When artificial intelligence meets PD-1/PD-L1 inhibitors: Population screening, response prediction and efficacy evaluation

Biomarkers and computational models for predicting efficacy to tumor ICI immunotherapy

Numerous studies have shown that immune checkpoint inhibitor (ICI) immunotherapy has great potential as a cancer treatment, leading to significant clinical improvements in numerous cases. However, it benefits a minority of patients, underscoring the importance of discovering reliable biomarkers that can be used to screen for potential beneficiaries and ultimately reduce the risk of overtreatment. Our comprehensive review focuses on the latest advancements in predictive biomarkers for ICI therapy, particularly emphasizing those that enhance the efficacy of programmed cell death protein 1 (PD-1)/programmed cell death-ligand 1 (PD-L1) inhibitors and cytotoxic T-lymphocyte antigen-4 (CTLA-4) inhibitors immunotherapies. We explore biomarkers derived from various sources, including tumor cells, the tumor immune microenvironment (TIME), body fluids, gut microbes, and metabolites. Among them, tumor cells-derived biomarkers include tumor mutational burden (TMB) biomarker, tumor neoantigen burden (TNB) biomarker, microsatellite instability (MSI) biomarker, PD-L1 expression biomarker, mutated gene biomarkers in pathways, and epigenetic biomarkers. TIME-derived biomarkers include immune landscape of TIME biomarkers, inhibitory checkpoints biomarkers, and immune repertoire biomarkers. We also discuss various techniques used to detect and assess these biomarkers, detailing their respective datasets, strengths, weaknesses, and evaluative metrics. Furthermore, we present a comprehensive review of computer models for predicting the response to ICI therapy. The computer models include knowledge-based mechanistic models and data-based machine learning (ML) models. Among the knowledge-based mechanistic models are pharmacokinetic/pharmacodynamic (PK/PD) models, partial differential equation (PDE) models, signal networks-based models, quantitative systems pharmacology (QSP) models, and agent-based models (ABMs). ML models include linear regression models, logistic regression models, support vector machine (SVM)/random forest/extra trees/k-nearest neighbors (KNN) models, artificial neural network (ANN) and deep learning models. Additionally, there are hybrid models of systems biology and ML. We summarized the details of these models, outlining the datasets they utilize, their evaluation methods/metrics, and their respective strengths and limitations. By summarizing the major advances in the research on predictive biomarkers and computer models for the therapeutic effect and clinical utility of tumor ICI, we aim to assist researchers in choosing appropriate biomarkers or computer models for research exploration and help clinicians conduct precision medicine by selecting the best biomarkers.

Non-invasive decision support for clinical treatment of non-small cell lung cancer using a multiscale radiomics approach

BACKGROUND

Selecting therapeutic strategies for cancer patients is typically based on key target-molecule biomarkers that play an important role in cancer onset, progression, and prognosis. Thus, there is a pressing need for novel biomarkers that can be utilized longitudinally to guide treatment selection.

METHODS

Using data from 508 non-small cell lung cancer (NSCLC) patients across three institutions, we developed and validated a comprehensive predictive biomarker that distinguishes six genotypes and infiltrative immune phenotypes. These features were analyzed to establish the association between radiological phenotypes and tumor genotypes/immune phenotypes and to create a radiological interpretation of molecular features. In addition, we assessed the sensitivity of the models by evaluating their performance at five different voxel intervals, resulting in improved generalizability of the proposed approach.

FINDINGS

The radiomics model we developed, which integrates clinical factors and multi-regional features, outperformed the conventional model that only uses clinical and intratumoral features. Our combined model showed significant performance for EGFR, KRAS, ALK, TP53, PIK3CA, and ROS1 mutation status with AUCs of 0.866, 0.874, 0.902, 0.850, 0.860, and 0.900, respectively. Additionally, the predictive performance for PD-1/PD-L1 was 0.852. Although the performance of all models decreased to different degrees at five different voxel space resolutions, the performance advantage of the combined model did not change.

CONCLUSIONS

We validated multiscale radiomic signatures across tumor genotypes and immunophenotypes in a multi-institutional cohort. This imaging-based biomarker offers a non-invasive approach to select patients with NSCLC who are sensitive to targeted therapies or immunotherapy, which is promising for developing personalized treatment strategies during therapy.

Correlation Between ImageJ and Conventional Manual Scoring Methods for Programmed Death-Ligand 1 Immuno-Histochemically Stained Sections

Background: One of the most frequently used methods for quantifying PD-L1 (programmed cell death-ligand 1) expression in tumor tissue is IHC (immunohistochemistry). This may predict the patient's response to anti-PD1/PD-L1 therapy in cancer. Methods: ImageJ software was used to score IHC-stained sections for PD-L1 and compare the results with the conventional manual method. Results: In diffuse large B cell lymphoma, no significant difference between the scores obtained by the conventional method and ImageJ scores obtained using the option "RGB" or "Brightness/Contrast." On the other hand, a significant difference was found between the conventional and HSB scoring methods. ImageJ faced some challenges in analyzing head and neck squamous cell carcinoma tissues because of tissue heterogenicity. A significant difference was found between the conventional and ImageJ scores using HSB or RGB but not with the "Brightness/Contrast" option. Scores obtained by ImageJ analysis after taking images using 20 × objective lens gave significantly higher readings compared to 40 × magnification. A significant difference between camera-captured images' scores and scanner whole slide images' scores was observed. Conclusion: ImageJ can be used to score homogeneous tissues. In the case of highly heterogeneous tissues, it is advised to use the conventional method rather than ImageJ scoring.

Contrast-enhanced CT-based radiomic analysis for determining the response to anti-programmed death-1 therapy in esophageal squamous cell carcinoma patients: A pilot study

BACKGROUND

In view of the fact that radiomics features have been reported as predictors of immunotherapy to various cancers, this study aimed to develop a prediction model to determine the response to anti-programmed death-1 (anti-PD-1) therapy in esophageal squamous cell carcinoma (ESCC) patients from contrast-enhanced CT (CECT) radiomics features.

METHODS

Radiomic analysis of images was performed retrospectively for image samples before and after anti-PD-1 treatment, and efficacy analysis was performed for the results of two different time node evaluations. A total of 68 image samples were included in this study. Quantitative radiomic features were extracted from the images, and the least absolute shrinkage and selection operator method was applied to select radiomic features. After obtaining selected features, three classification models were used to establish a radiomics model to predict the ESCC status and efficacy of therapy. A cross-validation strategy utilizing three folds was employed to train and test the model. Performance evaluation of the model was done using the area under the curve (AUC) of receiver operating characteristic, sensitivity, specificity, and precision metric.

RESULTS

Wavelet and area of gray level change (log-sigma) were the most significant radiomic features for predicting therapy efficacy. Fifteen radiomic features from the whole tumor and peritumoral regions were selected and comprised of the fusion radiomics score. A radiomics classification was developed with AUC of 0.82 and 0.884 in the before and after-therapy cohorts, respectively.

CONCLUSIONS

The combined model incorporating radiomic features and clinical CECT predictors helps to predict the response to anti-PD-1therapy in patients with ESCC.

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.

Non-small cell lung cancer patients treated with Anti-PD1 immunotherapy show distinct microbial signatures and metabolic pathways according to progression-free survival and PD-L1 status

Due to the high variance in response rates concerning anti-PD1 immunotherapy (IT), there is an unmet need to discover innovative biomarkers to predict immune checkpoint inhibitor (ICI)-efficacy. Our study included 62 Caucasian advanced-stage non-small cell lung cancer (NSCLC) patients treated with anti-PD1 ICI. Gut bacterial signatures were evaluated by metagenomic sequencing and correlated with progression-free survival (PFS), PD-L1 expression and other clinicopathological parameters. We confirmed the predictive role of PFS-related key bacteria with multivariate statistical models (Lasso- and Cox-regression) and validated on an additional patient cohort (n = 60). We find that alpha-diversity showed no significant difference in any comparison. However, there was a significant difference in beta-diversity between patients with long- (>6 months) vs. short (≤6 months) PFS and between chemotherapy (CHT)-treated vs. CHT-naive cases. Short PFS was associated with increased abundance of Firmicutes (F) and Actinobacteria phyla, whereas elevated abundance of Euryarchaeota was specific for low PD-L1 expression. F/Bacteroides (F/B) ratio was significantly increased in patients with short PFS. Multivariate analysis revealed an association between Alistipes shahii, Alistipes finegoldii, Barnesiella visceriola, and long PFS. In contrast, Streptococcus salivarius, Streptococcus vestibularis, and Bifidobacterium breve were associated with short PFS. Using Random Forest machine learning approach, we find that taxonomic profiles performed superiorly in predicting PFS (AUC = 0.74), while metabolic pathways including Amino Acid Synthesis and Fermentation were better predictors of PD-L1 expression (AUC = 0.87). We conclude that specific metagenomic features of the gut microbiome, including bacterial taxonomy and metabolic pathways might be suggestive of ICI efficacy and PD-L1 expression in NSCLC patients.

The Applications of Artificial Intelligence in Digestive System Neoplasms: A Review

Importance

Digestive system neoplasms (DSNs) are the leading cause of cancer-related mortality with a 5-year survival rate of less than 20%. Subjective evaluation of medical images including endoscopic images, whole slide images, computed tomography images, and magnetic resonance images plays a vital role in the clinical practice of DSNs, but with limited performance and increased workload of radiologists or pathologists. The application of artificial intelligence (AI) in medical image analysis holds promise to augment the visual interpretation of medical images, which could not only automate the complicated evaluation process but also convert medical images into quantitative imaging features that associated with tumor heterogeneity.

Highlights

We briefly introduce the methodology of AI for medical image analysis and then review its clinical applications including clinical auxiliary diagnosis, assessment of treatment response, and prognosis prediction on 4 typical DSNs including esophageal cancer, gastric cancer, colorectal cancer, and hepatocellular carcinoma.

Conclusion

AI technology has great potential in supporting the clinical diagnosis and treatment decision-making of DSNs. Several technical issues should be overcome before its application into clinical practice of DSNs.

Targeted nanomedicines remodeling immunosuppressive tumor microenvironment for enhanced cancer immunotherapy

Cancer immunotherapy has significantly flourished and revolutionized the limited conventional tumor therapies, on account of its good safety and long-term memory ability. Discouragingly, low patient response rates and potential immune-related side effects make it rather challenging to literally bring immunotherapy from bench to bedside. However, it has become evident that, although the immunosuppressive tumor microenvironment (TME) plays a pivotal role in facilitating tumor progression and metastasis, it also provides various potential targets for remodeling the immunosuppressive TME, which can consequently bolster the effectiveness of antitumor response and tumor suppression. Additionally, the particular characteristics of TME, in turn, can be exploited as avenues for designing diverse precise targeting nanomedicines. In general, it is of urgent necessity to deliver nanomedicines for remodeling the immunosuppressive TME, thus improving the therapeutic outcomes and clinical translation prospects of immunotherapy. Herein, we will illustrate several formation mechanisms of immunosuppressive TME. More importantly, a variety of strategies concerning remodeling immunosuppressive TME and strengthening patients' immune systems, will be reviewed. Ultimately, we will discuss the existing obstacles and future perspectives in the development of antitumor immunotherapy. Hopefully, the thriving bloom of immunotherapy will bring vibrancy to further exploration of comprehensive cancer treatment.