Computed tomography texture-based radiomics analysis in gallbladder cancer: initial experience

Preoperative clinical radiomics model based on deep learning in prognostic assessment of patients with gallbladder carcinoma

OBJECTIVE

We aimed to develop a preoperative clinical radiomics survival prediction model based on the radiomics features via deep learning to provide a reference basis for preoperative assessment and treatment decisions for patients with gallbladder carcinoma (GBC).

METHODS

A total of 168 GBC patients who underwent preoperative upper abdominal enhanced CT from one high-volume medical center between January 2011 to December 2020 were retrospectively analyzed. The region of interest (ROI) was manually outlined by two physicians using 3D Slicer software to establish a nnU-Net model. The DeepSurv survival prediction model was developed by combining radiomics features and preoperative clinical variables.

RESULTS

A total of 1502 radiomics features were extracted from the ROI results based on the nnU-Net model and manual segmentation, and 13 radiomics features were obtained through the 4-step dimensionality reduction methods, respectively. The C-index and AUC of 1-, 2-, and 3-year survival prediction for the nnU-Net based clinical radiomics DeepSurv model was higher than clinical and nnU-Net based radiomics DeepSurv models in the training and testing sets, and close to manual based clinical radiomics DeepSurv model. Delong-test was performed on the AUC of 1-, 2-, and 3-year survival prediction for the two preoperative clinical radiomics DeepSurv prediction models in the testing set, and the results showed that the two models had the same prediction efficiency (all P > 0.05).

CONCLUSIONS

By using the DeepSurv model via nnU-Net segmentation, postoperative survival outcomes for individual gallbladder carcinoma patients could be assessed and stratified, which can provide references for preoperative diagnosis and treatment decisions.

Radiomic nomograms in CT diagnosis of gall bladder carcinoma: a narrative review

Radiomics is a method that extracts many features from medical images using various algorithms. Medical nomograms are graphical representations of statistical predictive models that produce a likelihood of a clinical event for a specific individual based on biological and clinical data. The radiomic nomogram was first introduced in 2016 to study the integration of specific radiomic characteristics with clinically significant risk factors for patients with colorectal cancer lymph node metastases. Thereby it gained momentum and made its way into different domains of breast, liver, and head and neck cancer. Deep learning-based radiomics which automatically generates and extracts significant features from the input data using various neural network architectures, along with the generation and usage of nomograms are the latest developments in the application of radiomics for the diagnosis of gall bladder carcinoma. Although radiomics has demonstrated encouraging outcomes in the diagnosis of gall bladder carcinoma, but most of the studies conducted suffer from a lack of external validation cohorts, smaller sample sizes, and paucity of prospective utility in routine clinical settings.

Texture analysis based on CT for predicting the differentiation of esophageal squamous cancer: An observational study

To explore the feasibility and application value of texture analysis based on computed tomography (CT) for predicting the differentiation of esophageal squamous cell carcinoma (ESCC). Patients diagnosed with ESCC who underwent chest contrast-enhanced CT before treatment were selected. Based on the pathological results, the patients were stratified into poorly differentiated and moderately well-differentiated groups. FireVoxel software was used to analyze the region of interest based on venous phase CT images. Texture parameters including the mean, median, standard deviation (SD), inhomogeneity, skewness, kurtosis, and entropy were obtained automatically. Differences in the texture parameters and their relationship with the degree of differentiation between the 2 groups were analyzed. The value of CT texture parameters in identifying poor differentiation and moderate-well differentiation of esophageal cancer was analyzed using the ROC curve. A total of 48 patients with ESCC were included, including 24 patients in the poorly differentiated group and 24 patients in the moderate-well-differentiated group. There were negative correlations between SD, inhomogeneity, entropy, and the degree of differentiation of esophageal cancer (P < .05). The correlation of inhomogeneity was the highest (r = -0.505, P < .001). SD, inhomogeneity, and entropy could effectively distinguish between the poorly and moderately well-differentiated groups, with statistically significant differences between the 2 groups (P < .05). The best critical values for SD, inhomogeneity, and entropy were 17.538, 0.017, and 3.917, respectively. The areas under the ROC curve were 0.793, 0.792, and 0.729, respectively, with the SD and inhomogeneity being the best. The application of texture analysis on venous phase CT images holds promise as a method for forecasting the degree of differentiation in esophageal cancers, which could significantly contribute to the preoperative noninvasive evaluation of tumor differentiation.

A deep learning model based on contrast-enhanced computed tomography for differential diagnosis of gallbladder carcinoma

BACKGROUND

Gallbladder carcinoma (GBC) is highly malignant, and its early diagnosis remains difficult. This study aimed to develop a deep learning model based on contrast-enhanced computed tomography (CT) images to assist radiologists in identifying GBC.

METHODS

We retrospectively enrolled 278 patients with gallbladder lesions (> 10 mm) who underwent contrast-enhanced CT and cholecystectomy and divided them into the training (n = 194) and validation (n = 84) datasets. The deep learning model was developed based on ResNet50 network. Radiomics and clinical models were built based on support vector machine (SVM) method. We comprehensively compared the performance of deep learning, radiomics, clinical models, and three radiologists.

RESULTS

Three radiomics features including LoG_3.0 gray-level size zone matrix zone variance, HHL first-order kurtosis, and LHL gray-level co-occurrence matrix dependence variance were significantly different between benign gallbladder lesions and GBC, and were selected for developing radiomics model. Multivariate regression analysis revealed that age ≥ 65 years [odds ratios (OR) = 4.4, 95% confidence interval (CI): 2.1-9.1, P < 0.001], lesion size (OR = 2.6, 95% CI: 1.6-4.1, P < 0.001), and CA-19-9 > 37 U/mL (OR = 4.0, 95% CI: 1.6-10.0, P = 0.003) were significant clinical risk factors of GBC. The deep learning model achieved the area under the receiver operating characteristic curve (AUC) values of 0.864 (95% CI: 0.814-0.915) and 0.857 (95% CI: 0.773-0.942) in the training and validation datasets, which were comparable with radiomics, clinical models and three radiologists. The sensitivity of deep learning model was the highest both in the training [90% (95% CI: 82%-96%)] and validation [85% (95% CI: 68%-95%)] datasets.

CONCLUSIONS

The deep learning model may be a useful tool for radiologists to distinguish between GBC and benign gallbladder lesions.

Gallbladder cancer: Progress in the Indian subcontinent

Gallbladder cancer (GBC) is one of the commonest biliary malignancies seen in India, Argentina, and Japan. The disease has dismal outcome as it is detected quite late due to nonspecific symptoms and signs. Early detection is the only way to improve the outcome. There have been several advances in basic as well as clinical research in the hepatobiliary and pancreatic diseases in the West and other developed countries but not enough has been done in GBC. Therefore, it is important and the responsibility of the countries with high burden of GBC to find solutions to the many unanswered questions like etiopathogenesis, early diagnosis, treatment, and prognostication. As India being one of the largest hubs for GBC in the world, it is important to know how the country has progressed on GBC. In this review, we will discuss the outcome of the publications from India highlighting the work and the developments taken place in past several decades both in basic and clinical research.

Contrast-Enhanced CT-Based Deep Learning Radiomics Nomogram for the Survival Prediction in Gallbladder Cancer

RATIONALE AND OBJECTIVES

An accurate prognostic model is essential for the development of treatment strategies for gallbladder cancer (GBC). This study proposes an integrated model using clinical features, radiomics, and deep learning based on contrast-enhanced computed tomography (CT) images for survival prediction in patients with GBC after surgical resection.

METHODS

A total of 167 patients with GBC who underwent surgical resection at two medical institutions were retrospectively enrolled. After obtaining the pre-treatment CT images, the tumor lesions were manually segmented, and handcrafted radiomics features were extracted. A clinical prognostic signature and radiomics signature were built using machine learning algorithms based on the optimal clinical features or handcrafted radiomics features, respectively. Subsequently, a DenseNet121 model was employed for transfer learning on the radiomics image data and as the basis for the deep learning signature. Finally, we used logistic regression on the three signatures to obtain the unified multimodal model for comprehensive interpretation and analysis.

RESULTS

The integrated model performed better than the other models, exhibiting the highest area under the curve (AUC) of 0.870 in the test set, and the highest concordance index (C-index) of 0.736 in predicting patient survival rates. A Kaplan-Meier analysis demonstrated that patients in high-risk group had a lower survival probability compared to those in low-risk group (log-rank p < 0.05).

CONCLUSION

The nomogram is useful for predicting the survival of patients with GBC after surgical resection, helping in the identification of high-risk patients with poor prognosis and ultimately facilitating individualized management of patients with GBC.

Radiomics-based machine learning and deep learning to predict serosal involvement in gallbladder cancer

OBJECTIVE

Our study aimed to determine whether radiomics models based on contrast-enhanced computed tomography (CECT) have considerable ability to predict serosal involvement in gallbladder cancer (GBC) patients.

MATERIALS AND METHODS

A total of 152 patients diagnosed with GBC were retrospectively enrolled and divided into the serosal involvement group and no serosal involvement group according to paraffin pathology results. The regions of interest (ROIs) in the lesion on all CT images were drawn by two radiologists using ITK-SNAP software (version 3.8.0). A total of 412 features were extracted from the CT images of each patient. The Mann‒Whitney U test was applied to identify features with significant differences between groups. Seven machine learning algorithms and a deep learning model based on fully connected neural networks (f-CNNs) were used for radiomics model construction. The prediction efficacy of the models was evaluated using receiver operating characteristic (ROC) curve analysis.

RESULTS

Through the Mann‒Whitney U test, 75 of the 412 features extracted from the CT images of patients were significantly different between groups (P < 0.05). Among all the algorithms, logistic regression achieved the highest performance with an area under the curve (AUC) of 0.944 (sensitivity 0.889, specificity 0.8); the f-CNN deep learning model had an AUC of 0.916, and the model showed high predictive power for serosal involvement, with a sensitivity of 0.733 and a specificity of 0.801.

CONCLUSION

Radiomics models based on features derived from CECT showed convincing performances in predicting serosal involvement in GBC.

Technological Advancements in Interventional Oncology

Interventional radiology, and particularly interventional oncology, represents one of the medical subspecialties in which technological advancements and innovations play an utterly fundamental role. Artificial intelligence, consisting of big data analysis and feature extrapolation through computational algorithms for disease diagnosis and treatment response evaluation, is nowadays playing an increasingly important role in various healthcare fields and applications, from diagnosis to treatment response prediction. One of the fields which greatly benefits from artificial intelligence is interventional oncology. In addition, digital health, consisting of practical technological applications, can assist healthcare practitioners in their daily activities. This review aims to cover the most useful, established, and interesting artificial intelligence and digital health innovations and updates, to help physicians become more and more involved in their use in clinical practice, particularly in the field of interventional oncology.

Imaging patterns of wall thickening type of gallbladder cancer

Gallbladder cancer (GBC) has a high incidence in certain geographical regions. Morphologically, GBC presents as a mass replacing the gallbladder, a polypoidal lesion, or wall thickening. The incidence of preoperative diagnosis of wall thickening type of GBC is less well studied. The patterns of mural involvement and extramural spread are not well described in the literature. Additionally, wall thickening in the gallbladder does not always indicate malignancy and can be secondary to inflammatory or benign gallbladder diseases and extracholecystic causes and systemic pathologies. Objective reporting of gallbladder wall thickening will help us appreciate GBC's early features. In this review, we illustrate the imaging patterns of wall thickening type of GBC.