The current standard of care relies on polypropylene mesh implants, and here the clinical record is troubling. Polypropylene is rigid, hydrophobic, and non-degradable, creating profound biological and mechanical mismatches with soft pelvic tissues. While the mesh provides short-term passive support, its stiffness imposes persistent mechanical overstimulation, and its water-repelling surface promotes nonspecific protein adsorption and inflammatory cell adhesion. The result is often chronic inflammation, foreign body reactions, fibrotic encapsulation, and ultimately mesh curling, displacement, exposure, or erosion. A team of researchers in China, led by Xinting Yang and Quan Lin of Jilin University, has now proposed a radically different approach: a degradable, soft, electrically active scaffold that does not merely hold tissue in place but actively instructs the body to rebuild it. Their work, published in Materials Today Bio, describes an oriented hydrogel designed to mimic the parallel-aligned architecture of skeletal muscle fibers.

The material, named PGZA, is assembled from four biocompatible components: poly(vinyl alcohol), glycyrrhizic acid, zinc ions, and an aniline tetramer grafted onto oxidized alginate. Each ingredient plays a distinct role. Glycyrrhizic acid and zinc ions self-assemble into a first crosslinked network that stabilizes the gel, while simultaneously acting as a synergistic antioxidant system that scavenges reactive oxygen species, molecules known to drive inflammation and push immune cells toward a destructive pro-inflammatory state. The aniline tetramer component supplies electroactivity, enabling electron transfer through conjugated structures and pi-pi interactions. Critically, the entire network is frozen directionally against a chilled brass block, so that ice crystals growing in one direction organize the polymer chains into parallel aligned microchannels, just as muscle fibers align along lines of force in living tissue.

The structural order is not merely aesthetic. Small-angle X-ray scattering revealed a Hermans orientation factor of 0.37 for the directionally frozen gel, compared with 0.01 for a randomly structured control, confirming a genuinely aligned microstructure. That alignment translates directly into performance. In the parallel direction, the optimized PGZA2 formulation, containing 2 milligrams per milliliter of the aniline-grafted alginate, withstood tensile stress of about 229 kilopascals, nearly twice the 122 kilopascals tolerated by the random network version. Its Young’s modulus reached 65 kilopascals with toughness of 181 kilojoules per cubic meter, roughly double the random control in both measures. Conductivity along the alignment direction measured 0.32 siemens per meter, about twenty percent higher than the isotropic version, because ordered conductive chains propagate electrical signals more efficiently. The gel could be stretched to 150 percent and compressed to 60 percent of its original dimensions without breaking, and it retained its mechanical properties after a week in body-temperature fluid, degrading gradually to about 60 percent mass loss over twelve weeks, a timeline that could allow newly formed tissue to assume load-bearing duties as the scaffold disappears.

Electrical stimulation itself has an established role in pelvic medicine, activating signaling cascades such as PI3K/AKT and MAPK/ERK that promote cell migration, differentiation, and extracellular matrix synthesis, and clinical studies have already explored intravaginal stimulation for urinary incontinence. The Jilin team reasoned that a scaffold capable of transmitting such signals along the body’s natural fiber axes would amplify these benefits. In laboratory cultures of fibroblasts, cells grown on the oriented PGZA2 hydrogel showed significantly higher viability by day seven than cells on control materials, and adding electrical stimulation pushed viability higher still. A scratch assay demonstrated the same pattern for migration: the hydrogel accelerated cell movement into wounded areas, and stimulation enhanced the effect further. Under the microscope, cells on the oriented gel aligned preferentially with the microchannels, and with electrical stimulation the alignment became strikingly more pronounced, suggesting that the scaffold and the external field act together as compass and road for migrating tissue-building cells.

The hydrogel also attacked a key biochemical enemy of healing: oxidative stress. Mechanical injury to the pelvic floor triggers accumulation of reactive oxygen species, which inflame the local environment and bias macrophages, the immune system’s tissue-resident first responders, toward the M1 pro-inflammatory phenotype. Using standard DPPH and ABTS radical scavenging assays, the researchers showed that PGZA2 eliminated 66 percent of DPPH radicals and 82 percent of ABTS radicals, far outperforming plain poly(vinyl alcohol) gels. Intracellular reactive oxygen levels in treated cells dropped significantly, and in vitro vascularization assays revealed that the hydrogel, especially with electrical stimulation, promoted the formation of blood vessel-like structures, a crucial capability because regenerating tissue requires a reliable supply of oxygen and nutrients.

To test the material in a living body, the team used a rat model of full-thickness abdominal wall muscle defect, chosen as a surrogate for pelvic floor repair because both tissues are collagen-rich, load-bearing connective structures that heal through similar inflammatory and remodeling phases. Female rats received a one-centimeter circular defect and were divided into untreated controls, and groups receiving the base hydrogel without the electroactive component, the full PGZA2 hydrogel, or PGZA2 plus electrical stimulation at 15 hertz. Transcriptome sequencing of the repaired tissue told a striking story at the level of genes. Compared with controls, 385 genes were upregulated and 266 downregulated, with enrichment in innate immune response pathways, TNF signaling, and IL-17 signaling. Most tellingly, Ifit3, a marker of inflammatory M1 macrophages, was significantly downregulated, while Lgals9, a marker of reparative M2 macrophages, was significantly upregulated, indicating that the treatment had shifted the local immune environment from a state of chronic aggression toward one of resolution and reconstruction.

Histology confirmed the molecular signals. By six weeks after surgery, hematoxylin and eosin staining showed that tissue from the PGZA2 plus stimulation group was the most compact and organized, with the fewest inflammatory infiltrates. Elastica Van Gieson staining revealed the densest network of mature elastic fibers in that group, and Masson’s trichrome staining showed the greatest amount of well-structured collagen, in contrast to the disorganized early fibrosis seen in lesser formulations. Immunofluorescence sealed the case: TNF-alpha, the signature pro-inflammatory cytokine, was most strongly suppressed in the combined treatment group, while TGF-beta, a driver of anti-inflammatory repair and matrix remodeling, reached its highest expression there. The reciprocal cytokine pattern, together with the macrophage marker shift, indicates that the scaffold converts a hostile inflammatory wound bed into a pro-regenerative one.

The authors are candid about the road ahead. The abdominal wall model, while relevant, is not the pelvic cavity, and the long-term fixation stability, synchronization of degradation with tissue ingrowth, and functional restoration in anatomically accurate models remain to be demonstrated. Clinically, they envision the hydrogel first serving as an adjunct at mesh-tissue interfaces during procedures such as laparoscopic lateral suspension, providing compliant early support and calming inflammation while permanent constructs maintain suspension, before full replacement of mesh can be considered. They also sketch a wireless future in which capacitive or inductive coupling, or piezoelectric and triboelectric materials embedded in the gel, could harvest energy from body movement or ultrasound to deliver electrical cues without implanted batteries. If those steps succeed, the muscle-mimicking hydrogel would represent a genuine paradigm shift, moving pelvic floor repair away from passive structural substitution and toward active biological guidance, in which the implant’s job is to make itself unnecessary.

Subject of Research: An oriented, conductive, immunomodulatory hydrogel designed to treat pelvic organ prolapse by regenerating pelvic floor connective tissue

Article Title: Oriented hydrogel biomimicking muscle fibers to treat pelvic organ prolapse via integrated immunomodulation and electrical stimulation

Article References: Yang, X., Li, H., Feng, Y., Wei, C., Guo, Y., Yang, B., Xu, T., & Lin, Q. (2026). Oriented hydrogel biomimicking muscle fibers to treat pelvic organ prolapse via integrated immunomodulation and electrical stimulation. Materials Today Bio, 41, Article 103658. https://doi.org/10.1016/j.mtbio.2026.103658

Image Credits: AI Generated

DOI: 10.1016/j.mtbio.2026.103658

Keywords: pelvic organ prolapse, hydrogel, tissue engineering, electrical stimulation, immunomodulation, biomaterials, collagen remodeling, regenerative medicine, macrophage polarization, polypropylene mesh, glycyrrhizic acid, reactive oxygen species

The clinical problem the researchers set out to solve is deceptively simple to state but difficult to solve in practice. Dynamic transperineal ultrasound, or TPUS, is a noninvasive imaging method in which a probe is placed on the perineum, the area between the vagina and the anus, to visualize the bladder, urethra, and surrounding pelvic structures. During the examination, the patient is asked to perform the Valsalva maneuver, forcefully exhaling against a closed airway as if straining, which increases abdominal pressure and causes pelvic organs to descend. The sonographer must then identify the single most informative frame from the resulting video, trace the position of the urethrovesical junction, the point where the urethra meets the bladder, and grade the degree of descent according to the Green classification system, a scheme first proposed in 1975 that divides cystocele severity into types I, II, and III based on the angle and orientation of the urethra relative to the bladder base.

Every one of those steps depends on human judgment. Selecting the peak Valsalva frame requires recognizing the moment of maximal descent amid a noisy, rapidly changing image sequence. Placing landmarks on the urethrovesical junction demands anatomical expertise, and small errors in landmark placement can shift a patient from one Green type to another. Studies of pelvic floor ultrasound have long documented substantial variability between observers, and the classification is further complicated by confounders such as levator co-activation, in which involuntary contraction of the pelvic floor muscles during straining masks the true extent of organ descent. The result is that Green classification, despite its clinical value in guiding surgical planning for anterior vaginal wall prolapse, remains operator-dependent in a way that many other ultrasound measurements do not.

The Green-AttGRU system was designed to compress that entire manual workflow into an automated pipeline. The architecture combines a deep convolutional neural network for visual feature extraction with a gated recurrent unit, a type of recurrent neural network well suited to sequential data, augmented with an attention mechanism that allows the model to focus on the most diagnostically relevant frames in the ultrasound video. In practical terms, the network watches the whole Valsalva sequence the way a sonographer would, learns which frames capture the moment of maximal bladder neck descent, localizes the urethrovesical junction, and outputs a Green type classification without any manual frame selection or landmark tracing. The name reflects this design: the attention-enhanced gated recurrent unit sits at the heart of the classification engine.

To train and validate the system, the team assembled a dataset of 881 patients examined at Shengjing Hospital, a tertiary referral center. Of these, 688 patients formed a retrospective development cohort used to train the model, while 193 patients were enrolled prospectively and formed an independent test cohort that the model had never seen during training. This separation matters enormously in machine learning for medicine, because models that are evaluated only on the data they were trained on routinely overstate their performance. The prospective design, in which patients were enrolled and scanned after the model architecture was fixed, provides a more honest estimate of how the system would behave in clinical use. The study was approved by the hospital’s ethics committee and conducted in accordance with the Declaration of Helsinki, with written informed consent obtained from prospective participants.

The standalone performance of Green-AttGRU on the complete prospective test cohort was strong. The model achieved a macro-averaged area under the receiver operating characteristic curve, a measure of diagnostic discrimination across all severity classes, of 0.939, with a 95 percent confidence interval of 0.897 to 0.971. Its overall accuracy was 0.902, meaning it agreed with the reference standard in roughly nine out of ten cases. For a three-class classification task performed on dynamic ultrasound video, where the boundaries between Green types are defined by continuous anatomical angles that patients can sit near, those numbers place the automated system in the range of what experienced human readers can achieve, but with the crucial advantage of perfect repeatability: the same input always produces the same output.

The more clinically revealing experiment was the reader study, which asked whether the AI could make human radiologists better rather than simply replace them. Four radiologists, two junior and two intermediate in experience, independently interpreted 67 prospective patient examinations under two conditions: unaided, and with the AI system’s output available as decision support. Without AI assistance, the four readers achieved overall accuracies ranging from 0.761 to 0.821, with macro-averaged F1 scores, which balance precision and recall across classes, between 0.660 and 0.777. With the AI’s classification available, accuracy rose to a range of 0.851 to 0.881, and macro-F1 climbed to 0.820 to 0.860. The improvement was consistent across readers, suggesting that the benefit was not confined to the least experienced members of the panel.

Perhaps the most striking findings concerned agreement and speed. Before AI assistance, the four radiologists agreed with one another only moderately, with a Fleiss’ kappa, a statistic that measures inter-rater agreement beyond chance, of 0.453. After consulting the AI, that figure jumped to 0.786, indicating substantial agreement. In other words, the system did not just make the readers more accurate; it made them more consistent with one another, converging on a shared interpretation of ambiguous scans. At the same time, the pooled median interpretation time per case fell from 26.7 seconds to 9.9 seconds, a reduction of more than 60 percent. For a busy pelvic floor imaging service, that difference compounds quickly, and it points to a workflow benefit that goes beyond diagnostic quality alone.

The study’s authors are careful to frame these results as evidence of preliminary feasibility rather than proof of readiness for unsupervised clinical deployment. The data come from a single tertiary referral hospital, and the reader study involved eight radiologists in total across two experience levels, a sample that cannot capture the full spectrum of expertise and scanning conditions found in the wider clinical world. The system was also designed and evaluated for one specific task, Green classification of the anterior compartment, whereas a complete pelvic floor ultrasound assessment involves additional measurements, including hiatal dimensions and organ descent at rest and on straining, that the current pipeline does not address. External validation at multiple centers, with different scanner hardware and patient populations, remains the necessary next step before any regulatory or guideline body would consider routine use.

Even with those caveats, the work adds to a rapidly growing body of evidence that deep learning can standardize the interpretation of pelvic floor ultrasound, a field that has historically lagged behind obstetric imaging in automation. Recent studies have demonstrated deep learning models for identifying pelvic floor organs in the midsagittal plane, for automating the evaluation of female pelvic organ descent, and for enhancing three-dimensional transperineal ultrasound biometry in prolapse assessment. What distinguishes the present study is its end-to-end scope, spanning frame selection, landmark localization, and classification within a single workflow-oriented system, and its prospective reader study design, which follows the kind of evaluation framework that clinical prediction model reporting guidelines now recommend. If subsequent multicenter studies replicate these results, AI-assisted Green classification could become a practical tool for reducing variability in pelvic floor imaging, shortening examination times, and ultimately helping clinicians choose the right surgical approach for the millions of women whose bladder support fails them.

Subject of Research: Development and prospective validation of an AI-assisted clinical decision support system for automated Green classification of cystocele on dynamic transperineal ultrasound.

Article Title: An AI-assisted Clinical Decision Support System for Green Classification of Cystocele on Dynamic Transperineal Ultrasound

Article References: Zhu, H., Geng, X., Zhou, H., Guo, W., Dai, Y., Zhang, H., Dong, M., Li, H., & Wang, X. (2026). An AI-assisted Clinical Decision Support System for Green Classification of Cystocele on Dynamic Transperineal Ultrasound. Journal of Medical Systems, 50(1), Article 127. https://doi.org/10.1007/s10916-026-02453-7

Image Credits: AI Generated

DOI: 10.1007/s10916-026-02453-7

Keywords: cystocele, transperineal ultrasound, Green classification, artificial intelligence, clinical decision support, pelvic organ prolapse, deep learning, reader study, urethrovesical junction, Valsalva maneuver, radiology, pelvic floor