Artificial intelligence combining radiomics and clinical data for predicting response to immunotherapy

Ligero, Marta; García-Ruiz, Alonso; Viaplana, Cristina; Raciti, Maria Vittoria; Matos, Ignacio; Liberal, Juan Martin; Hierro, Cinta; González, M.; Barrera, Rafael; Suárez, Cristina; Élez, Elena; Braña, Irene; Muñoz‐Couselo, Eva; Oaknin, Ana; Felip, Enriqueta; Tabernero, Josep; Carles, Joan; Dienstmann, Rodrigo; Garralda, Elena; Lopez, Romain

doi:10.1093/annonc/mdz253.002

Cited by 6 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the gray-level non uniformity descriptor derived from T1-WI images was the most predictive feature for these three immune cell markers (Figure 5). This confirms the potential of radiomic features for predicting immune markers [49,56,57].…”

Section: Discussionsupporting

confidence: 78%

Deep radiomic signature with immune cell markers predicts the survival of glioma patients

et al. 2022

View full text Add to dashboard Cite

Section: Discussionsupporting

confidence: 78%

Deep radiomic signature with immune cell markers predicts the survival of glioma patients

et al. 2022

View full text Add to dashboard Cite

“…However, the model statistically significantly predicted OS in both tumor types (NSCLC: AUC: 0.76, p < 0.01; melanoma: AUC: 0.77, p < 0.01) [197]. Correlations of CT-based radiomic features and therapy response were also reported for patients with advanced ovarian cancer [198] and bladder cancer [199] undergoing immune-checkpoint blockade. Table 6 summarizes radiomics studies predicting clinical outcome with immune-checkpoint blockade.…”

Section: Radiomics Predict Clinical Outcome With Ici Therapymentioning

confidence: 82%

“…Prediction of clinical benefit by intratumoral heterogeneity (radiomic feature) and by number of disease sites [199] Ligero et al solid tumors ↑ ORR prediction by clinical-radiomics signature score [200] Tunali et al On the one hand, a subset of advanced cancer patients derives long-term survival from immune-checkpoint blockade, on the other hand, up to nine per cent of patients experience hyperprogressive disease with rapid fatal outcome upon initiation of anti-PD-1/anti-PD-L1 therapy [203]. In a clinical-radiomic approach Tunali et al were able to identify patients with a time to progression < 2 months or hyperprogressive disease within an advanced NSCLC cohort treated with single agent or double agent immunotherapy [200].…”

Section: Melanoma Nsclcmentioning

confidence: 99%

Combination Strategies for Immune-Checkpoint Blockade and Response Prediction by Artificial Intelligence

Huemer

Leisch

Geisberger³

et al. 2020

IJMS

View full text Add to dashboard Cite

The therapeutic concept of unleashing a pre-existing immune response against the tumor by the application of immune-checkpoint inhibitors (ICI) has resulted in long-term survival in advanced cancer patient subgroups. However, the majority of patients do not benefit from single-agent ICI and therefore new combination strategies are eagerly necessitated. In addition to conventional chemotherapy, kinase inhibitors as well as tumor-specific vaccinations are extensively investigated in combination with ICI to augment therapy responses. An unprecedented clinical outcome with chimeric antigen receptor (CAR-)T cell therapy has led to the approval for relapsed/refractory diffuse large B cell lymphoma and B cell acute lymphoblastic leukemia whereas response rates in solid tumors are unsatisfactory. Immune-checkpoints negatively impact CAR-T cell therapy in hematologic and solid malignancies and as a consequence provide a therapeutic target to overcome resistance. Established biomarkers such as programmed death ligand 1 (PD-L1) and tumor mutational burden (TMB) help to select patients who will benefit most from ICI, however, biomarker negativity does not exclude responses. Investigating alterations in the antigen presenting pathway as well as radiomics have the potential to determine tumor immunogenicity and response to ICI. Within this review we summarize the literature about specific combination partners for ICI and the applicability of artificial intelligence to predict ICI therapy responses.

show abstract

“…Furthermore, assessing the models based on R Squared scores revealed all negative results -the radiomic input data simply does not follow a trend to the output mm 3 responses. In future work, including more patients in the modeling as well as clinical data [127] may serve to reduce the error of predicted mm 3 GTV changes [127,128].…”

Section: Volume-specific Predictionsmentioning

confidence: 99%

Predicting Tumour Response With Radiomics and Machine Learning in MR-Guided Cervix Brachytherapy

Bellis

2024

Preprint

View full text Add to dashboard Cite

This study seeks to determine if radiomic features extracted from whole or part of the gross tumour volume of locally advanced cervical cancer (LACC) patients can be used to predict tumour response prior to brachytherapy treatment. 12 machine learning algorithms were tested with 5-fold cross validation using 1183 radiomic features extracted from 20 patients from T1, T2 and diffusion-weighted MR images. Recursive Feature Elimination was used to indicate the most predictive radiomic features of the most accurate models. Several models, particularly Ensemble Methods, performed with accuracies of up to 85%. After combining the 11 most predictive features into a single dataset, a random forest model achieved an accuracy of 93%. Overall, this study showed that machine learning models coupled with radiomic features are capable of accurately predicting LACC tumour response prior to administering the first fraction of brachytherapy treatment.

show abstract

Artificial intelligence combining radiomics and clinical data for predicting response to immunotherapy

Cited by 6 publications

References 0 publications

Deep radiomic signature with immune cell markers predicts the survival of glioma patients

Deep radiomic signature with immune cell markers predicts the survival of glioma patients

Combination Strategies for Immune-Checkpoint Blockade and Response Prediction by Artificial Intelligence

Predicting Tumour Response With Radiomics and Machine Learning in MR-Guided Cervix Brachytherapy

Contact Info

Product

Resources

About