An MRI-Based Deep Transfer Learning Radiomics Nomogram to Predict Ki-67 Proliferation Index of Meningioma

Duan, Chongfeng; Hao, Dapeng; Cui, Jiufa; Wang, Gang; Xu, Wenjian; Li, Nan; Liu, Xuejun

doi:10.1007/s10278-023-00937-3

Cited by 1 publication

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We identified predictors of CSS that were consistent with previous studies, including race, age at diagnosis, primary site, grade, N stage, CEA status, liver metastasis, lung metastasis, bone metastasis, brain metastasis, surgery, and chemotherapy[ 18 ]. For patients with mCRC, both surgery and chemotherapy are important for improving outcomes, as recommended by the United States National Comprehensive Cancer Network (NCCN) guidelines and the European Society of Medical Oncology guidelines[ 19 ]. Modest suggested that the effective rate of first-line systemic treatment is 38% to 65%, and the disease control rate is 81% to 90%[ 20 ].…”

Section: Discussionmentioning

confidence: 99%

Analysis of cancer-specific survival in patients with metastatic colorectal cancer: A evidence-based medicine study

Zhou,

Tan,

Zhuang

et al. 2024

World J Gastrointest Surg

View full text Add to dashboard Cite

BACKGROUND Metastatic colorectal cancer (mCRC) is a common malignancy whose treatment has been a clinical challenge. Cancer-specific survival (CSS) plays a crucial role in assessing patient prognosis and treatment outcomes. However, there is still limited research on the factors affecting CSS in mCRC patients and their correlation. AIM To predict CSS, we developed a new nomogram model and risk grading system to classify risk levels in patients with mCRC. METHODS Data were extracted from the United States Surveillance, Epidemiology, and End Results database from 2018 to 2023. All eligible patients were randomly divided into a training cohort and a validation cohort. The Cox proportional hazards model was used to investigate the independent risk factors for CSS. A new nomogram model was developed to predict CSS and was evaluated through internal and external validation. RESULTS A multivariate Cox proportional risk model was used to identify independent risk factors for CSS. Then, new CSS columns were developed based on these factors. The consistency index (C-index) of the histogram was 0.718 (95%CI: 0.712-0.725), and that of the validation cohort was 0.722 (95%CI: 0.711-0.732), indicating good discrimination ability and better performance than tumor-node-metastasis staging (C-index: 0.712-0.732). For the training set, 0.533, 95%CI: 0.525-0.540; for the verification set, 0.524, 95%CI: 0.513-0.535. The calibration map and clinical decision curve showed good agreement and good potential clinical validity. The risk grading system divided all patients into three groups, and the Kaplan-Meier curve showed good stratification and differentiation of CSS between different groups. The median CSS times in the low-risk, medium-risk, and high-risk groups were 36 months (95%CI: 34.987-37.013), 18 months (95%CI: 17.273-18.727), and 5 months (95%CI: 4.503-5.497), respectively. CONCLUSION Our study developed a new nomogram model to predict CSS in patients with synchronous mCRC. In addition, the risk-grading system helps to accurately assess patient prognosis and guide treatment.

show abstract

Section: Discussionmentioning

confidence: 99%