Ultrasound Image-Based Deep Features and Radiomics for the Discrimination of Small Fat-Poor Angiomyolipoma and Small Renal Cell Carcinoma

Development of a multi-phase CT-based radiomics model to differentiate heterotopic pancreas from gastrointestinal stromal tumor

BACKGROUND

To investigate whether CT-based radiomics can effectively differentiate between heterotopic pancreas (HP) and gastrointestinal stromal tumor (GIST), and whether different resampling methods can affect the model's performance.

METHODS

Multi-phase CT radiological data were retrospectively collected from 94 patients. Of these, 40 with HP and 54 with GISTs were enrolled between April 2017 and November 2021. One experienced radiologist manually delineated the volume of interest and then resampled the voxel size of the images to 0.5 × 0.5 × 0.5 mm3, 1 × 1 × 1 mm3, and 2 × 2 × 2 mm3, respectively. Radiomics features were extracted using PyRadiomics, resulting in 1218 features from each phase image. The datasets were randomly divided into training set (n = 66) and validation set (n = 28) at a 7:3 ratio. After applying multiple feature selection methods, the optimal features were screened. Radial basis kernel function-based support vector machine (RBF-SVM) was used as the classifier, and model performance was evaluated using the area under the receiver operating curve (AUC) analysis, as well as accuracy, sensitivity, and specificity.

RESULTS

The combined phase model performed better than the other phase models, and the resampling method of 0.5 × 0.5 × 0.5 mm3 achieved the highest performance with an AUC of 0.953 (0.881-1), accuracy of 0.929, sensitivity of 0.938, and specificity of 0.917 in the validation set. The Delong test showed no significant difference in AUCs among the three resampling methods, with p > 0.05.

CONCLUSIONS

Radiomics can effectively differentiate between HP and GISTs on CT images, and the diagnostic performance of radiomics is minimally affected by different resampling methods.

CNN-based automatic segmentations and radiomics feature reliability on contrast-enhanced ultrasound images for renal tumors

Objective

To investigate the feasibility and efficiency of automatic segmentation of contrast-enhanced ultrasound (CEUS) images in renal tumors by convolutional neural network (CNN) based models and their further application in radiomic analysis.

Materials and methods

From 94 pathologically confirmed renal tumor cases, 3355 CEUS images were extracted and randomly divided into training set (3020 images) and test set (335 images). According to the histological subtypes of renal cell carcinoma, the test set was further split into clear cell renal cell carcinoma (ccRCC) set (225 images), renal angiomyolipoma (AML) set (77 images) and set of other subtypes (33 images). Manual segmentation was the gold standard and serves as ground truth. Seven CNN-based models including DeepLabV3+, UNet, UNet++, UNet3+, SegNet, MultilResUNet and Attention UNet were used for automatic segmentation. Python 3.7.0 and Pyradiomics package 3.0.1 were used for radiomic feature extraction. Performance of all approaches was evaluated by the metrics of mean intersection over union (mIOU), dice similarity coefficient (DSC), precision, and recall. Reliability and reproducibility of radiomics features were evaluated by the Pearson coefficient and the intraclass correlation coefficient (ICC).

Results

All seven CNN-based models achieved good performance with the mIOU, DSC, precision and recall ranging between 81.97%-93.04%, 78.67%-92.70%, 93.92%-97.56%, and 85.29%-95.17%, respectively. The average Pearson coefficients ranged from 0.81 to 0.95, and the average ICCs ranged from 0.77 to 0.92. The UNet++ model showed the best performance with the mIOU, DSC, precision and recall of 93.04%, 92.70%, 97.43% and 95.17%, respectively. For ccRCC, AML and other subtypes, the reliability and reproducibility of radiomic analysis derived from automatically segmented CEUS images were excellent, with the average Pearson coefficients of 0.95, 0.96 and 0.96, and the average ICCs for different subtypes were 0.91, 0.93 and 0.94, respectively.

Conclusion

This retrospective single-center study showed that the CNN-based models had good performance on automatic segmentation of CEUS images for renal tumors, especially the UNet++ model. The radiomics features extracted from automatically segmented CEUS images were feasible and reliable, and further validation by multi-center research is necessary.

Update on the Applications of Radiomics in Diagnosis, Staging, and Recurrence of Intrahepatic Cholangiocarcinoma

BACKGROUND

This paper offers an assessment of radiomics tools in the evaluation of intrahepatic cholangiocarcinoma.

METHODS

The PubMed database was searched for papers published in the English language no earlier than October 2022.

RESULTS

We found 236 studies, and 37 satisfied our research criteria. Several studies addressed multidisciplinary topics, especially diagnosis, prognosis, response to therapy, and prediction of staging (TNM) or pathomorphological patterns. In this review, we have covered diagnostic tools developed through machine learning, deep learning, and neural network for the recurrence and prediction of biological characteristics. The majority of the studies were retrospective.

CONCLUSIONS

It is possible to conclude that many performing models have been developed to make differential diagnosis easier for radiologists to predict recurrence and genomic patterns. However, all the studies were retrospective, lacking further external validation in prospective and multicentric cohorts. Furthermore, the radiomics models and the expression of results should be standardized and automatized to be applicable in clinical practice.