Prognostic impact of combining whole-body PET/CT and brain PET/MR in patients with lung adenocarcinoma and brain metastases

MRI radiomics for predicting intracranial progression in non-small-cell lung cancer patients with brain metastases treated with epidermal growth factor receptor tyrosine kinase inhibitors

AIM

To identify clinical and magnetic resonance imaging (MRI) radiomics predictors specialised for intracranial progression (IP) after first-line epidermal growth factor receptor (EGFR) tyrosine kinase inhibitor (TKI) treatment in non-small-cell lung cancer (NSCLC) patients with brain metastases (BMs).

MATERIALS AND METHODS

Seventy EGFR-mutated NSCLC patients with a total of 212 BMs who received first-line EGFR-TKI therapy were enrolled. Radiomics features were extracted from the BM regions on the pretreatment contrast-enhanced T1-weighted images, and the radiomics score (rad-score) of each BM was established based on the selected features. Furthermore, the mean rad-score derived from the average rad-score of all included BMs in each patient was calculated. Univariate and multivariate logistic regression analyses were performed to identify potential predictors of IP. Prediction models based on different predictors and their combinations were constructed, and nomogram based on the optimal prediction model was evaluated.

RESULTS

Thirty-three (47.1 %) patients developed IP, and the remaining 37 (52.9 %) patients were IP-free. EGFR-19del mutation (OR 0.19, 95 % CI 0.05-0.69), third-generation TKI treatment (OR 0.33, 95 % CI 0.16-0.67) and mean rad-score (OR 5.71, 95 % CI 1.65-19.68) were found to be independent predictive factors. Models based on these three predictors alone and in combination (combined model) achieved AUCs of 0.64, 0.64, 0.74, and 0.86 and 0.64, 0.64, 0.75, and 0.84 in the training and validation sets, respectively, and the combined model demonstrated optimal performance for predicting IP.

CONCLUSIONS

The model integrating EGFR-19del mutation, third-generation TKI treatment and mean rad-score had good predictive value for IP after EGFR-TKI treatment in NSCLC patients with BM.

Construction of an individualized brain metabolic network in patients with advanced non-small cell lung cancer by the Kullback-Leibler divergence-based similarity method: A study based on 18F-fluorodeoxyglucose positron emission tomography

Background

Lung cancer has one of the highest mortality rates of all cancers, and non-small cell lung cancer (NSCLC) accounts for the vast majority (about 85%) of lung cancers. Psychological and cognitive abnormalities are common in cancer patients, and cancer information can affect brain function and structure through various pathways. To observe abnormal brain function in NSCLC patients, the main purpose of this study was to construct an individualized metabolic brain network of patients with advanced NSCLC using the Kullback-Leibler divergence-based similarity (KLS) method.

Methods

This study included 78 patients with pathologically proven advanced NSCLC and 60 healthy individuals, brain 18F-FDG PET images of these individuals were collected and all patients with advanced NSCLC were followed up (>1 year) to confirm their overall survival. FDG-PET images were subjected to individual KLS metabolic network construction and Graph theoretical analysis. According to the analysis results, a predictive model was constructed by machine learning to predict the overall survival of NSLCL patients, and the correlation with the real survival was calculated.

Results

Significant differences in the degree and betweenness distributions of brain network nodes between the NSCLC and control groups (p<0.05) were found. Compared to the normal group, patients with advanced NSCLC showed abnormal brain network connections and nodes in the temporal lobe, frontal lobe, and limbic system. The prediction model constructed using the abnormal brain network as a feature predicted the overall survival time and the actual survival time fitting with statistical significance (r=0.42, p=0.012).

Conclusions

An individualized brain metabolic network of patients with NSCLC was constructed using the KLS method, thereby providing more clinical information to guide further clinical treatment.

18F-FDG PET/MRI in Detection of Pulmonary Malignancies: A Systematic Review and Meta-Analysis

Background There have been conflicting results regarding fluorine 18-labeled fluorodeoxyglucose (¹⁸F-FDG) PET/MRI diagnostic performance in lung malignant neoplasms. Purpose To evaluate the diagnostic performance of ¹⁸F-FDG PET/MRI for the detection of pulmonary malignant neoplasms. Materials and Methods A systematic search was conducted within the Scopus, Web of Science, and PubMed databases until December 31, 2021. Published original articles that met the following criteria were considered eligible for meta-analysis: (a) detecting malignant lesions in the lung, (b) comparing ¹⁸F-FDG PET/MRI with a valid reference standard, and (c) providing data for the meta-analytic calculations. A hierarchical method was used to pool the performances. The bivariate model was used to find the summary points and 95% CIs. The hierarchical summary receiver operating characteristic model was used to draw the summary receiver operating characteristic curve and calculate the area under the curve. The Higgins I² statistic and Cochran Q test were used for heterogeneity assessment. Results A total of 43 studies involving 1278 patients met the inclusion criteria and were included in the meta-analysis. ¹⁸F-FDG PET/MRI had a pooled sensitivity and specificity of 96% (95% CI: 84, 99) and 100% (95% CI: 98, 100), respectively. ¹⁸F-FDG PET/CT had a pooled sensitivity and specificity of 99% (95% CI: 61, 100) and 99% (95% CI: 94, 100), respectively, which were comparable with those of ¹⁸F-FDG PET/MRI. At meta-regression, studies in which contrast media (P = .03) and diffusion-weighted imaging (P = .04) were used as a part of a pulmonary ¹⁸F-FDG PET/MRI protocol showed significantly higher sensitivities. Conclusion Fluorine 18-labeled fluorodeoxyglucose (¹⁸F-FDG) PET/MRI was found to be accurate and comparable with ¹⁸F-FDG PET/CT in the detection of malignant pulmonary lesions, with significantly improved sensitivity when advanced acquisition protocols were used. © RSNA, 2023 Supplemental material is available for this article.

Update on the Use of PET/MRI Contrast Agents and Tracers in Brain Oncology: A Systematic Review

The recent advancements in hybrid positron emission tomography–magnetic resonance imaging systems (PET/MRI) have brought massive value in the investigation of disease processes, in the development of novel treatments, in the monitoring of both therapy response and disease progression, and, not least, in the introduction of new multidisciplinary molecular imaging approaches. While offering potential advantages over PET/CT, the hybrid PET/MRI proved to improve both the image quality and lesion detectability. In particular, it showed to be an effective tool for the study of metabolic information about lesions and pathological conditions affecting the brain, from a better tumor characterization to the analysis of metabolic brain networks. Based on the PRISMA guidelines, this work presents a systematic review on PET/MRI in basic research and clinical differential diagnosis on brain oncology and neurodegenerative disorders. The analysis includes literature works and clinical case studies, with a specific focus on the use of PET tracers and MRI contrast agents, which are usually employed to perform hybrid PET/MRI studies of brain tumors. A systematic literature search for original diagnostic studies is performed using PubMed/MEDLINE, Scopus and Web of Science. Patients, study, and imaging characteristics were extracted from the selected articles. The analysis included acquired data pooling, heterogeneity testing, sensitivity analyses, used tracers, and reported patient outcomes. Our analysis shows that, while PET/MRI for the brain is a promising diagnostic method for early diagnosis, staging and recurrence in patients with brain diseases, a better definition of the role of tracers and imaging agents in both clinical and preclinical hybrid PET/MRI applications is needed and further efforts should be devoted to the standardization of the contrast imaging protocols, also considering the emerging agents and multimodal probes.

Recent Technical Advances in Accelerating the Clinical Translation of Small Animal Brain Imaging: Hybrid Imaging, Deep Learning, and Transcriptomics

Small animal models play a fundamental role in brain research by deepening the understanding of the physiological functions and mechanisms underlying brain disorders and are thus essential in the development of therapeutic and diagnostic imaging tracers targeting the central nervous system. Advances in structural, functional, and molecular imaging using MRI, PET, fluorescence imaging, and optoacoustic imaging have enabled the interrogation of the rodent brain across a large temporal and spatial resolution scale in a non-invasively manner. However, there are still several major gaps in translating from preclinical brain imaging to the clinical setting. The hindering factors include the following: (1) intrinsic differences between biological species regarding brain size, cell type, protein expression level, and metabolism level and (2) imaging technical barriers regarding the interpretation of image contrast and limited spatiotemporal resolution. To mitigate these factors, single-cell transcriptomics and measures to identify the cellular source of PET tracers have been developed. Meanwhile, hybrid imaging techniques that provide highly complementary anatomical and molecular information are emerging. Furthermore, deep learning-based image analysis has been developed to enhance the quantification and optimization of the imaging protocol. In this mini-review, we summarize the recent developments in small animal neuroimaging toward improved translational power, with a focus on technical improvement including hybrid imaging, data processing, transcriptomics, awake animal imaging, and on-chip pharmacokinetics. We also discuss outstanding challenges in standardization and considerations toward increasing translational power and propose future outlooks.

Clinical Utility of F-18 Labeled Fibroblast Activation Protein Inhibitor (FAPI) for Primary Staging in Lung Adenocarcinoma: a Prospective Study

PURPOSE

The purpose of this study was to compare the primary staging of F-18 labeled fibroblast activation protein inhibitor ([¹⁸F]F-FAPI) with that of F-18 labeled fluordesoxyglucose positron emission tomography/computed tomography ([¹⁸F]F-FDG PET/CT) in patients with lung adenocarcinoma (LAD).

PROCEDURES

We prospectively analyzed the images of LAD patients who underwent [¹⁸F]F-FAPI and [¹⁸F]F-FDG PET/CT between May 2020 and August 2021. [¹⁸F]F-FAPI and [¹⁸F]F-FDG uptakes were compared using the paired samples t test, and lesion numbers were compared using the Wilcoxon signed-rank test.

RESULTS

Thirty-four LAD patients were evaluated. Patients showed high [¹⁸F]F-FAPI uptake in primary lesions (SUVmax 12.54 ± 3.77). Both [¹⁸F]F-FAPI and [¹⁸F]F-FDG had 100% detection rates for primary tumors. However, [¹⁸F]F-FAPI showed higher SUV_max than [¹⁸F]F-FDG in lesions of the lymph nodes, pleura, bones, and other tissues (all P ≤ 0.05). Although the absolute uptake values of [¹⁸F]F-FAPI in brain lesions were lower than those of [¹⁸F]F-FDG (1.56 ± 2.19 vs.7.34 ± 3.54, P < 0.0001), the tumor-to-background (T/B) ratios were significantly higher than those of [¹⁸F]F-FDG (9.53 ± 12.07 vs.1.01 ± 0.49, P < 0.0001). Generally, [¹⁸F]F-FAPI PET/CT could visualize more total lesions than [¹⁸F]F-FDG (554 vs.464, P = 0.003), especially in lymph nodes (258 vs.229, P = 0.039), the brain (34 vs.9, P = 0.002), and pleura (56 vs.30, P = 0.041). However, contrast-enhanced brain magnetic-resonance imaging (MRI) showed more brain lesions than [¹⁸F]F-FAPI PET/CT (56 vs.34, P = 0.002). Compared with the [¹⁸F]F-FDG-based TNM stage, the [¹⁸F]F-FAPI-based TNM stage was upgraded in six patients (17.6%).

CONCLUSIONS

[¹⁸F]F-FAPI PET/CT showed a very high detection rate for primary LAD. In addition, ¹⁸F-FAPI PET/CT demonstrated clearer tumor delineation and more lesions than [¹⁸F]F-FDG PET/CT, especially in lymph nodes, the brain, and pleura. Therefore, [¹⁸F]F-FAPI had an advantage over [¹⁸F]F-FDG for primary staging of LAD. However, brain MRI could identify more and smaller lesions than [¹⁸F]F-FAPI PET/CT.

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.

Deep neural network correlation learning mechanism for CT brain tumor detection

Modern medical clinics support medical examinations with computer systems which use Computational Intelligence on the way to detect potential health problems in more efficient way. One of the most important applications is evaluation of CT brain scans, where the most precise results come from deep learning approaches. In this article, we propose a novel correlation learning mechanism (CLM) for deep neural network architectures that combines convolutional neural network (CNN) with classic architecture. The support neural network helps CNN to find the most adequate filers for pooling and convolution layers. As a result, the main neural classifier learns faster and reaches higher efficiency. Results show that our CLM model is able to reach about 96% accuracy, and about 95% precision and recall. We have described our proposed mechanism and discussed numerical results to draw conclusions and show future works.