Investigating the histopathologic correlates of 18F-FDG PET heterogeneity in non-small-cell lung cancer

Prognostic 18F-FDG Radiomic Features in Advanced High-Grade Serous Ovarian Cancer

High-grade serous ovarian cancer (HGSOC) is an aggressive disease with different clinical outcomes and poor prognosis. This could be due to tumor heterogeneity. The 18F-FDG PET radiomic parameters permit addressing tumor heterogeneity. Nevertheless, this has been not well studied in ovarian cancer. The aim of our work was to assess the prognostic value of pretreatment 18F-FDG PET radiomic features in patients with HGSOC. A review of 36 patients diagnosed with advanced HGSOC between 2016 and 2020 in our center was performed. Radiomic features were obtained from pretreatment 18F-FDGPET. Disease-free survival (DFS) and overall survival (OS) were calculated. Optimal cutoff values with receiver operating characteristic curve/median values were used. A correlation between radiomic features and DFS/OS was made. The mean DFS was 19.6 months and OS was 37.1 months. Total Lesion Glycolysis (TLG), GLSZM_ Zone Size Non-Uniformity (GLSZM_ZSNU), and GLRLM_Run Length Non-Uniformity (GLRLM_RLNU) were significantly associated with DFS. The survival-curves analysis showed a significant difference of DSF in patients with GLRLM_RLNU > 7388.3 versus patients with lower values (19.7 months vs. 31.7 months, p = 0.035), maintaining signification in the multivariate analysis (p = 0.048). Moreover, Intensity-based Kurtosis was associated with OS (p = 0.027). Pretreatment 18F-FDG PET radiomic features GLRLM_RLNU, GLSZM_ZSNU, and Kurtosis may have prognostic value in patients with advanced HGSOC.

Added value of histogram analysis of ADC in predicting radiation-induced temporal lobe injury of patients with nasopharyngeal carcinoma treated by intensity-modulated radiotherapy

BACKGROUND

This study evaluated the predictive potential of histogram analysis derived from apparent diffusion coefficient (ADC) maps in radiation-induced temporal lobe injury (RTLI) of nasopharyngeal carcinoma (NPC) after intensity-modulated radiotherapy (IMRT).

RESULTS

Pretreatment diffusion-weighted imaging (DWI) of the temporal lobes of 214 patients with NPC was retrospectively analyzed to obtain ADC histogram parameters. Of the 18 histogram parameters derived from ADC maps, 7 statistically significant variables in the univariate analysis were included in the multivariate logistic regression analysis. The final best prediction model selected by backward stepwise elimination with Akaike information criteria as the stopping rule included kurtosis, maximum energy, range, and total energy. A Rad-score was established by combining the four variables, and it provided areas under the curve (AUCs) of 0.95 (95% confidence interval [CI] 0.91-0.98) and 0.89 (95% CI 0.81-0.97) in the training and validation cohorts, respectively. The combined model, integrating the Rad-score with the T stage (p = 0.02), showed a favorable prediction performance in the training and validation cohorts (AUC = 0.96 and 0.87, respectively). The calibration curves showed a good agreement between the predicted and actual RTLI occurrences.

CONCLUSIONS

Pretreatment histogram analysis of ADC maps and their combination with the T stage showed a satisfactory ability to predict RTLI in NPC after IMRT.

Magnetic resonance imaging-based radiomics model for predicting radiation-induced temporal lobe injury in nasopharyngeal carcinoma after intensity-modulated radiotherapy

BACKGROUND

To develop a model based on magnetic resonance imaging (MRI) radiomics and clinical features for predicting radiation-induced temporal lobe injury (RTLI) in patients with nasopharyngeal carcinoma (NPC) after intensity-modulated radiotherapy (IMRT).

METHODS

Two hundred and sixteen patients with NPC were retrospectively included. Radiomics features were extracted and selected. The logistic regression analysis was performed for prediction models construction. The area under the receiver operating characteristic curve (AUC) was calculated for performance evaluation.

RESULTS

Three radiomics features were selected to construct the radiomics signature (AUC of 0.94 and 0.92). The clinical-radiomics model, integrating radiomics signature with T classification, achieved higher predictive performance in the training and validation cohorts (AUC of 0.95 and 0.93), as well as improved accuracy of the classification of RTLI outcomes (net reclassification improvement: 0.711; 95% CI: 0.57-0.86; p < 0.001).

CONCLUSIONS

The clinical-radiomics model and radiomics signature both showed great performance in predicting RTLI in patients with NPC.

Quantification of tumor heterogeneity: from data acquisition to metric generation

Tumors are unique and complex ecosystems, in which heterogeneous cell subpopulations with variable molecular profiles, aggressiveness, and proliferation potential coexist and interact. Understanding how heterogeneity influences tumor progression has important clinical implications for improving diagnosis, prognosis, and treatment response prediction. Several recent innovations in data acquisition methods and computational metrics have enabled the quantification of spatiotemporal heterogeneity across different scales of tumor organization. Here, we summarize the most promising efforts from a common experimental and computational perspective, discussing their advantages, shortcomings, and challenges. With personalized medicine entering a new era of unprecedented opportunities, our vision is that of future workflows integrating across modalities, scales, and dimensions to capture intricate aspects of the tumor ecosystem and to open new avenues for improved patient care.

Progress and future prospective of FDG-PET/CT imaging combined with optimized procedures in lung cancer: toward precision medicine

With a 5-year overall survival of approximately 20%, lung cancer has always been the number one cancer-specific killer all over the world. As a fusion of positron emission computed tomography (PET) and computed tomography (CT), PET/CT has revolutionized cancer imaging over the past 20 years. In this review, we focused on the optimization of the function of ¹⁸F-flurodeoxyglucose (FDG)-PET/CT in diagnosis, prognostic prediction and therapy management of lung cancers by computer programs. FDG-PET/CT has demonstrated a surprising role in development of therapeutic biomarkers, prediction of therapeutic responses and long-term survival, which could be conducive to solving existing dilemmas. Meanwhile, novel tracers and optimized procedures are also developed to control the quality and improve the effect of PET/CT. With the continuous development of some new imaging agents and their clinical applications, application value of PET/CT has broad prospects in this area.

The diagnostic value of metabolic, morphological and heterogeneous parameters of 18F-FDG PET/CT in mediastinal lymph node metastasis of non-small cell lung cancer

OBJECTIVES

To investigate the value of PET/CT metabolic, morphological and heterogeneous parameters in the diagnosis of 18F-FDG positive mediastinal lymph node metastasis in non-small cell lung cancer (NSCLC).

PATIENTS AND METHODS

A total of 156 patients with pathologically diagnosed NSCLC and underwent 18F-FDG PET/CT scans were enrolled in this study. Mediastinal lymph nodes with 18F-FDG uptake greater than the mediastinum were analyzed. The metabolic parameters of maximum and mean standardized uptake value (SUVmax, SUVmean), SUVratio (node SUVmax/mediastinum SUVmax), metabolic tumor volume (MTV), total lesion glycolysis (TLG), morphological parameters of maximum short diameter (Dmin), CT values and metabolic heterogeneity parameter of coefficient of variation (COV) were measured. The performance of each parameter and their combinations for diagnosis of lymph node metastasis was evaluated through receiver operating characteristic (ROC) curves and binary logistic regression analysis.

RESULTS

There were 206 lymph nodes with pathological evidence included in the study, including 103 metastatic and 103 nonmetastatic nodes. The SUVmax, SUVmean, SUVratio, TLG, COV and Dmin of metastatic lymph nodes were significantly higher/greater than those in nonmetastatic ones (P < 0.05). ROC curve analysis revealed that the combination of SUVratio, Dmin and COV showed the highest diagnostic efficacy among all single and combined parameters, the area under the curve (AUC) was 0.907 (P = 0.000), these three parameters all increased the risk of lymph node metastasis, with odds ratios of 1.848, 1.293 and 1.258, respectively (all P < 0.05).

CONCLUSION

Heterogeneity parameter was helpful for the accurate distinction of mediastinal lymph node metastasis in NSCLC. The combination of the SUVratio, Dmin and COV could improve the diagnostic accuracy. Multiple-parameters analysis plays an important complementary role in the diagnosis of lymph node metastasis.

18F-FDG-PET/CT analysis in hospitalized patients affected by pulmonary disease: The experience of the Nuclear Medicine Unit of "Policlinico Tor Vegata"

OBJECTIVE

The main aim of this study was to retrospectively evaluate the clinical data and outcomes of a cohort of 492 hospitalized patients who underwent fluorine-18-fluorodeoxyglucose (F-FDG)-PET/CT analysis at the nuclear medicine unit of 'Policlinico Tor Vergata' in Rome during the years 2017 and 2018 with particular emphasis for patients affected by pulmonary diseases.

METHODS

Anamnestic data (age and gender), main pathologic conditions, results of F-FDG-PET/CT examination, appropriateness of the request, and medical records of 492 consecutive hospitalized patients who underwent F-FDG-PET/CT analysis (55.38 ± 3.78 years; range 33-81 years) from January 2017 to December 2018 were obtained.

RESULTS

Considering all examinations, positive results were observed in 66.9% of cases whereas it was not possible to perform a diagnosis in 12.7% of cases (doubt results). About 20-fold increase in the percentage of doubt results was observed in F-FDG-PET/CT analysis with no appropriateness as compared to those with double appropriateness (both the request and clinical). Noteworthy, our data showed a 95% higher concordance between the positive results of the F-FDG-PET/CT examination and the histologic diagnosis. Conversely, the concordance between the analysis of the bronchoalveolar lavages and the PET analysis was very low.

CONCLUSION

Data here reported showed the high accuracy of the F-FDG-PET/CT performed in our department, mainly for pulmonary diseases, also highlighting the importance of continuously updating the selection criteria for patients who need PET examinations.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

Background: Although many works have supported the utility of PET radiomics, several authors have raised concerns over the robustness and replicability of the results. This study aimed to perform a systematic review on the topic of PET radiomics and the used methodologies. Methods: PubMed was searched up to 15 October 2020. Original research articles based on human data specifying at least one tumor type and PET image were included, excluding those that apply only first-order statistics and those including fewer than 20 patients. Each publication, cancer type, objective and several methodological parameters (number of patients and features, validation approach, among other things) were extracted. Results: A total of 290 studies were included. Lung (28%) and head and neck (24%) were the most studied cancers. The most common objective was prognosis/treatment response (46%), followed by diagnosis/staging (21%), tumor characterization (18%) and technical evaluations (15%). The average number of patients included was 114 (median = 71; range 20–1419), and the average number of high-order features calculated per study was 31 (median = 26, range 1–286). Conclusions: PET radiomics is a promising field, but the number of patients in most publications is insufficient, and very few papers perform in-depth validations. The role of standardization initiatives will be crucial in the upcoming years.

A Role for FDG PET Radiomics in Personalized Medicine?

Radiomics describes the extraction of multiple features from medical images, including molecular imaging modalities, that with bioinformatic approaches, provide additional clinically relevant information that may be invisible to the human eye. This information may complement standard radiological interpretation with data that may better characterize a disease or that may provide predictive or prognostic information. Progressing from predefined image features, often describing heterogeneity of voxel intensities within a volume of interest, there is increasing use of machine learning to classify disease characteristics and deep learning methods based on artificial neural networks that can learn features without a priori definition and without the need for preprocessing of images. There have been advances in standardization and harmonization of methods to a level that should support multicenter studies. However, in this relatively early phase of research in the field, there are limited aspects that have been adopted into routine practice. Most of the reports in the molecular imaging field describe radiomic approaches in cancer using 18F-fluorodeoxyglucose positron emission tomography (18F-FDG-PET). In this review, we will describe radiomics in molecular imaging and summarize the pertinent literature in lung cancer where reports are most prevalent and mature.

COV is a readily available quantitative indicator of metabolic heterogeneity for predicting survival of patients with early and locally advanced NSCLC manifesting as central lung cancer

OBJECTIVES

The aim of our study was to investigate the value of a simple metabolic heterogeneity parameter, COV (coefficient of variation), by 18 F-fluorodeoxyglucose (FDG) positron emission tomography (PET) in the prognosis prediction of central lung cancer in early and locally advanced non-small-cell lung cancer (NSCLC).

METHODS

Seventy-three patients with NSCLC manifesting as central lung cancer were included retrospectively, and we used the COV to evaluate metabolic heterogeneity. Univariate and multivariate analyses were used to evaluate the predictive value in terms of overall survival (OS) and progression-free survival (PFS).

RESULT

For all 73 patients with pathologically confirmed NSCLC, 69.9 % had SCC, and 30.1 % had ADC or other types of NSCLC. The COV was a statistically significant factor in the univariate analysis for the OS rate. The optimal cut-off value was 23.1366, with sensitivity = 0.737 and specificity = 0.771. The COV values were dichotomized by this value and included with atelectasis in the Cox multivariate analysis. Both COV and atelectasis were independent risk factors for OS as follows: for COV (HR, 3.162, P = 0.0002), the 2-year OS rate was 62.5 % and 26.9 % in the low and high COV groups, respectively. For atelectasis (HR 2.047, P = 0.041), the 2-year OS rate was 30.6 % and 65.2 % in the groups with and without atelectasis, respectively (P = 0.017). For PFS, only COV (HR, 2.636, P = 0.001) was a significant predictor. The 2-year PFS rate was 29.7 % in the low COV group and 8% in the high COV group.

CONCLUSION

The pre-treatment metabolic heterogeneity parameter COV is a simple and easy way to predict the OS and PFS of patients with NSCLC manifesting as central lung cancer. Therefore, COV plays an important role in prognostic risk classification in NSCLC. The presence of atelectasis could also be a risk factor for poor prognosis of OS.

Maximum standardized uptake value of primary tumor (SUVmax_PT) and horizontal range between two most distant PET-positive lymph nodes predict patient outcome in inoperable stage III NSCLC patients after chemoradiotherapy

Background

18F-FDG-positron emission tomography (PET)/computed tomography (CT) is a standard for initial staging in patients with locally advanced stage III non-small cell lung cancer (NSCLC). We evaluated a PET/CT staging score to characterize disease extension and patient outcome in this disease.

Methods

Ninety-nine consecutive patients with NSCLC stage IIIA–B (UICC 7th edition), who underwent 18F-FDG-PET/CT before the start of chemoradiotherapy (CRT) were analyzed. Maximum standardized uptake value of primary tumor (SUVmax_PT) and range between two most distant PET-positive (SUV ≥2.5) lymph nodes in two directions were analyzed for their correlation with patient outcome. The vertical distance was defined as A- and the horizontal as a B-line.

Results

According to the results of univariate analysis, score included the SUVmax_PT and horizontal B-line, patients were divided into three risk subgroups: low, intermediate and high-risk subgroups. Subgroups were defined as SUVmax_PT <8 and B-line <3.7 cm, SUVmax_PT >8 or B-line >3.7 cm and SUVmax_PT >8 plus B-line >3.7 cm, respectively. Twenty-eight (28%), 45 (46%) and 26 (26%) patients were assigned to the low, intermediate and high-risk subgroup, respectively. Median event-free survival (EFS) in low, intermediate and high-risk subgroups was 16 (95% CI: 7–25), 13 (95% CI: 12–15) and 10 (95% CI: 7–13) months (P=0.002, log-rank test). Median OS in the low, intermediate and high-risk subgroups was 40 (95% CI: 11–69), 23 (95% CI: 15–31) and 14 (95% CI: 13–14) months (P=0.0001, log-rank test). In the multivariate analysis, SUV, B-line and PET/CT score were significantly associated with EFS [harard ratio (HR) 2.12 (95% CI: 1.27–3.55) and intermediate risk HR 2.01 (95% CI: 1.13–3.59), P=0.003] and OS [high-risk HR 2.79 (95% CI: 1.16–4.55) and intermediate risk HR 2.30 (95% CI: 1.58–4.94), P=0.001].

Conclusions

A PET/CT score was developed for inoperable stage III NSCLC patients treated with CRT and was an independent predictor of patient outcome in the single-center cohort.

Treatment-related changes in neuroendocrine tumors as assessed by textural features derived from 68Ga-DOTATOC PET/MRI with simultaneous acquisition of apparent diffusion coefficient

Background

Neuroendocrine tumors (NETs) frequently overexpress somatostatin receptors (SSTRs), which is the molecular basis for ⁶⁸Ga-DOTATOC positron-emission tomography (PET) and radiopeptide therapy (PRRT). However, SSTR expression fluctuates and can be subject to treatment-related changes. The aim of this retrospective study was to assess, which changes in PET and apparent diffusion coefficient (ADC) occur for different treatments and if pre-therapeutic ⁶⁸Ga-DOTATOC-PET/MRI was able to predict treatment response to PRRT.

Methods

Patients with histopathologically confirmed NET, at least one liver metastasis > 1 cm and at least two ⁶⁸Ga-DOTATOC-PET/MRI including ADC maps were eligible. ⁶⁸Ga-DOTATOC-PET/MRI of up to 5 liver lesions per patients was subsequently analyzed. Extracted features comprise conventional PET parameters, such as maximum and mean standardized uptake value (SUVmax and SUVmean) and ADC values. Furthermore, textural features (TFs) from both modalities were extracted. In patients with multiple ⁶⁸Ga-DOTATOC-PET/MRI a pair of 2 scans each was analyzed separately and the parameter changes between both scans calculated. The same image analysis was performed in patients with ⁶⁸Ga-DOTATOC-PET/MRI before PRRT. Differences in PET and ADC maps parameters between PRRT-responders and non-responders were compared using Mann-Whitney test to test differences among groups for statistical significance.

Results

29 pairs of ⁶⁸Ga-DOTATOC-PET/MRI scans of 18 patients were eligible for the assessment of treatment-related changes. In 12 cases patients were treated with somatostatin analogues between scans, in 9 cases with PRRT and in 2 cases each patients received local treatment, chemotherapy and sunitinib. Treatment responders showed a statistically significant decrease in lesion volume and a borderline significant decrease in entropy on ADC maps when compared to non-responders. Patients treated with standalone SSA showed a borderline significant decrease in mean and maximum ADC, compared to patients treated with PRRT. No parameters were able to predict treatment response to PRRT on pre-therapeutic ⁶⁸Ga-DOTATOC-PET/MRI.

Conclusions

Patients responding to current treatment showed a statistically significant decrease in lesion volume on ADC maps and a borderline significant decrease in entropy. No statistically significant changes in PET parameters were observed. No PET or ADC maps parameters predicted treatment response to PRRT. However, the sample size of this preliminary study is small and further research needed.

What can artificial intelligence teach us about the molecular mechanisms underlying disease?

While molecular imaging with positron emission tomography or single-photon emission computed tomography already reports on tumour molecular mechanisms on a macroscopic scale, there is increasing evidence that there are multiple additional features within medical images that can further improve tumour characterization, treatment prediction and prognostication. Early reports have already revealed the power of radiomics to personalize and improve patient management and outcomes. What remains unclear is how these additional metrics relate to underlying molecular mechanisms of disease. Furthermore, the ability to deal with increasingly large amounts of data from medical images and beyond in a rapid, reproducible and transparent manner is essential for future clinical practice. Here, artificial intelligence (AI) may have an impact. AI encompasses a broad range of 'intelligent' functions performed by computers, including language processing, knowledge representation, problem solving and planning. While rule-based algorithms, e.g. computer-aided diagnosis, have been in use for medical imaging since the 1990s, the resurgent interest in AI is related to improvements in computing power and advances in machine learning (ML). In this review we consider why molecular and cellular processes are of interest and which processes have already been exposed to AI and ML methods as reported in the literature. Non-small-cell lung cancer is used as an exemplar and the focus of this review as the most common tumour type in which AI and ML approaches have been tested and to illustrate some of the concepts.