Combining positron emission tomography/computed tomography, radiomics, and sentinel lymph node mapping for nodal staging of endometrial cancer patients

Determining Accurate Dye Combinations for Sentinel Lymph Node Detection: A Systematic Review

Background

Lymphatic dyes are commonly used to map the drainage path from tumor to lymphatics, which are biopsied to determine if spread has occurred. A blue dye in combination with technetium-99 is considered the gold standard for mapping, although many other dyes and dye combinations are used. Not all of these substances have the same detection efficacy.

Methods

A systematic review of PubMed, SCOPUS, Web of Science, and Medline was performed. The predefined search terms were (indocyanine green OR isosulfan blue OR lymphazurin OR patent blue OR methylene blue OR fluorescein OR technetium-99) AND combination AND dye AND (sentinel lymph node biopsy OR lymphedema OR lymphatics OR lymph OR microsurgery OR cancer OR tumor OR melanoma OR carcinoma OR sarcoma).

Results

The initial search returned 4267 articles. From these studies, 37 were selected as candidates that met inclusion criteria. After a full-text review, 34 studies were selected for inclusion. Eighty-nine methods of sentinel lymph node (SLN) detection were trialed using 22 unique dyes, dye combinations, or other tracers. In total, 12,157 SLNs of 12,801 SLNs were identified. Dye accuracy ranged from 100% to 69.8% detection. Five dye combinations had 100% accuracy. Dye combinations were more accurate than single dyes.

Conclusions

Combining lymphatic dyes improves SLN detection results. Replacing technetium-99 with ICG may allow for increased access to SLN procedures with comparable results. The ideal SLN tracer is a low-cost molecule with a high affinity for lymphatic vessels due to size and chemical composition, visualization without specialized equipment, and no adverse effects.

The value of machine learning in preoperative identification of lymph node metastasis status in endometrial cancer: a systematic review and meta-analysis

Background

The early identification of lymph node metastasis status in endometrial cancer (EC) is a serious challenge in clinical practice. Some investigators have introduced machine learning into the early identification of lymph node metastasis in EC patients. However, the predictive value of machine learning is controversial due to the diversity of models and modeling variables. To this end, we carried out this systematic review and meta-analysis to systematically discuss the value of machine learning for the early identification of lymph node metastasis in EC patients.

Methods

A systematic search was conducted in Pubmed, Cochrane, Embase, and Web of Science until March 12, 2023. PROBAST was used to assess the risk of bias in the included studies. In the process of meta-analysis, subgroup analysis was performed according to modeling variables (clinical features, radiomic features, and radiomic features combined with clinical features) and different types of models in various variables.

Results

This systematic review included 50 primary studies with a total of 103,752 EC patients, 12,579 of whom had positive lymph node metastasis. Meta-analysis showed that among the machine learning models constructed by the three categories of modeling variables, the best model was constructed by combining radiomic features with clinical features, with a pooled c-index of 0.907 (95%CI: 0.886-0.928) in the training set and 0.823 (95%CI: 0.757-0.890) in the validation set, and good sensitivity and specificity. The c-index of the machine learning model constructed based on clinical features alone was not inferior to that based on radiomic features only. In addition, logistic regression was found to be the main modeling method and has ideal predictive performance with different categories of modeling variables.

Conclusion

Although the model based on radiomic features combined with clinical features has the best predictive efficiency, there is no recognized specification for the application of radiomics at present. In addition, the logistic regression constructed by clinical features shows good sensitivity and specificity. In this context, large-sample studies covering different races are warranted to develop predictive nomograms based on clinical features, which can be widely applied in clinical practice.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO, identifier CRD42023420774.

A Radiomic-Based Machine Learning Model Predicts Endometrial Cancer Recurrence Using Preoperative CT Radiomic Features: A Pilot Study

BACKGROUND

Current prognostic models lack the use of pre-operative CT images to predict recurrence in endometrial cancer (EC) patients. Our study aimed to investigate the potential of radiomic features extracted from pre-surgical CT scans to accurately predict disease-free survival (DFS) among EC patients.

METHODS

Contrast-Enhanced CT (CE-CT) scans from 81 EC cases were used to extract the radiomic features from semi-automatically contoured volumes of interest. We employed a 10-fold cross-validation approach with a 6:4 training to test set and utilized data augmentation and balancing techniques. Univariate analysis was applied for feature reduction leading to the development of three distinct machine learning (ML) models for the prediction of DFS: LASSO-Cox, CoxBoost and Random Forest (RFsrc).

RESULTS

In the training set, the ML models demonstrated AUCs ranging from 0.92 to 0.93, sensitivities from 0.96 to 1.00 and specificities from 0.77 to 0.89. In the test set, AUCs ranged from 0.86 to 0.90, sensitivities from 0.89 to 1.00 and specificities from 0.73 to 0.90. Patients classified as having a high recurrence risk prediction by ML models exhibited significantly worse DSF (p-value < 0.001) across all models.

CONCLUSIONS

Our findings demonstrate the potential of radiomics in predicting EC recurrence. While further validation studies are needed, our results underscore the promising role of radiomics in forecasting EC outcomes.

Radiomics-based fertility-sparing treatment in endometrial carcinoma: a review

In recent years, with the increasing incidence of endometrial carcinoma in women of child-bearing age, to decision of whether to preserve patients' fertility during treatment has become increasingly complex, presenting a formidable challenge for both physicians and patients. Non-fertility-sparing treatment can remove lesions more thoroughly than fertility-sparing treatment. However, patients will permanently lose their fertility. In contrast, fertility-sparing treatment can treat tumors without impairing fertility, but the risk of disease progression is high as compared with non-fertility-sparing treatment. Therefore, it is extremely important to accurately identify patients who are suitable for fertility-sparing treatments. The evaluation of prognostic factors, including myometrial invasion, the presence of lymph node metastases, and histopathological type, is vital for determining whether a patient can receive fertility-sparing treatment. As a non-invasive and quantitative approach, radiomics has the potential to assist radiologists and other clinicians in determining more precise judgments with regard to the above factors by extracting imaging features and establishing predictive models. In this review, we summarized currently available fertility-sparing strategies and reviewed the performance of radiomics in predicting risk factors associated with fertility-sparing treatment. This review aims to assist clinicians in identifying patients suitable for fertility-sparing treatment more accurately and comprehensively and informs more appropriate and rigorous treatment decisions for endometrial cancer patients of child-bearing age.Critical relevance statement: Radiomics is a promising tool that may assist clinicians identify risk factors about fertility-sparing more accurately and comprehensively.

Magnetic resonance imaging-radiomics in endometrial cancer: a systematic review and meta-analysis

OBJECTIVE

Endometrial carcinoma is the most common gynecological tumor in developed countries. Clinicopathological factors and molecular subtypes are used to stratify the risk of recurrence and to tailor adjuvant treatment. The present study aimed to assess the role of radiomics analysis in pre-operatively predicting molecular or clinicopathological prognostic factors in patients with endometrial carcinoma.

METHODS

Literature was searched for publications reporting radiomics analysis in assessing diagnostic performance of MRI for different outcomes. Diagnostic accuracy performance of risk prediction models was pooled using the metandi command in Stata.

RESULTS

A search of MEDLINE (PubMed) resulted in 153 relevant articles. Fifteen articles met the inclusion criteria, for a total of 3608 patients. MRI showed pooled sensitivity and specificity 0.785 and 0.814, respectively, in predicting high-grade endometrial carcinoma, deep myometrial invasion (pooled sensitivity and specificity 0.743 and 0.816, respectively), lymphovascular space invasion (pooled sensitivity and specificity 0.656 and 0.753, respectively), and nodal metastasis (pooled sensitivity and specificity 0.831 and 0.736, respectively).

CONCLUSIONS

Pre-operative MRI-radiomics analyses in patients with endometrial carcinoma is a good predictor of tumor grading, deep myometrial invasion, lymphovascular space invasion, and nodal metastasis.

A systematic review about the role of preoperative 18F-FDG PET/CT for prognosis and risk stratification in patients with endometrial cancer

OBJECTIVE

To analyse the available literature on the prognostic value of preoperative ¹⁸F-FDG PET/CT metabolic parameters and their usefulness in risk stratification in patients with endometrial cancer (EC).

MATERIAL AND METHODS

Pubmed searches used "(endometr* OR uter*) AND (PET OR FDG)" as keywords from January-2000 to June-2020. References in included articles were checked for possible publications not included in the first search. Studies evaluating the prognostic value of preoperative ¹⁸F-FDG PET/CT and its role for risk stratification in patients with EC were included. Non-original articles (reviews, editorials, letters, legal cases, interviews, case reports, etc.) were not included.

RESULTS

Twenty-six studies (1918 patients) were selected according to the inclusion criteria in this review. Thirteen studies (939 patients) related to the prognostic role of preoperative ¹⁸F-FDG PET/CT and 14 studies (1036 patients) related to its role in risk stratification were included. Parameters such as SUVmax, metabolic tumour volume (MTV) and total lesion glycolysis (TLG) of the primary tumour were analysed.

CONCLUSIONS

Preoperative SUVmax is useful for non-invasive diagnosis and for deciding the appropriate therapeutic strategy, as it could be used as an independent prognostic marker for recurrence and survival in EC. In addition, both preoperative VTM and GTL could be independent prognostic factors for predicting recurrence and survival, but there is still insufficient scientific evidence. The usefulness of SUVmax for risk stratification is limited (there is insufficient literature that ¹⁸F-FDG PET/CT can replace surgical staging), although VTM and GTL are more accurate and have a valuable role in risk stratification of EC. However, larger multicentre studies with adequate follow-up time are needed to confirm these findings.

Radiomics in Oncological PET Imaging: A Systematic Review-Part 2, Infradiaphragmatic Cancers, Blood Malignancies, Melanoma and Musculoskeletal Cancers

The objective of this review was to summarize published radiomics studies dealing with infradiaphragmatic cancers, blood malignancies, melanoma, and musculoskeletal cancers, and assess their quality. PubMed database was searched from January 1990 to February 2022 for articles performing radiomics on PET imaging of at least 1 specified tumor type. Exclusion criteria includd: non-oncological studies; supradiaphragmatic tumors; reviews, comments, cases reports; phantom or animal studies; technical articles without a clinically oriented question; studies including <30 patients in the training cohort. The review database contained PMID, first author, year of publication, cancer type, number of patients, study design, independent validation cohort and objective. This database was completed twice by the same person; discrepant results were resolved by a third reading of the articles. A total of 162 studies met inclusion criteria; 61 (37.7%) studies included >100 patients, 13 (8.0%) were prospective and 61 (37.7%) used an independent validation set. The most represented cancers were esophagus, lymphoma, and cervical cancer (n = 24, n = 24 and n = 19 articles, respectively). Most studies focused on 18F-FDG, and prognostic and response to treatment objectives. Although radiomics and artificial intelligence are technically challenging, new contributions and guidelines help improving research quality over the years and pave the way toward personalized medicine.

Hybrid PET/MRI in Staging Endometrial Cancer: Diagnostic and Predictive Value in a Prospective Cohort

AIM

The assessment of deep myometrial invasion (MI) and lymph node involvement is of utmost importance in the preoperative staging of endometrial cancer (EC). Imaging parameters derived respectively from MRI and PET have shown good predictive value. The main aim of the present study is to assess the diagnostic performance of hybrid 18F-FDG PET/MRI in EC staging, with particular focus on MI and lymphnodal involvement detection.

PATIENTS AND METHODS

Prospective monocentric study including 35 patients with biopsy-proven EC undergoing preoperative 18F-FDG PET/MRI (December 2018-March 2021) for staging purpose. Histological examination was the reference standard. PET (SUVmax, SUVmean with a threshold of 40% of SUVmax-SUVmean40, metabolic tumor volume, total lesion glycolysis) and MRI (volume index [VI], total tumor volume, tumor volume ratio [TVR], mean apparent diffusion coefficient, minimum apparent diffusion coefficient) parameters were calculated on the primary tumor, and their role in predicting EC risk group, the presence of lymphovascular space invasion (LVSI), and MI was assessed. Receiver operating characteristics analysis was used to assess the predictive value of PET and MRI parameters on EC characteristics.

RESULTS

Patients' median age was 66.57 years (SD, 10.21 years). 18F-FDG PET/MRI identified the primary tumor in all patients. Twenty-two of 35 patients had high-risk EC and 13/35 low-risk disease; 13/35 presented LVSI, 22/35 had deep MI at histological examination, and 13/35 had p53 hyperexpression.PET/MRI was able to detect lymphnodal involvement with high accuracy and high specificity (sensitivity of 0.8571, specificity of 0.9286, accuracy of 0.9143), also showing a high negative predictive value (NPV) for lymphnodal involvement (NPV of 0.9630, positive predictive value [PPV] of 0.7500).The assessment of deep MI using PET/MRI correctly staged 27 patients (77.1%; sensitivity of 0.7273, specificity of 0.8462, accuracy of 0.7714), with also a good PPV (PPV of 0.8889, NPV of 0.647).MRI-derived total tumor volume, VI, and TVR were significant in predicting EC groups (high-risk vs low-risk patients) (P = 0.0059, 0.0235, 0.0181, respectively). MRI-derived volume, VI, TVR, and PET-derived metabolic tumor volume and total lesion glycolysis were able to predict LVSI (P = 0.0023, 0.0068, 0.0068, 0.0027, 0.01394, respectively). Imaging was not able to predict grading, presence of deep MI, nor hyperexpression of p53.

CONCLUSIONS

18F-FDG PET/MRI has good accuracy in preoperative staging of EC; PET and MRI parameters have synergic role in preoperatively predicting LVSI, with MRI parameters being also predictive for EC risk group.

Fusion imaging in preoperative assessment of extent of disease in patients with advanced ovarian cancer: feasibility and agreement with laparoscopic findings

OBJECTIVES

Fusion imaging is an emerging technique that combines real-time ultrasound examination with images acquired previously using other modalities, such as computed tomography (CT), magnetic resonance imaging and positron emission tomography. The primary aim of this study was to evaluate the feasibility of fusion imaging in patients with suspicion of ovarian or peritoneal cancer. Secondary aims were: to compare the agreement of findings on fusion imaging, CT alone and ultrasound imaging alone with laparoscopic findings, in the assessment of extent of intra-abdominal disease; and to evaluate the time required for the fusion imaging technique.

METHODS

Patients with clinical and/or radiographic suspicion of advanced ovarian or peritoneal cancer who were candidates for surgery were enrolled prospectively between December 2019 and September 2020. All patients underwent a CT scan and ultrasound and fusion imaging to evaluate the presence or absence of the following abdominal-cancer features according to the laparoscopy-based scoring model (predictive index value (PIV)): supracolic omental disease, visceral carcinomatosis on the liver, lesser omental carcinomatosis and/or visceral carcinomatosis on the lesser curvature of the stomach and/or spleen, involvement of the paracolic gutter(s) and/or anterior abdominal wall, involvement of the diaphragm and visceral carcinomatosis on the small and/or large bowel (regardless of rectosigmoid involvement). The feasibility of the fusion examination in these patients was evaluated. Agreement of each imaging method (ultrasound, CT and fusion imaging) with laparoscopy (considered as reference standard) was calculated using Cohen's kappa coefficient.

RESULTS

Fifty-two patients were enrolled into the study. Fusion imaging was feasible in 51 (98%) of these patients (in one patient, it was not possible for technical reasons). Two patients were excluded because laparoscopy was not performed, leaving 49 women in the final analysis. Kappa values for CT, ultrasound and fusion imaging, using laparoscopy as the reference standard, in assessing the PIV parameters were, respectively: 0.781, 0.845 and 0.896 for the great omentum; 0.329, 0.608 and 0.847 for the liver surface; 0.472, 0.549 and 0.756 for the lesser omentum and/or stomach and/or spleen; 0.385, 0.588 and 0.795 for the paracolic gutter(s) and/or anterior abdominal wall; 0.385, 0.497 and 0.657 for the diaphragm; and 0.336, 0.410 and 0.469 for the bowel. The median time needed to perform the fusion examination was 20 (range, 10-40) min.

CONCLUSION

Fusion of CT images and real-time ultrasound imaging is feasible in patients with suspicion of ovarian or peritoneal cancer and improves the agreement with surgical findings when compared with ultrasound or CT scan alone. © 2021 International Society of Ultrasound in Obstetrics and Gynecology.

Radiomics in cervical and endometrial cancer

Radiomics is an emerging field of research that aims to find associations between quantitative information extracted from imaging examinations and clinical data to support the best clinical decision. In the last few years, some papers have been evaluating the role of radiomics in gynecological malignancies, mainly focusing on ovarian cancer. Nonetheless, cervical cancer is the most frequent gynecological malignancy in developing countries and endometrial cancer is the most common in western countries. The purpose of this narrative review is to give an overview of the latest published papers evaluating the role of radiomics in cervical and endometrial cancer, mostly evaluating association with tumor prognostic factors, with response to therapy and with prediction of recurrence and distant metastasis.

Artificial intelligence-based radiomics models in endometrial cancer: A systematic review

BACKGROUND

Radiological preoperative assessment of endometrial cancer (EC) is in some cases not precise enough and its performances improvement could lead to a clinical benefit. Radiomics is a recent field of application of artificial intelligence (AI) in radiology.

AIMS

To investigate the contribution of radiomics on the radiological preoperative assessment of patients with EC; and to establish a simple and reproducible AI Quality Score applicable to Machine Learning and Deep Learning studies.

METHODS

We conducted a systematic review of current literature including original articles that studied EC through imaging-based AI techniques. Then, we developed a novel Simplified and Reproducible AI Quality score (SRQS) based on 10 items which ranged to 0 to 20 points in total which focused on clinical relevance, data collection, model design and statistical analysis. SRQS cut-off was defined at 10/20.

RESULTS

We included 17 articles which studied different radiological parameters such as deep myometrial invasion, lympho-vascular space invasion, lymph nodes involvement, etc. One article was prospective, and the others were retrospective. The predominant technique was magnetic resonance imaging. Two studies developed Deep Learning models, while the others machine learning ones. We evaluated each article with SRQS by 2 independent readers. Finally, we kept only 7 high-quality articles with clinical impact. SRQS was highly reproducible (Kappa = 0.95 IC 95% [0.907-0.988]).

CONCLUSION

There is currently insufficient evidence on the benefit of radiomics in EC. Nevertheless, this field is promising for future clinical practice. Quality should be a priority when developing these new technologies.

Additional Value of PET/CT-Based Radiomics to Metabolic Parameters in Diagnosing Lynch Syndrome and Predicting PD1 Expression in Endometrial Carcinoma

Purpose

We aim to compare the radiomic features and parameters on 2-deoxy-2-[fluorine-18] fluoro-D-glucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) between patients with endometrial cancer with Lynch syndrome and those with endometrial cancer without Lynch syndrome. We also hope to explore the biologic significance of selected radiomic features.

Materials and Methods

We conducted a retrospective cohort study, first using the 18F-FDG PET/CT images and clinical data from 100 patients with endometrial cancer to construct a training group (70 patients) and a test group (30 patients). The metabolic parameters and radiomic features of each tumor were compared between patients with and without Lynch syndrome. An independent cohort of 23 patients with solid tumors was used to evaluate the value of selected radiomic features in predicting the expression of the programmed cell death 1 (PD1), using 18F-FDG PET/CT images and RNA-seq genomic data.

Results

There was no statistically significant difference in the standardized uptake values on PET between patients with endometrial cancer with Lynch syndrome and those with endometrial cancer without Lynch syndrome. However, there were significant differences between the 2 groups in metabolic tumor volume and total lesion glycolysis (p < 0.005). There was a difference in the radiomic feature of gray level co-occurrence matrix entropy (GLCMEntropy; p < 0.001) between the groups: the area under the curve was 0.94 in the training group (sensitivity, 82.86%; specificity, 97.14%) and 0.893 in the test group (sensitivity, 80%; specificity, 93.33%). In the independent cohort of 23 patients, differences in GLCMEntropy were related to the expression of PD1 (r_s =0.577; p < 0.001).

Conclusions

In patients with endometrial cancer, higher metabolic tumor volumes, total lesion glycolysis values, and GLCMEntropy values on 18F-FDG PET/CT could suggest a higher risk for Lynch syndrome. The radiomic feature of GLCMEntropy for tumors is a potential predictor of PD1 expression.

Value of preoperative staging of endometrial carcinoma with contrast-enhanced ultrasonography: A PRISMA compliant meta-analysis

INTRODUCTION

Endometrial carcinoma (EC) is the most common gynecologic carcinoma in developed countries and accounts for nearly 5% of carcinoma cases and more than 2% of deaths due to female carcinomas worldwide. Because of this reported risk, it is very important to diagnose and stage it accurately. Therefore, we investigated the staging accuracy of EC with contrast-enhanced ultrasonography (CEUS). Due to a lack of studies on the use of CEUS in staging EC, we performed a systematic review and meta-analysis.

METHOD

We searched PubMed, EMBASE, Cochrane Library, Scopus, Web of science, China National Knowledge Infrastructure (CNKI), and CBM for studies on CEUS in EC diagnosis. Our search keywords were "ultrasonic angiography," "endometrial neoplasms," and their synonyms. The studies were screened according to the inclusion and exclusion criteria, and 4 tabular data were extracted. Quality evaluation was performed with the Quality Assessment of Diagnostic Accuracy Studies (QUADAS) scale. Statistical analysis was done with Stata version 15.1. A random effect model was selected to calculate the pooled sensitivity and specificity. The summary receiver operating characteristic (SROC) curve was obtained, and the area under the curve was calculated.

RESULT

Fifteen studies with 685 patients were included in this quantitative synthesis. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio (OR) of CEUS in the diagnosis of EC was 0.81 (95% confidence interval, .76-.85), .90 (.87-.92), 8 (5.8-11.1), .21 (.16-.28), and 38 (22-67), respectively. The area under the curve was 0.93 (.90-.95).

CONCLUSION

CEUS has a high sensitivity and specificity in the diagnosis of EC. It can be considered as an effective and feasible method for EC staging.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

Background: Although many works have supported the utility of PET radiomics, several authors have raised concerns over the robustness and replicability of the results. This study aimed to perform a systematic review on the topic of PET radiomics and the used methodologies. Methods: PubMed was searched up to 15 October 2020. Original research articles based on human data specifying at least one tumor type and PET image were included, excluding those that apply only first-order statistics and those including fewer than 20 patients. Each publication, cancer type, objective and several methodological parameters (number of patients and features, validation approach, among other things) were extracted. Results: A total of 290 studies were included. Lung (28%) and head and neck (24%) were the most studied cancers. The most common objective was prognosis/treatment response (46%), followed by diagnosis/staging (21%), tumor characterization (18%) and technical evaluations (15%). The average number of patients included was 114 (median = 71; range 20–1419), and the average number of high-order features calculated per study was 31 (median = 26, range 1–286). Conclusions: PET radiomics is a promising field, but the number of patients in most publications is insufficient, and very few papers perform in-depth validations. The role of standardization initiatives will be crucial in the upcoming years.

Receiver Operating Characteristic Prediction for Classification: Performances in Cross-Validation by Example

The stability of receiver operating characteristic in context of random split used in development and validation sets, as compared to the full models for three inflammatory ratios (neutrophil-to-lymphocyte (NLR), derived neutrophil-to-lymphocyte (dNLR) and platelet-to-lymphocyte (PLR) ratio) evaluated as predictors for metastasis in patients with colorectal cancer, was investigated. Data belonging to patients admitted with the diagnosis of colorectal cancer from January 2014 until September 2019 in a single hospital were used. There were 1688 patients eligible for the study, 418 in the metastatic stage. All investigated inflammatory ratios proved to be significant classification models on both the full models and on cross-validations (AUCs > 0.05). High variability of the cut-off values was observed in the unrestricted and restricted split (full models: 4.255 for NLR, 2.745 for dNLR and 255.56 for PLR; random splits: cut-off from 3.215 to 5.905 for NLR, from 2.625 to 3.575 for dNLR and from 134.67 to 335.9 for PLR), but with no effect on the models characteristics or performances. The investigated biomarkes proved limited value as predictors for metastasis (AUCs < 0.8), with largely sensitivity and specificity (from 33.3% to 79.2% for the full model and 29.1% to 82.7% in the restricted splits). Our results showed that a simple random split of observations, weighting or not the patients with and whithout metastasis, in a ROC analysis assures the performances similar to the full model, if at least 70% of the available population is included in the study.