DMF mineralization and substrate specificity mechanism of Aminobacter ciceronei DMFA1.

N,N-dimethylformamide (DMF) is widely used in various industries, but its direct release into water poses high risks to human beings. Although a lot of DMF-degrading bacteria has been isolated, limited studies focus on the degradation preference among DMF and its analogues. In this study, an efficient DMF mineralization bacterium designated Aminobacter ciceronei DMFA1 was isolated from marine sediment. When exposed to a 0.2% DMF (∼1900 mg/L), strain DMFA1 exhibited a degradation efficiency of 100% within 4 days. The observed growth using formamide as the sole carbon source implied the possible DMF degradation pathway of strain DMFA1. Meanwhile,the strain DMFA1 possesses a broad-spectrum substrate degradation, which could effectively degraded 0.2% N,N-dimethylacetamide (DMAC) and N-methylformamide (NMF). Genomic analysis further confirmed the supposed pathway through annotating the genes encoding N, N-dimethylformamidase (DMFase), formamidase, and formate dehydrogenase. The existence of sole DMFase indicating its substrate specificity controlled the preference of DMAc of strain DMFA1. By integrating multiple sequence alignment, homology modeling and molecular docking, the preference of the DMFase in strain DMFA1 towards DMAc are related to: 1) Mutations in key active site residues; 2) the absence of small subunit; and 3) no energy barrier for substrates entering the active site.

Soil Metaproteomics for Microbial Community Profiling: Methodologies and Challenges.

Soil represents a complex and dynamic ecosystem, hosting a myriad of microorganisms that coexist and play vital roles in nutrient cycling and organic matter transformation. Among these microorganisms, bacteria and fungi are key members of the microbial community, profoundly influencing the fate of nitrogen, sulfur, and carbon in terrestrial environments. Understanding the intricacies of soil ecosystems and the biological processes orchestrated by microbial communities necessitates a deep dive into their composition and metabolic activities. The advent of next-generation sequencing and 'omics' techniques, such as metagenomics and metaproteomics, has revolutionized our understanding of microbial ecology and the functional dynamics of soil microbial communities. Metagenomics enables the identification of microbial community composition in soil, while metaproteomics sheds light on the current biological functions performed by these communities. However, metaproteomics presents several challenges, both technical and computational. Factors such as the presence of humic acids and variations in extraction methods can influence protein yield, while the absence of high-resolution mass spectrometry and comprehensive protein databases limits the depth of protein identification. Notwithstanding these limitations, metaproteomics remains a potent tool for unraveling the intricate biological processes and functions of soil microbial communities. In this review, we delve into the methodologies and challenges of metaproteomics in soil research, covering aspects such as protein extraction, identification, and bioinformatics analysis. Furthermore, we explore the applications of metaproteomics in soil bioremediation, highlighting its potential in addressing environmental challenges.

The cryptic step in the biogeochemical tellurium (Te) cycle: Indirect elementary Te oxidation mediated by manganese-oxidizing bacteria Bacillus sp. FF-1.

Tellurium (Te) is a rare element within the chalcogen group, and its biogeochemical cycle has been studied extensively. Tellurite (Te(IV)) is the most soluble Te species and is highly toxic to organisms. Chemical or biological Te(IV) reduction to elemental tellurium (Te0) is generally considered an effective detoxification route for Te(IV)-containing wastewater. This study unveils a previously unnoticed Te0 oxidation process mediated by the manganese-oxidizing bacterium Bacillus sp. FF-1. This bacterium, which exhibits both Mn(II)-oxidizing and Te(IV)-reducing abilities, can produce manganese oxides (BioMnOx) and Te0 (BioTe0) when exposed to Mn(II) and Te(IV), respectively. When 5 mM Mn(II) was added after incubating 0.1 mM or 1 mM Te(IV) with strain FF-1 for 16 h, BioTe0 was certainly re-oxidized to Te(IV) by BioMnOx. Chemogenic and exogenous biogenic Te0 can also be oxidized by BioMnOx, although at different rates. This study highlights a new transformation process of tellurium species mediated by manganese-oxidizing bacteria, revealing that the environmental fate and ecological risks of Te0 need to be re-evaluated.

UWV-Yolox: A Deep Learning Model for Underwater Video Object Detection.

Underwater video object detection is a challenging task due to the poor quality of underwater videos, including blurriness and low contrast. In recent years, Yolo series models have been widely applied to underwater video object detection. However, these models perform poorly for blurry and low-contrast underwater videos. Additionally, they fail to account for the contextual relationships between the frame-level results. To address these challenges, we propose a video object detection model named UWV-Yolox. First, the Contrast Limited Adaptive Histogram Equalization method is used to augment the underwater videos. Then, a new CSP_CA module is proposed by adding Coordinate Attention to the backbone of the model to augment the representations of objects of interest. Next, a new loss function is proposed, including regression and jitter loss. Finally, a frame-level optimization module is proposed to optimize the detection results by utilizing the relationship between neighboring frames in videos, improving the video detection performance. To evaluate the performance of our model, We construct experiments on the UVODD dataset built in the paper, and select mAP@0.5 as the evaluation metric. The mAP@0.5 of the UWV-Yolox model reaches 89.0%, which is 3.2% better than the original Yolox model. Furthermore, compared with other object detection models, the UWV-Yolox model has more stable predictions for objects, and our improvements can be flexibly applied to other models.

Single Micelle Vectors based on Lipid/Block Copolymer Compositions as mRNA Formulations for Efficient Cancer Immunogene Therapy.

Immunogene therapy provides a new strategy for the treatment of colorectal cancer. Compared to plasmid DNA, mRNA possesses several advantages as a therapeutic nucleic acid material and shows high potential in cancer therapy. Although efforts have been made to conquer the limited efficiency of mRNA delivery, most of the current mRNA vectors possess complex structures or compositions, which introduces additional toxicity and hinders their further clinical application. Hence, it is highly necessary to develop potent mRNA delivery systems with simple structures. Here, we report efficient mRNA delivery using the biodegradable micelle delivery system of DMP (DOTAP-mPEG-PCL). Biodegradable DMP micelles were simply prepared by the self-assembly of cationic lipid DOTAP and the diblock polymer monomethoxy poly(ethylene glycol)-poly(ε-caprolactone). With an average size of only 30 nm, we proved that these single-structured cationic micelles are highly potent in condensing and protecting mRNA molecules, with a delivery efficiency of 60.59% on C26 mouse colon cancer cells. The micelles triggered specific internalization pathways and were fully degraded in vivo. After binding with IL-22BP (interleukin-22 binding protein)-encoding mRNA, a strongly elevated IL-22BP mRNA level was detected in C26 cells. After intraperitoneal and intratumoral injection of the DMP/mIL-22BP complex, strong inhibition effects on C26 colon cancer models were observed, with high therapeutic efficiency and safety when systemically administrated. These data suggest that the DMP micelle is an advanced single-structured mRNA delivery system with high safety.

Selective detection of cadmium ions using plasmonic optical fiber gratings functionalized with bacteria.

Environmental monitoring and potable water control are key applications where optical fiber sensing solutions can outperform other technologies. In this work, we report a highly sensitive plasmonic fiber-optic probe that has been developed to determine the concentration of cadmium ions (Cd2+) in solution. This original sensor was fabricated by immobilizing the Acinetobacter sp. around gold-coated tilted fiber Bragg gratings (TFBGs). To this aim, the immobilization conditions of bacteria on the gold-coated optical fiber surface were first experimentally determined. Then, the coated sensors were tested in vitro. The relative intensity of the sensor response experienced a change of 1.1 dB for a Cd2+ concentration increase from 0.1 to 1000 ppb. According to our test procedure, we estimate the experimental limit of detection to be close to 1 ppb. Cadmium ions strongly bind to the sensing surface, so the sensor exhibits a much higher sensitivity to Cd2+ than to other heavy metal ions such as Pb2+, Zn2+ and CrO42- found in contaminated water, which ensures a good selectivity.

Management of medically inoperable and tyrosine kinase inhibitor-naïve early-stage lung adenocarcinoma with epidermal growth factor receptor mutations: a retrospective multi-institutional analysis.

BACKGROUND: The clinical value of combined local radiation and epidermal growth factor receptor (EGFR)-tyrosine kinase inhibitors (TKIs) for medically inoperable and TKI-naïve early-stage lung adenocarcinoma patients with EGFR mutations has not yet been determined. In this study, we aimed to pool multi-institutional data to compare the therapeutic effect of EGFR-TKI treatment alone and combined radiation and TKI treatment on the survival outcomes in this patient subgroup. METHODS: A total of 132 cases of medically inoperable stage I to III EGFR mutant lung adenocarcinoma were retrospectively reviewed based on data from 5 centers. Among these patients, 65 received combined radiation and EGFR-TKI therapy (R + TKI) (49.2%), while 67 received EGFR-TKI (50.8%) treatment alone. All patients were followed until death. RESULTS: For the R + TKI group, the median overall survival (OS) after primary therapy was 42.6 months, while that of the TKI alone group was 29.4 months (log-rank p < 0.001). In terms of progression-free survival (PFS), the median PFS in these two treatment groups was 24 months and 14.7 months respectively (log-rank p < 0.001). Multivariate analysis showed that R + TKI was independently associated with improved OS (adjusted HR 0.420; 95% CI 0.287 to 0.614; p < 0.001) and PFS (adjusted HR 0.420; 95% CI 0.291 to 0.605; p < 0.001) compared to TKI alone. Subgroup analysis confirmed the significant OS benefits in stage III patients and RFS benefits in stage II/III patients. CONCLUSIONS: Upfront radiation to primary sites with subsequent TKI treatment is a feasible option for patients with medically inoperable EGFR-mutant non-small-cell lung carcinoma (NSCLC) during first-line EGFR-TKI treatment, with significantly improved PFS and OS compared with those yielded by TKI treatment alone.

MiRNAs expression profiling of rat ovaries displaying PCOS with insulin resistance.

PURPOSE: The present study established microRNA (miRNA) expression profiles for rat ovaries displaying polycystic ovary syndrome (PCOS) with insulin resistance and explored the underlying biological functions of differentially expressed miRNAs. METHODS: A PCOS with insulin resistance rat model was created by administering letrozole and a high-fat diet. Total RNA was extracted from the ovaries of PCOS with insulin resistance rats and normal rats. Three ovaries from each group were used to identify differentially expressed miRNAs by deep sequencing. A hierarchical clustering heatmap and volcano plot were used to display the pattern of differentially expressed miRNAs. Gene ontology (GO) analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were conducted to explore the potential target genes of the differentially expressed miRNAs and identify their putative biological function. Nine of the differentially expressed miRNAs were selected for validation by Real-time Quantitative PCR (qRT-PCR). RESULTS: A total of 58 differentially expressed miRNAs were identified in the rat ovaries exhibiting PCOS with insulin resistance compared with control ovaries, including 23 miRNAs that were upregulated and 35 miRNAs that were downregulated. GO and KEGG pathway analyses revealed that the predicted target genes were related to metabolic processes, cellular processes, and metabolic pathways. Furthermore, qRT-PCR confirmed that miR-3585-5p and miR-30-5p were significantly upregulated and miR-146-5p was downregulated in the ovaries of PCOS with insulin resistance rats compared with the controls. CONCLUSION: These results indicate that differentially expressed miRNAs in rat ovaries may be involved in the pathophysiology of insulin resistance in PCOS. Our study may be beneficial in establishing miRNAs as novel diagnostic and therapeutic biomarkers for insulin resistance in PCOS.

A Bayesian Scene-Prior-Based Deep Network Model for Face Verification.

Face recognition/verification has received great attention in both theory and application for the past two decades. Deep learning has been considered as a very powerful tool for improving the performance of face recognition/verification recently. With large labeled training datasets, the features obtained from deep learning networks can achieve higher accuracy in comparison with shallow networks. However, many reported face recognition/verification approaches rely heavily on the large size and complete representative of the training set, and most of them tend to suffer serious performance drop or even fail to work if fewer training samples per person are available. Hence, the small number of training samples may cause the deep features to vary greatly. We aim to solve this critical problem in this paper. Inspired by recent research in scene domain transfer, for a given face image, a new series of possible scenarios about this face can be deduced from the scene semantics extracted from other face individuals in a face dataset. We believe that the "scene" or background in an image, that is, samples with more different scenes for a given person, may determine the intrinsic features among the faces of the same individual. In order to validate this belief, we propose a Bayesian scene-prior-based deep learning model in this paper with the aim to extract important features from background scenes. By learning a scene model on the basis of a labeled face dataset via the Bayesian idea, the proposed method transforms a face image into new face images by referring to the given face with the learnt scene dictionary. Because the new derived faces may have similar scenes to the input face, the face-verification performance can be improved without having background variance, while the number of training samples is significantly reduced. Experiments conducted on the Labeled Faces in the Wild (LFW) dataset view #2 subset illustrated that this model can increase the verification accuracy to 99.2% by means of scenes' transfer learning (99.12% in literature with an unsupervised protocol). Meanwhile, our model can achieve 94.3% accuracy for the YouTube Faces database (DB) (93.2% in literature with an unsupervised protocol).

A hybrid CNN feature model for pulmonary nodule malignancy risk differentiation.

The malignancy risk differentiation of pulmonary nodule is one of the most challenge tasks of computer-aided diagnosis (CADx). Most recently reported CADx methods or schemes based on texture and shape estimation have shown relatively satisfactory on differentiating the risk level of malignancy among the nodules detected in lung cancer screening. However, the existing CADx schemes tend to detect and analyze characteristics of pulmonary nodules from a statistical perspective according to local features only. Enlightened by the currently prevailing learning ability of convolutional neural network (CNN), which simulates human neural network for target recognition and our previously research on texture features, we present a hybrid model that takes into consideration of both global and local features for pulmonary nodule differentiation using the largest public database founded by the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). By comparing three types of CNN models in which two of them were newly proposed by us, we observed that the multi-channel CNN model yielded the best discrimination in capacity of differentiating malignancy risk of the nodules based on the projection of distributions of extracted features. Moreover, CADx scheme using the new multi-channel CNN model outperformed our previously developed CADx scheme using the 3D texture feature analysis method, which increased the computed area under a receiver operating characteristic curve (AUC) from 0.9441 to 0.9702.

Draft genome of Pseudomonas sp. XK-1, a marine bacterium capable of degrading lignin and Mn(II) oxidation.

We report the draft genome sequence of marine bacteria, Pseudomonas sp. XK-1. Strain XK-1 could facilitate Mn(II) oxidation with lignin as the sole carbon source. The genome length of XK-1 is 4,751,776 bp, with a G + C content of 62.61%. Genome analyses reveal the carbon and manganese cycling driven by bacteria.

Effectiveness of acupuncture on urinary retention after radical hysterectomy for cervical cancer in China: a systematic review and meta-analysis.

Background: Cervical cancer is one of the most common malignant tumors worldwide. Radical hysterectomy is the first choice for patients with early-stage cervical cancer. Studies have suggested that acupuncture may be a more effective therapy for the prevention and treatment of urinary retention after radical hysterectomy. Objective: To systematically evaluate the clinical efficacy of acupuncture in the prevention and treatment of urinary retention after radical hysterectomy. Methods: We searched the Cochrane library, Web of science, PubMed, Embase, Chinese Biomedical Literature Database, Wanfang database, Wipu database, China National Knowledge Infrastructure Database and ClinicalTrials.gov with the time from inception until December 2023, to collect randomized controlled studies on the clinical efficacy of acupuncture for prevention and treatment of urinary retention after radical hysterectomy. Literature meeting criteria was screened for data extraction. Quality evaluation was performed according to the Cochrane Handbook for Systematic Reviews of Interventions. And meta-analysis was performed using RevMan5.3 and stata14.0 software. Results: 22 Randomized controlled trials with 1,563 patients, 854 in treatment group and 709 in control group, were included totally. Meta-analysis results showed that: the total effective rate in acupuncture group was higher than that in control group, with a statistically significant difference [relative risk (RR)] = 1.43, 95% confidence interval (CI 1.22, 1.68), p < 0.0001; the rate of urinary tract infection in acupuncture group was lower than that in control group, with a statistically significant difference [RR] = 0.23, 95% CI (0.07, 0.78), p < 0.05; the time of indwelling urinary catheter was reduced in acupuncture group compared with control group, with a statistically significant mean difference = -3.45, 95% CI (-4.30, -2.59), p < 0.00001; the incidence of urinary retention was lower in acupuncture group than in control group, and the difference was statistically significant [RR = 0.37, 95% CI (0.27, 0.50), p < 0.00001]; the residual urine volume was reduced in acupuncture group compared with control group, with a statistically significant mean difference = -50.73, 95% CI (-63.61, -7.85), p < 0.00001. Conclusion: Acupuncture treatment based on conventional therapy can better prevent and improve urinary retention after radical hysterectomy for cervical cancer, could be a better option for them. Systematic review registration: Registered by PROSPERO and the registration number is CRD42023452387.

[Retracted] Nicotinamide N­methyltransferase promotes epithelial­mesenchymal transition in gastric cancer cells by activating transforming growth factor­ß1 expression.

[This retracts the article DOI: 10.3892/ol.2018.7885.].

Toxicity effects and mechanism of micro/nanoplastics and loaded conventional pollutants on zooplankton: An overview.

Micro/nanoplastics in aquatic environments is a noteworthy environmental problem. Zooplankton, an important biological group in aquatic ecosystems, readily absorb micro/nanoplastics and produce a range of toxic endpoints due to their small size. This review summarises relevant studies on the effects of micro/nanoplastics on zooplankton, including combined effects with conventional pollutants. Frequently reported adverse effects include acute/chronic lethal effects, oxidative stress, gene expression, energetic homeostasis, and growth and reproduction. Obstruction by plastic entanglement and blockage is the physical mechanism. Genotoxicity and cytotoxicity are molecular mechanisms. Properties of micro/nanoplastics, octanol/water partition coefficients of conventional pollutants, species and intestinal environments are important factors influencing single and combined toxicity. Selecting a wider range of micro/nanoplastics, focusing on the aging process and conducting field studies, adopting diversified zooplankton models, and further advancing the study of mechanisms are the outstanding prospects for deeper understanding of impacts of micro/nanoplastics on aquatic ecosystem.

Interactive segmentation of medical images using deep learning.

Medical image segmentation algorithms based on deep learning have achieved good segmentation results in recent years, but they require a large amount of labeled data. When performing pixel-level labeling on medical images, labeling a target requires marking ten or even hundreds of points along its edge, which requires a lot of time and labor costs. To reduce the labeling cost, we utilize a click-based interactive segmentation method to generate high-quality segmentation labels. However, in current interactive segmentation algorithms, only the interaction information clicked by the user and the image features are fused as the input of the backbone network (so-called early fusion). The early fusion method has the problem that the interactive information is much sparse at this time. Furthermore, the interactive segmentation algorithms do not take into account the boundary problem, resulting in poor model performance. So we propose early fusion and late fusion strategy to prevent the interaction information from being diluted prematurely and make better use of the interaction information. At the same time, we propose a decoupled head structure, by extracting the image boundary information, and combining the boundary loss function to establish the boundary constraint term, so that the network can pay more attention to the boundary information and further improve the performance of the network. Finally, we conduct experiments on three medical datasets (Chaos, VerSe and Uterine Myoma MRI) to verify the effectiveness of our network. The experimental results show that our network greatly improved compared with the baseline, and NoC@80(the number of interactive clicks over 80% of the IoU threshold) improved by 0.1, 0.1, and 0.2. In particular, we have achieved a NoC@80 score of 1.69 on Chaos. According to statistics, manual annotation takes 25 min to label a case(Uterine Myoma MRI). Annotating a medical image with our method can be done in only 2 or 3 clicks, which can save more than 50% of the cost.

Isolation, characteristics, and poly(butylene adipate-co-terephthalate) (PBAT) degradation mechanism of a marine bacteria Roseibium aggregatum ZY-1.

Marine microorganisms have been reported to degrade microplastics. However, the degradation mechanisms are still poorly understood. In this study, a bacterium Roseibium aggregatum ZY-1 was isolated from seawater, which can degrade poly(butylene adipate-co-terephthalate) (PBAT). The PBAT-PLA(polylactic acid, PLA) films, before and after degradation, were characterized by scanning electron microscope (SEM) and Fourier transform infrared spectrometer (FTIR), the weight loss rate and water contact angle were measured. The results indicate that ZY-1 colonized on PBAT-PLA film, changed the functional groups and decreased water contact angle of PBAT-PLA film. Moreover, liquid chromatography mass spectrometry (LC-MS) analysis reveales that PBAT was degraded into its oligomers (TB, BTB) and monomers (T, A) during 10 days, and adipic acid (A) could be used as a sole carbon source. The whole genome sequencing analyses illustrate the mechanisms and enzymes such as PETase, carboxylesterases, arylesterase (PpEst) and genes like pobA, pcaBCDFGHIJKT, dcaAEIJK, paaGHJ involved in PBAT degradation. Therefore, the R. aggregatum ZY-1 will be a promising candidate of PBAT degradation.

Can xenobiotics support the growth of Mn(II)-oxidizing bacteria (MnOB)? A case of phenol-utilizing bacteria Pseudomonas sp. AN-1.

Biogenic manganese oxides (BioMnOx) produced by Mn(II)-oxidizing bacteria (MnOB) have garnered considerable attention for their exceptional adsorption and oxidation capabilities. However, previous studies have predominantly focused on the role of BioMnOx, neglecting substantial investigation into MnOB themselves. Meanwhile, whether the xenobiotics could support the growth of MnOB as the sole carbon source remains uncertain. In this study, we isolated a strain termed Pseudomonas sp. AN-1, capable of utilizing phenol as the sole carbon source. The degradation of phenol took precedence over the accumulation of BioMnOx. In the presence of 100 mg L-1 phenol and 100 µM Mn(II), phenol was entirely degraded within 20 h, while Mn(II) was completely oxidized within 30 h. However, at the higher phenol concentration (500 mg L-1), phenol degradation reduced to 32% and Mn(II) oxidation did not appear to occur. TOC determination confirmed the ability of strain AN-1 to mineralize phenol. Based on the genomic and proteomics studies, the Mn(II) oxidation and phenol mineralization mechanism of strain AN-1 was further confirmed. Proteome analysis revealed down-regulation of proteins associated with Mn(II) oxidation, including MnxG and McoA, with increasing phenol concentration. Notably, this study observed for the first time that the expression of Mn(II) oxidation proteins is modulated by the concentration of carbon sources. This work provides new insight into the interaction between xenobiotics and MnOB, thus revealing the complexity of biogeochemical cycles of Mn and C.

Large-scale uterine myoma MRI dataset covering all FIGO types with pixel-level annotations.

Uterine myomas are the most common pelvic tumors in women, which can lead to abnormal uterine bleeding, abdominal pain, pelvic compression symptoms, infertility, or adverse pregnancy. In this article, we provide a dataset named uterine myoma MRI dataset (UMD), which can be used for clinical research on uterine myoma imaging. The UMD is the largest publicly available uterine MRI dataset to date including 300 cases of uterine myoma T2-weighted imaging (T2WI) sagittal patient images and their corresponding annotation files. The UMD covers 9 types of uterine myomas classified by the International Federation of Obstetrics and Gynecology (FIGO), which were annotated and reviewed by 11 experienced doctors to ensure the authority of the annotated data. The UMD is helpful for uterine myomas classification and uterine 3D reconstruction tasks, which has important implications for clinical research on uterine myomas.

Research progress on the role of biofilm in heavy metals adsorption-desorption characteristics of microplastics: A review.

Microplastics (MPs) have been found to be widely distributed in aquatic environments, where they will interact with toxic heavy metals and result in more serious adverse effects on the aquatic environments and organisms. However, after entering the aquatic environments, MPs are quickly covered by biofilms, which significantly modify MPs properties and relevant heavy metals adsorption-desorption characteristics In order to better understand the adsorption behavior of heavy metals on biofilm developed MPs (BMPs), we comprehensively reviewed representative studies in this area. First, we summarized the formation process of biofilms on MPs. Subsequently, we reviewed the current understanding on the influence of biofilm formation on the properties of MPs and discussed the metal adsorption-desorption characteristics of MPs affected by these changes. Finally, based on the systematic literature review, some future research needs and strategies were proposed to further understand the interactions between MPs and heavy metals.

Revolutionizing hysteroscopy outcomes: AI-powered uterine myoma diagnosis algorithm shortens operation time and reduces blood loss.

Background: The application of artificial intelligence (AI) powered algorithm in clinical decision-making is globally popular among clinicians and medical scientists. In this research endeavor, we harnessed the capabilities of AI to enhance the precision of hysteroscopic myomectomy procedures. Methods: Our multidisciplinary team developed a comprehensive suite of algorithms, rooted in deep learning technology, addressing myomas segmentation tasks. We assembled a cohort comprising 56 patients diagnosed with submucosal myomas, each of whom underwent magnetic resonance imaging (MRI) examinations. Subsequently, half of the participants were randomly designated to undergo AI-augmented procedures. Our AI system exhibited remarkable proficiency in elucidating the precise spatial localization of submucosal myomas. Results: The results of our study showcased a statistically significant reduction in both operative duration (41.32 ± 17.83 minutes vs. 32.11 ± 11.86 minutes, p=0.03) and intraoperative blood loss (10.00 (6.25-15.00) ml vs. 10.00 (5.00-15.00) ml, p=0.04) in procedures assisted by AI. Conclusion: This work stands as a pioneering achievement, marking the inaugural deployment of an AI-powered diagnostic model in the domain of hysteroscopic surgery. Consequently, our findings substantiate the potential of AI-driven interventions within the field of gynecological surgery.