Quantifying heterogeneity in human tumours using MRI and PET

Evaluating the prognostic value of radiomics and clinical features in metastatic prostate cancer using [68Ga]Ga-PSMA-11 PET/CT

Prostate cancer is a significant global health issue due to its high incidence and poor outcomes in metastatic disease. This study aims to develop models predicting overall survival for patients with metastatic biochemically recurrent prostate cancer, potentially helping to identify high-risk patients and enabling more tailored treatment options. A multi-centre cohort of 180 such patients underwent [68Ga]Ga-PSMA-11 PET/CT scans, with lesions semi-automatically segmented and radiomic features extracted from lesions. The analysis included two phases: univariable and multivariable. Univariable analysis used Kaplan-Meier curves and Cox proportional hazards models to correlate individual features with overall survival. Multivariable analysis used the LASSO Cox proportional hazards method to create 13 models: radiomics-only, clinical-only, and various combinations of radiomic and clinical features. Each model included six features and was bootstrapped 1000 times to obtain concordance indices with 95% confidence intervals, followed by optimism correction. In the univariable analysis, 6 out of 8 clinical features and 68 out of 89 radiomic features were significantly correlated with overall survival, including age, disease stage, total lesional uptake and total lesional volume. The optimism-corrected concordance indices from the multivariable models were 0.722 (95% CI 0.653-0.784) for the clinical model, 0.681 (95% CI 0.616-0.745) for the radiomics model, and 0.704 (95% CI 0.648-0.768) for the combined model with three clinical and three radiomic features, when extracting radiomic features from the largest lesion only. While univariable analysis showed significant prognostic value for many radiomic features, their integration into multivariable models did not improve predictive accuracy beyond clinical features alone.

[Investigation of the Influence of Image Reconstruction Parameters to Improve the Ability to Depict Internal Tumor Necrosis]

PURPOSE

There are attempts to assess tumor heterogeneity by texture analysis. However, the ordered subsets-expectation maximization (OSEM) reconstruction method has problems depicting heterogeneities. The aim of this study was to identify image reconstruction parameters that improve the ability to depict internal tumor necrosis using a self-made phantom that simulates internal necrosis.

METHODS

Self-made phantoms were prepared using polypropylene cylinders with inner diameters of 18.0 mm and 6.0 mm. The concentration ratios of the simulated tumor : tumor interior were 4 : 0 and 4 : 1. For each reconstruction method, the iteration for OSEM and OSEM+point spread function (PSF) were 1 to 25 and the subset was 12. The β values for block sequential regularized expectation maximization (BSREM) were set between 10 and 400. We evaluated the features of the profile curve, contrast-to-noise ratio, and grey-level co-occurrence matrix (GLCM).

RESULTS

In the phantom study, OSEM and OSEM+PSF showed a better delineation of the differences between the inside and outside of the cylinder as iteration was increased and BSREM showed a better delineation as β was decreased. The highest value for each feature, both 4 : 0 and 4 : 1, was BSREM β 10 for angular second moment (ASM) and inverse differential moment (IDM), OSEM iteration 25 for contrast and entropy.

CONCLUSION

We have identified image reconstruction parameters that improve the ability to visualize internal tumor necrosis. The parameter was BRSEM β 10.

Radiomics analysis of R2* maps to predict early recurrence of single hepatocellular carcinoma after hepatectomy

Objectives

This study aimed to evaluate the effectiveness of radiomics analysis with R2* maps in predicting early recurrence (ER) in single hepatocellular carcinoma (HCC) following partial hepatectomy.

Methods

We conducted a retrospective analysis involving 202 patients with surgically confirmed single HCC having undergone preoperative magnetic resonance imaging between 2018 and 2021 at two different institutions. 126 patients from Institution 1 were assigned to the training set, and 76 patients from Institution 2 were assigned to the validation set. A least absolute shrinkage and selection operator (LASSO) regularization was conducted to operate a logistic regression, then features were identified to construct a radiomic score (Rad-score). Uni- and multi-variable tests were used to assess the correlations of clinicopathological features and Rad-score with ER. We then established a combined model encompassing the optimal Rad-score and clinical-pathological risk factors. Additionally, we formulated and validated a predictive nomogram for predicting ER in HCC. The nomogram's discrimination, calibration, and clinical utility were thoroughly evaluated.

Results

Multivariable logistic regression revealed the Rad-score, microvascular invasion (MVI), and α fetoprotein (AFP) level > 400 ng/mL as significant independent predictors of ER in HCC. We constructed a nomogram based on these significant factors. The areas under the receiver operator characteristic curve of the nomogram and precision-recall curve were 0.901 and 0.753, respectively, with an F1 score of 0.831 in the training set. These values in the validation set were 0.827, 0.659, and 0.808.

Conclusion

The nomogram that integrates the radiomic score, MVI, and AFP demonstrates high predictive efficacy for estimating the risk of ER in HCC. It facilitates personalized risk classification and therapeutic decision-making for HCC patients.

Predictive value of 18F-FDG PET/CT multi-metabolic parameters and tumor metabolic heterogeneity in the prognosis of gastric cancer

OBJECTIVE

We aimed to investigate the predictive value of pre-treatment 18F-FDG PET/CT multi-metabolic parameters and tumor metabolic heterogeneity for gastric cancer prognosis.

METHODS

Seventy-one patients with gastric cancer were included. All patients underwent 18F-FDG PET/CT whole-body scans prior to treatment and had pathologically confirmed gastric adenocarcinomas. Each metabolic parameter, including SUVmax, SUVmean, MTV, and TLG, was collected from the primary lesions of gastric cancer in all patients, and the slope of the linear regression between the MTV corresponding to different SUVmax thresholds (40% × SUVmax, 80% × SUVmax) of the primary lesions was calculated. The absolute value of the slope was regarded as the metabolic heterogeneity of the primary lesions, expressed as the heterogeneity index HI-1, and the coefficient of variance of the SUVmean of the primary lesions was regarded as HI-2. Patient prognosis was assessed by PFS and OS, and a nomogram of the prognostic prediction model was constructed, after which the clinical utility of the model was assessed using DCA.

RESULTS

A total of 71 patients with gastric cancer, including 57 (80.3%) males and 14 (19.7%) females, had a mean age of 61 ± 10 years; disease progression occurred in 27 (38.0%) patients and death occurred in 24 (33.8%) patients. Multivariate Cox regression analysis showed that HI-1 alone was a common independent risk factor for PFS (HR: 1.183; 95% CI: 1.010-1.387, P < 0.05) and OS (HR: 1.214; 95% CI: 1.016-1.450, P < 0.05) in patients with gastric cancer. A nomogram created based on the results of Cox regression analysis increased the net clinical benefit for patients. Considering disease progression as a positive event, patients were divided into low-, intermediate-, and high-risk groups, and Kaplan-Meier survival analysis showed that there were significant differences in PFS among the three groups. When death was considered a positive event and patients were included in the low- and high-risk groups, there were significant differences in OS between the two groups.

CONCLUSION

The heterogeneity index HI-1 of primary gastric cancer lesions is an independent risk factor for patient prognosis. A nomogram of prognostic prediction models constructed for each independent factor can increase the net clinical benefit and stratify the risk level of patients, providing a reference for guiding individualized patient treatment.

Machine learning‑based radiomics models for prediction of locoregional recurrence in patients with breast cancer

Locoregional recurrence (LRR) is the predominant pattern of relapse after definitive breast cancer treatment. The present study aimed to develop machine learning (ML)-based radiomics models to predict LRR in patients with breast cancer by using preoperative magnetic resonance imaging (MRI) data. Data from patients with localized breast cancer that underwent preoperative MRI between January 2013 and December 2017 were collected. Propensity score matching (PSM) was performed to adjust for clinical factors between patients with and without LRR. Radiomics features were obtained from T2-weighted with and without fat-suppressed MRI and contrast-enhanced T1-weighted with fat-suppressed MRI. In the present study five ML models were designed, three base models (support vector machine, random forest, and logistic regression) and two ensemble models (voting model and stacking model) composed of the three base models, and the performance of each base model was compared with the stacking model. After PSM, 28 patients with LRR and 86 patients without LRR were included. Of these 114 patients, 80 patients were randomly selected to train the models, and the remaining 34 patients were used to evaluate the performance of the trained models. In total, 5,064 features were obtained from each patient, and 47-51 features were selected by applying variance threshold and least absolute shrinkage and selection operator. The stacking model demonstrated superior performance in area under the receiver operating characteristic curve (AUC), with an AUC of 0.78 compared to a range of 0.61 to 0.70 for the other models. An external validation study to investigate the efficacy of the stacking model of the present study was initiated and is still ongoing (Korean Radiation Oncology Group 2206).

Intratumoral Heterogeneity of Fibrosarcoma Xenograft Models: Whole-Tumor Histogram Analysis of DWI and IVIM

RATIONAL AND OBJECTIVE

To explore the correlations of histogram parameters from diffusion-weighted imaging (DWI) and intravoxel incoherent motion (IVIM) with the heterogeneous features in a nude mouse model of fibrosarcoma.

MATERIALS AND METHODS

A total of 44 fibrosarcoma xenograft models were established by inoculating HT-1080 cells on the right thigh of mice and subjected tumors to DWI and IVIM imaging with 3.0 T MRI. Whole-tumor histogram parameters were calculated on apparent diffusion coefficient (ADC), pure diffusion coefficient (D), pseudo-diffusion coefficient (D*), and perfusion fraction (f). Heterogeneous features, including necrosis rate, cell density, Ki-67 labeling index (LI), and microvascular density (MVD) were measured. Intraclass correlation coefficients (ICC), Pearson or Spearman correlation tests, and receiver operating characteristics (ROC) were performed.

RESULTS

The 90th percentile, skewness and kurtosis of ADC and D histograms showed correlations with necrosis rate, and the highest correlation coefficient was found for D90th (r = 0.485). ADC and D histogram parameters showed correlations with cell density and Ki-67 LI; D90th showed the highest correlation coefficient with cell density (r = -0.504); and Dmedian showed the most significant correlation with Ki-67 LI (r = -0.525). D*skewness, D*kurtosis, D*90th, fmean, and fmedian showed correlations with MVD. ADC90th, ADCskewness, ADCkurtosis, D90th, and Dskewness showed significant differences between the low necrosis and high necrosis groups, and the combination model showed the best diagnostic ability (AUC = 0.882), with 97% sensitivity, and 72.7% specificity.

CONCLUSION

Whole-tumor histogram parameters of DWI and IVIM were correlated with heterogeneous features in nude murine models of fibrosarcoma.

Heterogeneity of the tumor immune microenvironment and clinical interventions

The tumor immune microenvironment (TIME) is broadly composed of various immune cells, and its heterogeneity is characterized by both immune cells and stromal cells. During the course of tumor formation and progression and anti-tumor treatment, the composition of the TIME becomes heterogeneous. Such immunological heterogeneity is not only present between populations but also exists on temporal and spatial scales. Owing to the existence of TIME, clinical outcomes can differ when a similar treatment strategy is provided to patients. Therefore, a comprehensive assessment of TIME heterogeneity is essential for developing precise and effective therapies. Facilitated by advanced technologies, it is possible to understand the complexity and diversity of the TIME and its influence on therapy responses. In this review, we discuss the potential reasons for TIME heterogeneity and the current approaches used to explore it. We also summarize clinical intervention strategies based on associated mechanisms or targets to control immunological heterogeneity.

MRI Apparent Diffusion Coefficient (ADC) as a Biomarker of Tumour Response: Imaging-Pathology Correlation in Patients with Hepatic Metastases from Colorectal Cancer (EORTC 1423)

Background: Tumour apparent diffusion coefficient (ADC) from diffusion-weighted magnetic resonance imaging (MRI) is a putative pharmacodynamic/response biomarker but the relationship between drug-induced effects on the ADC and on the underlying pathology has not been adequately defined. Hypothesis: Changes in ADC during early chemotherapy reflect underlying histological markers of tumour response as measured by tumour regression grade (TRG). Methods: Twenty-six patients were enrolled in the study. Baseline, 14 days, and pre-surgery MRI were performed per study protocol. Surgical resection was performed in 23 of the enrolled patients; imaging-pathological correlation was obtained from 39 lesions from 21 patients. Results: There was no evidence of correlation between TRG and ADC changes at day 14 (study primary endpoint), and no significant correlation with other ADC metrics. In scans acquired one week prior to surgery, there was no significant correlation between ADC metrics and percentage of viable tumour, percentage necrosis, percentage fibrosis, or Ki67 index. Conclusions: Our hypothesis was not supported by the data. The lack of meaningful correlation between change in ADC and TRG is a robust finding which is not explained by variability or small sample size. Change in ADC is not a proxy for TRG in metastatic colorectal cancer.

Role of Textural Analysis of Pretreatment 18F Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography in Response Prediction in Esophageal Carcinoma Patients

Introduction

Positron emission tomography/computed tomography (PET/CT) is routinely used for staging, response assessment, and surveillance in esophageal carcinoma patients. The aim of this study was to investigate whether textural features of pretreatment 18F-fluorodeoxyglucose (18F-FDG) PET/CT images can contribute to prognosis prediction in carcinoma oesophagus patients.

Materials and Methods

This is a retrospective study of 30 diagnosed carcinoma esophagus patients. These patients underwent pretreatment 18F-FDG PET/CT for staging. The images were processed in a commercially available textural analysis software. Region of interest was drawn over primary tumor with a 40% threshold and was processed further to derive 92 textural and radiomic parameters. These parameters were then compared between progression group and nonprogression group. The original dataset was subject separately to receiver operating curve analysis. Receiver operating characteristic (ROC) curves were used to identify the cutoff values for textural features with a P < 0.05 for statistical significance. Feature selection was done with principal component analysis. The selected features of each evaluator were subject to 4 machine-learning algorithms. The highest area under the curve (AUC) values was selected for 10 features.

Results

A retrospective study of 30 primary carcinoma esophagus patients was done. Patients were followed up after chemo-radiotherapy and they underwent follow-up PET/CT. On the basis of their response, patients were divided into progression group and nonprogression group. Among them, 15 patients showed disease progression and 15 patients were in the nonprogression group. Ten textural analysis parameters turned out to be significant in the prediction of disease progression. Cutoff values were calculated for these parameters according to the ROC curves, GLZLM_long zone emphasis (Gray Level Zone Length Matrix)_long zone emphasis (44.9), GLZLM_low gray level zone emphasis (0.006), GLZLM_short zone low gray level emphasis (0.0032), GLZLM_long zone low gray level emphasis (0.185), GLRLM_long run emphasis (Gray Level Run Length Matrix) (1.31), GLRLM_low gray level run emphasis (0.0058), GLRLM_short run low gray level emphasis (0.005496), GLRLM_long run low gray level emphasis (0.00727), NGLDM_Busyness (Neighborhood Gray Level Difference Matrix) (0.75), and gray level co-occurrence matrix_homogeneity (0.37). Feature selection by principal components analysis and feature classification by the K-nearest neighbor machine-learning model using independent training and test samples yielded the overall highest AUC.

Conclusions

Textural analysis parameters could provide prognostic information in carcinoma esophagus patients. Larger multicenter studies are needed for better clinical prognostication of these parameters.

The sub-molecular characterization identification for cervical cancer

Background

The efficacy of therapy in cervical cancer (CESC) is blocked by high molecular heterogeneity. Thus, the sub-molecular characterization remains primarily explored for personalizing the treatment of CESC patients.

Methods

Datasets with 741 CESC patients were obtained from TCGA and GEO databases. The NMF algorithm, random forest algorithm, and multivariate Cox analysis were utilized to construct a classifier for defining the sub-molecular characterization. Then, the biological characteristics, genomic variations, prognosis, and immune landscape in molecular subtypes were explored. The significance of classifier genes was validated by quantitative Real-Time PCR, cell transfection, cell colony formation assay, wound healing assay, cell proliferation assay, and Western blot.

Results

The CESC patients were classified into two subtypes, and the high classifier-score patients with significant differences in ECM-receptor interaction, PI3K-Akt signaling pathway, and MAPK signaling pathway showed a poorer prognosis in OS (p < 0.001), DFI (p = 0.016), PFI (p < 0.001) and DSS (p < 0.001), and with high the M0 Macrophage and resting Mast cells infiltration and low HLA family gene expression. Moreover, the constructed classifier owns a high identified accuracy in the tumor/normal groups (AUC: 0.993), the tumor/CIN1-CIN3 groups (AUC: 0.963), and normal/CIN1-CIN3 groups (AUC: 0.962), and the total prediction performance is better than currently published signatures in CESC (C-index: 0,763). The combined prediction performance further indicated that Nomogram (AUC = 0.837) is superior to the classifier (AUC = 0.835) and Stage (AUC = 0.568), and the C-index of calibration curves is 0.784. The potential biological function of classifier genes indicated that silencing GALNT2 inhibited the cancer cell's proliferation, migration, and colony formation; Conversely, the cancer cell's proliferation, migration, and colony formation were increased after the upregulation of GALNT2. The Epithelial-Mesenchymal Transition Experiment showed that GALNT2 knockdown might reduce the levels of Snail and Vimentin proteins and increase E-cadherin; Conversely, the levels of Snail and Vimentin proteins were increased, E-cadherin was reduced by GALNT2 upregulation.

Conclusion

The classifier we constructed may help improve our understanding of subtype characteristics and provide a new strategy for developing CESC therapeutics. Remarkably, GALNT2 may be an option to directly target drivers in CESC cancer therapy.

Considering whole-body metabolism in hyperpolarized MRI through 13 C breath analysis-An alternative way to quantification and normalization?

PURPOSE

Hyperpolarized [1-¹³ C]pyruvate MRI is an emerging clinical tool for metabolic imaging. It has the potential for absolute quantitative metabolic imaging. However, the method itself is not quantitative, limiting comparison of images across both time and between individuals. Here, we propose a simple signal normalization to the whole-body oxidative metabolism to overcome this limitation.

THEORY AND METHODS

A simple extension of the model-free ratiometric analysis of hyperpolarized [1-¹³ C]pyruvate MRI is presented, using the expired ¹³ CO₂ in breath for normalization. The proposed framework was investigated in two porcine cohorts (N = 11) subjected to local renal hypoperfusion defects and subsequent [1-¹³ C]pyruvate MRI. A breath sample was taken before the [1-¹³ C]pyruvate injection and 5 min after. The raw MR signal from both the healthy and intervened kidney in the two cohorts was normalized using the ¹³ CO₂ in the expired air.

RESULTS

¹³ CO₂ content in the expired air was significantly different between the two cohorts. Normalization to this reduced the coefficients of variance in the aerobic metabolic sensitive pathways by 25% for the alanine/pyruvate ratio, and numerical changes were observed in the bicarbonate/pyruvate ratio. The lactate/pyruvate ratio was largely unaltered (<2%).

CONCLUSION

Our results indicate that normalizing the hyperpolarized ¹³ C-signal ratios by the ¹³ CO₂ content in expired air can reduce variation as well as improve specificity of the method by normalizing the metabolic readout to the overall metabolic status of the individual. The method is a simple and cheap extension to the hyperpolarized ¹³ C exam.

Tumour Heterogeneity and the Consequent Practical Challenges in the Management of Gastroenteropancreatic Neuroendocrine Neoplasms

Tumour heterogeneity is a common phenomenon in neuroendocrine neoplasms (NENs) and a significant cause of treatment failure and disease progression. Genetic and epigenetic instability, along with proliferation of cancer stem cells and alterations in the tumour microenvironment, manifest as intra-tumoural variability in tumour biology in primary tumours and metastases. This may change over time, especially under selective pressure during treatment. The gastroenteropancreatic (GEP) tract is the most common site for NENs, and their diagnosis and treatment depends on the specific characteristics of the disease, in particular proliferation activity, expression of somatostatin receptors and grading. Somatostatin receptor expression has a major role in the diagnosis and treatment of GEP-NENs, while Ki-67 is also a valuable prognostic marker. Intra- and inter-tumour heterogeneity in GEP-NENS, however, may lead to inaccurate assessment of the disease and affect the reliability of the available diagnostic, prognostic and predictive tests. In this review, we summarise the current available evidence of the impact of tumour heterogeneity on tumour diagnosis and treatment of GEP-NENs. Understanding and accurately measuring tumour heterogeneity could better inform clinical decision making in NENs.

Ultrasmall silica nanoparticles in translational biomedical research: Overview and outlook

The exemplary progress of silica nanotechnology has attracted extensive attention across a range of biomedical applications such as diagnostics and imaging, drug delivery, and therapy of cancer and other diseases. Ultrasmall silica nanoparticles (USNs) have emerged as a particularly promising class demonstrating unique properties that are especially suitable for and have shown great promise in translational and clinical biomedical research. In this review, we discuss synthetic strategies that allow precise engineering of USNs with excellent control over size and surface chemistry, functionalization, and pharmacokinetic and toxicological profiles. We summarize the current state-of-the-art in the biomedical applications of USNs with a particular focus on select clinical studies. Finally, we illustrate long-standing challenges in the translation of inorganic nanotechnology, particularly in the context of ultrasmall nanomedicines, and provide our perspectives on potential solutions and future opportunities in accelerating the translation and widespread adoption of USN technology in biomedical research.

Prediction value of 18F-FDG PET/CT intratumor metabolic heterogeneity parameters for recurrence after radical surgery of stage II/III colorectal cancer

Purpose

We explored the predictive effect of intratumor metabolic heterogeneity indices extracted from ¹⁸F-FDG PET/CT on recurrence in stage II/III colorectal cancer after radical surgery.

Methods

A total of 140 stage II/III colorectal cancer patients who received preoperative ¹⁸F-FDG PET/CT and radical resection were enrolled. ¹⁸F-FDG traditional parameters including the maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) under different thresholds; heterogeneity indices including the coefficient of variation with SUV 2.5 as a threshold (CV2.5), CV40%, heterogeneity index-1 (HI-1) calculated by the fixed-threshold method, and HI-2 calculated by the percentage threshold method; and clinicopathological information were collected. We concluded that relationships exist between these data and patients’ disease-free survival (DFS).

Results

Regional lymph node status (P < 0.001), nerve invasion (P = 0.036), tumor thrombus (P = 0.005), and HI-1 (P = 0.010) exhibited significant differences between the relapse and non-relapse groups, while SUVmax, MTV2.5, MTV40%, TLG2.5, TLG40%, CV2.5, CV40%, HI-2, and other clinicopathological factors had no differences between the relapse and non-relapse groups. Multivariate analysis demonstrated that HI-1 (HR = 1.02, 1.00–1.04, P = 0.038), regional lymph node metastasis (HR = 2.95, 1.37–6.38, P = 0.006), and tumor thrombus status (HR = 2.37, 1.13–4.99, P = 0.022) were independent factors significantly related to DFS.

Conclusion

HI-1, tumor thrombus status, and regional lymph node status could predict the recurrence of stage II/III colorectal cancer after radical resection and had an advantage over other ¹⁸F-FDG PET/CT conventional parameters and heterogeneity indices.

Temporal Heterogeneity of HER2 Expression and Spatial Heterogeneity of 18F-FDG Uptake Predicts Treatment Outcome of Pyrotinib in Patients with HER2-Positive Metastatic Breast Cancer

Background: This study aimed to evaluate tumor heterogeneity of metastatic breast cancer (MBC) and investigate its impact on the efficacy of pyrotinib in patients with HER2-positive MBC. Methods: MBC patients who underwent 18F-FDG PET/CT before pyrotinib treatment were included. Temporal and spatial tumor heterogeneity was evaluated by the discordance between primary and metastatic immunohistochemistry (IHC) results and baseline 18F-FDG uptake heterogeneity (intertumoral and intratumoral heterogeneity indexes: HI-inter and HI-intra), respectively. Progression-free survival (PFS) was estimated by the Kaplan−Meier method and compared by a log-rank test. Results: A total of 572 patients were screened and 51 patients were included. In 36 patients with matched IHC results, 25% of them had HER2 status conversion. Patients with homogenous HER2 positivity had the longest PFS, followed by patients with gained HER2 positivity, while patients with HER2 negative conversion could not benefit from pyrotinib (16.8 vs. 13.7 vs. 3.6 months, p < 0.0001). In terms of spatial heterogeneity, patients with high HI-intra and HI-inter had significantly worse PFS compared to those with low heterogeneity (10.6 vs. 25.3 months, p = 0.023; 11.2 vs. 25.3 months, p = 0.040). Conclusions: Temporal heterogeneity of HER2 status and spatial heterogeneity of 18F-FDG uptake could predict the treatment outcome of pyrotinib in patients with HER2-positive MBC, which provide practically applicable methods to assess tumor heterogeneity and guidance for treatment decisions.

Development and Validation of a DeepSurv Nomogram to Predict Survival Outcomes and Guide Personalized Adjuvant Chemotherapy in Non-Small Cell Lung Cancer

Objective

To develop and validate a DeepSurv nomogram based on radiomic features extracted from computed tomography images and clinicopathological factors, to predict the overall survival and guide individualized adjuvant chemotherapy in patients with non-small cell lung cancer (NSCLC).

Patients and Methods

This retrospective study involved 976 consecutive patients with NSCLC (training cohort, n=683; validation cohort, n=293). DeepSurv was constructed based on 1,227 radiomic features, and the risk score was calculated for each patient as the output. A clinical multivariate Cox regression model was built with clinicopathological factors to determine the independent risk factors. Finally, a DeepSurv nomogram was constructed by integrating the risk score and independent clinicopathological factors. The discrimination capability, calibration, and clinical usefulness of the nomogram performance were assessed using concordance index evaluation, the Greenwood-Nam-D’Agostino test, and decision curve analysis, respectively. The treatment strategy was analyzed using a Kaplan–Meier curve and log-rank test for the high- and low-risk groups.

Results

The DeepSurv nomogram yielded a significantly better concordance index (training cohort, 0.821; validation cohort 0.768) with goodness-of-fit (P<0.05). The risk score, age, thyroid transcription factor-1, Ki-67, and disease stage were the independent risk factors for NSCLC.The Greenwood-Nam-D’Agostino test showed good calibration performance (P=0.39). Both high- and low-risk patients did not benefit from adjuvant chemotherapy, and chemotherapy in low-risk groups may lead to a poorer prognosis.

Conclusions

The DeepSurv nomogram, which is based on the risk score and independent risk factors, had good predictive performance for survival outcome. Further, it could be used to guide personalized adjuvant chemotherapy in patients with NSCLC.

Correlation between 18F-FDG PET/CT intra-tumor metabolic heterogeneity parameters and KRAS mutation in colorectal cancer

PURPOSE

The study aimed to evaluate the relationship between intra-tumor metabolic heterogeneity parameters of ¹⁸F-FDG and KRAS mutation status in colorectal cancer (CRC) patients and which threshold heterogeneity parameters could better reflect the heterogeneity characteristics of colorectal cancer.

METHODS

Medical data of 101 CRC patients who underwent ¹⁸F-FDG PET/CT and KRAS mutation analysis were selected. On PET scans, ¹⁸F-FDG traditional indices maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), total lesion glycolysis (TLG), and heterogeneity parameters coefficient of variation with a threshold of 2.5 (CV_2.5), CV_40%, heterogeneity index-1 (HI-1), and HI-2 of the primary lesions were obtained. We inferred correlations between these ¹⁸F-FDG parameters and KRAS mutation status.

RESULTS

41 patients (40.6%) had KRAS gene mutation. Assessment of FDG parameters showed that SUVmax (19.00 vs. 13.16, p < 0.001), MTV (11.64 vs. 8.83, p = 0.001), and TLG (102.85 vs. 69.76, p < 0.001), CV_2.5 (0.55 vs. 0.46, p = 0.006), and HI-2 (14.03 vs. 7.59, p < 0.001) of KRAS mutation were higher compared to wild-type (WT) KRAS. CV_40% (0.22 vs. 0.24, p = 0.001) was lower in the KRAS mutation group, while HI-1 had no significant difference between the two groups. Multivariate analysis showed that MTV (OR = 4.97, 1.04-23.83, p = 0.045) was the only significant predictor in KRAS mutation, using a cut-off of 7.62 (AUC = 0.695), and MTV showed a sensitivity of 90.2% and specificity of 45.0%. However, the PET parameters were not independent predictors in KRAS mutation.

CONCLUSION

KRAS gene mutant CRC patients had more ¹⁸F-FDG uptake (SUVmax, MTV, TLG) and heterogeneity (CV_2.5, HI-2) than WT KRAS. MTV was the only independent predictor of KRAS gene mutation in colorectal cancer patients.

Identification and Validation of Invasion-Related Molecular Subtypes and Prognostic Features for Cervical Cancer

Background

As one of the main causes leading to female cancer deaths, cervical cancer shows malignant features of local infiltration and invasion into adjacent organs and tissues. This study was designed to categorize novel molecular subtypes according to cervical cancer invasion and screen reliable prognostic markers.

Methods

Invasion-related gene sets and expression profiles of invasion-related genes were collected from the CancerSEA database and The Cancer Genome Atlas (TCGA), respectively. Samples were clustered by nonnegative matrix factorization (NMF) to obtain different molecular subgroups, immune microenvironment characteristics of which were further systematically compared. Limma was employed to screen differentially expressed gene sets in different subtypes, followed by Lasso analysis for dimension reduction. Multivariate and univariate Cox regression analysis was performed to determine prognostic characteristics. The Kaplan-Meier test showed the prognostic differences of patients with different risks. Additionally, receiver operating characteristic (ROC) curves were applied to validate the prognostic model performance. A nomogram model was developed using clinical and prognostic characteristics of cervical cancer, and its prediction accuracy was reflected by calibration curve.

Results

This study filtered 19 invasion-related genes with prognosis significance in cervical cancer and 2 molecular subtypes (C1, C2). Specifically, the C1 subtype had an unfavorable prognosis, which was associated with the activation of the TGF-beta signaling pathway, focal adhesion, and PI3K-Akt signaling pathway. 875 differentially expressed genes were screened, and 8 key genes were finally retained by the dimension reduction analysis. An 8-gene signature was established as an independent factor predictive of the prognosis of cervical cancer. The signature performance was even stronger when combined with N stage.

Conclusion

Based on invasion-related genes, the present study categorized two cervical cancer subtypes with distinct TME characteristics and established an 8-gene marker that can accurately and independently predict the prognosis of cervical cancer.

Prognostic Value of Intratumor Metabolic Heterogeneity Parameters on 18F-FDG PET/CT for Patients with Colorectal Cancer

Purpose

Intratumor metabolic heterogeneity parameters on ¹⁸F-2-fluoro-2-deoxy-D-glucose (¹⁸F-FDG) positron emission tomography-computed tomography (PET-CT) have been proven to be predictors of the clinical prognosis of cancer patients. The study aimed to examine the correlation between ¹⁸F-FDG PET-CT-defined heterogeneity parameters and the prognostic significance in patients with colorectal cancer.

Methods

The study included 188 patients with colorectal cancer who received surgery and ¹⁸F-FDG PET/CT examinations. Preoperative ¹⁸F-FDG PET/CT conventional and metabolic heterogeneity parameters were collected, including maximum, peak, and mean standardized uptake value (SUVmax, SUVpeak, and SUVmean), metabolic tumor volume (MTV), total lesion glycolysis (TLG), heterogeneity index-1 (HI-1) and heterogeneity index-2 (HI-2), and clinicopathological information. Correlations between these parameters and patient survival outcomes were inferred.

Results

The associations between ¹⁸F-FDG PET/CT parameters and clinical outcomes were analyzed. Tumor thrombus (P < 0.001), tumor stage (P=0.001), MTV (P=0.003), HI-1 (P=0.032), and HI-2 (P=0.001) differed between the two groups with and without recurrence. Multivariate analysis showed that, in the radical surgery group, HI-2 (HR = 1.10, 95% CI: 1.04–1.17, P=0.001), tumor stage (HR = 20.65, 95% CI: 4.81–88.62, P < 0.001), and regional lymph nodes status (HR = 0.16, 95% CI: 0.04–0.57, P=0.005) were independent variables significantly correlated with progression-free survival (PFS) and HI-2 (HR = 1.16, 95% CI: 1.07–1.26, P < 0.001) was an independent variable affecting overall survival (OS). In the palliative surgery group, HI-2 (HR = 1.03, 95% CI: 1.01–1.06, P=0.020) was an independent variable affecting PFS, and all the parameters were not statistically significant for OS.

Conclusion

HI-2, tumor stage, and regional lymph nodes status might predict the outcomes of colorectal cancer more effectively than other ¹⁸F-FDG PET/CT defined parameters.

Radiomics for Identification and Prediction in Metastatic Prostate Cancer: A Review of Studies

Metastatic Prostate Cancer (mPCa) is associated with a poor patient prognosis. mPCa spreads throughout the body, often to bones, with spatial and temporal variations that make the clinical management of the disease difficult. The evolution of the disease leads to spatial heterogeneity that is extremely difficult to characterise with solid biopsies. Imaging provides the opportunity to quantify disease spread. Advanced image analytics methods, including radiomics, offer the opportunity to characterise heterogeneity beyond what can be achieved with simple assessment. Radiomics analysis has the potential to yield useful quantitative imaging biomarkers that can improve the early detection of mPCa, predict disease progression, assess response, and potentially inform the choice of treatment procedures. Traditional radiomics analysis involves modelling with hand-crafted features designed using significant domain knowledge. On the other hand, artificial intelligence techniques such as deep learning can facilitate end-to-end automated feature extraction and model generation with minimal human intervention. Radiomics models have the potential to become vital pieces in the oncology workflow, however, the current limitations of the field, such as limited reproducibility, are impeding their translation into clinical practice. This review provides an overview of the radiomics methodology, detailing critical aspects affecting the reproducibility of features, and providing examples of how artificial intelligence techniques can be incorporated into the workflow. The current landscape of publications utilising radiomics methods in the assessment and treatment of mPCa are surveyed and reviewed. Associated studies have incorporated information from multiple imaging modalities, including bone scintigraphy, CT, PET with varying tracers, multiparametric MRI together with clinical covariates, spanning the prediction of progression through to overall survival in varying cohorts. The methodological quality of each study is quantified using the radiomics quality score. Multiple deficits were identified, with the lack of prospective design and external validation highlighted as major impediments to clinical translation. These results inform some recommendations for future directions of the field.

Computed Tomography-Based Radiomics Model to Preoperatively Predict Microsatellite Instability Status in Colorectal Cancer: A Multicenter Study

Objectives

To establish and validate a combined radiomics model based on radiomics features and clinical characteristics, and to predict microsatellite instability (MSI) status in colorectal cancer (CRC) patients preoperatively.

Methods

A total of 368 patients from four hospitals, who underwent preoperative contrast-enhanced CT examination, were included in this study. The data of 226 patients from a single hospital were used as the training dataset. The data of 142 patients from the other three hospitals were used as an independent validation dataset. The regions of interest were drawn on the portal venous phase of contrast-enhanced CT images. The filtered radiomics features and clinical characteristics were combined. A total of 15 different discrimination models were constructed based on a feature selection strategy from a pool of 3 feature selection methods and a classifier from a pool of 5 classification algorithms. The generalization capability of each model was evaluated in an external validation set. The model with high area under the curve (AUC) value from the training set and without a significant decrease in the external validation set was final selected. The Brier score (BS) was used to quantify overall performance of the selected model.

Results

The logistic regression model using the mutual information (MI) dimensionality reduction method was final selected with an AUC value of 0.79 for the training set and 0.73 for the external validation set to predicting MSI. The BS value of the model was 0.12 in the training set and 0.19 in the validation set.

Conclusion

The established combined radiomics model has the potential to predict MSI status in CRC patients preoperatively.

Relationship between tumor heterogeneity and volume in cervical cancer: Evidence from integrated fluorodeoxyglucose 18 PET/MR texture analysis

OBJECTIVE

The aim of this study was to evaluate the effect of cervical cancer volume on PET/magnetic resonance (MR) texture heterogeneity.

MATERIALS AND METHODS

We retrospectively analyzed the PET/MR images of 138 patients with pathologically diagnosed cervical squamous cell carcinoma, including 50 patients undergoing surgery and 88 patients receiving concurrent chemoradiotherapy. Fluorodeoxyglucose 18 (18FDG)-PET/MR examination were performed for each patient before treatment, and the PET and MR texture analysis were undertaken. The texture features of the tumor based on gray-level co-occurrence matrices were extracted, and the correlation between tumor texture features and volume parameters was analyzed using Spearman's rank correlation coefficient. Finally, the variation trend of tumor texture heterogeneity was analyzed as tumor volumes increased.

RESULTS

PET texture features were highly correlated with metabolic tumor volume (MTV), including entropy-log2, entropy-log10, energy, homogeneity, dissimilarity, contrast, correlation, and the correlation coefficients (rs) were 0.955, 0.955, -0.897, 0.883, -0.881, -0.876, and 0.847 (P < 0.001), respectively. In the range of smaller MTV, the texture heterogeneity of energy, entropy-log2, and entropy-log10 increases with an increase in tumor volume, whereas the texture heterogeneity of homogeneity, dissimilarity, contrast, and correlation decreases with an increase in tumor volume. Only homogeneity, contrast, correlation, and dissimilarity had high correlation with tumor volume on MRI. The correlation coefficients (rs) were 0.76, -0.737, 0.644, and -0.739 (P < 0.001), respectively. The texture heterogeneity of MRI features that are highly correlated with tumor volume decreases with increasing tumor volume.

CONCLUSION

In the small tumor volume range, the heterogeneity variation trend of PET texture features is inconsistent as the tumor volume increases, but the variation trend of MRI texture heterogeneity is consistent, and MRI texture heterogeneity decreases as tumor volume increases. These results suggest that MRI is a better imaging modality when compared with PET in determining tumor texture heterogeneity in the small tumor volume range.

Differences in Radiomics Signatures Between Patients with Early and Advanced T-Stage Nasopharyngeal Carcinoma Facilitate Prognostication

BACKGROUND

Accurately predicting the risk of death, recurrence, and metastasis of patients with nasopharyngeal carcinoma (NPC) is potentially important for personalized diagnosis and treatment. Survival outcomes of patients vary greatly in distinct stages of NPC. Prognostic models of stratified patients may aid in prognostication.

PURPOSE

To explore the prognostic performance of MRI-based radiomics signatures in stratified patients with NPC.

STUDY TYPE

Retrospective.

POPULATION

Seven hundred and seventy-eight patients with NPC (T1-2 stage: 298, T3-4 stage: 480; training cohort: 525, validation cohort: 253).

FIELD STRENGTH/SEQUENCE

Fast-spin echo (FSE) axial T1-weighted images, FSE axial T2-weighted images, contrast-enhanced FSE axial T1-weighted images at 1.5 T or 3.0 T.

ASSESSMENT

Radiomics signatures, clinical nomograms, and radiomics nomograms combining the radiomic score (Radscore) and clinical factors for predicting progression-free survival (PFS) were constructed on T1-2 stage patient cohort (A), T3-4 stage patient cohort (B), and the entire dataset (C).

STATISTICAL TESTS

Least absolute shrinkage and selection operator (LASSO) method was applied for radiomics modeling. Harrell's concordance indices (C-index) were employed to evaluate the predictive power of each model.

RESULTS

Among 4,410 MRI-extracted features, we selected 16, 16, and 14 radiomics features most relevant to PFS for Models A, B, and C, respectively. Only 0, 1, and 4 features were found overlapped between models A/B, A/C, and B/C, respectively. Radiomics signatures constructed on T1-2 stage and T3-4 stage patients yielded C-indices of 0.820 (95% confidence interval [CI]: 0.763-0.877) and 0.726 (0.687-0.765), respectively, which were larger than those on the entire validation cohort (0.675 [0.637-0.713]). Radiomics nomograms combining Radscore and clinical factors achieved significantly better performance than clinical nomograms (P < 0.05 for all).

DATA CONCLUSION

The selected radiomics features and prognostic performance of radiomics signatures differed per the type of NPC patients incorporated into the models. Radiomics models based on pre-stratified tumor stages had better prognostic performance than those on unstratified dataset.

LEVEL OF EVIDENCE

4 Technical Efficacy Stage: 5.

Heterogeneity analysis of MRI T2 maps for measurement of early tumor response to radiotherapy

External beam radiotherapy (XRT) is a widely used cancer treatment, yet responses vary dramatically among patients. These differences are not accounted for in clinical practice, partly due to a lack of sensitive early response biomarkers. We hypothesize that quantitative magnetic resonance imaging (MRI) measures reflecting tumor heterogeneity can provide a sensitive and robust biomarker of early XRT response. MRI T2 mapping was performed every 72 hours following 10 Gy dose XRT in two models of pancreatic cancer propagated in the hind limb of mice. Interquartile range (IQR) of tumor T2 was presented as a potential biomarker of radiotherapy response compared with tumor growth kinetics, and biological validation was performed through quantitative histology analysis. Quantification of tumor T2 IQR showed sensitivity for detection of XRT-induced tumor changes 72 hours after treatment, outperforming T2-weighted and diffusion-weighted MRI, with very good robustness. Histological comparison revealed that T2 IQR provides a measure of spatial heterogeneity in tumor cell density, related to radiation-induced necrosis. Early IQR changes were found to correlate to subsequent tumor volume changes, indicating promise for treatment response prediction. Our preclinical findings indicate that spatial heterogeneity analysis of T2 MRI can provide a translatable method for early radiotherapy response assessment. We propose that the method may in future be applied for personalization of radiotherapy through adaptive treatment paradigms.

A Phantom Study to Investigate Robustness and Reproducibility of Grey Level Co-Occurrence Matrix (GLCM)-Based Radiomics Features for PET

Quantification and classification of heterogeneous radiotracer uptake in Positron Emission Tomography (PET) using textural features (termed as radiomics) and artificial intelligence (AI) has the potential to be used as a biomarker of diagnosis and prognosis. However, textural features have been predicted to be strongly correlated with volume, segmentation and quantization, while the impact of image contrast and noise has not been assessed systematically. Further continuous investigations are required to update the existing standardization initiatives. This study aimed to investigate the relationships between textural features and these factors with 18F filled torso NEMA phantom to yield different contrasts and reconstructed with different durations to represent varying levels of noise. The phantom was also scanned with heterogeneous spherical inserts fabricated with 3D printing technology. All spheres were delineated using: (1) the exact boundaries based on their known diameters; (2) 40% fixed; and (3) adaptive threshold. Six textural features were derived from the gray level co-occurrence matrix (GLCM) using different quantization levels. The results indicate that homogeneity and dissimilarity are the most suitable for measuring PET tumor heterogeneity with quantization 64 provided that the segmentation method is robust to noise and contrast variations. To use these textural features as prognostic biomarkers, changes in textural features between baseline and treatment scans should always be reported along with the changes in volumes.

A practical method for multimodal registration and assessment of whole-brain disease burden using PET, MRI, and optical imaging

Many neurological diseases present with substantial genetic and phenotypic heterogeneity, making assessment of these diseases challenging. This has led to ineffective treatments, significant morbidity, and high mortality rates for patients with neurological diseases, including brain cancers and neurodegenerative disorders. Improved understanding of this heterogeneity is necessary if more effective treatments are to be developed. We describe a new method to measure phenotypic heterogeneity across the whole rodent brain at multiple spatial scales. The method involves co-registration and localized comparison of in vivo radiologic images (e.g. MRI, PET) with ex vivo optical reporter images (e.g. labeled cells, molecular targets, microvasculature) of optically cleared tissue slices. Ex vivo fluorescent images of optically cleared pathology slices are acquired with a preclinical in vivo optical imaging system across the entire rodent brain in under five minutes, making this methodology practical and feasible for most preclinical imaging labs. The methodology is applied in various examples demonstrating how it might be used to cross-validate and compare in vivo radiologic imaging with ex vivo optical imaging techniques for assessing hypoxia, microvasculature, and tumor growth.

3D DESI-MS lipid imaging in a xenograft model of glioblastoma: a proof of principle

Desorption electrospray ionisation mass spectrometry (DESI-MS) can image hundreds of molecules in a 2D tissue section, making it an ideal tool for mapping tumour heterogeneity. Tumour lipid metabolism has gained increasing attention over the past decade; and here, lipid heterogeneity has been visualised in a glioblastoma xenograft tumour using 3D DESI-MS imaging. The use of an automatic slide loader automates 3D imaging for high sample-throughput. Glioblastomas are highly aggressive primary brain tumours, which display heterogeneous characteristics and are resistant to chemotherapy and radiotherapy. It is therefore important to understand biochemical contributions to their heterogeneity, which may be contributing to treatment resistance. Adjacent sections to those used for DESI-MS imaging were used for H&E staining and immunofluorescence to identify different histological regions, and areas of hypoxia. Comparing DESI-MS imaging with biological staining allowed association of different lipid species with hypoxic and viable tissue within the tumour, and hence mapping of molecularly different tumour regions in 3D space. This work highlights that lipids are playing an important role in the heterogeneity of this xenograft tumour model, and DESI-MS imaging can be used for lipid 3D imaging in an automated fashion to reveal heterogeneity, which is not apparent in H&E stains alone.

Intra-tumor metabolic heterogeneity of gastric cancer on 18F-FDG PETCT indicates patient survival outcomes

The present study aimed to investigate the prognostic value of intra-tumor metabolic heterogeneity on 2-[18F] Fluoro-2-deoxy-D-glucose (¹⁸F-FDG) positron emission tomography/computed tomography (PET/CT) for patients with gastric cancer. Fifty-five patients with advanced gastric cancer that had received neoadjuvant chemotherapy and radical surgery were included. Clinicopathological information, ¹⁸F-FDG PET/CT before chemotherapy, pathological response, recurrence or metastasis, progression-free survival (PFS), and overall survival (OS) of the patients were collected. The maximum, peak, and mean standardized uptake values (SUV_max, SUV_peak, and SUV_mean), tumor-to-liver ratio (TLR), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) on PET/CT were measured. Heterogeneity index-1 (HI-1) was calculated as SUV_mean divided by the standard deviation, and heterogeneity index-2 (HI-2) was evaluated through linear regressions of MTVs according to different SUV thresholds. Associations between these parameters and patient survival outcomes were analyzed. None of the parameters on PET were associated with tumor recurrence. Pathological responders had significantly smaller TLR, MTV and HI-2 values than non-responders (P = 0.017, 0.017 and 0.013, respectively). In multivariate analysis of PFS, only HI-2 was an independent factor (hazard ratio [HR] = 2.693, P = 0.005) after adjusting for clinical tumor-node-metastasis (TNM) stage. In multivariate analysis of OS, HI-2 was also an independent predictive factor (HR = 2.281, P = 0.009) after adjusting for tumor recurrence. Thus, HI-2 generated from baseline ¹⁸F-FDG PET/CT is significantly associated with survival of patients with gastric cancer. Preoperative assessment of HI-2 by ¹⁸F-FDG PET/CT might be promising to identify patients with poor prognosis.

Robustness of CT radiomic features against image discretization and interpolation in characterizing pancreatic neuroendocrine neoplasms

PURPOSE

To explore the variation of the discriminative power of CT radiomic features (RF) against image discretization/interpolation in characterizing pancreatic neuro-endocrine (PanNEN) neoplasms.

MATERIALS AND METHODS

Thirty-nine PanNEN patients with pre-surgical high contrast CT available were considered. Image interpolation and discretization parameters were intentionally changed, including pixel size (0.73-2.19 mm²), slice thickness (2-5 mm) and binning (32-128 grey levels) and their combination generated 27 parameter's set. The ability of 69 RF in discriminating post-surgically assessed tumor grade (>G1), positive nodes, metastases and vascular invasion was tested: AUC changes when changing the parameters were quantified for selected RF, significantly associated to each end-point. The analysis was repeated for the corresponding images with contrast medium and in a sub-group of 29/39 patients scanned on a single scanner.

RESULTS

The median tumor volume was 1.57 cm³ (16%-84% percentiles: 0.62-34.58 cm³). RF variability against discretization/interpolation parameters was large: only 21/69 RF showed %COV < 20%. Despite this variability, AUC changes were limited for all end-points: with typical AUC values around 0.75-0.85, AUC ranges for the 27 parameter's set were on average 0.062 (1SD:0.037) for all end-points with maximum %COV equal to 5.5% (mean:2.3%). Performances significantly improved when excluding the 5 mm thickness case and fixing the binning to 64 (mean AUC range: 0.036, 1SD:0.019). Using contrast images or limiting the population to single-scanner patients had limited impact on AUC variability.

CONCLUSIONS

The discriminative power of CT RF for panNEN is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.

An Automated Segmentation Pipeline for Intratumoural Regions in Animal Xenografts Using Machine Learning and Saturation Transfer MRI

Saturation transfer MRI can be useful in the characterization of different tumour types. It is sensitive to tumour metabolism, microstructure, and microenvironment. This study aimed to use saturation transfer to differentiate between intratumoural regions, demarcate tumour boundaries, and reduce data acquisition times by identifying the imaging scheme with the most impact on segmentation accuracy. Saturation transfer-weighted images were acquired over a wide range of saturation amplitudes and frequency offsets along with T₁ and T₂ maps for 34 tumour xenografts in mice. Independent component analysis and Gaussian mixture modelling were used to segment the images and identify intratumoural regions. Comparison between the segmented regions and histopathology indicated five distinct clusters: three corresponding to intratumoural regions (active tumour, necrosis/apoptosis, and blood/edema) and two extratumoural (muscle and a mix of muscle and connective tissue). The fraction of tumour voxels segmented as necrosis/apoptosis quantitatively matched those calculated from TUNEL histopathological assays. An optimal protocol was identified providing reasonable qualitative agreement between MRI and histopathology and consisting of T₁ and T₂ maps and 22 magnetization transfer (MT)-weighted images. A three-image subset was identified that resulted in a greater than 90% match in positive and negative predictive value of tumour voxels compared to those found using the entire 24-image dataset. The proposed algorithm can potentially be used to develop a robust intratumoural segmentation method.

A Pilot Study of Texture Analysis of Primary Tumor [18F]FDG Uptake to Predict Recurrence in Surgically Treated Patients with Non-small Cell Lung Cancer

PURPOSE

To examine whether the heterogeneous texture parameters in primary tumor can predict prognosis of patients with non-small cell lung cancer (NSCLC) received surgery after 2-deoxy-2-[¹⁸F]fluoro-D-glucose ([¹⁸F]FDG) positron emission tomography (PET)/X-ray computed tomography (CT).

PROCEDURE

This retrospective study included 55 patients with NSCLC who underwent [¹⁸F]FDG-PET/CT before surgery from January 2011 and December 2015. SUV-related (SUVmax and SUVmean), volumetric (metabolic tumor volume [SUV ≥ 2.5], and total lesion glycolysis) and texture parameters (local parameters; entropy, homogeneity, and dissimilarity and regional parameters; intensity variability [IV], size-zone variability [SZV], and zone percentage [ZP]) were obtained. Tumor size, TNM stage, SUV-related, volumetric, and texture parameters were compared between the patients with progression and without progression using Mann-Whitney's U or χ² test and progression-free survival (PFS) and prognostic significance were assessed by Kaplan-Meier method and Cox regression analysis, respectively.

RESULTS

Nineteen patients eventually showed progression, and 36 patients were alive without progression during clinical follow-up (median follow-up PFS; 23 months [range, 1-71]). The patients with progression showed significantly larger tumor size (p < 0.001), higher IV (p = 0.010), and higher SZV (p = 0.007) than those without progression. PFS was significantly shorter in patients with large tumor size (p = 0.008), high T stage (p = 0.009), high stage (p = 0.013), high IV (p = 0.012), and high SZV (p = 0.015) at univariate analysis. At multivariate analysis, stage (hazard ratio [HR] 1.62, p = 0.035) and IV (hazard ratio 6.19, p = 0.048) were only remained independent predictors for PFS.

CONCLUSIONS

The regional heterogeneity texture parameters IV and SZV can predict tumor progression, and IV has the potential to predict prognosis of surgically treated NSCLC patients.

Predictive quantitative ultrasound radiomic markers associated with treatment response in head and neck cancer

Aim:

We aimed to identify quantitative ultrasound (QUS)-radiomic markers to predict radiotherapy response in metastatic lymph nodes of head and neck cancer.

Materials & methods:

Node-positive head and neck cancer patients underwent pretreatment QUS imaging of their metastatic lymph nodes. Imaging features were extracted using the QUS spectral form, and second-order texture parameters. Machine-learning classifiers were used for predictive modeling, which included a logistic regression, naive Bayes, and k-nearest neighbor classifiers.

Results:

There was a statistically significant difference in the pretreatment QUS-radiomic parameters between radiological complete responders versus partial responders (p < 0.05). The univariable model that demonstrated the greatest classification accuracy included: spectral intercept (SI)-contrast (area under the curve = 0.741). Multivariable models were also computed and showed that the SI-contrast + SI-homogeneity demonstrated an area under the curve = 0.870. The three-feature model demonstrated that the spectral slope-correlation + SI-contrast + SI-homogeneity-predicted response with accuracy of 87.5%.

Conclusion:

Multivariable QUS-radiomic features of metastatic lymph nodes can predict treatment response a priori.

In this study, quantitative ultrasound (QUS) and machine-learning classification was used to predict treatment outcomes in head and neck cancer patients. Metastatic lymph nodes in the neck were scanned using conventional frequency ultrasound (US). Quantitative data were collected from the US-radiofrequency signal a priori. Machine-learning classification models were computed using QUS features; these included the linear fit parameters of the power spectrum, and second-order texture parameters of the QUS parametric images. Treatment outcomes were measured based on radiological response. Patients were classified into binary groups: radiologic complete response (CR) or radiological partial response (PR), which was assessed 3 months following treatment. Initial results demonstrate high accuracy (%Acc = 87.5%) for predicting radiological response. The results of this study suggest that QUS can be used to predict head and neck cancer response to radiotherapy a priori.

Metastasis risk prediction model in osteosarcoma using metabolic imaging phenotypes: A multivariable radiomics model

BACKGROUND

Osteosarcoma (OS) is the most common primary bone tumor affecting humans and it has extreme heterogeneity. Despite modern therapy, it recurs in approximately 30-40% of patients initially diagnosed with no metastatic disease, with the long-term survival rates of patients with recurrent OS being generally 20%. Thus, early prediction of metastases in OS management plans is crucial for better-adapted treatments and survival rates. In this study, a radiomics model for metastasis risk prediction in OS was developed and evaluated using metabolic imaging phenotypes.

METHODS AND FINDINGS

The subjects were eighty-three patients with OS, and all were treated with surgery and chemotherapy for local control. All patients underwent a pretreatment 18F-FDG-PET scan. Forty-five features were extracted from the tumor region. The incorporation of features into multivariable models was performed using logistic regression. The multivariable modeling strategy involved cross validation in the following four steps leading to final prediction model construction: (1) feature set reduction and selection; (2) model coefficients computation through train and validation processing; and (3) prediction performance estimation. The multivariable logistic regression model was developed using two radiomics features, SUVmax and GLZLM-SZLGE. The trained and validated multivariable logistic model based on probability of endpoint (P) = 1/ (1+exp (-Z)) was Z = -1.23 + 1.53*SUVmax + 1.68*GLZLM-SZLGE with significant p-values (SUVmax: 0.0462 and GLZLM_SZLGE: 0.0154). The final multivariable logistic model achieved an area under the curve (AUC) receiver operating characteristics (ROC) curve of 0.80, a sensitivity of 0.66, and a specificity of 0.88 in cross validation.

CONCLUSIONS

The SUVmax and GLZLM-SZLGE from metabolic imaging phenotypes are independent predictors of metastasis risk assessment. They show the association between 18F-FDG-PET and metastatic colonization knowledge. The multivariable model developed using them could improve patient outcomes by allowing aggressive treatment in patients with high metastasis risk.

Segmentation of gliomas in 18F-fluorocholine PET/CT. A multiapproach study

AIM

Our aim was two-fold, to study the interobserver agreement in tumour segmentation and to search for a reliable methodology to segment gliomas using ¹⁸F-fluorocholine PET/CT.

METHODS

25 patients with glioma, from a prospective and non-randomized study (Functional and Metabolic Glioma Analysis), were included.Interobserver variability in tumour segmentation was assessed using fixed thresholds. Different strategies were used to segment the tumours. First, a semi-automatic tumour segmentation was performed, selecting the best SUVmax-% threshold for each lesion. Next we determined a variable SUVmax-% depending on the SUVmax. Finally a segmentation using a fixed SUVmax threshold was performed. To do so, a sampling of 10 regions of interest (ROI of 2.8cm²) located in the normal brain was performed. The upper value of the sample mean SUVmax±3 SD was used as cut-off. All procedures were tested and classified as effective or not for tumour segmentation by two observer's consensus.

RESULTS

In the pilot segmentation, the mean±SD of SUVmax, SUVmean and optimal SUVmax-% threshold were: 3.64±1.77, 1.32±0.57 and 21.32±8.39, respectively. Optimal SUVmax-% threshold showed a significant association with the SUVmax (Pearson=-0.653, p=.002). However, the linear regression model for the total sample was not good, that supported the division in two homogeneous groups, defining two formulas for predicting the optimal SUVmax-% threshold. As to the third procedure, the obtained value for the mean SUVmax background+3 SD was 0.33. This value allowed segmenting correctly a significant fraction of tumours, although not all.

CONCLUSION

A great interobserver variability in the tumour segmentation was found. None of the methods was able to segment correctly all the gliomas, probably explained by the wide tumour heterogeneity on ¹⁸F-fluorocholine PET/CT.

Radiomic detection of microscopic tumorous lesions in small animal liver SPECT imaging

BACKGROUND

Our aim was to present a new data analysis technique for the early detection of tumorous lesions using single-photon emission computed tomography (SPECT) imaging. Beyond standardized uptake value (SUV) and standardized uptake concentration (SUC), the skewness and kurtosis parameters of whole liver activity distribution histograms were examined in SPECT images to reveal the presence of tumorous cells.

METHODS

Four groups of mice were used in our experiment: a healthy control group, a group of obese mice with high body mass index, and two tumorous groups (primary liver cancer group with chemically induced hepatocellular carcinoma (HCC); metastatic liver tumor group-xenograft of human melanoma (HM)). For the SPECT measurements, ^99mTc-labeled aggregated albumin nanoparticles were administered intravenously 2 h before the liver SPECT scans (NanoSPECT/CT, Silver Upgrade, Mediso Ltd., Hungary) to image liver macrophages. Finally, SUV, SUC, skewness, and kurtosis of activity distributions were calculated from segmented whole liver volumes.

RESULTS

HCC animals showed moderate ^99mTc-albumin particle uptake with some visually identified cold spots indicating the presence of tumors. The visual detection of cold spots however was not a reliable marker of tumorous tissue in the metastatic group. The calculated SUV, SUC, and kurtosis parameters were not able to differentiate between the healthy and the tumorous groups. However, healthy and tumorous groups could be distinguished by comparing the skewness of the activity distribution.

CONCLUSION

Based on our results, ^99mTc-albumin nanoparticle injection followed by liver SPECT activity distribution skewness calculation is a suitable image analysis tool. This makes possible to effectively and quantitatively investigate liver macrophage inhomogeneity and identify invisible but present liver cold spot lesions. Skewness as a direct image-derived parameter is able to show altered tissue function even before the visual manifestation of liver tumor foci. The skewness of activity distribution might be related to an inhomogeneous distribution of macrophage cells as a consequence of microscopic tumor burden in the liver.

Dose-intensified chemoradiation is associated with altered patterns of failure and favorable survival in patients with newly diagnosed glioblastoma

BACKGROUND AND PURPOSE

We evaluated whether dose-intensified chemoradiation alters patterns of failure and is associated with favorable survival in the temozolomide era.

MATERIALS AND METHODS

Between 2003 and 2015, 82 patients with newly diagnosed glioblastoma were treated with 66-81 Gy in 30 fractions using conventional magnetic resonance imaging. Progression-free (PFS) and overall survival (OS) were calculated using Kaplan-Meier methods. Factors associated with improved PFS, OS, and time to progression were assessed using multivariate Cox model and linear regression.

RESULTS

Median follow-up was 23 months (95% CI 4-124 months). Sixty-one percent of patients underwent subtotal resection or biopsy, and 38% (10/26) of patients with available data had MGMT promoter methylation. Median PFS was 8.4 months (95% CI 7.3-11.0) and OS was 18.7 months (95% CI 13.1-25.3). Only 30 patients (44%) experienced central recurrence, 6 (9%) in-field, 16 (23.5%) marginal and 16 (23.5%) distant. On multivariate analysis, younger age (HR 0.95, 95% CI 0.93-0.97, p = 0.0001), higher performance status (HR 0.39, 95% CI 0.16-0.95, p = 0.04), gross total resection (GTR) versus biopsy (HR 0.37, 95% CI 0.16-0.85, p = 0.02) and MGMT methylation (HR 0.25, 95% CI 0.09-0.71, p = 0.009) were associated with improved OS. Only distant versus central recurrence (p = 0.03) and GTR (p = 0.02) were associated with longer time to progression. Late grade 3 neurologic toxicity was rare (6%) in patients experiencing long-term survival.

CONCLUSION

Dose-escalated chemoRT resulted in lower rates of central recurrence and prolonged time to progression compared to historical controls, although a significant number of central recurrences were still observed. Advanced imaging and correlative molecular studies may enable targeted treatment advances that reduce rates of in- and out-of-field progression.

18F-fluoromisonidazole positron emission tomography may be applicable in the evaluation of colorectal cancer liver metastasis

BACKGROUND

Positron emission tomography (PET) imaging is a non-invasive functional imaging method used to reflect tumor spatial information, and to provide biological characteristics of tumor progression. The aim of this study was to focus on the application of ¹⁸F-fluoromisonidazole (FMISO) PET quantitative parameter of maximum standardized uptake value (SUVmax) ratio to detect the liver metastatic potential of human colorectal cancer (CRC) in mice.

METHODS

Colorectal liver metastases (CRLM) xenograft models were established by injecting tumor cells (LoVo, HT29 and HCT116) into spleen of mice, tumor-bearing xenograft models were established by subcutaneously injecting tumor cells in the right left flank of mice. Wound healing assays were performed to examine the ability of cell migration in vitro. ¹⁸F-FMISO uptake in CRC cell lines was measured by cellular uptake assay. ¹⁸F-FMISO-based micro-PET imaging of CRLM and tumor-bearing mice was performed and quantified by tumor-to-liver SUVmax ratio. The correlation between the ¹⁸F-FMISO SUVmax ratio, liver metastases number, hypoxia-induced factor 1α (HIF-1α) and serum starvation-induced glucose transporter 1 (GLUT-1) was evaluated using Pearson correlation analysis.

RESULTS

Compared with HT29 and HCT116, LoVo-CRLM mice had significantly higher liver metastases ratio and shorter median survival time. LoVo cells exhibited stronger migration capacity and higher radiotracer uptake compared with HT29 and HCT116 in in vitro. Moreover, ¹⁸F-FMISO SUVmax ratio was significantly higher in both LoVo-CRLM model and LoVo-bearing tumor model compared to models established using HT29 and HCT116. In addition, Pearson correlation analysis revealed a significant correlation between ¹⁸F-FMISO SUVmax ratio of CRLM mice and number of liver metastases larger than 0.5 cm, as well as between ¹⁸F-FMISO SUVmax ratio and HIF-1α or GLUT-1 expression in tumor-bearing tissues.

CONCLUSIONS

¹⁸F-FMISO parameter of SUVmax ratio may provide useful tumor biological information in mice with CRLM, thus allowing for better prediction of CRLM and yielding useful radioactive markers for predicting liver metastasis potential in CRC.

Radiomics: Principles and radiotherapy applications

Radiomics is defined as the extraction of a large quantity of quantitative image features. The different radiomic indexes that have been proposed in the literature are described as well as the various factors that have an impact on the robustness of these indexes. We will see that several hundred quantitative features can be extracted per lesion and imaging modality. The ever-growing number of features studied raises the question of the statistical method of analysis used. This review addresses the research supporting the clinical use of radiomics in oncology in the staging of disease, discrimination between healthy and pathological tissues, the identification of genetic features, the prediction of patient survival, the response to treatment, the recurrence after radiotherapy and chemoradiotherapy and the side effects. Based on the existing literature, it remains difficult to identify features that should be used for current clinical practice.

Considering tumour volume for motion corrected DWI of colorectal liver metastases increases sensitivity of ADC to detect treatment-induced changes

ADC is a potential post treatment imaging biomarker in colorectal liver metastasis however measurements are affected by respiratory motion. This is compounded by increased statistical uncertainty in ADC measurement with decreasing tumour volume. In this prospective study we applied a retrospective motion correction method to improve the image quality of 15 tumour data sets from 11 patients. We compared repeatability of ADC measurements corrected for motion artefact against non-motion corrected acquisition of the same data set. We then applied an error model that estimated the uncertainty in ADC repeatability measurements therefore taking into consideration tumour volume. Test-retest differences in ADC for each tumour, was scaled to their estimated measurement uncertainty, and 95% confidence limits were calculated, with a null hypothesis that there is no difference between the model distribution and the data. An early post treatment scan (within 7 days of starting treatment) was acquired for 12 tumours from 8 patients. When accounting for both motion artefact and statistical uncertainty due to tumour volumes, the threshold for detecting significant post treatment changes for an individual tumour in this data set, reduced from 30.3% to 1.7% (95% limits of agreement). Applying these constraints, a significant change in ADC (5^th and 20^th percentiles of the ADC histogram) was observed in 5 patients post treatment. For smaller studies, motion correcting data for small tumour volumes increased statistical efficiency to detect post treatment changes in ADC. Lower percentiles may be more sensitive than mean ADC for colorectal metastases.

Haralick texture feature analysis for quantifying radiation response heterogeneity in murine models observed using Raman spectroscopic mapping

Tumour heterogeneity plays a large role in the response of tumour tissues to radiation therapy. Inherent biological, physical, and even dose deposition heterogeneity all play a role in the resultant observed response. We here implement the use of Haralick textural analysis to quantify the observed glycogen production response, as observed via Raman spectroscopic mapping, of tumours irradiated within a murine model. While an array of over 20 Haralick features have been proposed, we here concentrate on five of the most prominent features: homogeneity, local homogeneity, contrast, entropy, and correlation. We show that these Haralick features can be used to quantify the inherent heterogeneity of the Raman spectroscopic maps of tumour response to radiation. Furthermore, our results indicate that Haralick-calculated textural features show a statistically significant dose dependent variation in response heterogeneity, specifically, in glycogen production in tumours irradiated with clinically relevant doses of ionizing radiation. These results indicate that Haralick textural analysis provides a quantitative methodology for understanding the response of murine tumours to radiation therapy. Future work in this area can, for example, utilize the Haralick textural features for understanding the heterogeneity of radiation response as measured by biopsied patient tumour samples, which remains the standard of patient tumour investigation.

Multiparametric MRI and radiomics in prostate cancer: a review

Multiparametric MRI (mpMRI) is an imaging modality that combines anatomical MR imaging with one or more functional MRI sequences. It has become a versatile tool for detecting and characterising prostate cancer (PCa). The traditional role of mpMRI was confined to PCa staging, but due to the advanced imaging techniques, its role has expanded to various stages in clinical practises including tumour detection, disease monitor during active surveillance and sequential imaging for patient follow-up. Meanwhile, with the growing speed of data generation and the increasing volume of imaging data, it is highly demanded to apply computerised methods to process mpMRI data and extract useful information. Hence quantitative analysis for imaging data using radiomics has become an emerging paradigm. The application of radiomics approaches in prostate cancer has not only enabled automatic localisation of the disease but also provided a non-invasive solution to assess tumour biology (e.g. aggressiveness and the presence of hypoxia). This article reviews mpMRI and its expanding role in PCa detection, staging and patient management. Following that, an overview of prostate radiomics will be provided, with a special focus on its current applications as well as its future directions.

Prognostic modeling for patients with colorectal liver metastases incorporating FDG PET radiomic features

OBJECTIVE

We aimed to improve prediction of outcome for patients with colorectal liver metastases, via prognostic models incorporating PET-derived measures, including radiomic features that move beyond conventional standard uptake value (SUV) measures.

PATIENTS AND METHODS

A range of parameters including volumetric and heterogeneity measures were derived from FDG PET images of 52 patients with colorectal intrahepatic-only metastases (29 males and 23 females; mean age 62.9 years [SD 9.8; range 32-82]). The patients underwent PET/CT imaging as part of the clinical workup prior to final decision on treatment. Univariate and multivariate models were implemented, which included statistical considerations (to discourage false discovery and overfitting), to predict overall survival (OS), progression-free survival (PFS) and event-free survival (EFS). Kaplan-Meier survival analyses were performed, where the subjects were divided into high-risk and low-risk groups, from which the hazard ratios (HR) were computed via Cox proportional hazards regression.

RESULTS

Commonly-invoked SUV metrics performed relatively poorly for different prediction tasks (SUVmax HR = 1.48, 0.83 and 1.16; SUVpeak HR = 2.05, 1.93, and 1.64, for OS, PFS and EFS, respectively). By contrast, the number of liver metastases and metabolic tumor volume (MTV) each performed well (with respective HR values of 2.71, 2.61 and 2.42, and 2.62, 1.96 and 2.29, for OS, PFS and EFS). Total lesion glycolysis (TLG) also resulted in similar performance as MTV. Multivariate prognostic modeling incorporating different features (including those quantifying intra-tumor heterogeneity) resulted in further enhanced prediction. Specifically, HR values of 4.29, 4.02 and 3.20 (p-values = 0.00004, 0.0019 and 0.0002) were obtained for OS, PFS and EFS, respectively.

CONCLUSIONS

PET-derived measures beyond commonly invoked SUV parameters hold significant potential towards improved prediction of clinical outcome in patients with liver metastases, especially when utilizing multivariate models.

Characterizing Trastuzumab-Induced Alterations in Intratumoral Heterogeneity with Quantitative Imaging and Immunohistochemistry in HER2+ Breast Cancer

The purpose of this study is to investigate imaging and histology-based measurements of intratumoral heterogeneity to evaluate early treatment response to targeted therapy in a murine model of HER2+ breast cancer. BT474 tumor-bearing mice (N = 30) were treated with trastuzumab or saline and imaged longitudinally with either dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) or 18F-fluoromisonidazole (FMISO) positron emission tomography (PET). At the imaging study end point (day 4 for MRI or 7 for PET), each tumor was excised for immunohistochemistry analysis. Voxel-based histogram analysis was performed on imaging-derived parametric maps (i.e., Ktrans and ve from DCE-MRI, SUV from 18F-FMISO-PET) of the tumor region of interest to measure heterogeneity. Image processing and histogram analysis of whole tumor slice immunohistochemistry data were performed to validate the in vivo imaging findings. Trastuzumab-treated tumors had increased heterogeneity in quantitative imaging measures of cellularity (ve), with a mean Kolmogorov-Smirnov (K-S) distance of 0.32 (P = .05) between baseline and end point distributions. Trastuzumab-treated tumors had increased vascular heterogeneity (Ktrans) and decreased hypoxic heterogeneity (SUV), with a mean K-S distance of 0.42 (P < .01) and 0.46 (P = .047), respectively, between baseline and study end points. These observations were validated by whole-slice immunohistochemistry analysis with mean interquartile range of CD31 distributions of 1.72 for treated and 0.95 for control groups (P = .02). Quantitative longitudinal changes in tumor cellular and vascular heterogeneity in response to therapy may provide evidence for early prediction of response and guide therapy for patients with HER2+ breast cancer.