The accuracy of intraoperative frozen section examination of sentinel lymph nodes in squamous cell cancer of the vulva

Preoperative prediction model of lymph node metastasis in the inguinal and femoral region based on radiomics and artificial intelligence

OBJECTIVE

To predict preoperative inguinal lymph node metastasis in vulvar cancer patients using a machine learning model based on imaging features and clinical data from pelvic magnetic resonance imaging (MRI).

METHODS

52 vulvar cancer patients were divided into a training set (n=37) and validation set (n=15). Clinical data and MRI images were collected, and regions of interest were delineated by experienced radiologists. A total of 1688 quantitative imaging features were extracted using the Radcloud platform. Dimensionality reduction and feature selection were applied, resulting in a radiomics signature. Clinical characteristics were screened, and a combined model integrating the radiomics signature and significant clinical features was constructed using logistic regression. Four machine learning classifiers (K nearest neighbor, random forest, adaptive boosting, and latent dirichlet allocation) were trained and validated. Model performance was evaluated using the receiver operating characteristic curve and the area under the curve (AUC), as well as decision curve analysis.

RESULTS

The radiomics score significantly differentiated between lymph node metastasis positive and negative patients in both the training and validation sets. The combined model demonstrated excellent discrimination, with AUC values of 0.941 and 0.933 in the training and validation sets, respectively. The calibration curve and decision curve analysis confirmed the model's high predictive accuracy and clinical utility. Among the machine learning classifiers, latent dirichlet allocation and random forest models achieved AUC values >0.7 in the validation set. Integrating all four classifiers resulted in a total model with an AUC of 0.717 in the validation set.

CONCLUSION

Radiomics combined with artificial intelligence can provide a new method for prediction of inguinal lymph node metastasis of vulvar cancer before surgery.

Intraoperative frozen section in gynaecology cancers with special reference to ovarian tumours: time to "unfreeze" the pitfalls in the path of the Derby horse of Oncology

PURPOSE

In an oncological set up the role of frozen section biopsy is undeniable. They serve as an important tool for surgeon's intraoperative decision making but the diagnostic reliability of intraoperative frozen section may vary from institute to institute. The surgeon should be well aware of the accuracy of the frozen section reports in their setup to enable them to take decisions based on the report. This is why we had conducted a retrospective study at Dr B. Borooah Cancer Institute, Guwahati, Assam, India to find out our institutional frozen section accuracy.

METHODS

The study was conducted from 1st January 2017 to 31st December 2022 (5 years). All gynaecology oncology patients who were operated on during the study period and had an intraoperative frozen section done were included in the study. Patients who had incomplete final histopathological report (HPR) or no final HPR were excluded from the study. Frozen section and final histopathology report were compared and analysed and discordant cases were analysed based on the degree of discordancy.

RESULTS

For benign ovarian disease, the IFS accuracy, sensitivity and specificity are 96.7%, 100% and 93%, respectively. For borderline ovarian disease the IFS accuracy, sensitivity and specificity are 96.7%, 80% and 97.6%, respectively. For malignant ovarian disease the IFS accuracy, sensitivity and specificity are 95.4%, 89.1% and 100%, respectively. Sampling error was the most common cause of discordancy.

CONCLUSION

Intraoperative frozen section may not have 100% diagnostic accuracy but still it is the running horse of our oncological institute.

European Society of Gynaecological Oncology Guidelines for the Management of Patients with Vulvar Cancer - Update 2023

BACKGROUND

As part of its mission to improve the quality of care for women with gynecological cancers across Europe, the European Society of Gynaecological Oncology (ESGO) first published in 2017 evidence-based guidelines for the management of patients with vulvar cancer.

OBJECTIVE

To update the ESGO guidelines based on the new evidence addressing the management of vulvar cancer and to cover new topics in order to provide comprehensive guidelines on all relevant issues of diagnosis and treatment of vulvar cancer.

METHODS

The ESGO Council nominated an international development group comprised of practicing clinicians who provide care to vulvar cancer patients and have demonstrated leadership through their expertize in clinical care and research, national and international engagement and profile as well as dedication to the topics addressed to serve on the expert panel (18 experts across Europe). To ensure that the statements were evidence-based, new data identified from a systematic search were reviewed and critically appraised. In the absence of any clear scientific evidence, judgment was based on the professional experience and consensus of the international development group. Prior to publication, the guidelines were reviewed by 206 international practitioners in cancer care delivery and patient representatives.

RESULTS

The updated guidelines cover comprehensively diagnosis and referral, staging, pathology, pre-operative investigations, surgical management (local treatment, groin treatment, sentinel lymph node procedure, reconstructive surgery), (chemo)radiotherapy, systemic treatment, treatment of recurrent disease (vulvar, inguinal, pelvic, and distant recurrences), and follow-up. Management algorithms are also defined.

Sentinel Lymph Node Mapping: Current Applications and Future Perspectives in Gynecology Malignant Tumors

The sentinel lymph nodes (SLNs) is a group of lymph nodes initially involved in the metastatic spread of cancer cells. SLN mapping refers to intraoperative localization and biopsy of SLNs with specific tracers to assess lymph node metastases. It is widely used in a variety of tumor surgeries for its high sensitivity and high negative predictive value. In the evaluation of the status of lymph node metastases in gynecological malignancies, it has received increasingly more attention due to its minor invasiveness, few complications, and high diagnosis rate. The National Comprehensive Cancer Network (NCCN) guidelines provide an excellent introduction to the indications and methods of SLN techniques in vulvar, cervical, and endometrial cancers, but they provide little explanation about some specific issues. In this review, we summarize different dyes and injection methods and discuss the indications of application and the clinical trials of SLN mapping in gynecological malignant tumors, aiming to provide a reference for the rational application of sentinel techniques in gynecology malignant tumors before relevant guidelines are updated.