โก Quick Summary
This study developed radiomics models utilizing 18F-FDG PET/CT imaging to predict the expression status of Her-2 and Ki-67 in gastric cancer patients. The logistic regression model demonstrated an impressive AUC of 0.86 for Ki-67, indicating its potential as a non-invasive diagnostic tool.
๐ Key Details
- ๐ Dataset: 90 patients with gastric cancer
- ๐งฉ Imaging Technique: 18F-FDG PET/CT
- โ๏ธ Analysis Tools: PyRadiomics package for feature extraction
- ๐ Models Used: Logistic Regression (LR) and Support Vector Machine (SVM)
- ๐ Performance Metrics: AUC and accuracy for Ki-67 and Her-2
๐ Key Takeaways
- ๐ฌ Radiomics features from visceral adipose tissue can predict Her-2 and Ki-67 expression in gastric cancer.
- ๐ Logistic Regression model outperformed SVM for predicting Ki-67 with an AUC of 0.86.
- ๐ Significant correlation found between wavelet transform features and Her-2 expression (p < 0.001).
- ๐ Overall accuracy for Ki-67 was 79% with LR, while Her-2 accuracy was 86%.
- ๐ก Non-invasive imaging could replace traditional immunohistochemistry methods.
- ๐ Study published in the British Journal of Hospital Medicine.
- ๐ PMID: 39347666.
๐ Background
Gastric cancer (GC) remains a significant health challenge globally, often diagnosed at advanced stages. Traditional methods for assessing biomarkers like Her-2 and Ki-67 rely on invasive techniques such as immunohistochemistry (IHC), which may not reflect real-time tumor characteristics. The integration of radiomics and advanced imaging techniques offers a promising alternative for non-invasive diagnostics.
๐๏ธ Study
The study involved 90 patients diagnosed with gastric cancer, aiming to establish a relationship between radiomics features derived from visceral adipose tissue and the expression levels of Her-2 and Ki-67. Using the PyRadiomics package, researchers extracted various imaging features from 18F-FDG PET/CT scans and applied machine learning techniques to develop predictive models.
๐ Results
The results indicated that the logistic regression model for Ki-67 achieved an AUC of 0.86 and an accuracy of 79%, showcasing its superior predictive capability. For Her-2, the LR model yielded an AUC of 0.84 and an accuracy of 86%. Notably, specific wavelet transform features were significantly correlated with Her-2 expression status (p < 0.001).
๐ Impact and Implications
The findings from this study highlight the potential of 18F-FDG PET/CT-based radiomics as a non-invasive tool for predicting critical biomarkers in gastric cancer. This approach could significantly enhance preoperative planning and personalized treatment strategies, ultimately improving patient outcomes. The ability to assess tumor characteristics in real-time without invasive procedures represents a substantial advancement in cancer diagnostics.
๐ฎ Conclusion
This research underscores the promising role of radiomics in the preoperative assessment of gastric cancer. By leveraging advanced imaging techniques, healthcare professionals can gain valuable insights into tumor biology, paving the way for more tailored therapeutic approaches. Continued exploration in this field could lead to transformative changes in cancer care.
๐ฌ Your comments
What are your thoughts on the use of radiomics in cancer diagnostics? We invite you to share your insights and engage in a discussion! ๐ฌ Leave your comments below or connect with us on social media:
Preoperative Prediction of Her-2 and Ki-67 Status in Gastric Cancer Using 18F-FDG PET/CT Radiomics Features of Visceral Adipose Tissue.
Abstract
Aims/Background Immunohistochemistry (IHC) is the main method to detect human epidermal growth factor receptor 2 (Her-2) and Ki-67 expression levels. However, IHC is invasive and cannot reflect their expression status in real-time. This study aimed to build radiomics models based on visceral adipose tissue (VAT)’s 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) imaging, and to evaluate the relationship between radiomics features of VAT and positive expression of Her-2 and Ki-67 in gastric cancer (GC). Methods Ninety patients with GC were enrolled in this study. 18F-FDG PET/CT radiomics features were calculated using the PyRadiomics package. Two methods were employed to reduce radiomics features. The machine learning models, logistic regression (LR), and support vector machine (SVM), were constructed and estimated by the receiver operator characteristic (ROC) curve. The correlation of outstanding features with Ki-67 and Her-2 expression status was evaluated. Results For the Ki-67 set, the area under of the receiver operator characteristic curve (AUC) and accuracy were 0.86 and 0.79 for the LR model and 0.83 and 0.69 for the SVM model. For the Her-2 set, the AUC and accuracy were 0.84 and 0.86 for the LR model and 0.65 and 0.85 for the SVM model. The LR model for Ki-67 exhibited outstanding prediction performance. Three wavelet transform features were correlated with Her-2 expression status (p all < 0.001), and one wavelet transform feature was correlated with the expression status of Ki-67 (p = 0.042). Conclusion 18F-FDG PET/CT-based radiomics models of VAT demonstrate good performance in predicting Her-2 and Ki-67 expression status in patients with GC. Radiomics features can be used as imaging biomarkers for GC.
Author: [‘Chen D’, ‘Zhou R’, ‘Li B’]
Journal: Br J Hosp Med (Lond)
Citation: Chen D, et al. Preoperative Prediction of Her-2 and Ki-67 Status in Gastric Cancer Using 18F-FDG PET/CT Radiomics Features of Visceral Adipose Tissue. Preoperative Prediction of Her-2 and Ki-67 Status in Gastric Cancer Using 18F-FDG PET/CT Radiomics Features of Visceral Adipose Tissue. 2024; 85:1-18. doi: 10.12968/hmed.2024.0350