Contrast Administration Impacts CT-Based Radiomics of Colorectal Liver Metastases and Non-Tumoral Liver Parenchyma Revealing the "Radiological" Tumour Microenvironment

Comparative analysis of radiomics and deep-learning algorithms for survival prediction in hepatocellular carcinoma

To examine the comparative robustness of computed tomography (CT)-based conventional radiomics and deep-learning convolutional neural networks (CNN) to predict overall survival (OS) in HCC patients. Retrospectively, 114 HCC patients with pretherapeutic CT of the liver were randomized into a development (n = 85) and a validation (n = 29) cohort, including patients of all tumor stages and several applied therapies. In addition to clinical parameters, image annotations of the liver parenchyma and of tumor findings on CT were available. Cox-regression based on radiomics features and CNN models were established and combined with clinical parameters to predict OS. Model performance was assessed using the concordance index (C-index). Log-rank tests were used to test model-based patient stratification into high/low-risk groups. The clinical Cox-regression model achieved the best validation performance for OS (C-index [95% confidence interval (CI)] 0.74 [0.57-0.86]) with a significant difference between the risk groups (p = 0.03). In image analysis, the CNN models (lowest C-index [CI] 0.63 [0.39-0.83]; highest C-index [CI] 0.71 [0.49-0.88]) were superior to the corresponding radiomics models (lowest C-index [CI] 0.51 [0.30-0.73]; highest C-index [CI] 0.66 [0.48-0.79]). A significant risk stratification was not possible (p > 0.05). Under clinical conditions, CNN-algorithms demonstrate superior prognostic potential to predict OS in HCC patients compared to conventional radiomics approaches and could therefore provide important information in the clinical setting, especially when clinical data is limited.

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.

A virtual biopsy of liver parenchyma to predict the outcome of liver resection

The preoperative risk assessment of liver resections (LR) is still an open issue. Liver parenchyma characteristics influence the outcome but cannot be adequately evaluated in the preoperative setting. The present study aims to elucidate the contribution of the radiomic analysis of non-tumoral parenchyma to the prediction of complications after elective LR. All consecutive patients undergoing LR between 2017 and 2021 having a preoperative computed tomography (CT) were included. Patients with associated biliary/colorectal resection were excluded. Radiomic features were extracted from a virtual biopsy of non-tumoral liver parenchyma (a 2 mL cylinder) outlined in the portal phase of preoperative CT. Data were internally validated. Overall, 378 patients were analyzed (245 males/133 females-median age 67 years-39 cirrhotics). Radiomics increased the performances of the preoperative clinical models for both liver dysfunction (at internal validaton, AUC = 0.727 vs. 0.678) and bile leak (AUC = 0.744 vs. 0.614). The final predictive model combined clinical and radiomic variables: for bile leak, segment 1 resection, exposure of Glissonean pedicles, HU-related indices, NGLDM_Contrast, GLRLM indices, and GLZLM_ZLNU; for liver dysfunction, cirrhosis, liver function tests, major hepatectomy, segment 1 resection, and NGLDM_Contrast. The combined clinical-radiomic model for bile leak based on preoperative data performed even better than the model including the intraoperative data (AUC = 0.629). The textural features extracted from a virtual biopsy of non-tumoral liver parenchyma improved the prediction of postoperative liver dysfunction and bile leak, implementing information given by standard clinical data. Radiomics should become part of the preoperative assessment of candidates to LR.

Non-contrast CT synthesis using patch-based cycle-consistent generative adversarial network (Cycle-GAN) for radiomics and deep learning in the era of COVID-19

Handcrafted and deep learning (DL) radiomics are popular techniques used to develop computed tomography (CT) imaging-based artificial intelligence models for COVID-19 research. However, contrast heterogeneity from real-world datasets may impair model performance. Contrast-homogenous datasets present a potential solution. We developed a 3D patch-based cycle-consistent generative adversarial network (cycle-GAN) to synthesize non-contrast images from contrast CTs, as a data homogenization tool. We used a multi-centre dataset of 2078 scans from 1,650 patients with COVID-19. Few studies have previously evaluated GAN-generated images with handcrafted radiomics, DL and human assessment tasks. We evaluated the performance of our cycle-GAN with these three approaches. In a modified Turing-test, human experts identified synthetic vs acquired images, with a false positive rate of 67% and Fleiss' Kappa 0.06, attesting to the photorealism of the synthetic images. However, on testing performance of machine learning classifiers with radiomic features, performance decreased with use of synthetic images. Marked percentage difference was noted in feature values between pre- and post-GAN non-contrast images. With DL classification, deterioration in performance was observed with synthetic images. Our results show that whilst GANs can produce images sufficient to pass human assessment, caution is advised before GAN-synthesized images are used in medical imaging applications.

Mapping Tumor Heterogeneity via Local Entropy Assessment: Making Biomarkers Visible

Advanced imaging and analysis improve prediction of pathology data and outcomes in several tumors, with entropy-based measures being among the most promising biomarkers. However, entropy is often perceived as statistical data lacking clinical significance. We aimed to generate a voxel-by-voxel visual map of local tumor entropy, thus allowing to (1) make entropy explainable and accessible to clinicians; (2) disclose and quantitively characterize any intra-tumoral entropy heterogeneity; (3) evaluate associations between entropy and pathology data. We analyzed the portal phase of preoperative CT of 20 patients undergoing liver surgery for colorectal metastases. A three-dimensional core kernel (5 × 5 × 5 voxels) was created and used to compute the local entropy value for each voxel of the tumor. The map was encoded with a color palette. We performed two analyses: (a) qualitative assessment of tumors' detectability and pattern of entropy distribution; (b) quantitative analysis of the entropy values distribution. The latter data were compared with standard Hounsfield data as predictors of post-chemotherapy tumor regression grade (TRG). Entropy maps were successfully built for all tumors. Metastases were qualitatively hyper-entropic compared to surrounding parenchyma. In four cases hyper-entropic areas exceeded the tumor margin visible at CT. We identified four "entropic" patterns: homogeneous, inhomogeneous, peripheral rim, and mixed. At quantitative analysis, entropy-derived data (percentiles/mean/median/root mean square) predicted TRG (p < 0.05) better than Hounsfield-derived ones (p = n.s.). We present a standardized imaging technique to visualize tumor heterogeneity built on a voxel-by-voxel entropy assessment. The association of local entropy with pathology data supports its role as a biomarker.

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.

Radiomics-Based Inter-Lesion Relation Network to Describe [18F]FMCH PET/CT Imaging Phenotypes in Prostate Cancer

Advanced image analysis, including radiomics, has recently acquired recognition as a source of biomarkers, although there are some technical and methodological challenges to face for its application in the clinic. Among others, proper phenotyping of metastatic or systemic disease where multiple lesions coexist is an issue, since each lesion contributes to characterization of the disease. Therefore, the radiomic profile of each lesion should be modeled into a more complex architecture able to reproduce each "unit" (lesion) as a part of the "entire" (patient). This work aimed to characterize intra-tumor heterogeneity underpinning metastatic prostate cancer using an exhaustive innovative approach which consist of a i) feature transformation method to build an agnostic (i.e., irrespective of pre-existence knowledge, experience, and expertise) radiomic profile of lesions extracted from [¹⁸F]FMCH PET/CT, ii) qualitative assessment of intra-tumor heterogeneity of patients, iii) quantitative representation of the intra-tumor heterogeneity of patients in terms of the relationship between their lesions' profiles, to be associated with prognostic factors. We confirmed that metastatic prostate cancer patients encompassed lesions with different radiomic profiles that exhibited intra-tumor radiomic heterogeneity and that the presence of many radiomic profiles within the same patient impacted the outcome.

Prognostic value of texture analysis of the primary tumour in high-risk neuroblastoma: An 18 F-DOPA PET study

PURPOSE

To evaluate the prognostic value of texture analysis of the primary tumour with ¹⁸ fluorine-dihydroxyphenylalanine positron emission tomography/X-ray computed tomography (¹⁸ F-DOPA PET/CT) in patients affected by high-risk neuroblastoma (HR-NBL).

METHODS

We retrospectively analysed 18 patients with HR-NBL, which had been prospectively enrolled in the course of a previous trial investigating the diagnostic role of ¹⁸ F-DOPA PET/CT at the time of the first onset. Texture analysis of the primary tumour was carried out on the PET images using LifeX. Conventional indices, histogram parameters, grey level co-occurrence (GLCM), run-length (GLRLM), neighbouring difference (NGLDM) and zone-length (GLZLM) matrices parameter were extracted; their values were compared with the overall metastatic load, expressed by means of whole-body metabolic burden (WBMB) score and the progression-free/overall survival (PFS and OS).

RESULTS

There was a direct correlation between WBMB and radiomics parameter describing uptake intensity (SUV_mean : p = .004) and voxel heterogeneity (entropy: p = .026; GLCM_Contrast: p = .001). Conversely, texture indices of homogeneity showed an inverse correlation with WBMB (energy: p = .026; GLCM_Homogeneity: p = .006). On the multivariate model, WBMB (p < .01) and the first standardised uptake value (SUV) quartile (p < .001) predicted PFS; OS was predicted by WBMB and the N-myc proto-oncogene protein (MYCN) amplification (p < .05) for both.

CONCLUSIONS

Textural parameters describing heterogeneity and metabolic intensity of the primary HR-NBL are closely associated with its overall metastatic burden. In turn, the whole-body tumour load appears to be one of the most relevant predictors of progression-free and overall survival.

Distant supervision for imaging-based cancer sub-typing in Intrahepatic Cholangiocarcinoma

Finding effective ways to perform cancer sub-typing is currently a trending research topic for therapy opti-mization and personalized medicine. Stemming from genomic field, several algorithms have been proposed. In the context of texture analysis, limited efforts have been attempted, yet imaging information is known to entail useful knowledge for clinical practice. We propose a distant supervision model for imaging-based cancer sub-typing in Intrahepatic Cholangiocar-cinoma patients. A clinically informed stratification of patients is built and homogeneous groups of patients are characterized in terms of survival probabilities, qualitative cancer variables and radiomic feature description. Moreover, the contributions of the information derived from the ICC area and from the peri tumoral area are evaluated. The findings suggest the reliability of the proposed model in the context of cancer research and testify the importance of accounting for data coming from both the tumour and the tumour-tissue interface. Clinical relevance - In order to accurately predict cancer prognosis for patients affected by ICC, radiomic variables of both core cancer and surrounding area should be exploited and employed in a model able to manage complex information.

AX-Unet: A Deep Learning Framework for Image Segmentation to Assist Pancreatic Tumor Diagnosis

Image segmentation plays an essential role in medical imaging analysis such as tumor boundary extraction. Recently, deep learning techniques have dramatically improved performance for image segmentation. However, an important factor preventing deep neural networks from going further is the information loss during the information propagation process. In this article, we present AX-Unet, a deep learning framework incorporating a modified atrous spatial pyramid pooling module to learn the location information and to extract multi-level contextual information to reduce information loss during downsampling. We also introduce a special group convolution operation on the feature map at each level to achieve information decoupling between channels. In addition, we propose an explicit boundary-aware loss function to tackle the blurry boundary problem. We evaluate our model on two public Pancreas-CT datasets, NIH Pancreas-CT dataset, and the pancreas part in medical segmentation decathlon (MSD) medical dataset. The experimental results validate that our model can outperform the state-of-the-art methods in pancreas CT image segmentation. By comparing the extracted feature output of our model, we find that the pancreatic region of normal people and patients with pancreatic tumors shows significant differences. This could provide a promising and reliable way to assist physicians for the screening of pancreatic tumors.

Radiomics of Biliary Tumors: A Systematic Review of Current Evidence

Biliary tumors are rare diseases with major clinical unmet needs. Standard imaging modalities provide neither a conclusive diagnosis nor robust biomarkers to drive treatment planning. In several neoplasms, texture analyses non-invasively unveiled tumor characteristics and aggressiveness. The present manuscript aims to summarize the available evidence about the role of radiomics in the management of biliary tumors. A systematic review was carried out through the most relevant databases. Original, English-language articles published before May 2021 were considered. Three main outcome measures were evaluated: prediction of pathology data; prediction of survival; and differential diagnosis. Twenty-seven studies, including a total of 3605 subjects, were identified. Mass-forming intrahepatic cholangiocarcinoma (ICC) was the subject of most studies (n = 21). Radiomics reliably predicted lymph node metastases (range, AUC = 0.729−0.900, accuracy = 0.69−0.83), tumor grading (AUC = 0.680−0.890, accuracy = 0.70−0.82), and survival (C-index = 0.673−0.889). Textural features allowed for the accurate differentiation of ICC from HCC, mixed HCC-ICC, and inflammatory masses (AUC > 0.800). For all endpoints (pathology/survival/diagnosis), the predictive/prognostic models combining radiomic and clinical data outperformed the standard clinical models. Some limitations must be acknowledged: all studies are retrospective; the analyzed imaging modalities and phases are heterogeneous; the adoption of signatures/scores limits the interpretability and applicability of results. In conclusion, radiomics may play a relevant role in the management of biliary tumors, from diagnosis to treatment planning. It provides new non-invasive biomarkers, which are complementary to the standard clinical biomarkers; however, further studies are needed for their implementation in clinical practice.

Radiomics of Contrast-Enhanced Computed Tomography: A Potential Biomarker for Pretreatment Prediction of the Response to Bacillus Calmette-Guerin Immunotherapy in Non-Muscle-Invasive Bladder Cancer

Background:Bacillus Calmette-Guerin (BCG) instillation is recommended postoperatively after transurethral resection of bladder cancer (TURBT) in patients with high-risk non-muscle-invasive bladder cancer (NMIBC). An accurate prediction model for the BCG response can help identify patients with NMIBC who may benefit from alternative therapy.

Objective: To investigate the value of computed tomography (CT) radiomics features in predicting the response to BCG instillation among patients with primary high-risk NMIBC.

Methods: Patients with pathologically confirmed high-risk NMIBC were retrospectively reviewed. Patients who underwent contrast-enhanced CT examination within one to 2 weeks before TURBT and received ≥5 BCG instillation treatments in two independent hospitals were enrolled. Patients with a routine follow-up of at least 1 year at the outpatient department were included in the final cohort. Radiomics features based on CT images were extracted from the tumor and its periphery in the training cohort, and a radiomics signature was built with recursive feature elimination. Selected features further underwent an unsupervised radiomics analysis using the newly introduced method, non-negative matrix factorization (NMF), to compute factor factorization decompositions of the radiomics matrix. Finally, a robust component, which was most associated with BCG failure in 1 year, was selected. The performance of the selected component was assessed and tested in an external validation cohort.

Results: Overall, 128 patients (training cohort, n = 104; external validation cohort, n = 24) were included, including 12 BCG failures in the training cohort and 11 failures in the validation cohort each. NMF revealed five components, of which component 3 was selected for the best discrimination of BCG failure; it had an area under the curve (AUC) of .79, sensitivity of .79, and specificity of .65 in the training set. In the external validation cohort, it achieved an AUC of .68, sensitivity of .73, and specificity of .69. Survival analysis showed that patients with higher component scores had poor recurrence-free survival (RFS) in both cohorts (C-index: training cohort, .69; validation cohort, .68).

Conclusion: The study suggested that radiomics components based on NMF might be a potential biomarker to predict BCG response and RFS after BCG treatment in patients with high-risk NMIBC.

Radiogenomics: Hunting Down Liver Metastasis in Colorectal Cancer Patients

Simple Summary

Colorectal cancer (CRC) is the third leading cause of cancer and the second most deadly tumor type in the world. The liver is the most common site of metastasis in CRC patients. The conversion of new imaging biomarkers into diagnostic, prognostic and predictive signatures, by the development of radiomics and radiogenomics, is an important potential new tool for the clinical management of cancer patients. In this review, we assess the knowledge gained from radiomics and radiogenomics studies in liver metastatic colorectal cancer patients and their possible use for early diagnosis, response assessment and treatment decisions.

Abstract

Radiomics is a developing new discipline that analyzes conventional medical images to extract quantifiable data that can be mined for new biomarkers that show the biology of pathological processes at microscopic levels. These data can be converted into image-based signatures to improve diagnostic, prognostic and predictive accuracy in cancer patients. The combination of radiomics and molecular data, called radiogenomics, has clear implications for cancer patients’ management. Though some studies have focused on radiogenomics signatures in hepatocellular carcinoma patients, only a few have examined colorectal cancer metastatic lesions in the liver. Moreover, the need to differentiate between liver lesions is fundamental for accurate diagnosis and treatment. In this review, we summarize the knowledge gained from radiomics and radiogenomics studies in hepatic metastatic colorectal cancer patients and their use in early diagnosis, response assessment and treatment decisions. We also investigate their value as possible prognostic biomarkers. In addition, the great potential of image mining to provide a comprehensive view of liver niche formation is examined thoroughly. Finally, new challenges and current limitations for the early detection of the liver premetastatic niche, based on radiomics and radiogenomics, are also discussed.