An international phase II trial and immune profiling of SBRT and atezolizumab in advanced pretreated colorectal cancer.

BACKGROUND: Immuno-radiotherapy may improve outcomes for patients with advanced solid tumors, although optimized combination modalities remain unclear. Here, we report the colorectal (CRC) cohort analysis from the SABR-PDL1 trial that evaluated the PD-L1 inhibitor atezolizumab in combination with stereotactic body radiation therapy (SBRT) in advanced cancer patients. METHODS: Eligible patients received atezolizumab 1200 mg every 3 weeks until progression or unmanageable toxicity, together with ablative SBRT delivered concurrently with the 2nd cycle (recommended dose of 45 Gy in 3 fractions, adapted upon normal tissue tolerance constraint). SBRT was delivered to at least one tumor site, with at least one additional measurable lesion being kept from the radiation field. The primary efficacy endpoint was one-year progression-free survival (PFS) rate from the start of atezolizumab. Sequential tumor biopsies were collected for deep multi-feature immune profiling. RESULTS: Sixty pretreated (median of 2 prior lines) advanced CRC patients (38 men [63%]; median age, 59 years [range, 20-81 years]; 77% with liver metastases) were enrolled in five centers (France: n = 4, Spain: n = 1) from 11/2016 to 04/2019. All but one (98%) received atezolizumab and 54/60 (90%) received SBRT. The most frequently irradiated site was lung (n = 30/54; 56.3%). Treatment-related G3 (no G4-5) toxicity was observed in 3 (5%) patients. Median OS and PFS were respectively 8.4 [95%CI:5.9-11.6] and 1.4 months [95%CI:1.2-2.6], including five (9%) patients with PFS > 1 year (median time to progression: 19.2 months, including 2/5 MMR-proficient). Best overall responses consisted of stable disease (n = 38; 64%), partial (n = 3; 5%) and complete response (n = 1; 2%). Immune-centric multiplex IHC and RNAseq showed that SBRT redirected immune cells towards tumor lesions, even in the case of radio-induced lymphopenia. Baseline tumor PD-L1 and IRF1 nuclear expression (both in CD3 + T cells and in CD68 + cells) were higher in responding patients. Upregulation of genes that encode for proteins known to increase T and B cell trafficking to tumors (CCL19, CXCL9), migration (MACF1) and tumor cell killing (GZMB) correlated with responses. CONCLUSIONS: This study provides new data on the feasibility, efficacy, and immune context of tumors that may help identifying advanced CRC patients most likely to respond to immuno-radiotherapy. TRIAL REGISTRATION: EudraCT N°: 2015-005464-42; Clinicaltrial.gov number: NCT02992912.

Integrating Artificial Intelligence and PET Imaging for Drug Discovery: A Paradigm Shift in Immunotherapy.

The integration of artificial intelligence (AI) and positron emission tomography (PET) imaging has the potential to become a powerful tool in drug discovery. This review aims to provide an overview of the current state of research and highlight the potential for this alliance to advance pharmaceutical innovation by accelerating the development and deployment of novel therapeutics. We previously performed a scoping review of three databases (Embase, MEDLINE, and CENTRAL), identifying 87 studies published between 2018 and 2022 relevant to medical imaging (e.g., CT, PET, MRI), immunotherapy, artificial intelligence, and radiomics. Herein, we reexamine the previously identified studies, performing a subgroup analysis on articles specifically utilizing AI and PET imaging for drug discovery purposes in immunotherapy-treated oncology patients. Of the 87 original studies identified, 15 met our updated search criteria. In these studies, radiomics features were primarily extracted from PET/CT images in combination (n = 9, 60.0%) rather than PET imaging alone (n = 6, 40.0%), and patient cohorts were mostly recruited retrospectively and from single institutions (n = 10, 66.7%). AI models were used primarily for prognostication (n = 6, 40.0%) or for assisting in tumor phenotyping (n = 4, 26.7%). About half of the studies stress-tested their models using validation sets (n = 4, 26.7%) or both validation sets and test sets (n = 4, 26.7%), while the remaining six studies (40.0%) either performed no validation at all or used less stringent methods such as cross-validation on the training set. Overall, the integration of AI and PET imaging represents a paradigm shift in drug discovery, offering new avenues for more efficient development of therapeutics. By leveraging AI algorithms and PET imaging analysis, researchers could gain deeper insights into disease mechanisms, identify new drug targets, or optimize treatment regimens. However, further research is needed to validate these findings and address challenges such as data standardization and algorithm robustness.

Automatic gross tumor volume segmentation with failure detection for safe implementation in locally advanced cervical cancer.

Background and Purpose: Automatic segmentation methods have greatly changed the RadioTherapy (RT) workflow, but still need to be extended to target volumes. In this paper, Deep Learning (DL) models were compared for Gross Tumor Volume (GTV) segmentation in locally advanced cervical cancer, and a novel investigation into failure detection was introduced by utilizing radiomic features. Methods and materials: We trained eight DL models (UNet, VNet, SegResNet, SegResNetVAE) for 2D and 3D segmentation. Ensembling individually trained models during cross-validation generated the final segmentation. To detect failures, binary classifiers were trained using radiomic features extracted from segmented GTVs as inputs, aiming to classify contours based on whether their Dice Similarity Coefficient ( DSC ) < T and DSC ⩾ T . Two distinct cohorts of T2-Weighted (T2W) pre-RT MR images captured in 2D sequences were used: one retrospective cohort consisting of 115 LACC patients from 30 scanners, and the other prospective cohort, comprising 51 patients from 7 scanners, used for testing. Results: Segmentation by 2D-SegResNet achieved the best DSC, Surface DSC ( SDSC 3 mm ), and 95th Hausdorff Distance (95HD): DSC = 0.72 ± 0.16, SDSC 3 mm =0.66 ± 0.17, and 95HD = 14.6 ± 9.0 mm without missing segmentation ( M =0) on the test cohort. Failure detection could generate precision ( P = 0.88 ), recall ( R = 0.75 ), F1-score ( F = 0.81 ), and accuracy ( A = 0.86 ) using Logistic Regression (LR) classifier on the test cohort with a threshold T = 0.67 on DSC values. Conclusions: Our study revealed that segmentation accuracy varies slightly among different DL methods, with 2D networks outperforming 3D networks in 2D MRI sequences. Doctors found the time-saving aspect advantageous. The proposed failure detection could guide doctors in sensitive cases.