Matteo Pavone

Cutting Edge Microscopic Intraoperative Tissue Assessment for Guidance in Oncologic Surgery: A Systematic Review of the Role of Optical Coherence Tomography

Enhancing surgical precision in ovarian cancer with FRα-fluorescence-guided surgery

Complete cytoreduction is a key prognostic factor in advanced ovarian cancer. Folate receptor alpha (FRα)-targeted intraoperative fluorescence imaging has emerged as a promising tool to enhance identification of tumor localization. Agents like pafolacianine (OTL38) and EC17 improve real-time visualization of malignant lesions, overcoming limitations of conventional methods relying on visual inspection and palpation. we conducted a systematic review to evaluate the safety, efficacy, and feasibility of FRα-targeted fluorescence imaging in ovarian cancer surgery. Studies were identified through comprehensive searches in PubMed, Scopus, and Web of Science. Clinical and preclinical studies assessing FRα-targeted agents with near-infrared or other fluorescence modalities were included. Bias risk was assessed using the Cochrane Risk of Bias Tool for randomized trials and the Newcastle-Ottawa Scale for non-randomized studies. Eleven studies, including clinical and preclinical trials, were analyzed. OTL38 significantly improved lesion detection, identifying additional malignant lesions in 33 % of patients undergoing debulking surgery and enhancing detection by 29 % over standard methods, with sensitivity exceeding 85 %. EC17, assessed in smaller studies, identified 16 % more malignant lesions undetected by conventional methods, though autofluorescence was a challenge. Adverse events, predominantly mild, included nausea, vomiting, and transient skin flushing. FRα-targeted imaging may enhance lesion detection during cytoreductive surgery, increasing resection completeness. While EC17 shows feasibility, larger trials support the potential of OTL38. Future research should optimize imaging agents to reduce autofluorescence and assess their impact on survival outcomes.

Efficacy and safety of pressurized intraperitoneal aerosol chemotherapy (PIPAC) in ovarian cancer: a systematic review of current evidence

Abstract Background PIPAC is a recent approach for intraperitoneal chemotherapy with promising results for patients with peritoneal carcinomatosis. A systematic review was conducted to assess current evidence on the efficacy and outcomes of PIPAC in patients affected by ovarian cancer. Methods The study adhered to the PRISMA guidelines. PubMed, Google Scholar and ClinicalTrials.gov were searched up to December 2023. Studies reporting data on patients with OC treated with PIPAC were included in the qualitative analysis. Results Twenty-one studies and six clinical trials with 932 patients who underwent PIPAC treatment were identified. The reported first access failure was 4.9%. 89.8% of patients underwent one, 60.7% two and 40% received three or more PIPAC cycles. Pathological tumour response was objectivated in 13 studies. Intra-operative complications were reported in 11% of women and post-operative events in 11.5% with a 0.82% of procedure-related mortality. Quality of life scores have been consistently stable or improved during the treatment time. The percentage of OC patients who became amenable for cytoreductive surgery due to the good response after PIPAC treatment for palliative purposes is reported to be 2.3%. Conclusion The results showed that PIPAC is safe and effective for palliative purposes, with a good pathological tumour response and quality of life. Future prospective studies would be needed to explore the role of this treatment in different stages of the disease, investigating a paradigm shift towards the use of PIPAC with curative intent for women who are not eligible for primary cytoreductive surgery. Graphical abstract

Therapeutic role of para-aortic lymphadenectomy in patients with intermediate- and high-risk endometrial cancer: a systematic review and meta-analysis

Lymph nodal involvement is a prognostic factor in endometrial cancer. The added value of para-aortic lymphadenectomy compared with pelvic nodal evaluation alone remains a matter of debate in the management of patients with intermediate- and high-risk endometrial cancer. A systematic review and meta-analysis was conducted to assess the prognostic value of para-aortic lymphadenectomy in terms of overall survival and disease-free survival in patients with intermediate- and high-risk endometrial cancer. The study adhered to the PRISMA guidelines. PubMed, Google Scholar and ClinicalTrials.gov were searched from January 2000 to April 2023. Studies on intermediate- and high-risk patients who underwent pelvic versus pelvic and para-aortic dissection were included in the analysis. The Methodological Index for Nonrandomized Studies (MINORS) and the Quality Assessment of Diagnostic Accuracy Studies 2 tool (QUADAS-2) were used for quality assessment of the selected articles. Fourteen studies were identified, encompassing 9415 patients with a median age of 62 years (IQR 56.5-66.5). The majority had International Federation of Gynecology and Obstetrics stage I-II disease (76%) and endometrioid histology (89%). The 72% of patients who underwent only pelvic nodal evaluation and the 87% who underwent pelvic and para-aortic lymphadenectomy received adjuvant treatment (p=0.44). Pelvic and para-aortic lymphadenectomy was associated with a significant improvement in 5-year overall survival (RR=0.71, 95% CI 0.57 to 0.88, p<0.01), translating to a 41% reduction in the risk of overall death. However, no significant differences were observed in the 5-year risk of recurrence (RR=1.12, 95% CI 0.94 to 1.34, p=0.15). Additionally, patients undergoing pelvic and para-aortic lymphadenectomy experienced a 26% increased risk of post-operative complications (RR=1.26, 95% CI 1.04 to 1.53, p=0.03) and prolonged operative times (MD=56.27, 95% CI 15.94 to 96.60, p<0.01). Pelvic and para-aortic lymphadenectomy appears to confer a prognostic benefit in patients with intermediate- and high-risk endometrial cancer. Robust prospective studies are needed to further validate these findings and elucidate the precise role of para-aortic lymphadenectomy in the optimal management of these patients.

Uterine transposition versus uterine ventrofixation before radiotherapy as a fertility sparing option in young women with pelvic malignancies: Systematic review of the literature and dose simulation

Critical view of safety assessment in sentinel node dissection for endometrial and cervical cancer: artificial intelligence to enhance surgical safety and lymph node detection (LYSE study)

This study aims to evaluate the feasibility of video-based assessment rate of Critical Views of Safety criteria for sentinel lymph node dissection in endometrial and cervical cancer. Goal of these Critical Views of Safety is to help standardize the evaluation of surgical quality, improve the precision of sentinel lymph node identification, and lead to better patient outcomes. This international multi-center observational prospective study was conducted from April to September 2024. Surgical videos from patients with cervical and endometrial carcinoma undergoing minimally invasive sentinel lymph node dissection were collected. A total of 3 Critical Views of Safety criteria (lateral pararectal space, lateral paravesical space, internal iliac artery) were proposed based on the anatomical structures defined as mandatory to be identified before sentinel node dissection, according to previously published expert consensus. A total of 3 independent surgeons, blinded to each other's assessments, evaluated whether the proposed criteria were identifiable in the endoscopic surgical video to establish applicability (content validity) and inter-rater agreement (reliability). A total of 80 patients were enrolled, of these, 71 cases (88.8%) had videos suitable for annotation, 64 (90.1%) underwent sentinel lymph node dissection for endometrial cancer, and 7 (9.9%) for cervical cancer; the median age was 52 years (IQR 34-71) and median body mass index was 28.8 kg/m The low assessment rate of the internal iliac artery criteria should raise concerns about missing sentinel lymph nodes in the internal iliac and pre-sacral area. The assessment of such standardized safety criteria could potentially standardize the procedures, thereby improving adherence to guidelines. The introduction of the video assessment of these criteria lays the foundation for exploring the feasibility of artificial intelligence algorithms to automatically assess and document the Critical Views of Safety in surgical videos.

Performance of molecular classification in predicting oncologic outcomes of fertility-sparing treatment for atypical endometrial hyperplasia and endometrial cancer

Endometrial cancers can be classified into 4 molecular sub-groups: (1) POLE mutated (POLEmut), (2) mismatch repair deficiency/microsatellite-instable (MMRd/MSI-H), (3) TP53-mutant or p53 abnormal (p53abn), and (4) no specific mutational profile (NSMP). Although molecular classification is increasingly applied in oncology, its role in guiding fertility-sparing treatments for endometrial cancer remains unclear. This study examines the prognostic role of molecular classification in fertility-sparing treatment and its potential to guide treatment decisions. We conducted a systematic review and meta-analysis of studies applying molecular classifiers in patients with endometrial cancer or atypical hyperplasia who underwent fertility-sparing treatment (International Prospective Register of Systematic Reviews, identification CRD42024555559). A literature search was performed across Scopus, PubMed/MEDLINE, ScienceDirect, and the Cochrane Library (2013-February 2024). Studies included full-text English articles with pre-operative assessments (histology, magnetic resonance imaging, or ultrasound) and molecular classification through next-generation sequencing or Proactive Molecular Risk Classifier for Endometrial Cancer. Both randomized controlled trials and observational studies were considered. Outcomes included complete response, partial response, stable disease, progression, and recurrence, with pooled analyses performed. Eight retrospective cohort studies comprising 363 patients met the inclusion criteria. Next-generation sequencing was used in 5 studies. The distribution of molecular sub-groups was POLEmut (5.8%), p53abn (3.3%), MMRd/MSI-H (12.1%), and NSMP (78.8%). Complete response and recurrence rates were POLEmut (66.6% and 14.3%), p53abn (50% and 33%), MMRd/MSI-H (48.8% and 42.8%), and NSMP (78.4% and 18.4%). Significant differences in complete response (p <.001) and recurrence rates (p = .005) were found across sub-groups. Pairwise analysis revealed lower complete response and higher recurrence rates for MMRd/MSI-H (p <.001, p = .01) and lower response for p53abn (p = .03) than for NSMP. POLEmut did not show superior success to other groups. Molecular classification indicates prognostic value in fertility-sparing treatment for endometrial cancer. NSMP had the highest response rates, whereas MMRd/MSI-H and p53abn were associated with poorer outcomes.

Assessing the Accuracy of Large Language Models on European Guidelines for Cervical Cancer: An In Silico Benchmarking Study

ABSTRACT Objective Although large language models are increasingly used in clinical and research settings, the validity of the information they provide remains uncertain. This study aimed to evaluate the accuracy, consistency, and reliability of three large language models—ChatGPT 4.0, DeepSeek R1, and Gemini 2.0—in answering cervical cancer‐related questions based on the ESGO/ESTRO/ESP guidelines. Design Prospective, comparative in silico benchmarking study. Setting Fondazione Policlinico Universitario A. Gemelli, Rome, Italy. Population or Sample: Fifty questions derived from the ESGO/ESTRO/ESP (European Society of Gynaecologic Oncology/European Society for Radiotherapy and Oncology/European Society of Pathology) Guidelines for Cervical Cancer. Methods Each question was submitted simultaneously to ChatGPT 4.0, DeepSeek R1, and Gemini 2.0, and re‐entered twice to assess response repeatability. Answers were evaluated for accuracy using a Global Quality Score (GQS) from 1 (poor) to 5 (completely accurate). Consistency (intra‐model response stability) and reliability (alignment with guidelines) were assessed using binary classification. Main Outcome Measures: Median GQS, percentage of GQS 5 responses, consistency between repeated answers, and reliability. Results ChatGPT 4.0 achieved the highest performance, with 42% of responses rated GQS 5, followed by Gemini 2.0 (30%) and DeepSeek R1 (28%). DeepSeek R1 and Gemini 2.0 scored lower in median GQS (3.50) compared to ChatGPT 4.0 (4.00). Response consistency varied significantly, with ChatGPT 4.0 and DeepSeek R1 showing differences from Gemini 2.0 ( p  = 0.034 and p  = 0.044, respectively). No significant difference was observed in reliability ( p  = 0.602). Conclusion All models demonstrated suboptimal accuracy in aligning with clinical guidelines. ChatGPT 4.0 was the most accurate and consistent whereas DeepSeek R1 underperformed. Despite similar reliability across models, expert oversight remains essential to ensure safe clinical application and prevent misinformation.

Reproductive, obstetrical and oncological outcomes of fertility-sparing treatment for cervical cancer according to the FIGO 2018 staging system: A systematic review

We assessed reproductive, obstetrical, and oncological outcomes in patients who underwent fertility-sparing treatment by including studies that adhere to the FIGO 2018 staging system. Data on recurrence, mortality, pregnancy rate, live birth rate, and preterm delivery rate were collected. In patients with stages IA1, IA2, and IB1, the recurrence rate was 4.7 % and the death rate was 0.6 %. For patients with stage IB2, the recurrence rate was 12.1 % and the death rate was 3.2 %. Pregnancy rates for conization/simple trachelectomy and radical trachelectomy were 61.7 % and 50 %, respectively. A higher live birth rate (84.4 % vs 58.6 %), and lower preterm birth rate (18.3 % vs 33.3 %) were observed in patients undergoing conization compared to radical trachelectomy. We found a recurrence rate of 4.7 % in patients with stage less than or equal to IB1 and 12.1 % in those with stage IB2. A higher rate of preterm delivery was observed in patients who underwent radical trachelectomy.

In-transit metastatic lymph nodes in cervical cancer: A new staging and therapeutic concept

It has been reported that metastatic lymph nodes can be present in the parauterine lymphovascular (PULT) and in lateral paracervical lymphatic tissue as in-transit disease in patients with cervical cancer. This study aimed to clarify the understanding of in-transit positive lymph nodes in PULT and lateral paracervix and its clinical management in patients with cervical cancer, based on insights gathered from an international expert survey. A 29-question survey was emailed to experts identified through a systematic literature search related to sentinel lymph nodes in gynecological cancer. The survey was divided into four sections: 1. Resection of parauterine lymphovascular tissue; 2. Discontinuous lymphatic paracervical involvement; 3. Positive para-uterine or paracervical nodes in fertility-sparing surgery; 4. The impact of positive in-transit nodes on the extent of nodal staging. Consensus was defined as an agreement among at least 70% of the respondents. Responders where only corresponding or last authors of articles addressing sentinel lymph nodes procedures. Results show general agreement on referring to the areas as "para-uterine lymphovascular tissue (PULT)" (84.85 %), with lymph nodes in these regions considered sentinel nodes if stained with indocyanine green (80 %). However, there is no consensus on surgical staging for isolated positive lymph nodes. Most respondents favour adjuvant treatment for in-transit macro or micrometastases (>95 %) but acknowledge the lack of conclusive evidence. In fertility-sparing settings, most would remove PULT while preserving uterine arteries (59 %) and would remove lateral paracervical tissue in low-risk cases (66.7 %). For isolated metastasis, most would recommend chemoradiation over fertility-sparing options (81.8 %). Finally, if a positive in-transit node is found, experts would request additional imaging (80.3 %), though there is no consensus on aortic lymphatic dissection or extended-field radiation without prior aortic staging. The survey highlights expert awareness of the clinical importance of in-transit positive lymph nodes. However, it is essential for the international societies to urgently address the impact of these nodes on staging and treatment guidelines, as current recommendations and evidence are lacking.

Minimally invasive simple hysterectomy in low-risk cervical cancer: a single-arm trial with stopping rules (ENGOT-cx23/MITO/LASH trial)

The oncologic safety of minimally invasive simple hysterectomy in low-risk cervical cancer has not been explored by an adequately powered clinical trial. This study aims to evaluate whether minimally invasive simple hysterectomy affects disease-free survival in low-risk early-stage cervical cancer. Minimally invasive simple hysterectomy represents an oncologically safe approach in selected patients with low-risk cervical cancer. This is a single-arm trial with stopping rules. All patients must undergo cervical conization. Patients with clear conization margins or absence of residual macroscopic disease at imaging after conization (re-conization is mandatory if these criteria are not met) are submitted to minimally invasive (laparoscopy or robot-assisted laparoscopy) simple hysterectomy with sentinel lymph node biopsy algorithm. Adjuvant therapy is given in case of tumor-involved surgical margins, and/or metastatic lymph nodes, and/or substantial lymphovascular space invasion with depth of stromal infiltration >2/3 (or tumor-free distance ≤3 mm). The major inclusion criteria are: squamous cell carcinoma, human papillomavirus-related adenocarcinoma, adenosquamous carcinoma of the uterine cervix; International Federation of Gynecology and Obstetrics 2018 stage IA2-IB1 (≤2 cm) with depth of infiltration ≤10 mm on conization specimen; International Federation of Gynecology and Obstetrics 2018 stage IA2-IB1 (≤2 cm) with depth of infiltration ≤50% at pre-conization magnetic resonance imaging scan or "expert" ultrasound scan. Women are not eligible if they have evidence of metastatic disease, contra-indications to surgery and/or lymph node assessment, or fertility sparing desire. The primary end point is 3-year disease-free survival of patients who undergo minimally invasive simple hysterectomy. A sample size of 974 patients will give a power of 80% at a significance level of 2.5% (1-sided) to reject the null hypothesis of a 3-year recurrence rate of 2.4%, assuming a 3-year recurrence rate of 1.2%. A maximum of 14 recurrences at 3 years should be observed to reject the null hypothesis. A stopping rule based on the number of recurrences observed at different timepoints will be implemented to avoid a higher recurrence rate with the study procedure. The trial will also be stopped if no recurrences are observed in the first 400 patients followed up for 2 years. The enrolment will last 60 months. After the surgery, the follow-up time will be ≥3 years. The trial is registered at ClinicalTrials.gov (NCT06416748) and as ENGOT/MITO trial (ENGOT-cx23).

Circulating tumor DNA as a biomarker for predicting progression-free survival and overall survival in patients with epithelial ovarian cancer: a systematic review and meta-analysis

Circulating tumor DNA (ctDNA) is emerging as a potential prognostic biomarker in multiple tumor types. However, despite the many studies available on small series of patients with ovarian cancer, a recent systematic review and meta-analysis is lacking. The objective of this study was to determine the association of ctDNA with progression-free-survival and overall survival in patients with epithelial ovarian cancer. An electronic search was conducted using PubMed (MEDLINE), Embase, CENTRAL (Cochrane Library), and CINAHL-Complete from January 2000 to September 15, 2023. To be included in the analysis the studies had to meet the following pre-specified inclusion criteria: (1) evaluable ctDNA; (2) progression-free-survival and overall survival reported as hazard ratio (HR); and (3) the patient population had epithelial ovarian cancer at the time of ctDNA detection. We evaluated the association of ctDNA with progression-free survival and overall survival. Secondary outcomes focused on sub-group analysis of genomic alterations and international Federation of Gynecology and Obstetrics (FIGO) stage. A total of 26 studies reporting on 1696 patients with epithelial ovarian cancer were included. The overall concordance rate between plasma-based and tissue-based analyses was approximately 62%. We found that a high level of ctDNA in epithelial ovarian cancer was associated with worse progression-free survival (HR 5.31, 95% CI 2.14 to 13.17, p<0.001) and overall survival (HR 2.98, 95% CI 1.86 to 4.76, p<0.0001). The sub-group analysis showed a greater than threefold increase in the risk of relapse in patients with positive HOXA9 meth-ctDNA (HR 3.84, 95% CI 1.57 to 9.41, p=0.003). ctDNA was significantly associated with worse progression-free survival and overall survival in patients with epithelial ovarian cancer. Further prospective studies are needed. CRD42023469390.

Simple hysterectomy versus radical hysterectomy in early-stage cervical cancer: A systematic review and meta-analysis

This systematic review (SR) and meta-analysis aims to compare the surgery-related results and oncological outcomes between SH and RH in patients with early-stage cervical cancer. We systematically searched databases including PubMed, Embase and Cochrane to collect studies that compared oncological and surgery-related outcomes between SH and RH groups in patients with stage IA2 and IB1 cervical cancer. A random-effect model calculated the weighted average difference of each primary outcome via Review Manager V.5.4. Seven studies comprising 6977 patients were included into our study. For oncological outcomes, we found no statistical difference in recurrence rate [OR = 0.88; 95% CI (0.50, 1.57); P = 0.68] and Overall Survival (OS) [OR = 1.23; 95% CI (0.69, 2.19), P = 0.48]. No difference was detected in the prevalence of positive LVSI and lymph nodes metastasis between the two groups. Concerning surgery-related outcomes, the comprehensive effects revealed that the bladder injury [OR = 0.28; 95% CI (0.08, 0.94), P = 0.04] and bladder disfunction [OR = 0.10; 95% CI (0.02, 0.53), P = 0.007] of the RH group were higher compared to the SH group. This meta-analysis suggested there are no significant differences in terms of both recurrence rate and overall survival among patients with stage IA2-IB1 cervical cancer undergoing SH or RH, while the SH group has better surgery-related outcomes. These data confirm the need to narrow the indication for RH in early-stage cervical cancer.

Laparoscopic-Assisted Vaginal Trachelectomy with Prophylactic Cerclage: A Safe Fertility-Sparing Treatment for Early Stage Cervical Cancer

In recent years fertility-sparing treatments are increasingly developing in patients with early stage cervical cancer. The first laparoscopic time is dedicated to the safe opening of the vesicouterine and rectovaginal spaces until the medial pararectal fossa. Ureters are found and bilateral ureterolysis performed under vision. Colpotomy is then vaginally achieved, and the cervix is closed in a vaginal cuff to avoid tumor spread. Careful dissection of the anterior and posterior septa is carried out until reunification with laparoscopic dissection. Bilateral parametrectomy is performed. Vaginal trachelectomy is finalized with a negative deep margin at the frozen section. In the second laparoscopic time a monofilament polypropylene sling cerclage is bilaterally positioned from posterior to anterior through the broad ligaments and fixed anteriorly on the uterine isthmus to prevent an eventual preterm delivery. Laparoscopic-assisted vaginal trachelectomy is a feasible procedure combining the conservative advantages of the vaginal approach and the oncological safety of laparoscopic spaces dissection with possible good obstetric outcomes.

Electronic nose-based volatile organic compound profiling in gynecologic oncology: current evidence and diagnostic accuracy

Volatile organic compounds profiling has emerged as a promising approach for cancer detection. Electronic noses are portable sensor-based devices capable of recognizing volatile organic compound patterns in various biological matrices, offering a rapid, non-invasive, and cost-effective diagnostic alternative. The aim of this systematic review was to evaluate the diagnostic performance of electronic noses in gynecologic oncology and to delineate their technical characteristics. This review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines and was registered in International Prospective Register of Systematic Reviews (CRD420251122293). PubMed, Scopus, and Google Scholar were searched up to August 2025. Eligible studies included prospective investigations evaluating volatile organic compound analysis through electronic noses in ovarian, cervical, endometrial, and vulvar cancers, as well as high-grade squamous intraepithelial lesions, using histopathology as the reference standard. Diagnostic performance parameters were extracted, and the risk of bias was assessed with Quality Assessment of Diagnostic Accuracy Studies 2. No meta-analysis was performed due to study heterogeneity. Fifteen studies with a total of 1224 patients were included. Among them, 562 (45.9%) had gynecologic malignancies, and 662 (54.1%) served as controls. Ten studies (66.7%) investigated ovarian cancer, 4 (26.7%) cervical cancer, and 1 (6.7%) high-grade squamous intraepithelial lesions of the cervix; no studies evaluated endometrial or vulvar cancers. Biological matrices analyzed included breath (33.3%), urine (20%), tissue (20%), plasma (6.7%), genitourinary secretions (6.7%), or combined samples (6.7%). Reported diagnostic performance ranged from 71% to 97.7% for sensitivity, from 63% to 100% for specificity, and from 71% to 95% for accuracy across all cancer types. In ovarian cancer studies, sensitivity ranged from 71% to 97.7%, specificity from 63% to 91.4%, and accuracy from 71% to 87%. In cervical cancer studies, sensitivity ranged from 88% to 93%, and specificity from 85% to 100%. Electronic nose technologies show encouraging diagnostic accuracy in gynecologic oncology, particularly for cervical cancer, whereas performance in ovarian cancer remains more variable depending on the biological matrix and comparator group. Despite promising results, the lack of standardized protocols and the heterogeneity of current evidence limit immediate clinical translation. Larger, multicenter, and standardized studies are needed to validate their integration into diagnostic workflows.

Artificial intelligence-enhanced magnetic resonance imaging-based pre-operative staging in patients with endometrial cancer

Evaluation of prognostic factors is crucial in patients with endometrial cancer for optimal treatment planning and prognosis assessment. This study proposes a deep learning pipeline for tumor and uterus segmentation from magnetic resonance imaging (MRI) images to predict deep myometrial invasion and cervical stroma invasion and thus assist clinicians in pre-operative workups. Two experts consensually reviewed the MRIs and assessed myometrial invasion and cervical stromal invasion as per the International Federation of Gynecology and Obstetrics staging classification, to compare the diagnostic performance of the model with the radiologic consensus. The deep learning method was trained using sagittal T2-weighted images from 142 patients and tested with a 3-fold stratified test with 36 patients in each fold. Our solution is based on a segmentation module, which employed a 2-stage pipeline for efficient uterus in the whole MRI volume and then tumor segmentation in the uterus predicted region of interest. A total of 178 patients were included. For deep myometrial invasion prediction, the model achieved an average balanced test accuracy over 3-folds of 0.702, while experts reached an average accuracy of 0.769. For cervical stroma invasion prediction, our model demonstrated an average balanced accuracy of 0.721 on the 3-fold test set, while experts achieved an average balanced accuracy of 0.859. Additionally, the accuracy rates for uterus and tumor segmentation, measured by the Dice score, were 0.847 and 0.579 respectively. Despite the current challenges posed by variations in data, class imbalance, and the presence of artifacts, our fully automatic approach holds great promise in supporting in pre-operative staging. Moreover, it demonstrated a robust capability to segment key regions of interest, specifically the uterus and tumors, highlighting the positive impact our solution can bring to health care imaging.

Minimally Invasive Simple Hysterectomy in Low Risk Cervical Cancer

The rationale of the present study is to assess the safety of the minimally invasive surgery approach in patients meeting the SHAPE trial inclusion criteria.The SHAPE trial was designed to answer the clinical question of whether simple hysterectomy could be performed instead of radical hysterectomy in low-risk early stage cervical cancer but not the surgical approach. The favorable oncological outcome observed in SHAPE despite 75% of patients were treated with minimally invasive approach suggests that this approach may be safe. However, the trial was not designed to analyze oncological outcomes from surgical approach.