MRI-based Radiomics nomogram to detect primary rectal cancer with synchronous liver metastases

We found that the model based on least absolute shrinkage and selection operator dimensionality construction had the maximum net benefit and in the validation set

Zhenyu Shu

2019

Scholarcy highlights

  • Rectal cancer is one of the most common malignant tumors of digestive tract with an increasing morbidity in the past few years, and 15~20% of the patients with rectal cancer have liver metastases at the time of diagnosis, which is defined as synchronous liver metastasis
  • T2-weighted imaging in magnetic resonance imaging is an important clinical imaging technique, which can provide high signal-to-noise ratio, spatial resolution and soft tissue contrast images for the tumor structures, and has been widely used for tumor grading based on morphological changes
  • The results indicated favorable intra and inter-observer feature extraction reproducibility
  • The radiomics signature showed favorable predictive efficacy, with an AUC of 0.857 in the training set and 0.834 in the validation set
  • The detect accuracy of the nomogram for detecting SLM was 0.921 in the training set and 0.912 in the validation set, respectively
  • It was widely accepted that the T2WI sequence was the most important for preoperatively assessing Tumor stage of rectal cancer, we developed a Radiomics nomogram based on T2WI
  • A radiomics nomogram has been constructed by combining Tumor stage factors with radiomics signature, which facilitates the accurate detection of the probability of a patient of rectal cancer with synchronous liver metastasis and may be helpful to physician in clinical decision

Need more features? Save interactive summary cards to your Scholarcy Library.