A deep learning model for lymph node metastasis prediction based on digital histopathological images of primary endometrial cancer

Preoperative computed tomography semantic features in predicting lymph node metastasis of part-solid nodules in non-small cell lung cancer: a multicenter retrospective study

Background

Lymph node metastasis (LNM) is the most common route of metastasis for lung cancer, and it is an independent risk factor for long-term survival and recurrence in patients with non-small cell lung cancer (NSCLC). The purpose of this study was to explore the value of preoperative computed tomography (CT) semantic features in the differential diagnosis of LNM in part-solid nodules (PSNs) of NSCLC.

Methods

A total of 955 patients with NSCLC confirmed by postoperative pathology were retrospectively enrolled from January 2019 to March 2023. The clinical, pathological data and preoperative CT images of these patients were investigated and statistically analyzed in order to identify the risk factors for LNM. Multivariate logistic regression was used to select independent risk factors and establish different prediction models. Ten-fold cross-validation was used for model training and validation. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was calculated, and the Delong test was used to compare the predictive performance between the models.

Results

LNM occurred in 68 of 955 patients. After univariate analysis and adjustment for confounding factors, smoking history, pulmonary disease, solid component proportion, pleural contact type, and mean diameter were identified as the independent risk factors for LNM. The image predictors model established by the four independent factors of CT semantic features, except smoking history, showed a good diagnostic efficacy for LNM. The AUC in the validation group was 0.857, and the sensitivity, specificity, and accuracy of the model were all 77.6%.

Conclusions

Preoperative CT semantic features have good diagnostic value for the LNM of NSCLC. The image predictors model based on pulmonary disease, solid component proportion, pleural contact type, and mean diameter demonstrated excellent diagnostic efficacy and can provide non-invasive evaluation in clinical practice.

Impact of artificial intelligence on the diagnosis, treatment and prognosis of endometrial cancer

Endometrial cancer is one of the most prevalent tumours in females and holds an 83% survival rate within 5 years of diagnosis. Hypoestrogenism is a major risk factor for the development of endometrial carcinoma (EC) therefore two major types are derived, type 1 being oestrogen-dependent and type 2 being oestrogen independent. Surgery, chemotherapeutic drugs, and radiation therapy are only a few of the treatment options for EC. Treatment of gynaecologic malignancies greatly depends on diagnosis or prognostic prediction. Diagnostic imaging data and clinical course prediction are the two core pillars of artificial intelligence (AI) applications. One of the most popular imaging techniques for spotting preoperative endometrial cancer is MRI, although this technique can only produce qualitative data. When used to classify patients, AI improves the effectiveness of visual feature extraction. In general, AI has the potential to enhance the precision and effectiveness of endometrial cancer diagnosis and therapy. This review aims to highlight the current status of applications of AI in endometrial cancer and provide a comprehensive understanding of how recent advancements in AI have assisted clinicians in making better diagnosis and improving prognosis of endometrial cancer. Still, additional study is required to comprehend its strengths and limits fully.

Predictive models for lymph node metastasis in endometrial cancer: A systematic review and bibliometric analysis

BACKGROUND

Lymph node metastasis is associated with a poorer prognosis in endometrial cancer.

OBJECTIVE

The objective was to synthesize and critically appraise existing predictive models for lymph node metastasis risk stratification in endometrial cancer.

DESIGN

This study is a systematic review.

DATA SOURCES AND METHODS

We searched the Web of Science for articles reporting models predicting lymph node metastasis in endometrial cancer, with a systematic review and bibliometric analysis conducted based upon which. Risk of bias was assessed by the Prediction model Risk Of BiAS assessment Tool (PROBAST).

RESULTS

A total of 64 articles were included in the systematic review, published between 2010 and 2023. The most common articles were "development only." Traditional clinicopathological parameters remained the mainstream in models, for example, serum tumor marker, myometrial invasion and tumor grade. Also, models based upon gene-signatures, radiomics and digital histopathological images exhibited an acceptable self-reported performance. The most frequently validated models were the Mayo criteria, which reached a negative predictive value of 97.1%-98.2%. Substantial variability and inconsistency were observed through PROBAST, indicating significant between-study heterogeneity. A further bibliometric analysis revealed a relatively weak link between authors and organizations on models predicting lymph node metastasis in endometrial cancer.

CONCLUSION

A number of predictive models for lymph node metastasis in endometrial cancer have been developed. Although some exhibited promising performance as they demonstrated adequate to good discrimination, few models can currently be recommended for clinical practice due to lack of independent validation, high risk of bias and low consistency in measured predictors. Collaborations between authors, organizations and countries were weak. Model updating, external validation and collaborative research are urgently needed.

REGISTRATION

None.

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.