With the increasing use of immune checkpoint inhibitors (ICIs), there is an urgent need to identify biomarkers to stratify responders and non-responders using programmed death-ligand (PD-L1) expression, and to predict patient-specific outcomes such as progression free survival (PFS). The current study is aimed to determine the feasibility of building imaging-based predictive biomarkers for PD-L1 and PFS through systematically evaluating a combination of several machine learning algorithms with different feature selection methods. A retrospective, multicenter study of 385 advanced NSCLC patients amenable to ICIs was undertaken in two academic centers. Radiomic features extracted from pretreatment CT scans were used to build predictive models for PD-L1 and PFS (short-term vs. long-term survivors). We first employed the LASSO methodology followed by five feature selection methods and seven machine learning approaches to build the predictors. From our analyses, we found several combinations of feature selection methods and machine learning algorithms to achieve a similar performance. Logistic regression with ReliefF feature selection (AUC = 0.64, 0.59 in discovery and validation cohorts) and SVM with Anova F-test feature selection (AUC = 0.64, 0.63 in discovery and validation datasets) were the best-performing models to predict PD-L1 and PFS. This study elucidates the application of suitable feature selection approaches and machine learning algorithms to predict clinical endpoints using radiomics features. Through this study, we identified a subset of algorithms that should be considered in future investigations for building robust and clinically relevant predictive models.

Deep learning (DL) methods have demonstrated remarkable effectiveness in assisting with lung cancer risk prediction tasks using computed tomography (CT) scans. However, the lack of comprehensive comparison and validation of state-of-the-art (SOTA) models in practical settings limits their clinical application. This study aims to review and analyze current SOTA deep learning models for lung cancer risk prediction (malignant-benign classification). To evaluate our model’s general performance, we selected 253 out of 467 patients from a subset of the National Lung Screening Trial (NLST) who had CT scans without contrast, which are the most commonly used, and divided them into training and test cohorts. The CT scans were preprocessed into 2D-image and 3D-volume formats according to their nodule annotations. We evaluated ten 3D and eleven 2D SOTA deep learning models, which were pretrained on large-scale general-purpose datasets (Kinetics and ImageNet) and radiological datasets (3DSeg-8, nnUnet and RadImageNet), for their lung cancer risk prediction performance. Our results showed that 3D-based deep learning models generally perform better than 2D models. On the test cohort, the best-performing 3D model achieved an AUROC of 0.86, while the best 2D model reached 0.79. The lowest AUROCs for the 3D and 2D models were 0.70 and 0.62, respectively. Furthermore, pretraining on large-scale radiological image datasets did not show the expected performance advantage over pretraining on general-purpose datasets. Both 2D and 3D deep learning models can handle lung cancer risk prediction tasks effectively, although 3D models generally have superior performance than their 2D competitors. Our findings highlight the importance of carefully selecting pretrained datasets and model architectures for lung cancer risk prediction. Overall, these results have important implications for the development and clinical integration of DL-based tools in lung cancer screening.

Background: Immune checkpoint inhibitors (ICIs) are a great breakthrough in cancer treatments and provide improved long-term survival in a subset of non-small cell lung cancer (NSCLC) patients. However, prognostic and predictive biomarkers of immunotherapy still remain an unmet clinical need. In this work, we aim to leverage imaging data and clinical variables to develop survival risk models among advanced NSCLC patients treated with immunotherapy. Methods: This retrospective study includes a total of 385 patients from two institutions who were treated with ICIs. Radiomics features extracted from pretreatment CT scans were used to build predictive models. The objectives were to predict overall survival (OS) along with building a classifier for short- and long-term survival groups. We employed the XGBoost learning method to build radiomics and integrated clinical-radiomics predictive models. Feature selection and model building were developed and validated on a multicenter cohort. Results: We developed parsimonious models that were associated with OS and a classifier for short- and long-term survivor groups. The concordance indices (C-index) of the radiomics model were 0.61 and 0.57 to predict OS in the discovery and validation cohorts, respectively. While the area under the curve (AUC) values of the radiomic models for short- and long-term groups were found to be 0.65 and 0.58 in the discovery and validation cohorts. The accuracy of the combined radiomics-clinical model resulted in 0.63 and 0.62 to predict OS and in 0.77 and 0.62 to classify the survival groups in the discovery and validation cohorts, respectively. Conclusions: We developed and validated novel radiomics and integrated radiomics-clinical survival models among NSCLC patients treated with ICIs. This model has important translational implications, which can be used to identify a subset of patients who are not likely to benefit from immunotherapy. The developed imaging biomarkers may allow early prediction of low-group survivors, though additional validation of these radiomics models is warranted.

Background: Immune checkpoint inhibitors (ICIs) have revolutionized non-small cell lung cancers (NSCLCs) treatment, but only 20–30% of patients benefit from these treatments. Currently, PD-L1 expression in tumor cells is the only clinically approved predictor of ICI response in lung cancer, but concerns arise due to its low negative and positive predictive value. Recent studies suggest that CXCL13+ T cells in the tumor microenvironment (TME) may be a good predictor of response. We aimed to assess if CXCL13+ cell localization within the TME can predict ICI response in advanced NSCLC patients. Methods: This retrospective study included 65 advanced NSCLC patients treated with Nivolumab/Pembrolizumab at IUCPQ or CHUM and for whom a pretreatment surgical specimen was available. Good responders were defined as having a complete radiologic response at 1 year, and bad responders were defined as showing cancer progression at 1 year. IHC staining for CXCL13 was carried out on a representative slide from a resection specimen, and CXCL13+ cell density was evaluated in tumor (T), invasive margin (IM), non-tumor (NT), and tertiary lymphoid structure (TLS) compartments. Cox models were used to analyze progression-free survival (PFS) and overall survival (OS) probability, while the Mann–Whitney test was used to compare CXCL13+ cell density between responders and non-responders. Results: We showed that CXCL13+ cell density localization within the TME is associated with ICI efficacy. An increased density of CXCL13+ cells across all compartments was associated with a poorer prognostic (OS; HR = 1.22; 95%CI = 1.04–1.42; p = 0.01, PFS; HR = 1.16; p = 0.02), or a better prognostic when colocalized within TLSs (PFS; HR = 0.84, p = 0.03). Conclusion: Our results support the role of CXCL13+ cells in advanced NSCLC patients, with favorable prognosis when localized within TLSs and unfavorable prognosis when present elsewhere. The concomitant proximity of CXCL13+ and CD20+ cells within TLSs may favor antigen presentation to T cells, thus enhancing the effect of PD-1/PD-L1 axis inhibition. Further validation is warranted to confirm the potential relevance of this biomarker in a clinical setting.

With the rapid development of artificial intelligence (AI), AI-assisted medical imaging analysis demonstrates remarkable performance in early lung cancer screening. However, the costly annotation process and privacy concerns limit the construction of large-scale medical datasets, hampering the further application of AI in healthcare. To address the data scarcity in lung cancer screening, we propose Lung-DDPM, a thoracic CT image synthesis approach that effectively generates high-fidelity 3D synthetic CT images, which prove helpful in downstream lung nodule segmentation tasks. Our method is based on semantic layout-guided denoising diffusion probabilistic models (DDPM), enabling anatomically reasonable, seamless, and consistent sample generation even from incomplete semantic layouts. Our results suggest that the proposed method outperforms other state-of-the-art (SOTA) generative models in image quality evaluation and downstream lung nodule segmentation tasks. Specifically, Lung-DDPM achieved superior performance on our large validation cohort, with a Fréchet inception distance (FID) of 0.0047, maximum mean discrepancy (MMD) of 0.0070, and mean squared error (MSE) of 0.0024. These results were 7.4×, 3.1×, and 29.5× better than the second-best competitors, respectively. Furthermore, the lung nodule segmentation model, trained on a dataset combining real and Lung-DDPM-generated synthetic samples, attained a Dice Coefficient (Dice) of 0.3914 and sensitivity of 0.4393. This represents 8.8% and 18.6% improvements in Dice and sensitivity compared to the model trained solely on real samples. The experimental results highlight Lung-DDPM's potential for a broader range of medical imaging applications, such as general tumor segmentation, cancer survival estimation, and risk prediction.

Objective: Radiation therapy is among the most effective and widely used modalities of cancer therapy in current clinical practice. In this era of personalized radiation medicine, high-throughput data now provide the means to investigate novel biomarkers of radiation response. Large-scale efforts have identified several radiation response signatures, which poses two challenges, namely, their analytical validity and redundancy of gene signatures. Methods: To address these fundamental radiogenomics questions, we curated a database of gene expression signatures predictive of radiation response under oxic and hypoxic conditions. RadiationGeneSigDB has a collection of 11 oxic and 24 hypoxic signatures with the standardized gene list as a gene symbol, Entrez gene ID, and its function. We present the utility of this database by gaining an understanding of hypoxia-associated miRNA by applying a penalized multivariate model: by comparing breast cancer oxic signatures in cell line data vs patient data: and by comparing the similarity of head and neck cancer hypoxia signatures at the pathway level in clinical tumour data. Results: We obtained a set of miRNA highly associated both positively and negatively to the hypoxia gene signatures, across pan-cancer. In addition, we identified moderate correlations between breast cancer oxic signatures in patient data, and significant differences across molecular subtypes. Moreover, we also found that different set of pathways to be enriched using the head and neck hypoxia signatures, although, they are found to be concordant when applied on the patient data. Conclusion: This valuable, curated repertoire of published gene expression signatures provides motivating case studies for how to search for similarities in radiation response for tumours arising from different tissues across model systems under oxic and hypoxic conditions, and how a well-curated set of gene signatures can be used to generate novel biological hypotheses about the functions of non-coding RNA. Advances in knowledge: We envision that RadiationSigDB database will help accelerate preclinical radiotherapeutic discovery pipelines in terms of analytical validity of novel biomarkers of radiation response and the need for ensemble approaches to clinical genomic biomarkers.