Early evaluation using a radiomic signature of unresectable hepatic metastases to predict outcome in patients with colorectal cancer treated with FOLFIRI and bevacizumab

Baseline hepatobiliary MRI for predicting chemotherapeutic response and prognosis in initially unresectable colorectal cancer liver metastases

PURPOSE

To evaluate the performance of hepatobiliary MRI parameters as predictors of clinical response to chemotherapy in patients with initially unresectable colorectal cancer liver metastases (CRLM).

METHODS

Eighty-five patients with initially unresectable CRLM were retrospectively enrolled from two hospitals and scanned using gadobenate dimeglumine-enhanced MRI before treatment. Therapy response was evaluated based on the Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1. Conventional parameters (i.e., signal intensity [SI]) and radiomics features of portal venous phase (PVP) and hepatobiliary phase (HBP) images were analyzed between the responders and non-responders. Next, the combined model was constructed, and the area under the receiver operating characteristic (ROC) curve (AUC) was calculated. The relationship between the combined model and progression-free survival (PFS) was analyzed using Cox regression.

RESULTS

Of the 85 patients from two hospitals, 42 were in the response group, and 43 were in the non-response group. Upon conducting five-fold cross-validation, the normalized relative enhancement (NRE) of CRLM during the PVP yielded an AUC of 0.625. Additionally, a radiomics feature derived from the tumor area in the HBP achieved an AUC of 0.698, while a separate feature extracted from the peritumoral region in the HBP recorded an AUC of 0.709. The model that integrated these three features outperformed the individual features, achieving an AUC of 0.818. Furthermore, the combined model exhibited a significant correlation with PFS (P < 0.001).

CONCLUSION

The combined model, based on baseline hepatobiliary MRI, aids in predicting chemotherapeutic response and PFS in patients with initially unresectable CRLM.

Pre-operative prediction of histopathological growth patterns of colorectal cancer liver metastasis using MRI-based radiomic models

PURPOSE

Histopathological growth patterns (HGPs) of colorectal liver metastases (CRLMs) have prognostic value. However, the differentiation of HGPs relies on postoperative pathology. This study aimed to develop a magnetic resonance imaging (MRI)-based radiomic model to predict HGP pre-operatively, following the latest guidelines.

METHODS

This retrospective study included 93 chemotherapy-naïve patients with CRLMs who underwent contrast-enhanced liver MRI and a partial hepatectomy between 2014 and 2022. Radiomic features were extracted from the tumor zone (RTumor), a 2-mm outer ring (RT+2), a 2-mm inner ring (RT-2), and a combined ring (R2+2) on late arterial phase MRI images. Analysis of variance method (ANOVA) and least absolute shrinkage and selection operator (LASSO) algorithms were used for feature selection. Logistic regression with five-fold cross-validation was used for model construction. Receiver operating characteristic curves, calibrated curves, and decision curve analyses were used to assess model performance. DeLong tests were used to compare different models.

RESULTS

Twenty-nine desmoplastic and sixty-four non-desmoplastic CRLMs were included. The radiomic models achieved area under the curve (AUC) values of 0.736, 0.906, 0.804, and 0.794 for RTumor, RT-2, RT+2, and R2+2, respectively, in the training cohorts. The AUC values were 0.713, 0.876, 0.785, and 0.777 for RTumor, RT-2, RT+2, and R2+2, respectively, in the validation cohort. RT-2 exhibited the best performance.

CONCLUSION

The MRI-based radiomic models could predict HGPs in CRLMs pre-operatively.

CT-based radiogenomics of intrahepatic cholangiocarcinoma

BACKGROUND

Intrahepatic cholangiocarcinoma (ICC) is an aggressive disease with increasing incidence and its genetic alterations could be the target of systemic therapies.

AIMS

To elucidate if radiomics extracted from computed tomography (CT) may non-invasively predict ICC genetic alterations.

METHODS

All consecutive patients with a diagnosis of a mass-forming ICC (01/2016-06/2022) were considered. Inclusion criteria were availability of a high-quality contrast-enhanced CT and molecular profiling by NGS or FISH for FGFR2 fusion/rearrangement. The CT scan at diagnosis was considered. Genetic analyses were performed on surgical specimens (resectable patients) or biopsies (unresectable ones). The radiomic features were extracted using the LifeX software. Multivariate predictive models of the commonest genetic alterations were built.

RESULTS

In the 90 enrolled patients (58 NGS/32 FISH, median age 65 years), the most common genetic alterations were FGFR2 (20/90), IDH1 (10/58), and KRAS (9/58). At internal validation, the combined clinical-radiomic models achieved the best performance for the prediction of FGFR2 (AUC = 0.892) and IDH1 status (AUC = 0.819), outperforming the pure clinical and radiomic models. The radiomic model for predicting KRAS mutations achieved an AUC = 0.767 (vs. 0.660 of the clinical model) without further improvements with the addition of clinical features.

CONCLUSIONS

CT-based radiomics provides a reliable non-invasive prediction of ICC genetic status with a major impact on therapeutic strategies.

Prognostic value of the tumor-to-liver density ratio in patients with metastatic colorectal cancer treated with bevacizumab-based chemotherapy. A post-hoc study of the STIC-AVASTIN trial

BACKGROUND

The Response Evaluation Criteria in Solid Tumors (RECIST) are often inadequate for the early assessment of the response to cancer therapy, particularly bevacizumab-based chemotherapy. In a first cohort of patients with colorectal cancer liver metastases (CRLM), we showed that variations of the tumor-to-liver density (TTLD) ratio and modified size-based criteria determined using computed tomography (CT) data at the first restaging were better prognostic criteria than the RECIST. The aims of this study were to confirm the relevance of these radiological biomarkers as early predictors of the long-term clinical outcome and to assess their correlation with contrast-enhanced ultrasound (CEUS) parameters in a new patient cohort.

METHODS

In this post-hoc study of the multicenter STIC-AVASTIN trial, we retrospectively reviewed CT data of patients with CRLM treated with bevacizumab-based regimens. We determined the size, density and TTLD ratio of target liver lesions at baseline and at the first restaging and also performed a morphologic evaluation according to the MD Anderson criteria. We assessed the correlation of these parameters with progression-free survival (PFS) and overall survival (OS) using the log-rank test and a Cox proportional hazard model. We also examined the association between TTLD ratio and quantitative CEUS parameters.

RESULTS

This analysis concerned 79 of the 137 patients included in the STIC-AVASTIN trial. PFS and OS were significantly longer in patients with tumor size reduction > 15% at first restaging, but were not correlated with TTLD ratio variations. However, PFS was longer in patients with TTLD ratio > 0.6 at baseline and first restaging than in those who did not reach this threshold. In the multivariate analysis, only baseline TTLD ratio > 0.6 was a significant survival predictor. TTLD ratio > 0.6 was associated with improved perfusion parameters.

CONCLUSIONS

Although TTLD ratio variations did not correlate with the long-term clinical outcomes, TTLD absolute values remained a good predictor of survival at baseline and first restaging, and may reflect tumor microvascular features that might influence bevacizumab-based treatment efficiency.

TRIAL REGISTRATION

NCT00489697, registration number of the STIC-AVASTIN trial.

CT texture analysis of vertebrobasilar artery calcification to identify culprit plaques

Objectives

The aim of this study was to extract radiomic features from vertebrobasilar artery calcification (VBAC) on head computed tomography (CT) images and investigate its diagnostic performance to identify culprit lesions responsible for acute cerebral infarctions.

Methods

Patients with intracranial atherosclerotic disease who underwent vessel wall MRI (VW-MRI) and head CT examinations from a single center were retrospectively assessed for VBAC visual and textural analyses. Each calcified plaque was classified by the likelihood of having caused an acute cerebral infarction identified on VW-MRI as culprit or non-culprit. A predefined set of texture features extracted from VBAC segmentation was assessed using the minimum redundancy and maximum relevance method. Five key features were selected to integrate as a radiomic model using logistic regression by the Aikaike Information Criteria. The diagnostic value of the radiomic model was calculated for discriminating culprit lesions over VBAC visual assessments.

Results

A total of 1,218 radiomic features were extracted from 39 culprit and 50 non-culprit plaques, respectively. In the VBAC visual assessment, culprit plaques demonstrated more observed presence of multiple calcifications, spotty calcification, and intimal predominant calcification than non-culprit lesions (all p < 0.05). In the VBAC texture analysis, 55 (4.5%) of all extracted features were significantly different between culprit and non-culprit plaques (all p < 0.05). The radiomic model incorporating 5 selected features outperformed multiple calcifications [AUC = 0.81 with 95% confidence interval (CI) of 0.72, 0.90 vs. AUC = 0.61 with 95% CI of 0.49, 0.73; p = 0.001], intimal predominant calcification (AUC = 0.67 with 95% CI of 0.58, 0.76; p = 0.04) and spotty calcification (AUC = 0.62 with 95% CI of 0.52, 0.72; p = 0.005) in the identification of culprit lesions.

Conclusion

Culprit plaques in the vertebrobasilar artery exhibit distinct calcification radiomic features compared to non-culprit plaques. CT texture analysis of VBAC has potential value in identifying lesions responsible for acute cerebral infarctions, which may be helpful for stroke risk stratification in clinical practice.

Application research of radiomics in colorectal cancer: A bibliometric study

BACKGROUND

Radiomics has shown great potential in the clinical field of colorectal cancer (CRC). However, few bibliometric studies have systematically analyzed existing research in this field. The purpose of this study is to understand the current research status and future development directions of CRC.

METHODS

Search the English documents on the application of radiomics in the field of CRC research included in the Web of Science Core Collection from its establishment to October 2023. VOSviewer and CiteSpace software were used to conduct bibliometric and visual analysis of online publications related to countries/regions, authors, journals, references, and keywords in this field.

RESULTS

A total of 735 relevant documents published from Web of Science Core Collection to October 2023 were retrieved, and a total of 419 documents were obtained based on the screening criteria, including 376 articles and 43 reviews. The number of publications is increasing year by year. Among them, China publishes the most relevant documents (n = 238), which is much higher than Italy (n = 69) and the United States (n = 63). Tian Jie is the author with the most publications and citations (n = 17, citations = 2128), GE Healthcare is the most productive institution (n = 26), Frontiers in Oncology is the journal with the most publications (n = 60), and European Radiology is the most cited journal (n = 776). Hot spots for the application of radiomics in CRC include magnetic resonance, neoadjuvant chemoradiotherapy, survival, texture analysis, and machine learning. These directions are the current hot spots for the application of radiomics research in CRC and may be the direction of continued development in the future.

CONCLUSION

Through bibliometric analysis, the application of radiomics in CRC has been increasing year by year. The application of radiomics improves the accuracy of preoperative diagnosis, prediction, and prognosis of CRC. The results of bibliometrics analysis provide a valuable reference for the research direction of radiomics. However, radiomics still faces many challenges in the future, such as the single nature of the data source which may affect the comprehensiveness of the results. Future studies can further expand the data sources and build a multicenter public database to more comprehensively reflect the research status and development trend of CRC radiomics.

Radiomics-Based Prediction Model for Outcome of Radioembolization in Metastatic Colorectal Cancer

PURPOSE

To evaluate the benefit of a contrast-enhanced computed tomography (CT) radiomics-based model for predicting response and survival in patients with colorectal liver metastases treated with transarterial Yttrium-90 radioembolization (TARE).

MATERIALS AND METHODS

Fifty-one patients who underwent TARE were included in this single-center retrospective study. Response to treatment was assessed using the Response Evaluation Criteria in Solid Tumors (RECIST 1.1) at 3-month follow-up. Patients were stratified as responders (complete/partial response and stable disease, n = 24) or non-responders (progressive disease, n = 27). Radiomic features (RF) were extracted from pre-TARE CT after segmentation of the liver tumor volume. A model was built based on a radiomic signature consisting of reliable RFs that allowed classification of response using multivariate logistic regression. Patients were assigned to high- or low-risk groups for disease progression after TARE according to a cutoff defined in the model. Kaplan-Meier analysis was performed to analyze survival between high- and low-risk groups.

RESULTS

Two independent RF [Energy, Maximal Correlation Coefficient (MCC)], reflecting tumor heterogeneity, discriminated well between responders and non-responders. In particular, patients with higher magnitude of voxel values in an image (Energy), and texture complexity (MCC), were more likely to fail TARE. For predicting treatment response, the area under the receiver operating characteristic curve of the radiomics-based model was 0.75 (95% CI 0.48-1). The high-risk group had a shorter overall survival than the low-risk group (3.4 vs. 6.4 months, p < 0.001).

CONCLUSION

Our CT radiomics model may predict the response and survival outcome by quantifying tumor heterogeneity in patients treated with TARE for colorectal liver metastases.

Extracellular volume fraction can predict the treatment response and survival outcome of colorectal cancer liver metastases

OBJECTIVE

To assess the prognostic value of pre- and post-therapeutic changes in extracellular volume (ECV) fraction of liver metastases (LMs) for treatment response (TR) and survival outcomes in colorectal cancer liver metastases (CRLM).

METHODS

186 LMs were confirmed by pathology or follow-up (Training: 130; Test: 56). We analyzed the changes in ECV fraction of LMs before and after 2 cycles of chemotherapy combined with bevacizumab. After 12 cycles, we evaluated the TR on LMs based on the RECIST v1.1. Relative changes in ECV fraction and Hounsfield Units (HU), defined as ΔECV and ΔHU, were associated with progression-free survival (PFS), overall survival (OS), and TR. We identified TR predictors with multivariate logistic regression and PFS, OS risk factors with COX analysis.

RESULTS

186 LMs were classified as TR lesions (TR+: 84) and non-TR lesions (TR-:102). ΔECV, ΔHUA-E, and texture could distinguish the TR of LMs in training and test set (P < 0.05). ΔECV [Odds ratio (OR): 1.03; 95% Confidence interval (CI): 1.02-1.05, P < 0.01] was an independent predictor of TR-. Area under the curve (AUC), sensitivity and specificity of TR model in training and test set were 0.87, 0.84, 90.14%, 90.32%, 72.88%, 64.00%, respectively. High CRD_score indicates that patients have shorter PFS [Hazard ratio (HR): 2.01; 95%CI: 1.02-3.98, P = 0.045)] and OS (HR: 1.89, 95%CI: 1.04-3.42, P = 0.038).

CONCLUSION

ΔECV can be used as an independent predictor of TR of CRLM chemotherapy combined with bevacizumab.

Radiomics and liver: Where we are and where we are headed?

Hepatic diffuse conditions and focal liver lesions represent two of the most common scenarios to face in everyday radiological clinical practice. Thanks to the advances in technology, radiology has gained a central role in the management of patients with liver disease, especially due to its high sensitivity and specificity. Since the introduction of computed tomography (CT) and magnetic resonance imaging (MRI), radiology has been considered the non-invasive reference modality to assess and characterize liver pathologies. In recent years, clinical practice has moved forward to a quantitative approach to better evaluate and manage each patient with a more fitted approach. In this setting, radiomics has gained an important role in helping radiologists and clinicians characterize hepatic pathological entities, in managing patients, and in determining prognosis. Radiomics can extract a large amount of data from radiological images, which can be associated with different liver scenarios. Thanks to its wide applications in ultrasonography (US), CT, and MRI, different studies were focused on specific aspects related to liver diseases. Even if broadly applied, radiomics has some advantages and different pitfalls. This review aims to summarize the most important and robust studies published in the field of liver radiomics, underlying their main limitations and issues, and what they can add to the current and future clinical practice and literature.

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.

Radiomics and Machine Learning for prediction of two-year disease-specific mortality and KRAS mutation status in metastatic colorectal cancer

PURPOSE

Colorectal cancer is usually accompanied by liver metastases. The prediction of patient evolution is essential for the choice of the appropriate therapy. The aim of this study is to develop and evaluate machine learning models to predict KRAS gene mutations and 2-year disease-specific mortality from medical images.

METHODS

Clinical and follow-up information was collected from patients with metastatic colorectal cancer who had undergone computed tomography prior to liver resection. The dominant liver lesion was segmented in each scan and radiomic features were extracted from the volumes of interest. The 65% of the cases were employed to perform feature selection and to train machine learning algorithms through cross-validation. The best performing models were assembled and evaluated in the remaining cases of the cohort.

RESULTS

For the mortality model development, 101 cases were used as training set (64 alive, 37 deceased) and 35 as test set (22 alive, 13 deceased); while for KRAS mutation models, 55 cases were used for training (31 wild-type, 24 mutated) and 30 for testing (17 wild-type, 13 mutated). The ensemble of top performing models resulted in an area under the receiver operating characteristic curve of 0.878 for mortality and 0.905 for KRAS prediction.

CONCLUSIONS

Predicting the prognosis of patients with metastatic colorectal cancer is useful for making timely decisions about the best treatment options. This study presents a noninvasive method based on quantitative analysis of baseline images to identify factors influencing patient outcomes, with the aim of incorporating these tools as support systems.

CT radiomics analysis of primary colon cancer patients with or without liver metastases: a correlative study with [18F]FDG PET uptake values

PURPOSE

Utilizing [18F]Fluoro-2-deoxy-D-glucose Positron Emission Tomography/Computed Tomography ([18F]FDG PET/CT) scans on primary colon cancer (CC) patients including with liver metastases (LM), we aimed to determine the relationship between structural CT radiomic features and metabolic PET standard uptake value (SUV) in these patients.

MATERIAL AND METHOD

A retrospective analysis was performed on 60 patients with primary CC, of which 40 had liver metastases that were more than 2 cm in diameter. [18F]FDG PET/CT was used to calculate SUVmax, and 42 CT radiomic characteristics were extracted from non-enhanced CT images. Tumors were manually segmented on fused PET/CT scans by two experienced nuclear medicine physicians. Sixty primary CC and forty LM lesions were segmented accordingly. In the cases of multiple LM lesions, the lesion with the largest diameter was chosen for segmentation. In a univariate analysis approach, we used Spearman correlation with multiple testing correction (Benjamini-Hutchberg false discovery rate (FDR), α = 0.05) to ascertain the relationship between SUVmax and CT radiomic features.

RESULT

Twenty-two (52.3%) and twenty-six (61.9%) CT radiomic features were found to be significantly correlated with SUVmax values of primary CC (n = 60) and LM (n = 40) lesions, respectively (FDR-corrected p value < 0.05 and 0.6 < |ρ| < 1). GLCM_homogeneity (ρ = 0.839), GLCM_dissimilarity (ρ = - 0.832), GLZLM_ZLNU (ρ = 0.827), and GLCM_contrast (ρ = - 0.815) were the 4 features most correlated with SUVmax in CC. On the other hand, in LM, the 4 features most correlated with SUVmax were GLRLM_LRHGE (ρ = 0.859), GLRLM_LRE (ρ = 0.859), GLRLM_LRLGE (ρ = 0.857), and GLRLM_RP (ρ = - 0.820).

CONCLUSION

We investigated the relationship between SUVmax of preoperative primary CC lesions and their LM with CT radiomic features. We found some CT radiomic features having relationships with the metabolic characteristics of lesions. This work suggests that non-invasive predictive imaging biomarkers for precision medicine can be derived from CT radiomic.

Radiomics and machine learning analysis by computed tomography and magnetic resonance imaging in colorectal liver metastases prognostic assessment

OBJECTIVE

The aim of this study was the evaluation radiomics analysis efficacy performed using computed tomography (CT) and magnetic resonance imaging in the prediction of colorectal liver metastases patterns linked to patient prognosis: tumor growth front; grade; tumor budding; mucinous type. Moreover, the prediction of liver recurrence was also evaluated.

METHODS

The retrospective study included an internal and validation dataset; the first was composed by 119 liver metastases from 49 patients while the second consisted to 28 patients with single lesion. Radiomic features were extracted using PyRadiomics. Univariate and multivariate approaches including machine learning algorithms were employed.

RESULTS

The best predictor to identify tumor growth was the Wavelet_HLH_glcm_MaximumProbability with an accuracy of 84% and to detect recurrence the best predictor was wavelet_HLH_ngtdm_Complexity with an accuracy of 90%, both extracted by T1-weigthed arterial phase sequence. The best predictor to detect tumor budding was the wavelet_LLH_glcm_Imc1 with an accuracy of 88% and to identify mucinous type was wavelet_LLH_glcm_JointEntropy with an accuracy of 92%, both calculated on T2-weigthed sequence. An increase statistically significant of accuracy (90%) was obtained using a linear weighted combination of 15 predictors extracted by T2-weigthed images to detect tumor front growth. An increase statistically significant of accuracy at 93% was obtained using a linear weighted combination of 11 predictors by the T1-weigthed arterial phase sequence to classify tumor budding. An increase statistically significant of accuracy at 97% was obtained using a linear weighted combination of 16 predictors extracted on CT to detect recurrence. An increase statistically significant of accuracy was obtained in the tumor budding identification considering a K-nearest neighbors and the 11 significant features extracted T1-weigthed arterial phase sequence.

CONCLUSIONS

The results confirmed the Radiomics capacity to recognize clinical and histopathological prognostic features that should influence the choice of treatments in colorectal liver metastases patients to obtain a more personalized therapy.

Deep radiomics-based fusion model for prediction of bevacizumab treatment response and outcome in patients with colorectal cancer liver metastases: a multicentre cohort study

Background

Accurate tumour response prediction to targeted therapy allows for personalised conversion therapy for patients with unresectable colorectal cancer liver metastases (CRLM). In this study, we aimed to develop and validate a multi-modal deep learning model to predict the efficacy of bevacizumab in patients with initially unresectable CRLM using baseline PET/CT, clinical data, and colonoscopy biopsy specimens.

Methods

In this multicentre cohort study, we retrospectively collected data of 307 patients with CRLM from the BECOME study (NCT01972490) (Zhongshan Hospital of Fudan University, Shanghai) and two independent Chinese cohorts (internal validation cohort from January 1, 2018 to December 31, 2018 at Zhongshan Hospital of Fudan University; external validation cohort from January 1, 2020 to December 31, 2020 at Zhongshan Hospital-Xiamen, Shanghai, and the First Hospital of Wenzhou Medical University, Wenzhou). The main inclusion criteria were that patients with CRLM had pre-treatment PET/CT images as well as colonoscopy specimens. After extracting PET/CT features with deep neural networks (DNN) and selecting related clinical factors using LASSO analysis, a random forest classifier was built as the Deep Radiomics Bevacizumab efficacy predicting model (DERBY). Furthermore, by combining histopathological biomarkers into DERBY, we established DERBY+. The performance of model was evaluated using area under the curve (AUC), sensitivity, specificity, positive predictive value, and negative predictive value.

Findings

DERBY achieved promising performance in predicting bevacizumab sensitivity with an AUC of 0.77 and 95% confidence interval (CI) [0.67-0.87]. After combining histopathological features, we developed DERBY+, which had more robust accuracy for predicting tumour response in external validation cohort (AUC 0.83 and 95% CI [0.75-0.92], sensitivity 80.4%, specificity 76.8%). DERBY+ also had prognostic value: the responders had longer progression-free survival (median progression-free survival: 9.6 vs 6.3 months, p = 0.002) and overall survival (median overall survival: 27.6 vs 18.5 months, p = 0.010) than non-responders.

Interpretation

This multi-modal deep radiomics model, using PET/CT, clinical data and histopathological data, was able to identify patients with bevacizumab-sensitive CRLM, providing a favourable approach for precise patient treatment. To further validate and explore the clinical impact of this work, future prospective studies with larger patient cohorts are warranted.

Funding

The National Natural Science Foundation of China; Fujian Provincial Health Commission Project; Xiamen Science and Technology Agency Program; Clinical Research Plan of SHDC; Shanghai Science and Technology Committee Project; Clinical Research Plan of SHDC; Zhejiang Provincial Natural Science Foundation of China; and National Science Foundation of Xiamen.

A contrast-enhanced CT-based whole-spleen radiomics signature for early prediction of oxaliplatin-related thrombocytopenia in patients with gastrointestinal malignancies: a retrospective study

Background

Thrombocytopenia is a common adverse event of oxaliplatin-based chemotherapy. Grade 2 or higher oxaliplatin-related thrombocytopenia may result in dose reduction, discontinuation or delay initiation of chemotherapy and may adversely affect the therapeutic efficacy and even overall survival of patients. Early recognition of patients at risk of developing grade 2 or higher thrombocytopenia is critical. However, to date there is no well-established method to early identify patients at high risk. The aims of this study were to develop and validate a contrast-enhanced CT-based whole-spleen radiomics signature for early prediction of grade 2 or higher thrombocytopenia in patients with gastrointestinal malignancies treated with oxaliplatin-based chemotherapy and to explore the incremental value of combining the radiomics signature and conventional clinical factors for risk prediction.

Methods

A total of 119 patients with gastrointestinal malignancies receiving oxaliplatin-based chemotherapy from March 2017 to December 2020 were retrospectively included and randomly divided into a training cohort (n = 85) and a validation cohort (n = 34). Grade 2 or higher thrombocytopenia occurred in 26.1% of patients (22 and nine patients in the training and validation cohort, respectively) with a median time interval of 101 days from the start of chemotherapy. The whole-spleen radiomics features were extracted on the portal venous phase of the first follow-up CT images. The least absolute shrinkage and selection operator (LASSO) algorithm was applied to select radiomics features and to build the radiomics signature for the prediction of grade 2 or higher thrombocytopenia. A clinical model that included clinical factors only and a clinical-radiomics model that incorporated clinical factors and radiomics signature were constructed. The performances of both models were evaluated and compared in the training, validation and the whole cohorts.

Results

The radiomics signature yielded favorable performance in predicting grade 2 or higher thrombocytopenia, with the area under the curve (AUC), sensitivity and specificity being 0.865, 81.8% and 84.1% in the training cohort and 0.747, 77.8% and 80.0% in the validation cohort. The AUCs of the clinical-radiomics model in the training and validation cohorts reached 0.913 (95% CI [0.720-0.935]) and 0.867 (95% CI [0.727-1.000]), greater than the AUCs of the clinical model. Integrated discrimination improvement (IDI) index showed that incorporating radiomic signature into conventional clinical factors significantly improved the predictive accuracy by 17.0% (95% CI [4.9%-29.1%], p = 0.006) in the whole cohort.

Conclusions

Contrast-enhanced CT-based whole-spleen radiomics signature might serve as an early predictor for grade 2 or higher thrombocytopenia during oxaliplatin-based chemotherapy in patients with gastrointestinal malignancies and provide incremental value over conventional clinical factors.

The prognostic value of radiomic features in liver-limited metastatic colorectal cancer patients from the TRIBE2 study

Aims: Evaluating the prognostic role of radiomic features in liver-limited metastatic colorectal cancer treated with first-line therapy at baseline and best response among patients undergoing resection. Patients & methods: Among patients enrolled in TRIBE2 (NCT02339116), the association of clinical and radiomic data, extracted by SOPHiA-DDM™ with progression-free and overall survival (OS) in the overall population and with disease-free survival/postresection OS in those undergoing resection was investigated. Results: Among 98 patients, radiomic parameters improved the prediction accuracy of our model for OS (area under the curve: 0.83; sensitivity: 0.85; specificity: 0.73; accuracy: 0.78), but not progression-free survival. Of 46 resected patients, small-distance high gray-level emphasis was associated with shorter disease-free survival and high gray-level zone emphasis/higher kurtosis with shorter postresection OS. Conclusion: Radiomic features should be implemented as tools of outcome prediction for liver-limited metastatic colorectal cancer.

Radiomics in colorectal cancer patients

The main therapeutic options for colorectal cancer are surgical resection and adjuvant chemotherapy in non-metastatic disease. However, the evaluation of the overall adjuvant chemotherapy benefit in patients with a high risk of recurrence is challenging. Radiological images can represent a source of data that can be analyzed by using automated computer-based techniques, working on numerical information coded within Digital Imaging and Communications in Medicine files: This image numerical analysis has been named "radiomics". Radiomics allows the extraction of quantitative features from radiological images, mainly invisible to the naked eye, that can be further analyzed by artificial intelligence algorithms. Radiomics is expanding in oncology to either understand tumor biology or for the development of imaging biomarkers for diagnosis, staging, and prognosis, prediction of treatment response and diseases monitoring and surveillance. Several efforts have been made to develop radiomics signatures for colorectal cancer patient using computed tomography (CT) images with different aims: The preoperative prediction of lymph node metastasis, detecting BRAF and RAS gene mutations. Moreover, the use of delta-radiomics allows the analysis of variations of the radiomics parameters extracted from CT scans performed at different timepoints. Most published studies concerning radiomics and magnetic resonance imaging (MRI) mainly focused on the response of advanced tumors that underwent neoadjuvant therapy. Nodes status is the main determinant of adjuvant chemotherapy. Therefore, several radiomics model based on MRI, especially on T2-weighted images and ADC maps, for the preoperative prediction of nodes metastasis in rectal cancer has been developed. Current studies mostly focused on the applications of radiomics in positron emission tomography/CT for the prediction of survival after curative surgical resection and assessment of response following neoadjuvant chemoradiotherapy. Since colorectal liver metastases develop in about 25% of patients with colorectal carcinoma, the main diagnostic tasks of radiomics should be the detection of synchronous and metachronous lesions. Radiomics could be an additional tool in clinical setting, especially in identifying patients with high-risk disease. Nevertheless, radiomics has numerous shortcomings that make daily use extremely difficult. Further studies are needed to assess performance of radiomics in stratifying patients with high-risk disease.

Early evaluation of liver metastasis using spectral CT to predict outcome in patients with colorectal cancer treated with FOLFOXIRI and bevacizumab

PURPOSE

Early evaluation of the efficacy of first-line chemotherapy combined with bevacizumab in patients with colorectal cancer liver metastasis (CRLM) remains challenging. This study used 2-month post-chemotherapy spectral computed tomography (CT) to predict the overall survival (OS) and response of CRLM patients with bevacizumab-containing therapy.

METHOD

This retrospective analysis was performed in 104 patients with pathologically confirmed CRLM between April 2017 and October 2021. Patients were treated with 5-fluorouracil, leucovorin, oxaliplatin or irinotecan with bevacizumab. Portal venous phase spectral CT was performed on the target liver lesion within 2 months of commencing chemotherapy to demonstrate the iodine concentration (IoD) of the target liver lesion. The patients were classified as responders (R +) or non-responders (R -) according to the Response Evaluation Criteria in Solid Tumors (RECIST) v1.1 at 6 months. Multivariate analysis was performed to determine the relationships of the spectral CT parameters, tumor markers, morphology of target lesions with OS and response. The differences in portal venous phase spectral CT parameters between the R + and R - groups were analyzed. Receiver operating characteristic (ROC) curves were used to evaluate the predictive power of spectral CT parameters.

RESULTS

Of the 104 patients (mean age ± standard deviation: 57.73 years ± 12.56; 60 men) evaluated, 28 (26.9%) were classified as R + . Cox multivariate analysis identified the iodine concentration (hazard ratio [HR]: 1.238; 95% confidence interval [95% CI]: 1.089-1.408; P < 0.001), baseline tumor longest diameter (BLD) (HR: 1.022; 95% CI: 1.005-1.038, P = 0.010), higher baseline CEA (HR: 1.670; 95% CI: 1.016-2.745, P = 0.043), K-RAS mutation (HR: 2.027; 95% CI: 1.192-3.449; P = 0.009), and metachronous liver metastasis (HR: 1.877; 95% CI: 1.179-2.988; P = 0.008) as independent risk factors for patient OS. Logistic multivariate analysis identified the IoD (Odds Ratio [OR]: 2.243; 95% CI: 1.405-4.098; P = 0.002) and clinical N stage of the primary tumor (OR: 4.998; 95% CI: 1.210-25.345; P = 0.035) as independent predictor of R + . Using IoD cutoff values of 4.75 (100ug/cm³) the area under the ROC curve was 0.916, sensitivity and specificity were 80.3% and 96.4%, respectively.

CONCLUSIONS

Spectral CT IoD can predict the OS and response of patients with CRLM after 2 months of treatment with bevacizumab-containing therapy.

Colorectal liver metastases patients prognostic assessment: prospects and limits of radiomics and radiogenomics

In this narrative review, we reported un up-to-date on the role of radiomics to assess prognostic features, which can impact on the liver metastases patient treatment choice. In the liver metastases patients, the possibility to assess mutational status (RAS or MSI), the tumor growth pattern and the histological subtype (NOS or mucinous) allows a better treatment selection to avoid unnecessary therapies. However, today, the detection of these features require an invasive approach. Recently, radiomics analysis application has improved rapidly, with a consequent growing interest in the oncological field. Radiomics analysis allows the textural characteristics assessment, which are correlated to biological data. This approach is captivating since it should allow to extract biological data from the radiological images, without invasive approach, so that to reduce costs and time, avoiding any risk for the patients. Several studies showed the ability of Radiomics to identify mutational status, tumor growth pattern and histological type in colorectal liver metastases. Although, radiomics analysis in a non-invasive and repeatable way, however features as the poor standardization and generalization of clinical studies results limit the translation of this analysis into clinical practice. Clear limits are data-quality control, reproducibility, repeatability, generalizability of results, and issues related to model overfitting.

Discrimination of Liver Metastases of Digestive System Neuroendocrine Tumors From Neuroendocrine Carcinoma by Computed Tomography-Based Radiomics Analysis

OBJECTIVE

The aim of the study is to investigate the value of computed tomography (CT) radiomics features to discriminate the liver metastases (LMs) of digestive system neuroendocrine tumors (NETs) from neuroendocrine carcinoma (NECs).

METHODS

Ninety-nine patients with LMs of digestive system neuroendocrine neoplasms from 2 institutions were included. Radiomics features were extracted from the portal venous phase CT images by the Pyradiomics and then selected by using the t test, Pearson correlation analysis, and least absolute shrinkage and selection operator method. The radiomics score (Rad score) for each patient was constructed by linear combination of the selected radiomics features. The radiological model was constructed by radiological features using the multivariable logistic regression. Then, the combined model was constructed by combining Rad score and the radiological model into logistic regression. The performance of all models was evaluated by the receiver operating characteristic curves with the area under curve (AUC).

RESULTS

In the radiological model, only the enhancement degree (odds ratio, 8.299; 95% confidence interval, 2.070-32.703; P = 0.003) was an independent predictor for discriminating the LMs of digestive system NETs from those of NECs. The combined model constructed by the Rad score in combination with the enhancement degree showed good discrimination performance, with AUCs of 0.893, 0.841, and 0.740 in the training, testing, and external validation groups, respectively. In addition, it performed better than radiological model in the training and testing groups (AUC, 0.893 vs 0.726; AUC, 0.841 vs 0.621).

CONCLUSIONS

The CT radiomics might be useful for discrimination LMs of digestive system NECs from NETs.

Artificial Intelligence, Augmented Reality, and Virtual Reality Advances and Applications in Interventional Radiology

Artificial intelligence (AI) uses computer algorithms to process and interpret data as well as perform tasks, while continuously redefining itself. Machine learning, a subset of AI, is based on reverse training in which evaluation and extraction of data occur from exposure to labeled examples. AI is capable of using neural networks to extract more complex, high-level data, even from unlabeled data sets, and better emulate, or even exceed, the human brain. Advances in AI have and will continue to revolutionize medicine, especially the field of radiology. Compared to the field of interventional radiology, AI innovations in the field of diagnostic radiology are more widely understood and used, although still with significant potential and growth on the horizon. Additionally, AI is closely related and often incorporated into the technology and programming of augmented reality, virtual reality, and radiogenomic innovations which have the potential to enhance the efficiency and accuracy of radiological diagnoses and treatment planning. There are many barriers that limit the applications of artificial intelligence applications into the clinical practice and dynamic procedures of interventional radiology. Despite these barriers to implementation, artificial intelligence in IR continues to advance and the continued development of machine learning and deep learning places interventional radiology in a unique position for exponential growth. This review describes the current and possible future applications of artificial intelligence, radiogenomics, and augmented and virtual reality in interventional radiology while also describing the challenges and limitations that must be addressed before these applications can be fully implemented into common clinical practice.

Value of pre-treatment 18F-FDG PET/CT radiomics in predicting the prognosis of stage III-IV colorectal cancer

Background and purpose

To investigate the value of radiomics features extracted from pre-treatment ¹⁸F-FDG PET/CT in predicting the outcomes of stage III-IV colorectal cancer (CRC), which may assist in clinical management strategies and precise treatment of stage III-IV CRC.

Materials and methods

124 patients with pathologically confirmed stage III-IV CRC who underwent pre-treatment ¹⁸F-FDG PET/CT scans were enrolled in this study. The least absolute shrinkage and selection operator Cox regression (LASSO-Cox) was used to select radiomics features, and the radiomics scores (Rad-scores) were calculated to build radiomics models. The performance of radiomics models was represented by the concordance index (C-index) and compared with clinical models and complex model. The bootstrap resampling method was used to create validation sets. Additionally, nomograms were developed based on complex models.

Results

The C-indices of the radiomics model for predicting PFS and OS were 0.712 (95%CI: 0.680-0.744) and 0.758 (0.728-0.789), respectively. In the clinical model, these values were 0.690 (0.664-0.0.717) and 0.738 (0.709-0.767), respectively. However, in the complex model were 0.734 (0.705-0.762) and 0.780 (0.754-0.807), respectively. The Kaplan-Meier curves demonstrated that the radiomics model could effectively separate patients with stage III-IV stage CRC into high- and low-risk groups (p < 0.001). Multivariate Cox regression analysis confirmed the independent prognostic value of Rad-scores.

Conclusion

Pre-treatment ¹⁸F-FDG PET/CT radiomics features can stratify the risk of patients with stage III-IV CRC and accurately predict their outcomes. These findings could be clinically valuable for precision treatment and management decisions in stage III-IV CRC.

Deep learning-based assessment of body composition and liver tumour burden for survival modelling in advanced colorectal cancer

BACKGROUND

Personalized therapy planning remains a significant challenge in advanced colorectal cancer care, despite extensive research on prognostic and predictive markers. A strong correlation of sarcopenia or overall body composition and survival has been described. Here, we explore whether automated assessment of body composition and liver metastases from standard of care CT images can add to clinical parameters in personalized survival risk prognostication.

METHODS

We retrospectively analysed clinical imaging data from 85 patients (50.6% female, mean age 58.9 SD 12.2 years) with colorectal cancer and synchronous liver metastases. Pretrained deep learning models were used to assess body composition and liver metastasis geometry from abdominal CT images before the initiation of systemic treatment. Abdominal muscle-to-bone ratio (MBR) was calculated by dividing abdominal muscle volume by abdominal bone volume. MBR was compared with body mass index (BMI), abdominal muscle volume, and abdominal muscle volume divided by height squared. Differences in overall survival based on body composition and liver metastasis parameters were compared using Kaplan-Meier survival curves. Results were correlated with clinical and biomarker data to develop a machine learning model for survival risk prognostication.

RESULTS

The MBR, unlike abdominal muscle volume or BMI, was significantly associated with overall survival (HR 0.39, 95% CI: 0.19-0.80, P = 0.009). The MBR (P = 0.022), liver metastasis surface area (P = 0.01) and primary tumour sidedness (P = 0.007) were independently associated with overall survival in multivariate analysis. Body composition parameters did not correlate with KRAS mutational status or primary tumour sidedness. A prediction model based on MBR, liver metastasis surface area and primary tumour sidedness achieved a concordance index of 0.69.

CONCLUSIONS

Automated segmentation enables to extract prognostic parameters from routine imaging data for personalized survival modelling in advanced colorectal cancer patients.

Notch-Jagged1 signaling and response to bevacizumab therapy in advanced colorectal cancer: A glance to radiomics or back to physiopathology?

Introduction

The Notch intracellular domain (NICD) and its ligands Jagged-1(Jag1), Delta-like ligand (DLL-3) and DLL4 play an important role in neoangiogenesis. Previous studies suggest a correlation between the tissue levels of NICD and response to therapy with bevacizumab in colorectal cancer (CRC). Another marker that may predict outcome in CRC is radiomics of liver metastases. The aim of this study was to investigate the expression of NICD and its ligands and the role of radiomics in the selection of treatment-naive metastatic CRC patients receiving bevacizumab.

Methods

Immunohistochemistry (IHC) for NICD, Jag1 and E-cadherin was performed on the tissue microarrays (TMAs) of 111 patients with metastatic CRC treated with bevacizumab and chemotherapy. Both the intensity and the percentage of stained cells were evaluated. The absolute number of CD4+ and CD8+ lymphocytes was counted in three different high-power fields and the mean values obtained were used to determine the CD4/CD8 ratio. The positivity of tumor cells to DLL3 and DLL4 was studied. The microvascular density (MVD) was assessed in fifteen cases by counting the microvessels at 20x magnification and expressed as MVD score. Abdominal CT scans were retrieved and imported into a dedicated workstation for radiomic analysis. Manually drawn regions of interest (ROI) allowed the extraction of radiomic features (RFs) from the tumor.

Results

A positive association was found between NICD and Jag1 expression (p < 0.001). Median PFS was significantly shorter in patients whose tumors expressed high NICD and Jag1 (6.43 months vs 11.53 months for negative cases; p = 0.001). Those with an MVD score ≥5 (CD31-high, NICD/Jag1 positive) experienced significantly poorer survival. The radiomic model developed to predict short and long-term survival and PFS yielded a ROC-AUC of 0.709; when integrated with clinical and histopathological data, the integrated model improved the predictive score (ROC-AUC of 0.823).

Discussion

These results show that high NICD and Jag1 expression are associated with progressive disease and early disease progression to anti VEGF-based therapy; the preliminary radiomic analyses show that the integration of quantitative information with clinical and histological data display the highest performance in predicting the outcome of CRC patients.

Artificial intelligence in diagnostic and interventional radiology: Where are we now?

The emergence of massively parallel yet affordable computing devices has been a game changer for research in the field of artificial intelligence (AI). In addition, dramatic investment from the web giants has fostered the development of a high-quality software stack. Going forward, the combination of faster computers with dedicated software libraries and the widespread availability of data has opened the door to more flexibility in the design of AI models. Radiomics is a process used to discover new imaging biomarkers that has multiple applications in radiology and can be used in conjunction with AI. AI can be used throughout the various processes of diagnostic imaging, including data acquisition, reconstruction, analysis and reporting. Today, the concept of "AI-augmented" radiologists is preferred to the theory of the replacement of radiologists by AI in many indications. Current evidence bolsters the assumption that AI-assisted radiologists work better and faster. Interventional radiology becomes a data-rich specialty where the entire procedure is fully recorded in a standardized DICOM format and accessible via standard picture archiving and communication systems. No other interventional specialty can bolster such readiness. In this setting, interventional radiology could lead the development of AI-powered applications in the broader interventional community. This article provides an update on the current status of radiomics and AI research, analyzes upcoming challenges and also discusses the main applications in AI in interventional radiology to help radiologists better understand and criticize articles reporting AI in medical imaging.

Predictive value of vascular endothelial growth factor polymorphisms for maintenance bevacizumab efficacy in metastatic colorectal cancer: an ancillary study of the PRODIGE 9 phase III trial

Background

Several studies have reported the impact of single nucleotide polymorphisms (SNPs) in vascular endothelial growth factor (VEGF) pathway genes on the efficacy of bevacizumab in metastatic colorectal cancer (mCRC), but results are still inconsistent. The PRODIGE 9 phase III study compared bevacizumab maintenance versus observation alone after induction chemotherapy with FOLFIRI plus bevacizumab.

Objective

We evaluated the impact of SNPs of VEGF-A, VEGF receptors (VEGFR-1, VEGFR-2), and hypoxia inducible factor-1α (HIF-1α) on tumor control duration (TCD), overall survival (OS), progression-free survival (PFS), and duration of first chemotherapy free-intervals (CFI).

Patients and methods

We included 314/491 patients from PRODIGE 9 with a DNA blood sample available. Nine SNPs were genotyped on germline DNA using real-time Polymerase Chain Reaction TaqMan TM (Thermo Fisher Scientific, Waltham, MA , USA 02451).

Results

In the bevacizumab arm, patients with the VEGFR-1 rs9582036 CC genotype (n = 14) had significantly longer TCD [22.4 months (95% confidence interval (CI): 14.75-not reached)] than patients with the AA or CA genotype [14.4 months (95% CI: 11.7-17.1)] (p = 0.036), whereas there was no significant difference in the observation arm. In the bevacizumab arm, no significant difference was found between the CC, and AA or CA genotype for OS [28.2 (95% CI: 18.1-42.8) versus 22.5 (95% CI: 18.6-24.6) months, p = 0.5], PFS [9.4 (95% CI: 7.2-11.3) versus 9.2 (95% CI: 8.71-10.1)], and duration of the first CFI [4.6 (95% CI: 1.6-13.3) versus 4.14 (95% CI: 0.5-29.0) months, p = 0.3].

Conclusion

Among mCRC patients treated with bevacizumab maintenance, those with the VEGFR-1 rs9582036 CC genotype experienced longer TCD. The presence of this genotype may thus predict a benefit of bevacizumab maintenance in mCRC.

CT-Based Radiomics Can Predict the Efficacy of Anlotinib in Advanced Non-Small-Cell Lung Cancer

Anlotinib is a small-molecule RTK inhibitor that has achieved certain results in further-line treatment, but many patients do not respond to this drug and lack effective methods for identification. Although radiomics has been widely used in lung cancer, very few studies have been conducted in the field of antiangiogenic drugs. This study aims to develop a new model to predict the efficacy of patients receiving anlotinib by combining pretreatment computed tomography (CT) radiomic characters with clinical characters, in order to assist precision medicine of pulmonary cancer. 254 patients from seven institutions were involved in the study. Lesions were selected according to the RECIST 1.1 criteria, and the corresponding radiomic features were obtained. We constructed prediction models based on clinical, NCE-CT, and CE-CT radiomic features, respectively, and evaluated the prediction performance of the models for training sets, internal validation sets, and external validation sets. In the RAD score only model, the area under curve(AUC) of the NCE-CT cohort was 0.740 (95% CI: 0.622, 0.857) for the training set, 0.711 (95% CI: 0.480, 0.942) for the internal validation set, and 0.633(95% CI: 0.479, 0.787) for the external validation set, while that of the CE-CT cohort was 0.815 (95% CI: 0.705, 0.926) for the training set, 0.771 (95% CI: 0.539, 1.000) for the internal validation set, and 0.701 (95% CI: 0.489, 0.913) for the external validation set. In the RAD score-combined model, the AUC of the NCE-CT cohort was 0.796 (95% CI: 0.691, 0.901) for the training set, 0.579 (95% CI: 0.309, 0.848) for the internal validation set, and 0.590 (95% CI: 0.427, 0.753) for the external validation set, while that of the CE-CT cohort was 0.902 (95% CI: 0.828, 0.977) for the training set, 0.865 (95% CI: 0.696, 1.000) for the internal validation set, and 0.837 (95% CI: 0.682, 0.992) for the external validation set. In conclusion, radiomics has accurate predictions for the efficacy of anlotinib. CE-CT-based radiomic models have the best predictive potential in predicting the efficacy of anlotinib, and model predictions become better when they are combined with clinical characteristics.

Correlation Analysis of Gene and Radiomic Features in Colorectal Cancer Liver Metastases

Colorectal cancer liver metastasis (CRLM) was one of the cancers with high mortality. Clinically, the target point was determined by invasive detection, which increased the suffering of patients and the cost of treatment. If the target point was found through the relationship between early radiomic information and genetic information, it was expected to assist doctors in diagnosing disease, formulating treatment plans, and reducing the pain and burden of patients. In this study, gene coexpression analysis and hub gene mining were first performed on the gene data; secondly, quantitative radiomic features were extracted from CT-enhanced radiomic data to obtain features highly correlated with CRLM; and finally, we analyzed the relationship between gene features and radiomic feature correlations by establishing a link between early radiomic features and gene sequencing and finding highly correlated expressions. This experiment demonstrated that radiomic features could be used to mine gene attributes. Based on the four previously identified genes (NRAS, KRAS, BRAF, and PIK3CA), we identified two novel genes, MAPK1 and STAT1, highly associated with CRLM. There were specific correlations between these 6 genes and radiomic features (shape_elongation, glcm, glszm, firstorder_10percentile, gradient, exponent_firstorder_Range, and gradient_glszm_SmallAreaLowGrayLevel). Therefore, this paper established the correlation between radiomic features and genes, and through radiomic features, we could find the genes associated with them, which was expected to achieve noninvasive prediction of liver metastasis.

The growth pattern of liver metastases on MRI predicts early recurrence in patients with colorectal cancer: a multicenter study

OBJECTIVES

The multicenter study aimed to explore the relationship between the growth pattern of liver metastases on preoperative MRI and early recurrence in patients with colorectal cancer liver metastases (CRCLM) after surgery.

METHODS

A total of 348 CRCLM patients from 3 independent centers were enrolled, including 130 patients with 339 liver metastases in the primary cohort and 218 patients in validation cohorts. Referring to the gross classification of hepatocellular carcinoma (HCC), the growth pattern of each liver metastasis on MRI was classified into four types: rough, smooth, focal extranodular protuberant (FEP), and nodular confluent (NC). Disease-free survival (DFS) curve was constructed using the Kaplan-Meier method.

RESULTS

In primary cohort, 42 (12.4%) of the 339 liver metastases were rough type, 237 (69.9%) were smooth type, 29 (8.6%) were FEP type, and 31 (9.1%) were NC type. Those patients with FEP- and/or NC-type liver metastases had shorter DFS than those without such metastases (p < 0.05). However, there were no significant differences in DFS between patients with rough- and smooth-type liver metastases and those without such metastases. The patients with FEP- and/or NC-type liver metastases also had shorter DFS than those without such metastases in two external validation cohorts. In addition, 40.5% of high-risk-type (FEP and NC) liver metastases converted to low-risk types (rough and smooth) after neoadjuvant chemotherapy.

CONCLUSION

The FEP- and NC-type liver metastases were associated with early recurrence, which may facilitate the clinical treatment of CRCLM patients.

KEY POINTS

• In the primary cohort, patients with FEP- and NC-type metastases had shorter disease-free survival (DFS) and a higher intrahepatic recurrence rate than patients without such metastases in the liver. • In the primary cohort, there were no significant differences in DFS or intrahepatic recurrence rate between patients with rough- and smooth-type metastases and those without such metastases in the liver. • High-risk patients had shorter DFS and a higher intrahepatic recurrence rate than low-risk patients in primary and external validation cohorts.

Imaging standardisation in metastatic colorectal cancer: A joint EORTC-ESOI-ESGAR expert consensus recommendation

BACKGROUND

Treatment monitoring in metastatic colorectal cancer (mCRC) relies on imaging to evaluate the tumour burden. Response Evaluation Criteria in Solid Tumors provide a framework on reporting and interpretation of imaging findings yet offer no guidance on a standardised imaging protocol tailored to patients with mCRC. Imaging protocol heterogeneity remains a challenge for the reproducibility of conventional imaging end-points and is an obstacle for research on novel imaging end-points.

PATIENTS AND METHODS

Acknowledging the recently highlighted potential of radiomics and artificial intelligence tools as decision support for patient care in mCRC, a multidisciplinary, international and expert panel of imaging specialists was formed to find consensus on mCRC imaging protocols using the Delphi method.

RESULTS

Under the guidance of the European Organisation for Research and Treatment of Cancer (EORTC) Imaging and Gastrointestinal Tract Cancer Groups, the European Society of Oncologic Imaging (ESOI) and the European Society of Gastrointestinal and Abdominal Radiology (ESGAR), the EORTC-ESOI-ESGAR core imaging protocol was identified.

CONCLUSION

This consensus protocol attempts to promote standardisation and to diminish variations in patient preparation, scan acquisition and scan reconstruction. We anticipate that this standardisation will increase reproducibility of radiomics and artificial intelligence studies and serve as a catalyst for future research on imaging end-points. For ongoing and future mCRC trials, we encourage principal investigators to support the dissemination of these imaging standards across recruiting centres.

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.

Complement C5 is a novel biomarker for liver metastasis of colorectal cancer

BACKGROUND

Colorectal cancer (CRC) is one of the most prominent malignant diseases, with a high incidence and a dismal prognosis. Metastasis to the liver is the leading cause of death in CRC patients. This study aimed to identify accurate metastatic biomarkers of CRC and investigate the potential molecular mechanisms of liver metastasis of colorectal cancer (LMCRC).

METHODS

Three independent datasets were screened and downloaded from the Gene Expression Omnibus (GEO) database. The GEO2R tool was used to identify differentially expressed genes (DEGs) in CRC tissues and liver metastases. Next, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were conducted using the Database for Annotation, Visualization, and Integrated Discovery (DAVID). Furthermore, the protein-protein interactions (PPIs) of the DEGs were analyzed using the Search Tool for the Retrieval of Interacting Genes (STRING) database, Cytoscape, and Molecular Complex Detection (MCODE). Next, the expression levels and Kaplan-Meier survival analysis of the target gene between normal colon and CRC tissues were performed by UALCAN. The expression of the target gene in tissues and cell lines was verified by quantitative reverse transcription-polymerase chain reaction (qRT-PCR), western blot, and immunohistochemistry (IHC) assay. The impact of the target gene on the proliferation, invasion, and migration ability of COAD cells was explored in vitro.

RESULTS

A total of 92 common DEGs were found in the three independent datasets. GO/KEGG enrichment analysis showed that the DEGs were mainly involved in 14 different pathways. The protein-protein interaction (PPI) network revealed that complement 5 (C5), the upstream gene of C8A in the complement system, was associated with C8 and other key hub genes. Meanwhile, the online UALCAN resource showed that C5 was up-regulated and facilitated malignant progression in COAD samples. Next, we confirmed that C5 remarkably increased and promoted cell proliferation, migration, and invasion in CRC cell lines, SW620 and SW480. The IHC assay showed C5 was also highly expressed in a majority of LMCRC tissues compared with paired CRC tissues.

CONCLUSIONS

The findings of our integrated bioinformatics study suggest that complement C5 might serve as a potential therapeutic target in patients with CRC.

The Role of Biomarkers in the Management of Colorectal Liver Metastases

Simple Summary

Colorectal cancer remains one of the most significant sources of cancer-related morbidity and mortality worldwide. The liver is the most common site of metastatic spread. Multiple modalities exist to manage and potentially cure patients with metastatic colorectal cancer. However, reliable biomarkers to assist with clinical decision-making are limited. Recent advances in genomic sequencing technology have greatly expanded our knowledge of colorectal cancer carcinogenesis and significantly reduced the cost and timing of the investigation. In this article, we discuss the current utility of biomarkers in the management of colorectal cancer liver metastases.

Abstract

Surgical management combined with improved systemic therapies have extended 5-year overall survival beyond 50% among patients with colorectal liver metastases (CRLM). Furthermore, a multitude of liver-directed therapies has improved local disease control for patients with unresectable CRLM. Unfortunately, a significant portion of patients treated with curative-intent hepatectomy develops disease recurrence. Traditional markers fail to risk-stratify and prognosticate patients with CRLM appropriately. Over the last few decades, advances in molecular sequencing technology have greatly expanded our knowledge of the pathophysiology and tumor microenvironment characteristics of CRLM. These investigations have revealed biomarkers with the potential to better inform management decisions in patients with CRLM. Actionable biomarkers such as RAS and BRAF mutations, microsatellite instability/mismatch repair status, and tumor mutational burden have been incorporated into national and societal guidelines. Other biomarkers, including circulating tumor DNA and radiomic features, are under active investigation to evaluate their clinical utility. Given the plethora of therapeutic modalities and lack of evidence on timing and sequence, reliable biomarkers are needed to assist clinicians with the development of patient-tailored management plans. In this review, we discuss the current evidence regarding biomarkers for patients with CRLM.

A primer on texture analysis in abdominal radiology

The number of publications on texture analysis (TA), radiomics, and radiogenomics has been growing exponentially, with abdominal radiologists aiming to build new prognostic or predictive biomarkers for a wide range of clinical applications including the use of oncological imaging to advance the field of precision medicine. TA is specifically concerned with the study of the variation of pixel intensity values in radiological images. Radiologists aim to capture pixel variation in radiological images to deliver new insights into tumor biology that cannot be derived from visual inspection alone. TA remains an active area of investigation and requires further standardization prior to its clinical acceptance and applicability. This review is for radiologists interested in this rapidly evolving field, who are thinking of performing research or want to better interpret results in this arena. We will review the main concepts in TA, workflow processes, and existing challenges and steps to overcome them, as well as look at publications in body imaging with external validation.

Clinical implications and mechanism of histopathological growth pattern in colorectal cancer liver metastases

Liver is the most common site of metastases of colorectal cancer, and liver metastases present with distinct histopathological growth patterns (HGPs), including desmoplastic, pushing and replacement HGPs and two rare HGPs. HGP is a miniature of tumor-host reaction and reflects tumor biology and pathological features as well as host immune dynamics. Many studies have revealed the association of HGPs with carcinogenesis, angiogenesis, and clinical outcomes and indicates HGP functions as bond between microscopic characteristics and clinical implications. These findings make HGP a candidate marker in risk stratification and guiding treatment decision-making, and a target of imaging observation for patient screening. Of note, it is crucial to determine the underlying mechanism shaping HGP, for instance, immune infiltration and extracellular matrix remodeling in desmoplastic HGP, and aggressive characteristics and special vascularization in replacement HGP (rHGP). We highlight the importance of aggressive features, vascularization, host immune and organ structure in formation of HGP, hence propose a novel "advance under camouflage" hypothesis to explain the formation of rHGP.

Tumor calcification is associated with better survival in metastatic colorectal cancer patients treated with bevacizumab plus chemotherapy

Aims: The purpose was to investigate the correlation between calcification and outcome in metastatic colorectal cancer (mCRC) patients who received bevacizumab plus chemotherapy as the first-line treatment. Methods: A single retrospective cohort study was conducted with all diagnosed mCRC cases who received bevacizumab and chemotherapy as the first-line therapy. Results: Among all enrolled patients (n = 159), 31 had tumor calcification. The median overall survival and progression-free survival were significantly better in patients with tumor calcification than in those without calcification. A higher objective overall response rate was also observed in the tumor calcification group. On multivariate analysis, tumor calcification was independently associated with overall survival and progression-free survival. Conclusions: Tumor calcification was independently associated with improved survival in mCRC patients treated with bevacizumab plus chemotherapy.

Filtration-histogram based texture analysis and CALIPER based pattern analysis as quantitative CT techniques in idiopathic pulmonary fibrosis: head-to-head comparison

OBJECTIVE

To assess the prognostic performance of two quantitative CT (qCT) techniques in idiopathic pulmonary fibrosis (IPF) compared to established clinical measures of disease severity (GAP index).

METHODS

Retrospective analysis of high-resolution CT scans for 59 patients (age 70.5 ± 8.8 years) with two qCT methods. Computer-aided lung informatics for pathology evaluation and ratings based analysis classified the lung parenchyma into six different patterns: normal, ground glass, reticulation, hyperlucent, honeycombing and pulmonary vessels. Filtration histogram-based texture analysis extracted texture features: mean intensity, standard deviation (SD), entropy, mean of positive pixels (MPPs), skewness and kurtosis at different spatial scale filters. Univariate Kaplan-Meier survival analysis assessed the different qCT parameters' performance to predict patient outcome and refine the standard GAP staging system. Multivariate cox regression analysis assessed the independence of the significant univariate predictors of patient outcome.

RESULTS

The predominant parenchymal lung pattern was reticulation (16.6% ± 13.9), with pulmonary vessel percentage being the most predictive of worse patient outcome (p = 0.009). Higher SD, entropy and MPP, in addition to lower skewness and kurtosis at fine texture scale (SSF2), were the most significant predictors of worse outcome (p < 0.001). Multivariate cox regression analysis demonstrated that SD (SSF2) was the only independent predictor of survival (p < 0.001). Better patient outcome prediction was achieved after adding total vessel percentage and SD (SSF2) to the GAP staging system (p = 0.006).

CONCLUSION

Filtration-histogram texture analysis can be an independent predictor of patient mortality in IPF patients.

ADVANCES IN KNOWLEDGE

qCT analysis can help in risk stratifying IPF patients in addition to clinical markers.

Interobserver Variability in CT-based Morphologic Tumor Response Assessment of Colorectal Liver Metastases

Purpose To evaluate interobserver variability in the morphologic tumor response assessment of colorectal liver metastases (CRLM) managed with systemic therapy and to assess the relation of morphologic response with gene mutation status, targeted therapy, and Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 measurements. Materials and Methods Participants with initially unresectable CRLM receiving different systemic therapy regimens from the randomized, controlled CAIRO5 trial (NCT02162563) were included in this prospective imaging study. Three radiologists independently assessed morphologic tumor response on baseline and first follow-up CT scans according to previously published criteria. Two additional radiologists evaluated disagreement cases. Interobserver agreement was calculated by using Fleiss κ. On the basis of the majority of individual radiologic assessments, the final morphologic tumor response was determined. Finally, the relation of morphologic tumor response and clinical prognostic parameters was assessed. Results In total, 153 participants (median age, 63 years [IQR, 56-71]; 101 men) with 306 CT scans comprising 2192 CRLM were included. Morphologic assessment performed by the three radiologists yielded 86 (56%) agreement cases and 67 (44%) disagreement cases (including four major disagreement cases). Overall interobserver agreement between the panel radiologists on morphology groups and morphologic response categories was moderate (κ = 0.53, 95% CI: 0.48, 0.58 and κ = 0.54, 95% CI: 0.47, 0.60). Optimal morphologic response was particularly observed in patients treated with bevacizumab (P = .001) and in patients with RAS/BRAF mutation (P = .04). No evidence of a relationship between RECIST 1.1 and morphologic response was found (P = .61). Conclusion Morphologic tumor response assessment following systemic therapy in participants with CRLM demonstrated considerable interobserver variability. Keywords: Tumor Response, Observer Performance, CT, Liver, Metastases, Oncology, Abdomen/Gastrointestinal Clinical trial registration no. NCT02162563 Supplemental material is available for this article. © RSNA, 2022.

Predicting survival for hepatic arterial infusion chemotherapy of unresectable colorectal liver metastases: Radiomics analysis of pretreatment computed tomography

Objective

Hepatic arterial infusion chemotherapy (HAIC) is an effective treatment for advanced unresectable colorectal cancer liver metastases (CRLM). This study was conducted to predict the efficacy of HAIC in patients with unresectable CRLM by radiomics methods based on pretreatment computed tomography (CT) examinations and clinical data.

Materials and Methods

A total of 63 patients were included in this study (41 in the training group and 22 in the validation group). All these patients underwent CT examination before HAIC. During the follow-up period, CT scans and laboratory examinations were performed regularly. Eighty-five radiological features were extracted from the regions of interest (ROIs) of CT images using the PyRadiomics program. The t-test and correlation were applied to select features. These features were analyzed using LASSO-Cox regression, and a linear model was developed to predict overall survival (OS).

Results

After reducing features by t-test and correlation test, seven features remained. After LASSO-Cox cross-validation, four features remained at λ = 0.232. They were gray level co-occurrence matrix (GLCM), gray level run length matrix (GLRLM), neighborhood gray tone difference matrix (NGTDM), and the location of the primary tumor. The C-index was 0.758 in the training group and 0.743 in the test group. Nomograms predicting 1-, 2-, and 3-year survival were established.

Conclusion

Our study demonstrates that a radiomics approach based on pretreatment CT texture analysis has the ability to predict early the outcome of HAIC in patients with advanced unresectable colorectal cancer with a high degree of accuracy and feasibility.

Deep Learning With Radiomics for Disease Diagnosis and Treatment: Challenges and Potential

The high-throughput extraction of quantitative imaging features from medical images for the purpose of radiomic analysis, i.e., radiomics in a broad sense, is a rapidly developing and emerging research field that has been attracting increasing interest, particularly in multimodality and multi-omics studies. In this context, the quantitative analysis of multidimensional data plays an essential role in assessing the spatio-temporal characteristics of different tissues and organs and their microenvironment. Herein, recent developments in this method, including manually defined features, data acquisition and preprocessing, lesion segmentation, feature extraction, feature selection and dimension reduction, statistical analysis, and model construction, are reviewed. In addition, deep learning-based techniques for automatic segmentation and radiomic analysis are being analyzed to address limitations such as rigorous workflow, manual/semi-automatic lesion annotation, and inadequate feature criteria, and multicenter validation. Furthermore, a summary of the current state-of-the-art applications of this technology in disease diagnosis, treatment response, and prognosis prediction from the perspective of radiology images, multimodality images, histopathology images, and three-dimensional dose distribution data, particularly in oncology, is presented. The potential and value of radiomics in diagnostic and therapeutic strategies are also further analyzed, and for the first time, the advances and challenges associated with dosiomics in radiotherapy are summarized, highlighting the latest progress in radiomics. Finally, a robust framework for radiomic analysis is presented and challenges and recommendations for future development are discussed, including but not limited to the factors that affect model stability (medical big data and multitype data and expert knowledge in medical), limitations of data-driven processes (reproducibility and interpretability of studies, different treatment alternatives for various institutions, and prospective researches and clinical trials), and thoughts on future directions (the capability to achieve clinical applications and open platform for radiomics analysis).

Is precision medicine for colorectal liver metastases still a utopia? New perspectives by modern biomarkers, radiomics, and artificial intelligence

The management of patients with liver metastases from colorectal cancer is still debated. Several therapeutic options and treatment strategies are available for an extremely heterogeneous clinical scenario. Adequate prediction of patients’ outcomes and of the effectiveness of chemotherapy and loco-regional treatments are crucial to reach a precision medicine approach. This has been an unmet need for a long time, but recent studies have opened new perspectives. New morphological biomarkers have been identified. The dynamic evaluation of the metastases across a time interval, with or without chemotherapy, provided a reliable assessment of the tumor biology. Genetics have been explored and, thanks to their strong association with prognosis, have the potential to drive treatment planning. The liver-tumor interface has been identified as one of the main determinants of tumor progression, and its components, in particular the immune infiltrate, are the focus of major research. Image mining and analyses provided new insights on tumor biology and are expected to have a relevant impact on clinical practice. Artificial intelligence is a further step forward. The present paper depicts the evolution of clinical decision-making for patients affected by colorectal liver metastases, facing modern biomarkers and innovative opportunities that will characterize the evolution of clinical research and practice in the next few years.

An MRI radiomics approach to predict survival and tumour-infiltrating macrophages in gliomas

Preoperative MRI is one of the most important clinical results for the diagnosis and treatment of glioma patients. The objective of this study was to construct a stable and validatable preoperative T₂-weighted MRI-based radiomics model for predicting the survival of gliomas.

A total of 652 glioma patients across three independent cohorts were covered in this study including their preoperative T₂-weighted MRI images, RNA-seq and clinical data. Radiomic features (1731) were extracted from preoperative T₂-weighted MRI images of 167 gliomas (discovery cohort) collected from Beijing Tiantan Hospital and then used to develop a radiomics prediction model through a machine learning-based method. The performance of the radiomics prediction model was validated in two independent cohorts including 261 gliomas from the The Cancer Genomae Atlas database (external validation cohort) and 224 gliomas collected in the prospective study from Beijing Tiantan Hospital (prospective validation cohort). RNA-seq data of gliomas from discovery and external validation cohorts were applied to establish the relationship between biological function and the key radiomics features, which were further validated by single-cell sequencing and immunohistochemical staining.

The 14 radiomic features-based prediction model was constructed from preoperative T₂-weighted MRI images in the discovery cohort, and showed highly robust predictive power for overall survival of gliomas in external and prospective validation cohorts. The radiomic features in the prediction model were associated with immune response, especially tumour macrophage infiltration.

The preoperative T₂-weighted MRI radiomics prediction model can stably predict the survival of glioma patients and assist in preoperatively assessing the extent of macrophage infiltration in glioma tumours.

Prime Time for Artificial Intelligence in Interventional Radiology

Machine learning techniques, also known as artificial intelligence (AI), is about to dramatically change workflow and diagnostic capabilities in diagnostic radiology. The interest in AI in Interventional Radiology is rapidly gathering pace. With this early interest in AI in procedural medicine, IR could lead the way to AI research and clinical applications for all interventional medical fields. This review will address an overview of machine learning, radiomics and AI in the field of interventional radiology, enumerating the possible applications of such techniques, while also describing techniques to overcome the challenge of limited data when applying these techniques in interventional radiology. Lastly, this review will address common errors in research in this field and suggest pathways for those interested in learning and becoming involved about AI.

Retrospective Analysis of the Value of Enhanced CT Radiomics Analysis in the Differential Diagnosis Between Pancreatic Cancer and Chronic Pancreatitis

Purpose

To investigate the feasibility of enhanced computed tomography (CT) radiomics analysis to differentiate between pancreatic cancer (PC) and chronic pancreatitis.

Methods and materials

The CT images of 151 PCs and 24 chronic pancreatitis were retrospectively analyzed in the three-dimensional regions of interest on arterial phase (AP) and venous phase (VP) and segmented by MITK software. A multivariable logistic regression model was established based on the selected radiomics features. The radiomics score was calculated, and the nomogram was established. The discrimination of each model was analyzed by the receiver operating characteristic curve (ROC). Decision curve analysis (DCA) was used to evaluate clinical utility. The precision recall curve (PRC) was used to evaluate whether the model is affected by data imbalance. The Delong test was adopted to compare the diagnostic efficiency of each model.

Results

Significant differences were observed in the distribution of gender (P = 0.034), carbohydrate antigen 19-9 (P < 0.001), and carcinoembryonic antigen (P < 0.001) in patients with PC and chronic pancreatitis. The area under the ROC curve (AUC) value of AP multivariate regression model, VP multivariate regression model, AP combined with VP features model (Radiomics), clinical feature model, and radiomics combined with clinical feature model (COMB) was 0.905, 0.941, 0.941, 0.822, and 0.980, respectively. The sensitivity and specificity of the COMB model were 0.947 and 0.917, respectively. The results of DCA showed that the COMB model exhibited net clinical benefits and PRC shows that COMB model have good precision and recall (sensitivity).

Conclusion

The COMB model could be a potential tool to distinguish PC from chronic pancreatitis and aid in clinical decisions.

Radiomics and Radiogenomics in Evaluation of Colorectal Cancer Liver Metastasis

Colorectal cancer is one common digestive malignancy, and the most common approach of blood metastasis of colorectal cancer is through the portal vein system to the liver. Early detection and treatment of liver metastasis is the key to improving the prognosis of the patients. Radiomics and radiogenomics use non-invasive methods to evaluate the biological properties of tumors by deeply mining the texture features of images and quantifying the heterogeneity of metastatic tumors. Radiomics and radiogenomics have been applied widely in the detection, treatment, and prognostic evaluation of colorectal cancer liver metastases. Based on the imaging features of the liver, this paper reviews the current application of radiomics and radiogenomics in the diagnosis, treatment, monitor of disease progression, and prognosis of patients with colorectal cancer liver metastases.

Delta-Radiomics Predicts Response to First-Line Oxaliplatin-Based Chemotherapy in Colorectal Cancer Patients with Liver Metastases

Simple Summary

Oxaliplatin-based chemotherapy remains the mainstay of first-line therapy in patients with metastatic colorectal cancer (mCRC). Unfortunately, only approximately 60% of treated patients achieve response, and half of responders will experience an early onset of disease progression. Furthermore, some individuals will develop a mixed response due to the emergence of resistant tumor subclones. The ability to predicting which patients will acquire resistance could help them avoid the unnecessary toxicity of oxaliplatin therapies. Furthermore, sorting out lesions that do not respond, in the context of an overall good response, could trigger further investigation into their mutational landscape, providing mechanistic insight towards the planning of a more comprehensive treatment. In this study, we validated a delta-radiomics signature capable of predicting response to oxaliplatin-based first-line treatment of individual liver colorectal cancer metastases. Findings could pave the way to a more personalized treatment of patients with mCRC.

Abstract

The purpose of this paper is to develop and validate a delta-radiomics score to predict the response of individual colorectal cancer liver metastases (lmCRC) to first-line FOLFOX chemotherapy. Three hundred one lmCRC were manually segmented on both CT performed at baseline and after the first cycle of first-line FOLFOX, and 107 radiomics features were computed by subtracting textural features of CT at baseline from those at timepoint 1 (TP1). LmCRC were classified as nonresponders (R−) if they showed progression of disease (PD), according to RECIST1.1, before 8 months, and as responders (R+), otherwise. After feature selection, we developed a decision tree statistical model trained using all lmCRC coming from one hospital. The final output was a delta-radiomics signature subsequently validated on an external dataset. Sensitivity, specificity, positive (PPV), and negative (NPV) predictive values in correctly classifying individual lesions were assessed on both datasets. Per-lesion sensitivity, specificity, PPV, and NPV were 99%, 94%, 95%, 99%, 85%, 92%, 90%, and 87%, respectively, in the training and validation datasets. The delta-radiomics signature was able to reliably predict R− lmCRC, which were wrongly classified by lesion RECIST as R+ at TP1, (93%, averaging training and validation set, versus 67% of RECIST). The delta-radiomics signature developed in this study can reliably predict the response of individual lmCRC to oxaliplatin-based chemotherapy. Lesions forecasted as poor or nonresponders by the signature could be further investigated, potentially paving the way to lesion-specific therapies.

An imaging signature to predict outcome in metastatic colorectal cancer using routine computed tomography scans

BACKGROUND & AIMS

Quantitative analysis of computed tomography (CT) scans of patients with metastatic colorectal cancer (mCRC) can identify imaging signatures that predict overall survival (OS).

METHODS

We retrospectively analysed CT images from 1584 mCRC patients on two phase III trials evaluating FOLFOX ± panitumumab (n = 331, 350) and FOLFIRI ± aflibercept (n = 437, 466). In the training set (n = 720), an algorithm was trained to predict OS landmarked from month 2; the output was a signature value on a scale from 0 to 1 (most to least favourable predicted OS). In the validation set (n = 864), hazard ratios (HRs) evaluated the association of the signature with OS using RECIST1.1 as a benchmark of comparison.

RESULTS

In the training set, the selected signature combined three features - change in tumour volume, change in tumour spatial heterogeneity, and tumour volume - to predict OS. In the validation set, RECIST1.1 classified patients in three categories: response (n = 166, 19.2%), stable disease (n = 636, 73.6%), and progression (n = 62, 7.2%). The HR was 3.93 (2.79-5.54). Using the same distribution for the signature, the HR was 21.04 (14.88-30.58), showing an incremental prognostic separation. Stable disease by RECIST1.1 was reclassified by the signature along a continuum where patients belonging to the most and least favourable signature quartiles had a median OS of 40.73 (28.49 to NA) months (n = 94) and 7.03 (5.66-7.89) months (n = 166), respectively.

CONCLUSIONS

A signature combining three imaging features provides early prognostic information that can improve treatment decisions for individual patients and clinical trial analyses.