Evaluation of hepatic tumor response to yttrium-90 radioembolization therapy using texture signatures generated from contrast-enhanced CT images

Radiomics Features Extracted From Pre- and Postprocedural Imaging in Early Prediction of Treatment Response in Patients Undergoing Transarterial Radioembolization of Hepatic Lesions: A Systematic Review, Meta-Analysis, and Quality Appraisal Study

INTRODUCTION

Transarterial radioembolization (TARE) is one of the most promising therapeutic options for hepatic masses. Radiomics features, which are quantitative numeric features extracted from medical images, are considered to have potential in predicting treatment response in TARE. This article aims to provide meta-analytic evidence and critically appraise the methodology of radiomics studies published in this regard.

METHODS

A systematic search was performed on PubMed, Scopus, Embase, and Web of Science. All relevant articles were retrieved, and the characteristics of the studies were extracted. The Radiomics Quality Score and Checklist for Evaluation of Radiomics Research were used to assess the methodologic quality of the studies. Pooled sensitivity, specificity, and area under the receiver operating characteristic curve in predicting objective response were determined.

RESULTS

The systematic review included 15 studies. The average Radiomics Quality Score of these studies was 11.4 ± 2.1, and the average Checklist for Evaluation of Radiomics Research score was 33± 6.7. There was a notable correlation (correlation coefficient = 0.73) between the two metrics. Adherence to quality measures differed considerably among the studies and even within different components of the same studies. The pooled sensitivity and specificity of the radiomics models in predicting complete or partial response were 83.5% (95% confidence interval 76%-88.9%) and 86.7% (95% confidence interval 78%-92%), respectively.

CONCLUSION

Radiomics models show great potential in predicting treatment response in TARE of hepatic lesions. However, the heterogeneity seen between the methodologic quality of studies may limit the generalizability of the results. Future initiatives should aim to develop radiomics signatures using multiple external datasets and adhere to quality measures in radiomics methodology.

The Role of Artificial Intelligence and Texture Analysis in Interventional Radiological Treatments of Liver Masses: A Narrative Review

Liver lesions, including both benign and malignant tumors, pose significant challenges in interventional radiological treatment planning and prognostication. The emerging field of artificial intelligence (AI) and its integration with texture analysis techniques have shown promising potential in predicting treatment outcomes, enhancing precision, and aiding clinical decision-making. This comprehensive review aims to summarize the current state-of-the-art research on the application of AI and texture analysis in determining treatment response, recurrence rates, and overall survival outcomes for patients undergoing interventional radiological treatment for liver lesions. Furthermore, the review addresses the challenges associated with the implementation of AI and texture analysis in clinical practice, including data acquisition, standardization of imaging protocols, and model validation. Future directions and potential advancements in this field are discussed. Integration of multi-modal imaging data, incorporation of genomics and clinical data, and the development of predictive models with enhanced interpretability are proposed as potential avenues for further research. In conclusion, the application of AI and texture analysis in predicting outcomes of interventional radiological treatment for liver lesions shows great promise in augmenting clinical decision-making and improving patient care. By leveraging these technologies, clinicians can potentially enhance treatment planning, optimize intervention strategies, and ultimately improve patient outcomes in the management of liver lesions.

Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review

OBJECTIVES

Machine learning (ML) for medical imaging is emerging for several organs and image modalities. Our objectives were to provide clinicians with an overview of this field by answering the following questions: (1) How is ML applied in liver computed tomography (CT) imaging? (2) How well do ML systems perform in liver CT imaging? (3) What are the clinical applications of ML in liver CT imaging?

METHODS

A systematic review was carried out according to the guidelines from the PRISMA-P statement. The search string focused on studies containing content relating to artificial intelligence, liver, and computed tomography.

RESULTS

One hundred ninety-one studies were included in the study. ML was applied to CT liver imaging by image analysis without clinicians' intervention in majority of studies while in newer studies the fusion of ML method with clinical intervention have been identified. Several were documented to perform very accurately on reliable but small data. Most models identified were deep learning-based, mainly using convolutional neural networks. Potentially many clinical applications of ML to CT liver imaging have been identified through our review including liver and its lesion segmentation and classification, segmentation of vascular structure inside the liver, fibrosis and cirrhosis staging, metastasis prediction, and evaluation of chemotherapy.

CONCLUSION

Several studies attempted to provide transparent result of the model. To make the model convenient for a clinical application, prospective clinical validation studies are in urgent call. Computer scientists and engineers should seek to cooperate with health professionals to ensure this.

KEY POINTS

• ML shows great potential for CT liver image tasks such as pixel-wise segmentation and classification of liver and liver lesions, fibrosis staging, metastasis prediction, and retrieval of relevant liver lesions from similar cases of other patients. • Despite presenting the result is not standardized, many studies have attempted to provide transparent results to interpret the machine learning method performance in the literature. • Prospective studies are in urgent call for clinical validation of ML method, preferably carried out by cooperation between clinicians and computer scientists.

Prediction of Response of Hepatocellular Carcinoma to Radioembolization: Machine Learning Using Preprocedural Clinical Factors and MR Imaging Radiomics

PURPOSE

To create and evaluate the ability of machine learning-based models with clinicoradiomic features to predict radiologic response after transarterial radioembolization (TARE).

MATERIALS AND METHODS

82 treatment-naïve patients (65 responders and 17 nonresponders; median age: 65 years; interquartile range: 11) who underwent selective TARE were included. Treatment responses were evaluated using the European Association for the Study of the Liver criteria at 3-month follow-up. Laboratory, clinical, and procedural information were collected. Radiomic features were extracted from pretreatment contrast-enhanced T1-weighted magnetic resonance images obtained within 3 months before TARE. Feature selection consisted of intraclass correlation, followed by Pearson correlation analysis and finally, sequential feature selection algorithm. Support vector machine, logistic regression, random forest, and LightGBM models were created with both clinicoradiomic features and clinical features alone. Performance metrics were calculated with a nested 5-fold cross-validation technique. The performances of the models were compared by Wilcoxon signed-rank and Friedman tests.

RESULTS

In total, 1,128 features were extracted. The feature selection process resulted in 12 features (8 radiomic and 4 clinical features) being included in the final analysis. The area under the receiver operating characteristic curve values from the support vector machine, logistic regression, random forest, and LightGBM models were 0.94, 0.94, 0.88, and 0.92 with clinicoradiomic features and 0.82, 0.83, 0.82, and 0.83 with clinical features alone, respectively. All models exhibited significantly higher performances when radiomic features were included (P = .028, .028, .043, and .028, respectively).

CONCLUSIONS

Based on clinical and imaging-based information before treatment, machine learning-based clinicoradiomic models demonstrated potential to predict response to TARE.

A Review of Radiomics in Predicting Therapeutic Response in Colorectal Liver Metastases: From Traditional to Artificial Intelligence Techniques

An early evaluation of colorectal cancer liver metastasis (CRCLM) is crucial in determining treatment options that ultimately affect patient survival rates and outcomes. Radiomics (quantitative imaging features) have recently gained popularity in diagnostic and therapeutic strategies. Despite this, radiomics faces many challenges and limitations. This study sheds light on these limitations by reviewing the studies that used radiomics to predict therapeutic response in CRCLM. Despite radiomics’ potential to enhance clinical decision-making, it lacks standardization. According to the results of this study, the instability of radiomics quantification is caused by changes in CT scan parameters used to obtain CT scans, lesion segmentation methods used for contouring liver metastases, feature extraction methods, and dataset size used for experimentation and validation. Accordingly, the study recommends combining radiomics with deep learning to improve prediction accuracy.

Tumor response prediction in 90Y radioembolization with PET-based radiomics features and absorbed dose metrics

Purpose

To evaluate whether lesion radiomics features and absorbed dose metrics extracted from post-therapy ⁹⁰Y PET can be integrated to better predict outcomes in microsphere radioembolization of liver malignancies

Methods

Given the noisy nature of ⁹⁰Y PET, first, a liver phantom study with repeated acquisitions and varying reconstruction parameters was used to identify a subset of robust radiomics features for the patient analysis. In 36 radioembolization procedures, ⁹⁰Y PET/CT was performed within a couple of hours to extract 46 radiomics features and estimate absorbed dose in 105 primary and metastatic liver lesions. Robust radiomics modeling was based on bootstrapped multivariate logistic regression with shrinkage regularization (LASSO) and Cox regression with LASSO. Nested cross-validation and bootstrap resampling were used for optimal parameter/feature selection and for guarding against overfitting risks. Spearman rank correlation was used to analyze feature associations. Area under the receiver-operating characteristics curve (AUC) was used for lesion response (at first follow-up) analysis while Kaplan-Meier plots and c-index were used to assess progression model performance. Models with absorbed dose only, radiomics only, and combined models were developed to predict lesion outcome.

Results

The phantom study identified 15/46 reproducible and robust radiomics features that were subsequently used in the patient models. A lesion response model with zone percentage (ZP) and mean absorbed dose achieved an AUC of 0.729 (95% CI 0.702–0.758), and a progression model with zone size nonuniformity (ZSN) and absorbed dose achieved a c-index of 0.803 (95% CI 0.790–0.815) on nested cross-validation (CV). Although the combined models outperformed the radiomics only and absorbed dose only models, statistical significance was not achieved with the current limited data set to establish expected superiority.

Conclusion

We have developed new lesion-level response and progression models using textural radiomics features, derived from ⁹⁰Y PET combined with mean absorbed dose for predicting outcome in radioembolization. These encouraging, but limited results, will need further validation in independent and larger datasets prior to any clinical adoption.

Supplementary Information

Supplementary information accompanies this paper at 10.1186/s40658-020-00340-9.

Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans

Liver and bile duct cancers are leading causes of worldwide cancer death. The most common ones are hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC). Influencing factors and prognosis of HCC and ICC are different. Precise classification of these two liver cancers is essential for treatment and prevention plans. The aim of this study is to develop a machine-based method that differentiates between the two types of liver cancers from multi-phase abdominal computerized tomography (CT) scans. The proposed method consists of two major steps. In the first step, the liver is segmented from the original images using a convolutional neural network model, together with task-specific pre-processing and post-processing techniques. In the second step, by looking at the intensity histograms of the segmented images, we extract features from regions that are discriminating between HCC and ICC, and use them as an input for classification using support vector machine model. By testing on a dataset of labeled multi-phase CT scans provided by Maharaj Nakorn Chiang Mai Hospital, Thailand, we have obtained 88% in classification accuracy. Our proposed method has a great potential in helping radiologists diagnosing liver cancer.

Outpatient treatment for haemophilic arthropathy with radiosynovectomy: Radiation dose to family members

One of the key features of good practice in medicine is the doctor-patient communication. Radiation protection standards for radiosynovectomy (RS) is limited. Yttrium-90 is a beta-emitting radioisotope used in RS to treat joint pain from haemophilic arthritis. ICRP 94 states that if a patient is treated with up to 200 MBq, there is no need for further precautions when it comes to public exposure, however, activities can go up to 370 MBq in RS for the knee. This study analysed 119 family members' safety (16.7% pregnant women). The ambient dose equivalent rate was measured within four distances. A survey was carried analysing risk groups and time spent next to patients. Results showed that family members should be advised to remain at 1.0 m from the patient to decrease accumulated dose by 97.6%. The dose per activity factors estimated in this study is also a useful tool during the risk assessment and doctor/patient communication. Pamphlets were distributed with radiation protection recommendations. Ambient dose equivalent was low enough to show that RS is a safe procedure for family members, which is essential to promote adherence to RS in countries where it is needed but not performed due to lack of information on radiation safety.

Differentiation of pyogenic hepatic abscesses from malignant mimickers using multislice-based texture acquired from contrast-enhanced computed tomography

BACKGROUND

Pyogenic hepatic abscess may mimic primary or secondary carcinoma of the liver on contrast-enhanced computed tomography (CECT). The present study was to explore the usefulness of the analysis of multislice-based texture acquired from CECT in the differentiation between pyogenic hepatic abscesses and malignant mimickers.

METHODS

This retrospective study included 25 abscesses in 20 patients and 33 tumors in 26 subjects who underwent CECT. To make comparison, we also enrolled 19 patients with hepatic single simple cyst. The images from CECT were analyzed using a Laplacian of Gaussian band-pass filter (5 filter levels with sigma weighting ranging from 1.0 to 2.5). We also quantified the uniformity, entropy, kurtosis and skewness of the multislice-based texture at different sigma weightings. Statistical significance for these parameters was tested with one-way ANOVA followed by Tukey honestly significant difference (HSD) test. Diagnostic performance was evaluated using the receiver operating characteristic (ROC) curve analysis.

RESULTS

There were significant differences in entropy and uniformity at all sigma weightings (P<0.001) among hepatic abscesses, malignant mimickers and simple cysts. The significant difference in kurtosis and skewness was shown at sigma 1.8 and 2.0 weightings (P=0.002-0.006). Tukey HSD test showed that the abscesses had a significantly higher entropy and lower uniformity compared with malignant mimickers (P=0.000-0.004). Entropy (at a sigma 2.0 weighting) had the largest area under the ROC curve (0.888) in differentiating abscesses from malignant mimickers, with a sensitivity of 81.8% and a specificity of 88.0% when the cutoff value was set to 3.64.

CONCLUSION

Multislice-based texture analysis may be useful for differentiating pyogenic hepatic abscesses from malignant mimickers.

CT texture analysis in colorectal liver metastases: A better way than size and volume measurements to assess response to chemotherapy?

BACKGROUND

Response Evaluation Criteria In Solid Tumors (RECIST) are known to have limitations in assessing the response of colorectal liver metastases (CRLMs) to chemotherapy.

OBJECTIVE

The objective of this article is to compare CT texture analysis to RECIST-based size measurements and tumor volumetry for response assessment of CRLMs to chemotherapy.

METHODS

Twenty-one patients with CRLMs underwent CT pre- and post-chemotherapy. Texture parameters mean intensity (M), entropy (E) and uniformity (U) were assessed for the largest metastatic lesion using different filter values (0.0 = no/0.5 = fine/1.5 = medium/2.5 = coarse filtration). Total volume (cm(3)) of all metastatic lesions and the largest size of one to two lesions (according to RECIST 1.1) were determined. Potential predictive parameters to differentiate good responders (n = 9; histological TRG 1-2) from poor responders (n = 12; TRG 3-5) were identified by univariable logistic regression analysis and subsequently tested in multivariable logistic regression analysis. Diagnostic odds ratios were recorded.

RESULTS

The best predictive texture parameters were Δuniformity and Δentropy (without filtration). Odds ratios for Δuniformity and Δentropy in the multivariable analyses were 0.95 and 1.34, respectively. Pre- and post-treatment texture parameters, as well as the various size and volume measures, were not significant predictors. Odds ratios for Δsize and Δvolume in the univariable logistic regression were 1.08 and 1.05, respectively.

CONCLUSIONS

Relative differences in CT texture occurring after treatment hold promise to assess the pathologic response to chemotherapy in patients with CRLMs and may be better predictors of response than changes in lesion size or volume.

False Discovery Rates in PET and CT Studies with Texture Features: A Systematic Review

Purpose

A number of recent publications have proposed that a family of image-derived indices, called texture features, can predict clinical outcome in patients with cancer. However, the investigation of multiple indices on a single data set can lead to significant inflation of type-I errors. We report a systematic review of the type-I error inflation in such studies and review the evidence regarding associations between patient outcome and texture features derived from positron emission tomography (PET) or computed tomography (CT) images.

Methods

For study identification PubMed and Scopus were searched (1/2000–9/2013) using combinations of the keywords texture, prognostic, predictive and cancer. Studies were divided into three categories according to the sources of the type-I error inflation and the use or not of an independent validation dataset. For each study, the true type-I error probability and the adjusted level of significance were estimated using the optimum cut-off approach correction, and the Benjamini-Hochberg method. To demonstrate explicitly the variable selection bias in these studies, we re-analyzed data from one of the published studies, but using 100 random variables substituted for the original image-derived indices. The significance of the random variables as potential predictors of outcome was examined using the analysis methods used in the identified studies.

Results

Fifteen studies were identified. After applying appropriate statistical corrections, an average type-I error probability of 76% (range: 34–99%) was estimated with the majority of published results not reaching statistical significance. Only 3/15 studies used a validation dataset. For the 100 random variables examined, 10% proved to be significant predictors of survival when subjected to ROC and multiple hypothesis testing analysis.

Conclusions

We found insufficient evidence to support a relationship between PET or CT texture features and patient survival. Further fit for purpose validation of these image-derived biomarkers should be supported by appropriate biological and statistical evidence before their association with patient outcome is investigated in prospective studies.

Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review

BACKGROUND

Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.

METHODOLOGY

The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.

PRINCIPAL FINDINGS

Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description.

CONCLUSIONS

In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.

Identification of intestinal wall abnormalities and ischemia by modeling spatial uncertainty in computed tomography imaging findings

Intestinal abnormalities and ischemia are medical conditions in which inflammation and injury of the intestine are caused by inadequate blood supply. Acute ischemia of the small bowel can be life-threatening. Computed tomography (CT) is currently a gold standard for the diagnosis of acute intestinal ischemia in the emergency department. However, the assessment of the diagnostic performance of CT findings in the detection of intestinal abnormalities and ischemia has been a difficult task for both radiologists and surgeons. Little effort has been found in developing computerized systems for the automated identification of these types of complex gastrointestinal disorders. In this paper, a geostatistical mapping of spatial uncertainty in CT scans is introduced for medical image feature extraction, which can be effectively applied for diagnostic detection of intestinal abnormalities and ischemia from control patterns. Experimental results obtained from the analysis of clinical data suggest the usefulness of the proposed uncertainty mapping model.