The “digital biopsy” in non-small cell lung cancer (NSCLC): a pilot study to predict the PD-L1 status from radiomics features of [18F]FDG PET/CT

Advances in artificial intelligence applications in the field of lung cancer

Lung cancer remains a leading cause of cancer-related deaths globally, with its incidence steadily rising each year, representing a significant threat to human health. Early detection, diagnosis, and timely treatment play a crucial role in improving survival rates and reducing mortality. In recent years, significant and rapid advancements in artificial intelligence (AI) technology have found successful applications in various clinical areas, especially in the diagnosis and treatment of lung cancer. AI not only improves the efficiency and accuracy of physician diagnosis but also aids in patient treatment and management. This comprehensive review presents an overview of fundamental AI-related algorithms and highlights their clinical applications in lung nodule detection, lung cancer pathology classification, gene mutation prediction, treatment strategies, and prognosis. Additionally, the rapidly advancing field of AI-based three-dimensional (3D) reconstruction in lung cancer surgical resection is discussed. Lastly, the limitations of AI and future prospects are addressed.

Prediction of HER2 Expression in Gastric Adenocarcinoma Based On Preoperative Noninvasive Multimodal 18F-FDG PET/CT Imaging

RATIONALE AND OBJECTIVES

This study aims to investigate the role of a flourine-18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) multimodal radiomics model in predicting the status of human epidermal growth factor receptor 2 (HER2) expression preoperatively in cases of gastric adenocarcinoma.

MATERIALS AND METHODS

This retrospective study included 133 patients with gastric adenocarcinoma who were classified into training (n = 93) and validation (n = 40) cohorts in a ratio of 7:3. Features were selected using Least Absolute Shrinkage and Selection Operator and Extreme Gradient Boosting (XGBoost) methods; further, prediction models were constructed using logistic regression and XGBoost. These models were evaluated and validated using area under the curve (AUC), decision curves, and calibration curves to select the best-performing model.

RESULTS

Six different models were established to predict HER2 expression. Among these, the comprehensive model, which integrates seven clinical features, one CT feature, and five PET features, demonstrated AUC values of 0.95 (95% confidence interval [CI]: 0.89-1.00) and 0.76 (95% CI: 0.52-1.00) in the training and validation cohorts, respectively. Compared with other models, this model exhibited a superior net benefit on the decision curve and demonstrated good alignment agreement with the observed values on the calibration curve. Based on these findings, we constructed a nomogram for visualizing the model, providing a noninvasive preoperative method for predicting HER2 expression.

CONCLUSION

The preoperative 18F-FDG PET/CT multimodal radiomics model can effectively predict HER2 expression in patients with gastric adenocarcinoma, thereby guiding clinical decision-making and advancing the field of precision medicine.

Intratumoral and Peritumoral Radiomics Based on Preoperative MRI for Evaluation of Programmed Cell Death Ligand-1 Expression in Breast Cancer

BACKGROUND

Programmed cell death ligand-1 (PD-L1) is a promising target for immune checkpoint blockade therapy in breast cancer. However, the preoperative evaluation of PD-L1 expression in breast cancer is rarely explored.

PURPOSE

To determine the ability of radiomics signatures based on preoperative dynamic contrast-enhanced (DCE) MRI to evaluate PD-L1 expression in breast cancer.

STUDY TYPE

Retrospective.

POPULATION

196 primary breast cancer patients with preoperative MRI and postoperative pathological evaluation of PD-L1 expression, divided into training (n = 137, 28 PD-L1-positive) and test cohorts (n = 59, 12 PD-L1-positive).

FIELD STRENGTH/SEQUENCE

3.0T; volume imaging for breast assessment DCE sequence.

ASSESSMENT

Radiomics features were extracted from the first phase of DCE-MRI by using the minimum redundancy maximum relevance method and least absolute shrinkage and selection operator algorithm. Three radiomics signatures were constructed based on the intratumoral, peritumoral, and combined intra- and peritumoral regions. The performance of the signatures was assessed using area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, and accuracy.

STATISTICAL TESTS

Univariable and multivariable logistic regression analysis, t-tests, chi-square tests, Fisher exact test or Yates correction, ROC analysis, and one-way analysis of variance. P < 0.05 was considered significant.

RESULTS

In the test cohort, the combined radiomics signature (AUC, 0.853) exhibited superior performance compared to the intratumoral (AUC, 0.816; P = 0.528) and peritumoral radiomics signatures (AUC, 0.846; P = 0.905) in PD-L1 status evaluation, although the differences did not reach statistical significance.

DATA CONCLUSION

Intratumoral and peritumoral radiomics signatures based on preoperative breast MRI showed some potential accuracy for the non-invasive evaluation of PD-L1 status in breast cancer.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: Stage 2.

Radiomics based on 18F-FDG PET/CT for prediction of pathological complete response to neoadjuvant therapy in non-small cell lung cancer

Purpose

This study aimed to establish and evaluate the value of integrated models involving 18F-FDG PET/CT-based radiomics and clinicopathological information in the prediction of pathological complete response (pCR) to neoadjuvant therapy (NAT) for non-small cell lung cancer (NSCLC).

Methods

A total of 106 eligible NSCLC patients were included in the study. After volume of interest (VOI) segmentation, 2,016 PET-based and 2,016 CT-based radiomic features were extracted. To select an optimal machine learning model, a total of 25 models were constructed based on five sets of machine learning classifiers combined with five sets of predictive feature resources, including PET-based alone radiomics, CT-based alone radiomics, PET/CT-based radiomics, clinicopathological features, and PET/CT-based radiomics integrated with clinicopathological features. Area under the curves (AUCs) of receiver operator characteristic (ROC) curves were used as the main outcome to assess the model performance.

Results

The hybrid PET/CT-derived radiomic model outperformed PET-alone and CT-alone radiomic models in the prediction of pCR to NAT. Moreover, addition of clinicopathological information further enhanced the predictive performance of PET/CT-derived radiomic model. Ultimately, the support vector machine (SVM)-based PET/CT radiomics combined clinicopathological information presented an optimal predictive efficacy with an AUC of 0.925 (95% CI 0.869-0.981) in the training cohort and an AUC of 0.863 (95% CI 0.740-0.985) in the test cohort. The developed nomogram involving radiomics and pathological type was suggested as a convenient tool to enable clinical application.

Conclusions

The 18F-FDG PET/CT-based SVM radiomics integrated with clinicopathological information was an optimal model to non-invasively predict pCR to NAC for NSCLC.

Assessment of PD-L1 Expression in Non-Small Cell Lung Cancers Using [68Ga]Ga-DOTA-WL12 PET/CT

Assessing programmed death ligand-1 (PD-L1) expression in non-small cell lung cancer (NSCLC), particularly in metastatic cases, remains challenging. In this study, surface plasmon resonance (SPR) analysis and [68Ga]Ga-DOTA-WL12 micro-PET/CT imaging are performed. [68Ga]Ga-DOTA-WL12 PET/CT and [18F]FDG PET/CT are performed on a cohort of 20 patients with NSCLC. Semi-quantitative assessments include SUVmax, metabolic tumor volume (MTV), total lesion glycolysis (TLG), and target-to-background ratio (TBR). DOTA-WL12 exhibits robust PD-L1 binding with a KD value of 0.2 nM. Subsequent human studies reveal significant correlations between PD-L1 expression and the [68Ga]Ga-DOTA-WL12 SUVmax in primary and metastatic lesions, surpassing the [18F]FDG results (r = 0.8889, p <0.0001 vs r = 0.0469, p = 0.8127). Notably, [68Ga]Ga-DOTA-WL12 imaging discerned SUVmax and TBR differences between PD-L1 TPS ≤1% and PD-L1 TPS > 1% groups (p all <0.001). In an NSCLC patient with brain metastases, [68Ga]Ga-DOTA-WL12 shows a SUVmean of 0.04 in the brain background, with TBR values of 17 and 23, underscoring its potential for detecting brain metastases. The study provides initial evidence for the clinical utility of [68Ga]Ga-DOTA-WL12 PET/CT for lesion detection, immunotherapy selection, and therapeutic efficacy evaluation in PD-L1-expressing NSCLC, demonstrating its potential as a valuable tool in NSCLC research and management.

Correlation between Radiological Characteristics, PET-CT and Histological Subtypes of Primary Lung Adenocarcinoma-A 102 Case Series Analysis

Background and Objectives: Lung cancer is the second most common form of cancer in the world for both men and women as well as the most common cause of cancer-related deaths worldwide. The aim of this study is to summarize the radiological characteristics between primary lung adenocarcinoma subtypes and to correlate them with FDG uptake on PET-CT. Materials and Methods: This retrospective study included 102 patients with pathohistologically confirmed lung adenocarcinoma. A PET-CT examination was performed on some of the patients and the values of SUVmax were also correlated with the histological and morphological characteristics of the masses in the lungs. Results: The results of this analysis showed that the mean size of AIS-MIA (adenocarcinoma in situ and minimally invasive adenocarcinoma) cancer was significantly lower than for all other cancer types, while the mean size of the acinar cancer was smaller than in the solid type of cancer. Metastases were significantly more frequent in solid adenocarcinoma than in acinar, lepidic, and AIS-MIA cancer subtypes. The maximum standardized FDG uptake was significantly lower in AIS-MIA than in all other cancer types and in the acinar predominant subtype compared to solid cancer. Papillary predominant adenocarcinoma had higher odds of developing contralateral lymph node involvement compared to other types. Solid adenocarcinoma was associated with higher odds of having metastases and with higher SUVmax. AIS-MIA was associated with lower odds of one unit increase in tumor size and ipsilateral lymph node involvement. Conclusions: The correlation between histopathological and radiological findings is crucial for accurate diagnosis and staging. By integrating both sets of data, clinicians can enhance diagnostic accuracy and determine the optimal treatment plan.

Digital counting of tissue cells for molecular analysis: the QuANTUM pipeline

The estimation of tumor cellular fraction (TCF) is a crucial step in predictive molecular pathology, representing an entry adequacy criterion also in the next-generation sequencing (NGS) era. However, heterogeneity of quantification practices and inter-pathologist variability hamper the robustness of its evaluation, stressing the need for more reliable results. Here, 121 routine histological samples from non-small cell lung cancer (NSCLC) cases with complete NGS profiling were used to evaluate TCF interobserver variability among three different pathologists (pTCF), developing a computational tool (cTCF) and assessing its reliability vs ground truth (GT) tumor cellularity and potential impact on the final molecular results. Inter-pathologist reproducibility was fair to good, with overall Wk ranging between 0.46 and 0.83 (avg. 0.59). The obtained cTCF was comparable to the GT (p = 0.129, 0.502, and 0.130 for surgical, biopsies, and cell block, respectively) and demonstrated good reliability if elaborated by different pathologists (Wk = 0.9). Overall cTCF was lower as compared to pTCF (30 ± 10 vs 52 ± 19, p < 0.001), with more cases < 20% (17, 14%, p = 0.690), but none containing < 100 cells for the algorithm. Similarities were noted between tumor area estimation and pTCF (36 ± 29, p < 0.001), partly explaining variability in the human assessment of tumor cellularity. Finally, the cTCF allowed a reduction of the copy number variations (CNVs) called (27 vs 29, - 6.9%) with an increase of effective CNVs detection (13 vs 7, + 85.7%), some with potential clinical impact previously undetected with pTCF. An automated computational pipeline (Qupath Analysis of Nuclei from Tumor to Uniform Molecular tests, QuANTUM) has been created and is freely available as a QuPath extension. The computational method used in this study has the potential to improve efficacy and reliability of TCF estimation in NSCLC, with demonstrated impact on the final molecular results.

Development of novel peptide-based radiotracers for detecting PD-L1 expression and guiding cancer immunotherapy

PURPOSE

Due to tumor heterogeneity, immunohistochemistry (IHC) showed poor accuracy in detecting the expression of programmed cell death ligand-1 (PD-L1) in patients. Positron emission tomography (PET) imaging is considered as a non-invasive technique to detect PD-L1 expression at the molecular level visually, real-timely and quantitatively. This study aimed to develop novel peptide-based radiotracers [68Ga]/[18F]AlF-NOTA-IMB for accurately detecting the PD-L1 expression and guiding the cancer immunotherapy.

METHODS

NOTA-IMB was prepared by connecting 2,2'-(7-(2-((2,5-dioxopyrrolidin-1-yl)oxy)- 2-oxoethyl)-1,4,7-triazonane-1,4-diyl) diacetic acid (NOTA-NHS) with PD-L1-targeted peptide IMB, and further radiolabeled with 68Ga or 18F-AlF. In vitro binding assay was conducted to confirm the ability of [68Ga]/[18F]AlF-NOTA-IMB to detect the expression of PD-L1. In vivo PET imaging of [68Ga]NOTA-IMB and [18F]AlF-NOTA-IMB in different tumor-bearing mice was performed, and dynamic changes of PD-L1 expression level induced by immunotherapy were monitored. Radioautography, western blotting, immunofluorescence staining and biodistribution analysis were carried out to further evaluate the specificity of radiotracers and efficacy of PD-L1 antibody immunotherapy.

RESULTS

[68Ga]NOTA-IMB and [18F]AlF-NOTA-IMB were both successfully prepared with high radiochemical yield (> 95% and > 60%, n = 5) and radiochemical purity (> 95% and > 98%, n = 5). Both tracers showed high affinity to human and murine PD-L1 with the dissociation constant (Kd) of 1.00 ± 0.16/1.09 ± 0.21 nM (A375-hPD-L1, n = 3) and 1.56 ± 0.58/1.21 ± 0.39 nM (MC38, n = 3), respectively. In vitro cell uptake assay revealed that both tracers can specifically bind to PD-L1 positive cancer cells A375-hPD-L1 and MC38 (5.45 ± 0.33/3.65 ± 0.15%AD and 5.87 ± 0.27/2.78 ± 0.08%AD at 120 min, n = 3). In vivo PET imaging and biodistribution analysis showed that the tracer [68Ga]NOTA-IMB and [18F]AlF-NOTA-IMB had high accumulation in A375-hPD-L1 and MC38 tumors, but low uptake in A375 tumor. Treatment of Atezolizumab induced dynamic changes of PD-L1 expression in MC38 tumor-bearing mice, and the tumor uptake of [68Ga]NOTA-IMB decreased from 3.30 ± 0.29%ID/mL to 1.58 ± 0.29%ID/mL (n = 3, P = 0.026) after five treatments. Similarly, the tumor uptake of [18F]AlF-NOTA-IMB decreased from 3.27 ± 0.63%ID/mL to 0.89 ± 0.18%ID/mL (n = 3, P = 0.0004) after five treatments. However, no significant difference was observed in the tumor uptake before and after PBS treatment. Biodistribution, radioautography, western blotting and immunofluorescence staining analysis further demonstrated that the expression level of PD-L1 in tumor-bearing mice treated with Atezolizumab significantly reduced about 3 times and correlated well with the PET imaging results.

CONCLUSION

[68Ga]NOTA-IMB and [18F]AlF-NOTA-IMB were successfully prepared for PET imaging the PD-L1 expression noninvasively and quantitatively. Dynamic changes of PD-L1 expression caused by immunotherapy can be sensitively detected by both tracers. Hence, the peptide-based radiotracers [68Ga]NOTA-IMB and [18F]AlF-NOTA-IMB can be applied for accurately detecting the PD-L1 expression in different tumors and monitoring the efficacy of immunotherapy.

Current status and prospect of PET-related imaging radiomics in lung cancer

Lung cancer is highly aggressive, which has a high mortality rate. Major types encompass lung adenocarcinoma, lung squamous cell carcinoma, lung adenosquamous carcinoma, small cell carcinoma, and large cell carcinoma. Lung adenocarcinoma and lung squamous cell carcinoma together account for more than 80% of cases. Diverse subtypes demand distinct treatment approaches. The application of precision medicine necessitates prompt and accurate evaluation of treatment effectiveness, contributing to the improvement of treatment strategies and outcomes. Medical imaging is crucial in the diagnosis and management of lung cancer, with techniques such as fluoroscopy, computed radiography (CR), digital radiography (DR), computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET)/CT, and PET/MRI being essential tools. The surge of radiomics in recent times offers fresh promise for cancer diagnosis and treatment. In particular, PET/CT and PET/MRI radiomics, extensively studied in lung cancer research, have made advancements in diagnosing the disease, evaluating metastasis, predicting molecular subtypes, and forecasting patient prognosis. While conventional imaging methods continue to play a primary role in diagnosis and assessment, PET/CT and PET/MRI radiomics simultaneously provide detailed morphological and functional information. This has significant clinical potential value, offering advantages for lung cancer diagnosis and treatment. Hence, this manuscript provides a review of the latest developments in PET-related radiomics for lung cancer.

PET/CT in treatment response assessment in lung cancer. When should it be recommended?

Non-small cell lung cancer (NSCLC) is the most common type of lung cancer. Different treatment options are now possible both for surgical candidates and for those NSCLC patients deemed not suitable for surgery. Despite the treatments available, only a limited number of less advanced stages are potentially curable, with many patients suffering local recurrence or distant metastases. FDG-PET/CT is commonly used in many centers for post-treatment evaluation, follow-up, or surveillance; Nonetheless, there is no clear consensus regarding the indications in these cases. Based upon the results of a literature review and local expertise from a large lung cancer unit, we built clinical evidence-based recommendations for the use of FDG-PET/CT in response assessment. We found that in general this is not recommended earlier than 3 months from treatment; however, as described in detail the correct timing will also depend upon the type of treatment used. We also present a structured approach to assessing treatment changes when reporting FDG-PET/CT, using visual or quantitative approaches.

Clinical Applications of Radiomics in Nuclear Medicine

Radiomics is an emerging field of artificial intelligence that focuses on the extraction and analysis of quantitative features such as intensity, shape, texture and spatial relationships from medical images. These features, often imperceptible to the human eye, can reveal complex patterns and biological insights. They can also be combined with clinical data to create predictive models using machine learning to improve disease characterization in nuclear medicine. This review article examines the current state of radiomics in nuclear medicine and shows its potential to improve patient care. Selected clinical applications for diseases such as cancer, neurodegenerative diseases, cardiovascular problems and thyroid diseases are examined. The article concludes with a brief classification in terms of future perspectives and strategies for linking research findings to clinical practice.

Combined morphologic-metabolic biomarkers from [18F]FDG-PET/CT stratify prognostic groups in low-risk NSCLC

AIM

The aim of this study was to derive prognostic parameters from 2-[18F]fluoro-2-deoxy-D-glucose ([18F]FDG-PET/CT) in patients with low-risk NSCLC and determine their prognostic value.

METHODS

81 (21 female, mean age 66 a) therapy-naive patients that underwent [18F]FDG-PET/CT before histologic confirmation of NSCLC with stadium I and II between 2008-2016 were included. A mean follow-up time of 58 months (13-176), overall and progression free survival (OS, PFS) were registered. A volume of interest for the primary tumor was defined on PET and CT images. Parameters SUVmax, PET-solidity, PET-circularity, and CT-volume were analyzed. To evaluate the prognostic value of each parameter for OS, a minimum p-value approach was used to define cutoff values, survival analysis, and log-rank tests were performed, including subgroup analysis for combinations of parameters.

RESULTS

Mean OS was 58±28 months. Poor OS was associated with a tumor CT-volume >14.3 cm3 (p=0.02, HR=7.0, CI 2.7-17.7), higher SUVmax values >12.2 (p=0.003; HR=3.0, CI 1.3-6.7) and PET-solidity >0.919 (p=0.004; HR=3.0, CI 1.0-8.9). Combined parameter analysis revealed worse prognosis in larger volume/high SUVmax tumors compared to larger volume/lower SUVmax (p=0.028; HR=2.5, CI 1.1-5.5), high PET-solidity/low volume (p=0.01; HR=2.4, CI 0.8-6.6) and low SUVmax/high PET-solidity (p=0.02, HR=4.0, CI 0.8-19.0).

CONCLUSION

Even in this group of low-risk NSCLC patients, we identified a subgroup with a significantly worse prognosis by combining morphologic-metabolic biomarkers from [18F]FDG-PET/CT. The combination of SUVmax and CT-volume performed best. Based on these preliminary data, future prospective studies to validate this combined morphologic-metabolic imaging biomarker for potential therapeutic decisions seem promising.

The radiomic biomarker in non-small cell lung cancer: 18F-FDG PET/CT characterisation of programmed death-ligand 1 status

AIM

To present an integrated 2-[18F]-fluoro-2-deoxy-d-glucose (18F-FDG) positron-emission tomography (PET)/computed tomography (CT) radiomic characterisation of programmed death-ligand 1 (PD-L1) status in non-small-cell lung cancer (NSCLC).

MATERIALS AND METHODS

In this retrospective study, 18F-FDG PET/CT images and clinical data of 394 eligible patients were divided into training (n=275) and test sets (n=119). Next, the corresponding nodule of interest was segmented manually on the axial CT images by radiologists. After which, the spatial position matching method was used to match the image positions of CT and PET, and radiomic features of the CT and PET images were extracted. Radiomic models were built using five different machine-learning classifiers and the performance of the radiomic models were further evaluated. Finally, a radiomic signature was established to predict the PD-L1 status in patients with NSCLC using the features in the best performing radiomic model.

RESULTS

The radiomic model based on the PET intranodular region determined using the logistic regression classifier preformed best, yielding an area under the receiver operating characteristics curve (AUC) of 0.813 (95% CI: 0.812, 0.821) on the test set. The clinical features did not improve the test set AUC (0.806, 95% CI: 0.801, 0.810). The final radiomic signature for PD-L1 status was consisted of three PET radiomic features.

CONCLUSION

This study showed that an 18F-FDG PET/CT-based radiomic signature could be used as a non-invasive biomarker to discriminate PD-L1-positive from PD-L1-negative in patients with NSCLC.

Histology of the Primary Tumor Correlates with False Positivity of Integrated 18F-FDG-PET/CT Lymph Node Staging in Resectable Lung Cancer Patients

This study aimed to evaluate the diagnostic accuracy and false positivity rate of lymph node (LN) staging assessed by integrated 18F-fluorodeoxyglucose positron emission computed tomography (18F-FDG-PET/CT) in patients with operable lung cancer to the tumor histology. In total, 129 consecutive patients with non-small-cell lung cancer (NSCLC) undergoing anatomical lung resections were included. Preoperative LN staging was evaluated in the relationship to the histology of the resected specimens (group 1: lung adenocarcinoma/LUAD; group 2: squamous cell carcinoma/SQCA). Statistical analysis was performed by the Mann-Whitney U-test, the chi² test, and binary logistic regression analysis. To establish an easy-to-use algorithm for the identification of LN false positivity, a decision tree including clinically meaningful parameters was generated. In total, 77 (59.7%) and 52 (40.3%) patients were included in the LUAD and SQCA groups, respectively. SQCA histology, non-G1 tumors, and tumor SUVmax > 12.65 were identified as independent predictors of LN false positivity in the preoperative staging. The corresponding ORs and their 95% CIs were 3.35 [1.10-10.22], p = 0.0339; 4.60 [1.06-19.94], p = 0.0412; and 2.76 [1.01-7.55], and p = 0.0483. The preoperative identification of false-positive LNs is an important aspect of the treatment regimen for patients with operable lung cancer; thus, these preliminary findings should be further evaluated in larger patient cohorts.

The artificial intelligence and machine learning in lung cancer immunotherapy

Since the past decades, more lung cancer patients have been experiencing lasting benefits from immunotherapy. It is imperative to accurately and intelligently select appropriate patients for immunotherapy or predict the immunotherapy efficacy. In recent years, machine learning (ML)-based artificial intelligence (AI) was developed in the area of medical-industrial convergence. AI can help model and predict medical information. A growing number of studies have combined radiology, pathology, genomics, proteomics data in order to predict the expression levels of programmed death-ligand 1 (PD-L1), tumor mutation burden (TMB) and tumor microenvironment (TME) in cancer patients or predict the likelihood of immunotherapy benefits and side effects. Finally, with the advancement of AI and ML, it is believed that "digital biopsy" can replace the traditional single assessment method to benefit more cancer patients and help clinical decision-making in the future. In this review, the applications of AI in PD-L1/TMB prediction, TME prediction and lung cancer immunotherapy are discussed.

Clinical application of AI-based PET images in oncological patients

Based on the advantages of revealing the functional status and molecular expression of tumor cells, positron emission tomography (PET) imaging has been performed in numerous types of malignant diseases for diagnosis and monitoring. However, insufficient image quality, the lack of a convincing evaluation tool and intra- and interobserver variation in human work are well-known limitations of nuclear medicine imaging and restrict its clinical application. Artificial intelligence (AI) has gained increasing interest in the field of medical imaging due to its powerful information collection and interpretation ability. The combination of AI and PET imaging potentially provides great assistance to physicians managing patients. Radiomics, an important branch of AI applied in medical imaging, can extract hundreds of abstract mathematical features of images for further analysis. In this review, an overview of the applications of AI in PET imaging is provided, focusing on image enhancement, tumor detection, response and prognosis prediction and correlation analyses with pathology or specific gene mutations in several types of tumors. Our aim is to describe recent clinical applications of AI-based PET imaging in malignant diseases and to focus on the description of possible future developments.

Preoperative computed tomography-based tumoral radiomic features prediction for overall survival in resectable non-small cell lung cancer

Objectives

The purpose of this study was to evaluate whether preoperative radiomics features could meliorate risk stratification for the overall survival (OS) of non-small cell lung cancer (NSCLC) patients.

Methods

After rigorous screening, the 208 NSCLC patients without any pre-operative adjuvant therapy were eventually enrolled. We segmented the 3D volume of interest (VOI) based on malignant lesion of computed tomography (CT) imaging and extracted 1542 radiomics features. Interclass correlation coefficients (ICC) and LASSO Cox regression analysis were utilized to perform feature selection and radiomics model building. In the model evaluation phase, we carried out stratified analysis, receiver operating characteristic (ROC) curve, concordance index (C-index), and decision curve analysis (DCA). In addition, integrating the clinicopathological trait and radiomics score, we developed a nomogram to predict the OS at 1 year, 2 years, and 3 years, respectively.

Results

Six radiomics features, including gradient_glcm_InverseVariance, logarithm_firstorder_Median, logarithm_firstorder_RobustMeanAbsoluteDeviation, square_gldm_LargeDependenceEmphasis, wavelet_HLL_firstorder_Kurtosis, and wavelet_LLL_firstorder_Maximum, were selected to construct the radiomics signature, whose areas under the curve (AUCs) for 3-year prediction reached 0.857 in the training set (n=146) and 0.871 in the testing set (n=62). The results of multivariate analysis revealed that the radiomics score, radiological sign, and N stage were independent prognostic factors in NSCLC. Moreover, compared with clinical factors and the separate radiomics model, the established nomogram exhibited a better performance in predicting 3-year OS.

Conclusions

Our radiomics model may provide a promising non-invasive approach for preoperative risk stratification and personalized postoperative surveillance for resectable NSCLC patients.

Comprehensive 18F-FDG PET-based radiomics in elevating the pathological response to neoadjuvant immunochemotherapy for resectable stage III non-small-cell lung cancer: A pilot study

PURPOSE

To develop a comprehensive PET radiomics model to predict the pathological response after neoadjuvant toripalimab with chemotherapy in resectable stage III non-small-cell lung cancer (NSCLC) patients.

METHODS

Stage III NSCLC patients who received three cycles of neoadjuvant toripalimab with chemotherapy and underwent ¹⁸F-FDG PET/CT were enrolled. Baseline ¹⁸F-FDG PET/CT was performed before treatment, and preoperative ¹⁸F-FDG PET/CT was performed three weeks after the completion of neoadjuvant treatment. Surgical resection was performed 4-5 weeks after the completion of neoadjuvant treatment. Standardized uptake value (SUV) statistics features and radiomics features were derived from baseline and preoperative PET images. Delta features were derived. The radiologic response and metabolic response were assessed by iRECIST and iPERCIST, respectively. The correlations between PD-L1 expression, driver-gene status, peripheral blood biomarkers, and the pathological responses (complete pathological response [CPR]; major pathological response [MPR]) were assessed. Associations between PET features and pathological responses were evaluated by logistic regression.

RESULTS

Thirty patients underwent surgery and 29 of them performed preoperative PET/CT. Twenty patients achieved MPR and 16 of them achieved CPR. In univariate analysis, five SUV statistics features and two radiomics features were significantly associated with pathological responses. In multi-variate analysis, SUV_max, SUV_peak, SUL_peak, and End-PET-GLDM-LargeDependenceHighGrayLevelEmphasis (End-GLDM-LDHGLE) were independently associated with CPR. SUV_peak and SUL_peak performed better than SUV_max and SUL_max for MPR prediction. No significant correlation, neither between the radiologic response and the pathological response, nor among PD-L1, driver gene status, and baseline PET features was found. Inflammatory response biomarkers by peripheral blood showed no difference in different treatment responses.

CONCLUSION

The logistic regression model using comprehensive PET features contributed to predicting the pathological response after neoadjuvant toripalimab with chemotherapy in resectable stage III NSCLC patients.

PET/CT molecular imaging in the era of immune-checkpoint inhibitors therapy

Cancer immunotherapy, especially immune-checkpoint inhibitors (ICIs), has paved a new way for the treatment of many types of malignancies, particularly advanced-stage cancers. Accumulating evidence suggests that as a molecular imaging modality, positron emission tomography/computed tomography (PET/CT) can play a vital role in the management of ICIs therapy by using different molecular probes and metabolic parameters. In this review, we will provide a comprehensive overview of the clinical data to support the importance of 18F-fluorodeoxyglucose PET/CT (18F-FDG PET/CT) imaging in the treatment of ICIs, including the evaluation of the tumor microenvironment, discovery of immune-related adverse events, evaluation of therapeutic efficacy, and prediction of therapeutic prognosis. We also discuss perspectives on the development direction of 18F-FDG PET/CT imaging, with a particular emphasis on possible challenges in the future. In addition, we summarize the researches on novel PET molecular probes that are expected to potentially promote the precise application of ICIs.

Correlation between PD-L1 expression and radiomic features in early-stage lung adenocarcinomas manifesting as ground-glass nodules

Background

Immunotherapy might be a promising auxiliary or alternative systemic treatment for early-stage lung adenocarcinomas manifesting as ground-glass nodules (GGNs). This study intended to investigate the PD-L1 expression in these patients, and to explore the non-invasive prediction model of PD-L1 expression based on radiomics.

Methods

We retrospectively analyzed the PD-L1 expression of patients with postoperative pathological diagnosis of lung adenocarcinomas and with imaging manifestation of GGNs, and divided patients into positive group and negative group according to whether PD-L1 expression ≥1%. Then, CT-based radiomic features were extracted semi-automatically, and feature dimensions were reduced by univariate analysis and LASSO in the randomly selected training cohort (70%). Finally, we used logistic regression algorithm to establish the radiomic models and the clinical-radiomic combined models for PD-L1 expression prediction, and evaluated the prediction efficiency of the models with the receiver operating characteristic (ROC) curves.

Results

A total of 839 “GGN-like lung adenocarcinoma” patients were included, of which 226 (26.9%) showed positive PD-L1 expression. 779 radiomic features were extracted, and 9 of them were found to be highly corelated with PD-L1 expression. The area under the curve (AUC) values of the radiomic models were 0.653 and 0.583 in the training cohort and test cohort respectively. After adding clinically significant and statistically significant clinical features, the efficacy of the combined model was slightly improved, and the AUC values were 0.693 and 0.598 respectively.

Conclusions

GGN-like lung adenocarcinoma had a fairly high positive PD-L1 expression rate. Radiomics was a hopeful noninvasive method for predicting PD-L1 expression, with better predictive efficacy in combination with clinical features.

What does radiomics do in PD-L1 blockade therapy of NSCLC patients?

With the in‐depth understanding of programmed cell death 1 ligand 1 (PD‐L1) in non‐small cell lung cancer (NSCLC), PD‐L1 has become a vital immunotherapy target and a significant biomarker. The clinical utility of detecting PD‐L1 by immunohistochemistry or next‐generation sequencing has been written into guidelines. However, the application of these methods is limited in some circumstances where the biopsy size is small or not accessible, or a dynamic monitor is needed. Radiomics can noninvasively, in real‐time, and quantitatively analyze medical images to reflect deeper information about diseases. Since radiomics was proposed in 2012, it has been widely used in disease diagnosis and differential diagnosis, tumor staging and grading, gene and protein phenotype prediction, treatment plan decision‐making, efficacy evaluation, and prognosis prediction. To explore the feasibility of the clinical application of radiomics in predicting PD‐L1 expression, immunotherapy response, and long‐term prognosis, we comprehensively reviewed and summarized recently published works in NSCLC. In conclusion, radiomics is expected to be a companion to the whole immunotherapy process.