, by 27 h or 26 h post-treatment, respectively (n = 5 and 6 respectively). PTB occurred by the morning of day 19 postbreeding in the Ovx group (36–44 h post-surgery, n = 5). Postpartum (PP) is the morning of the day of birth at term on day 22 postbreeding in Cons (n = 5). Typical estrous cycle serum progesterone concentrations range from 5–50 ng/ml in nonpregnant rats . For statistical comparisons, groups were assigned an individual letter, consecutively from ^a for Con D17.5 to ^l for Con PP groups. The letter above a bar indicates p<0.05 vs the respective treatment group (ANOVA with Tukey's test for individual comparisons). By example, ^a over bars for Ona D17.5, RU486 D17.5 and Con PP groups indicates a significant difference for each versus the Con D17.5 group. The absence of a letter, ^k for example, indicates no statistical difference for any group compared to Con D21.5. See Methods for experimental details.

Figure 2. Photomicrographs of rat cervix sections for comparison of gross and cellular anatomy.

Stitched multiple photomicrographs of a cervix section stained with the pan-macrophage marker ED-1 from A. a nonpregnant (NP, hematoxylin counterstain [30]) and E. a prepartum control rat (Con D21.5, day 21.5 postbreeding, methyl green counterstain). Green box highlights cervix lengthening and hypertrophy with pregnancy (scale bar = 1 mm). Vaginal folds surround the Os while uterine tissue body is generally above the green box, though a clear border between the cervix and uterus is difficult to define. Other photomicrographs of ED-1-stained, methyl green counterstained cervix sections from control rats on day 17.5 or 21.5 postbreeding or postpartum day 22 postbreeding (B. Con D17.5, C. Con D21.5, or G. Con PP, respectively) or from a rat treated with D. Ona or H. ovariectomized (Ovx) on day 17 postbreeding with preterm birth (PTB). F. Negative is a section from a Con D21.5 cervix that was processed without primary ED1 antibody (nonspecific background is not associated with methyl green-stained cell nucleus – example specified with black arrowhead). Box indicates area magnified in insets; examples of fully-stained macrophages with brown deposits are shown by arrows. Photomicrographs were taken at 40x and sized to fit; scale bars in 4 right panels are 25 μm and 5 μm for insets, respectively.

Figure 3. Reduced cell density in the cervix with preterm and term birth.

Number of cell nuclei/area in sections of cervix (mean±SE, n = 5–7 rats/group at each postbreeding date; 6 sections each with 6–8 non-overlapping photomicrographs/rat, i.e., average of 36–48 photomicrographs/rat) from groups of rats relative to days postbreeding or postpartum (PP) as described in Figure 1 legend. Decreased cell nuclei/area indicates hypertrophy and edema of tissue. For perspective, CN density for all groups were significantly reduced compared to NP = nonpregnant controls (9.3±0.45 µm³ ×10⁻⁴, n = 6 ; p<0.05 ANOVA). A Student's t-test compared data for Con versus Ona groups day 17.5 postbreeding (p = 0.04, t = 2.4, df = 8). Letters denote statistical significance from groups assigned letters ^a Con D17.5 through ^k Con D21.5. By example, ^f over the Ovx D18 group indicates a significant increase in cell nuclei number/area compared to that in RU486 D18 while the absence of letters ^{d or k} indicate the lack of significant difference for any group in comparison to Ovx D17.5 or Con D21.5 groups, respectively.

Figure 4. Increased density of macrophages in peripartum cervix at term and with PR antagonist-induced preterm birth.

Macrophages normalized to cell nuclei/area to account for tissue hypertrophy in sections of cervix (mean±SE, n = 4–7 rats/group at each postbreeding date). Groups and statistical comparisons are the same as in legends to Figures 1 and 3 (p<0.05 ANOVA; Con D21.5 vs D17.5, Student's t-test p = 0.04, t = 2.5, df = 8). ^# p<0.05 versus Con D17.5, D18, and D21.5 groups. For perspective, all pregnant rats in the present study had significantly more macrophage in cervix sections compared to that in nonpregnant rats (0.41±0.102/µm³ x 10⁻², n = 6 ; p<0.05 ANOVA).

Figure 5. Photomicrographs of single (PR or ED1) and double-stained cells in sections of cervix from rats at term and with PR antagonist-induced preterm birth (RU486 PTB, day 18 postbreeding).

A, B. PR or ED1 stained section, Vector Red by alkaline phosphatase or brown HRP-DAB respectively, from a Con PP rat on day of term birth (day 22 postbreeding). C, D. PR- and ED1-stained cervix sections from a postpartum Con PP rat at term or RU486 PTB rat with preterm birth. Cell nuclei were visualized with a methyl green counterstain. These photomicrographs are representative of observations from analyses of cervix sections from 3–4 rats/group with available sections (Con D17.5, 18, PP; RU486 D17.5, PTB; Ona D17.5; Ovx D18. Double-stained PR and ED1 cells were a sparse minority of the total number of single PR or ED1 stained cells. Staining characteristics, including the predominance of single-stained cells, are consistent with a previous report in the cervix from postpartum women . Arrows indicate examples of single stained cells. Examples of putative PR+ED1-stained cells are highlighted in the box in panels B and D (magnified inset). Scale bars indicating 15 µm and 30 µm (inset), respectively. See Methods for details.

Figure 6. Degradation of collagen content and structure in the peripartum cervix at term and in preterm birth.

Photomicrographs of picrosirius red dye-stained cervix sections from a rat that was A. nonpregnant (NP; [30]), or from rats in B. Con D21.5 preterm day 21.5 postbreeding, C. Ona PTB or D. Ovx PTB groups. Intensity of orange-red stain reflects extracellular collagen content and cross-linked fiber structure. Photomicrographs were obtained at magnifications of 40x, stitched, and sized to size. Scale bars indicate 1 mm. E. Optical density (mean±SE, n = 5–7 rats/group at each postbreeding date; analyses of 27 non-overlapping sections/rat) of picrosirius red-stained sections of cervix from Con, PR antagonist-treated, and Ovx rats normalized to cell nuclei number/area in each individual to account for tissue hypertrophy and edema. SE bars on some groups are small and obscured by the mean. Optical density is inversely related to collagen content and structure (details in Materials and Methods). Group designations and statistical comparisons are the same as in Figure 1 legend. By example, the ^b assigned to the Ona D17.5 group indicates, by comparison, a significant decrease in OD of cervix sections from the RU486 D17.5, Ovx D17.5, and Ona PTB groups (greater collagen content and structure). By contrast, lack of a letter ^k indicates not significant differences in comparison to the Con D21.5 group. For perspective, the OD of cervix sections from all groups of pregnant rats were significantly increased, i.e., reduced collagen content and structure, compared to that in nonpregnant controls (1.506±0.0309 µm³ ×10⁻¹, n = 6 ; p<0.05 ANOVA).