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

International Journal of Gynecological Cancer, Год журнала: 2023, Номер 33(7), С. 1070 - 1076

Опубликована: Апрель 24, 2023

Objective Endometrial carcinoma is the most common gynecological tumor in developed countries. Clinicopathological factors and molecular subtypes are used to stratify risk of recurrence tailor adjuvant treatment. The present study aimed assess role radiomics analysis pre-operatively predicting or clinicopathological prognostic patients with endometrial carcinoma. Methods Literature was searched for publications reporting assessing diagnostic performance MRI different outcomes. Diagnostic accuracy prediction models pooled using metandi command Stata. Results A search MEDLINE (PubMed) resulted 153 relevant articles. Fifteen articles met inclusion criteria, a total 3608 patients. showed sensitivity specificity 0.785 0.814, respectively, high-grade carcinoma, deep myometrial invasion (pooled 0.743 0.816, respectively), lymphovascular space 0.656 0.753, nodal metastasis 0.831 0.736, respectively). Conclusions Pre-operative MRI-radiomics analyses good predictor grading, invasion, metastasis.

Язык: Английский

---

Application of magnetic resonance imaging radiomics in endometrial cancer: a systematic review and meta-analysis

La radiologia medica, Год журнала: 2024, Номер 129(3), С. 439 - 456

Опубликована: Фев. 13, 2024

Язык: Английский

---

Differentiation between cerebral alveolar echinococcosis and brain metastases with radiomics combined machine learning approach

European journal of medical research, Год журнала: 2023, Номер 28(1)

Опубликована: Дек. 9, 2023

Abstract Background Cerebral alveolar echinococcosis (CAE) and brain metastases (BM) share similar in locations imaging appearance. However, they require distinct treatment approaches, with CAE typically treated chemotherapy surgery, while BM is managed radiotherapy targeted therapy for the primary malignancy. Accurate diagnosis crucial due to divergent strategies. Purpose This study aims evaluate effectiveness of radiomics machine learning techniques based on magnetic resonance (MRI) differentiate between BM. Methods We retrospectively analyzed MRI images 130 patients (30 100 BM) from Xinjiang Medical University First Affiliated Hospital The People's Kashi Prefecture, January 2014 December 2022. dataset was divided into training (91 cases) testing (39 sets. Three dimensional tumors were segmented by radiologists contrast-enhanced T1WI open resources software 3D Slicer. Features extracted Pyradiomics, further feature reduction carried out using univariate analysis, correlation least absolute shrinkage selection operator (LASSO). Finally, we built five models, support vector machine, logistic regression, linear discrimination k-nearest neighbors classifier, Gaussian naïve bias evaluated their performance via several metrics including sensitivity (recall), specificity, positive predictive value (precision), negative value, accuracy area under curve (AUC). Results (AUC) classifier (SVC), analysis (LDA), (KNN), gaussian (NB) algorithms (testing) sets are 0.99 (0.94), 1.00 (0.87), 0.98 (0.92), 0.97 (0.97), (0.93), respectively. Nested cross-validation demonstrated robustness generalizability models. Additionally, calibration plot decision practical usefulness these models clinical practice, lower toward different subgroups during decision-making. Conclusion combination approach contrast enhanced could well distinguish holds promise assisting doctors accurate

Язык: Английский

---

Multiparametric MRI radiomics improves preoperative diagnostic performance for local staging in patients with endometrial cancer

Abdominal Radiology, Год журнала: 2024, Номер 49(3), С. 875 - 887

Опубликована: Янв. 8, 2024

Язык: Английский

---

Evaluating the quality of radiomics-based studies for endometrial cancer using RQS and METRICS tools

European Radiology, Год журнала: 2024, Номер 35(1), С. 202 - 214

Опубликована: Июль 16, 2024

To assess the methodological quality of radiomics-based models in endometrial cancer using radiomics score (RQS) and METhodological radiomICs (METRICS).

Язык: Английский

---

A comparison of 2D and 3D magnetic resonance imaging-based intratumoral and peritumoral radiomics models for the prognostic prediction of endometrial cancer: a pilot study

Cancer Imaging, Год журнала: 2024, Номер 24(1)

Опубликована: Июль 31, 2024

Abstract Background Accurate prognostic assessment is vital for the personalized treatment of endometrial cancer (EC). Although radiomics models have demonstrated potential in EC, impact region interest (ROI) delineation strategies and clinical significance peritumoral features remain uncertain. Our study thereby aimed to explore predictive performance varying prediction LVSI, DMI, disease stage EC. Methods Patients with 174 histopathology-confirmed EC were retrospectively reviewed. ROIs manually delineated using 2D 3D approach on T2-weighted MRI images. Six involving intratumoral (2D intra ), peri combined + ) developed. Models constructed logistic regression method five-fold cross-validation. Area under receiver operating characteristic curve (AUC) was assessed, compared Delong’s test. Results No significant differences AUC observed between models, or all tasks ( P > 0.05). Significant difference LVSI (0.738 vs. 0.805) DMI (0.719 0.804). The significantly better 3 model both training validation cohorts < Conclusions Comparable models. Combined improved performance, especially delineation, suggesting that intra- can provide complementary information comprehensive prognostication

Язык: Английский

---

Accuracy of radiomics in the diagnosis and preoperative high-risk assessment of endometrial cancer: a systematic review and meta-analysis

Frontiers in Oncology, Год журнала: 2024, Номер 14

Опубликована: Янв. 25, 2024

Background With the increasing use of radiomics in cancer diagnosis and treatment, it has been applied by some researchers to preoperative risk assessment endometrial (EC) patients. However, comprehensive systematic evidence is needed assess its clinical value. Therefore, this study aims investigate application value treatment EC. Methods Pubmed, Cochrane, Embase, Web Science databases were retrieved up March 2023. Preoperative EC included high-grade EC, lymph node metastasis, deep myometrial invasion status, lymphovascular space status. The quality studies was appraised utilizing RQS scale. Results A total 33 primary our review, with an average score 7 (range: 5–12). ML models based on for malignant lesions predominantly employed logistic regression. In validation set, pooled c-index features malignancy, tumors, invasion, 0.900 (95%CI: 0.871–0.929), 0.901 0.877–0.926), 0.906 0.882–0.929), 0.795 0.693–0.897), 0.819 0.705–0.933), respectively. Conclusions Radiomics shows excellent accuracy detecting malignancies identifying risk. methodological diversity results significant heterogeneity among studies. future research should establish guidelines different imaging sources. Systematic review registration https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=364320 identifier CRD42022364320.

Язык: Английский

---

Radiomics model based on multi-sequence MRI for preoperative prediction of ki-67 expression levels in early endometrial cancer

Scientific Reports, Год журнала: 2023, Номер 13(1)

Опубликована: Дек. 12, 2023

To validate a radiomics model based on multi-sequence magnetic resonance imaging (MRI) in predicting the ki-67 expression levels early-stage endometrial cancer, 131 patients with early cancer who had undergone pathological examination and preoperative MRI scan were retrospectively enrolled divided into two groups levels. The features extracted from T2 weighted (T2WI), dynamic contrast enhanced T1 (DCE-T1WI), apparent diffusion coefficient (ADC) map screened using Pearson correlation coefficients (PCC). A multi-layer perceptual machine fivefold cross-validation used to construct model. receiver operating characteristic (ROC) curves analysis, calibration curves, decision curve analysis (DCA) assess models. combined of T2WI, DCE-T1WI, ADC showed better discriminatory powers than those only one sequence. models fusions achieved highest area under ROC (AUC). AUC value validation set was 0.852, an accuracy 0.827, sensitivity 0.844, specificity 0.773, precision 0.799. In conclusion, enables noninvasive prediction cancer. This provides objective basis for clinical diagnosis treatment.

Язык: Английский

---

Artificial Intelligence and Radiomics for Endometrial Cancer MRI: Exploring the Whats, Whys and Hows

Journal of Clinical Medicine, Год журнала: 2023, Номер 13(1), С. 226 - 226

Опубликована: Дек. 30, 2023

Endometrial cancer (EC) is intricately linked to obesity and diabetes, which are widespread risk factors. Medical imaging, especially magnetic resonance imaging (MRI), plays a major role in EC assessment, particularly for disease staging. However, the diagnostic performance of MRI exhibits variability detection clinically relevant prognostic factors (e.g., deep myometrial invasion metastatic lymph nodes assessment). To address these challenges enhance value MRI, radiomics artificial intelligence (AI) algorithms emerge as promising tools with potential impact treatment planning, prognosis prediction. These advanced post-processing techniques allow us quantitatively analyse medical images, providing novel insights into characteristics beyond conventional qualitative image evaluation. despite growing interest research efforts, integration AI management still far from clinical practice represents possible perspective rather than an actual reality. This review focuses on state emphasizing stratification factor prediction, aiming illuminate advancements existing field.

Язык: Английский

---

Predicting Risk Stratification in Early-Stage Endometrial Carcinoma: Significance of Multiparametric MRI Radiomics Model

Deleted Journal, Год журнала: 2024, Номер 37(1), С. 81 - 91

Опубликована: Янв. 18, 2024

Endometrial carcinoma (EC) risk stratification prior to surgery is crucial for clinical treatment. In this study, we intend evaluate the predictive value of radiomics models based on magnetic resonance imaging (MRI) and staging early-stage EC. The study included 155 patients who underwent MRI examinations were pathologically diagnosed with EC between January, 2020, September, 2022. Three-dimensional features extracted from segmented tumor images captured by scans (including T2WI, CE-T1WI delayed phase, ADC), 1521 each three modalities. Then, using five-fold cross-validation a multilayer perceptron algorithm, these filtered Pearson's correlation coefficient develop prediction model performance was assessed analyzing ROC curves calculating AUC, accuracy, sensitivity, specificity. terms stratification, CE-T1 sequence demonstrated highest accuracy 0.858 ± 0.025 an AUC 0.878 0.042 among sequences. However, combining all sequences resulted in enhanced reaching 0.881 0.040, corresponding increase 0.862 0.069. context staging, utilization combination involving T2WI led notably elevated 0.956 0.020, surpassing achieved when employing any singular feature. Correspondingly, 0.979 0.022. When incorporating concurrently, reached 0.000, accompanied 0.986 0.007. It noteworthy that level surpassed radiologist, which stood at 0.832. has potential accurately predict early

Язык: Английский

---