Predictive radiomics signature for treatment response to nivolumab in patients with advanced renal cell carcinoma

Abstract

Introduction: The anti-PD-1 immune checkpoint inhibitor nivolumab is currently approved for the treatment of patients with metastatic renal cell carcinoma (mRCC); approximately 25% of patients respond. We hypothesized that we could identify a biomarker of response using radiomics to train a machine learning classifier to predict nivolumab response outcomes. Methods: Patients with mRCC of different histologies treated with nivolumab in a single institution between 2013 and 2017 were retrospectively identified. Patients were labelled as responders (complete response [CR]/particle response [PR]/durable stable disease [SD]) or non-responders based on investigator tumor assessment using RECIST 1.1 criteria. For each patient, lesions were contoured from pre-treatment and first post-treatment computed tomography (CT) scans. This information was used to train a radial basis function support vector machine classifier to learn a prediction rule to distinguish responders from non-responders. The classifier was internally validated by a 10-fold nested cross-validation. Results: Thirty-seven patients were identified; 27 (73%) met the inclusion criteria. One hundred and four lesions were contoured from these 27 patients. The median patient age was 56 years, 78% were male, 89% had clear-cell histology, 89% had prior nephrectomy, and 89% had prior systemic therapy. There were 19 responders vs. eight non-responders. The lesions selected were lymph nodes (60%), lung metastases (23%), and renal/adrenal metastases (17%). For the classifier trained on the baseline CT scans, 69% accuracy was achieved. For the classifier trained on the first post-treatment CT scans, 66% accuracy was achieved. Conclusions: The set of radiomic signatures was found to have limited ability to discriminate nivolumab responders from non-responders. The use of novel texture features (two-point correlation measure, two-point cluster measure, and minimum spanning tree measure) did not improve performance.

Global research trends of artificial intelligence applied in esophageal carcinoma: A bibliometric analysis (2000-2022) via CiteSpace and VOSviewer

“…The clustering findings revealed that it could be classified into 38 groups, yet only the top 14 were shown in Figure 7A . The largest cluster was “radiomics” (#0) ( 53 – 56 ), while “tumor segmentation”(#6) ( 57 – 61 )was the earliest research in this field. “Endoscopy” (#9) ( 62 – 65 ) and “deep learning” (#2) ( 66 – 70 ) were the latest research hotspots.…”

Impact of Quantitative Computed Tomography-Based Analysis of Abdominal Adipose Tissue in Patients with Lymphoma

“…For example, the correlation between body fat at a young age (i.e., childhood, adolescence and young adulthood; age ≤ 30 years) and DLBCL is known [ 28 ]. Consequently, not only is the disease evaluated but also the patient as a whole to obtain additional information in an opportunistic way with minimal, if any, additional cost to improve and tailor personalized therapies, possibly improving clinical outcomes [ 29 , 30 , 31 , 32 , 33 , 34 ]. Indeed, artificial intelligence is a revolutionary technology that can obtain an automatic, fast and precise analysis of tissues [ 33 , 34 ].…”

“…This field is based on radiological images to obtain quantitative data that can predict features including tumor biology, molecular patterns or immune cell infiltrates. The potential advantages would be multiple: evaluation of the intratumoral heterogeneity and the interactions with the microenvironment, analysis of multiple lesions in parallel, evaluation of the variations of the lesions longitudinally over time, and, lastly, the non-invasiveness of the technique [ 32 ].…”