[Differences in dielectric properties between mucosal and serosal surface of malignant colorectal tissues, adjacent tissues at 1 cm and 3 cm and normal colorectal tissues]

[Comparison of dielectric properties of normal human esophagus and esophageal cancer using an open-ended coaxial probe]

OBJECTIVE

To study the difference in dielectric properties (relative permittivity and electrical conductivity) between normal human esophageal tissues and esophageal cancer tissues resected in esophageal cancer surgery for rapid identification of esophageal cancer during surgery.

METHODS

An open- end coaxial probe in the frequency range of 50 MHz to 4 GHz was used for dielectric measurement of the normal tissues and tumor tissues immediately after resection in 51 esophageal cancer cases. The difference in dielectric characteristics of the tissues was analyzed in the full frequency range, and the measurement data at 6 specific frequencies (64, 128, 298, 433, 915, and 2450 MHz) were analyzed statistically. The Cole-Cole model was used for data fitting in the entire frequency band and the measured values were compared with reported values.

RESULTS

In the frequency range of 50 MHz- 4 GHz, the dielectric measurement values of esophageal cancer tissues were significantly higher than those of normal esophageal tissues. At the 6 specific frequencies, the dielectric properties also differed significantly between normal esophageal tissues and esophageal cancer tissues (P < 0.01). The Cole-Cole model achieved a good fitting result of the measured data. The measured values in this study were lower than the reported values.

CONCLUSION

There are significant differences in the dielectric properties between normal esophageal tissue and tumor tissue, which may provide a new theoretical basis for rapid identification of esophageal cancer during surgery.

Classification of Metastatic and Non-Metastatic Thoracic Lymph Nodes in Lung Cancer Patients Based on Dielectric Properties Using Adaptive Probabilistic Neural Networks

Objective

Dielectric properties can be used in normal and malignant tissue identification, which requires an effective classifier because of the high throughput nature of the data. With easy training and fast convergence, probabilistic neural networks (PNNs) are widely applied in pattern classification problems. This study aims to propose a classifier to identify metastatic and non-metastatic thoracic lymph nodes in lung cancer patients based on dielectric properties.

Methods

The dielectric properties (permittivity and conductivity) of lymph nodes were measured using an open-ended coaxial probe. The Synthetic Minority Oversampling Technique method was adopted to modify the dataset. Feature parameters were scored to select the appropriate feature vector using a Statistical Dependency algorithm. The dataset was classified using adaptive PNNs with an optimized smooth factor using the simulated annealing PNN (SA-PNN). The results were compared with traditional Probabilistic, Support Vector Machines, k-Nearest Neighbor and the Classify functions in MATLAB.

Results

The conductivity frequencies of 3959, 3958, 3960, 3978, 3510, 3889, 3888, and 3976 MHz were selected as the feature vectors for 219 lymph nodes (178 non-metastatic and 41 metastatic). Compared with the other methods, SA-PNN achieved the highest classification accuracy (92.92%) and the corresponding specificity and sensitivity were 94.72% and 91.11%, respectively.

Conclusions

Compared with the other methods, the SA-PNN proposed in the present study achieved a higher classification accuracy, which provides a new scheme for classification of metastatic and non-metastatic thoracic lymph nodes in lung cancer patients based on dielectric properties.