Introduction Immunotherapy is regarded as one of the major breakthroughs in cancer treatment. Despite its success, only a subset of patients responds—urging the quest for predictive biomarkers. We hypothesize that artificial intelligence (AI) algorithms can automatically quantify radiographic characteristics that are related to and may therefore act as noninvasive radiomic biomarkers for immunotherapy response. Patients and methods In this study, we analyzed 1055 primary and metastatic lesions from 203 patients with advanced melanoma and non-small-cell lung cancer (NSCLC) undergoing anti-PD1 therapy. We carried out an AI-based characterization of each lesion on the pretreatment contrast-enhanced CT imaging data to develop and validate a noninvasive machine learning biomarker capable of distinguishing between immunotherapy responding and nonresponding. To define the biological basis of the radiographic biomarker, we carried out gene set enrichment analysis in an independent dataset of 262 NSCLC patients. Results The biomarker reached significant performance on NSCLC lesions (up to 0.83 AUC, P < 0.001) and borderline significant for melanoma lymph nodes (0.64 AUC, P = 0.05). Combining these lesion-wide predictions on a patient level, immunotherapy response could be predicted with an AUC of up to 0.76 for both cancer types ( P < 0.001), resulting in a 1-year survival difference of 24% ( P = 0.02). We found highly significant associations with pathways involved in mitosis, indicating a relationship between increased proliferative potential and preferential response to immunotherapy. Conclusions These results indicate that radiographic characteristics of lesions on standard-of-care imaging may function as noninvasive biomarkers for response to immunotherapy, and may show utility for improved patient stratification in both neoadjuvant and palliative settings.

Background & Aims: To assess the role of diffusion weighted imaging sequence (DWI), routinely used in hepatic magnetic resonance imaging (MRI) for the differentiation of focal liver lesions (FLLs) as benign or malignant. Method: 99 FLLs assessed by liver MRI in 80 patients were included in the present study. All lesions were retrospectively analyzed by two experienced radiologists, independent from each other, who were not aware of the previous results obtained by using different imaging techniques. All included FLLs had a final histological diagnosis or a final diagnosis based on consensus reading by two experienced radiologists and follow-up at 6 months. The FLLs signal was qualitatively appreciated on the b-800 sequences and on the apparent diffusion coefficient (ADC) map. The ADC value of each FLL was measured and the ADC ratio between the ADC value of the assessed FLL and that of the surrounding liver parenchyma were calculated. Results: The mean ADC value for benign FLLs as assessed by the two independent readers was 1.78 x 10¯³ and 1.72 x 10¯³, respectively. The mean ADC value for malignant FLLs was 0.92 x 10¯³ for the first reader and 0.95 x 10¯³ for the second reader. The mean ADC ratio for benign FLLs was 1.91 and 1.85 for the two readers and for malignant FLLs was 0.91 and 0.94, respectively. Using an ADC value lower than 1.024 x 10¯³ offers a specificity of 100% and a sensitivity of 62.5% for the diagnosis of malignant FLLs. The ADC value is an indicator which is less prone to interobserver variability (correlation of 0.919→1). The ADC ratio has, as the analysis of the ROC curve shows, the best predictive value for differentiation between benign and malignant FLLs. Analysis of the signal intensity on the DWI b-800 image alone is of no significance in differentiating benign from malignant FLLs (p>0.05). Conclusions: The ADC value and the ADC ratio assessed on liver DWI are useful diagnostic tools in the differential diagnosis of benign vs. malignant FLLs. Quantitative methods such as calculating the ADC value or ADC ratio have better diagnostic value than the qualitative techniques.

Background and aimTo assess the role of diffusion weighted imaging sequence (DWI), routinely used in hepatic magnetic resonance imaging (MRI) for the differentiation of hepatocellular carcinoma (HCC) from benign liver lesions.MethodsA number of 56 liver MRI examinations were retrospectively analyzed independently by two experienced radiologists, blinded to each other results. A total number of 70 Focal Liver Lesions (FLLs) assessed by liver MRI in 56 patients were included in the present study. All lesions were retrospectively analyzed by two experienced radiologists, independently from each other and who were not aware of the previous results given by using different imaging techniques. All included FLLs had a final histological diagnosis, or the final diagnosis was based on consensus reading by two experienced radiologists. The signal of the included FLLs was qualitatively appreciated on the b-800 sequences and on the apparent diffusion coefficient (ADC) map. The ADC value of each FLL was measured and the ADC ratio between the ADC value of the assessed FLL and that of the surrounding liver parenchyma was calculated.ResultsThe mean ADC value for benign FLLs as assessed by the two independent readers was 1.75 × 10−3 and 1.72 × 10−3. The mean ADC value for HCC nodules was 0.92 × 10−3 for the first reader and 0.91 × 10−3 for the second reader respectively. The mean ADC ratio for benign FLLs was 1.81 and 1.84 for the two readers, respectively. The ADC ratio for HCC nodules was 0.91 and 0.91, respectively. The ADC value is an indicator which is less prone to interobserver variability (correlation of 0.919→1). The ADC ratio has, as the analysis of the ROC curve shows, the best predictive value for differentiation between benign FLLs and HCC nodules. Analysis of the signal intensity on the DWI b-800 image alone is of no significance in differentiating benign FLLs from HCC nodules (p>0.005).ConclusionsThe ADC value and the ADC ratio assessed on liver DWI are useful diagnostic tools in the differential diagnosis of benign FLLs vs HCC nodules. Quantitative methods such as calculating the ADC value or ADC ratio have better diagnostic value than qualitative techniques.

e14520 Background: PD-1 checkpoint inhibitors have recently been approved for the treatment of patients with metastatic NSCLC. Predicting to what extent patients will benefit from these treatments is challenging. Research on predictive biomarkers focus on genetic and histological markers from biopsies, necessarily limited to parts of the tumor. Radiomics is a novel approach to quantify characteristics of the tumor on medical imaging, which may have potential value as non-invasive biomarkers. In this study, we explored the value of radiomic data from primary tumors to predict overall survival (OS) in patients with metastatic NSCLC treated with Nivolumab Methods: We retrospectively selected 64 metastatic NSCLC patients treated in 2ndline setting with Nivolumab (240 mg q 2 weeks until progression). Inclusion criteria were: primary tumor in situ with contrast enhanced CT scan (thorax abdomen; slice thickness ≤3mm) within 6 weeks before the start of the treatment. Exclusion criteria were: presence of atelectasis or fusion with other structures and presence of multiple lung lesions at first scan. A certified radiologist delineated the tumors on CT from which we extracted 1696 Radiomic features. Unsupervised feature selection was performed. Multivariate Cox Regression was used to model the OS based on the selected features, as well as, histopathological type (adeno vs squamous), age at the start of the treatment, and extent of metastatic disease ( < 5, 5–10, or > 10 metastasis) Results: The selection resulted in three textural features derived from a Laplacian of Gaussian (LoG): regions dissimilarity (GLRLM_rlnun), entropy (GLSZM_ze), and uniformity. The resulting model was significant (p = 0.005). Both regions dissimilarity (HR = 0.11, 95% CI 0.03–0.46, p = 0.002) and entropy (HR = 0.20, 95% CI 0.06–0.67, p = 0.009) were significant predictors of OS. Subtype and disease extent were close to significance (p = 0.099) Conclusions: Results indicate that more heterogeneous tumors with irregular patterns of intensities showed better OS. The availability of CT scans makes Radiomics a potentially valuable adjunct to other clinical biomarkers. Further validation of our findings in larger cohorts are warranted