Neoadjuvant ipilimumab and nivolumab induces high pathologic response rates (pRRs) in clinical stage III nodal melanoma, and pathologic response is strongly associated with prolonged relapse-free... Show moreNeoadjuvant ipilimumab and nivolumab induces high pathologic response rates (pRRs) in clinical stage III nodal melanoma, and pathologic response is strongly associated with prolonged relapse-free survival (RFS). The PRADO extension cohort of the OpACIN-neo trial (NCT02977052) addressed the feasibility and effect on clinical outcome of using pathologic response after neoadjuvant ipilimumab and nivolumab as a criterion for further treatment personalization. In total, 99 patients with clinical stage IIIb-d nodal melanoma were included and treated with 6 weeks of neoadjuvant ipilimumab 1 mg kg(-1) and nivolumab 3 mg kg(-1). In patients achieving major pathologic response (MPR, <= 10% viable tumor) in their index lymph node (ILN, the largest lymph node metastasis at baseline), therapeutic lymph node dissection (TLND) and adjuvant therapy were omitted. Patients with pathologic partial response (pPR; >10 to <= 50% viable tumor) underwent TLND only, whereas patients with pathologic non-response (pNR; >50% viable tumor) underwent TLND and adjuvant systemic therapy +/- synchronous radiotherapy. Primary objectives were confirmation of pRR (ILN, at week 6) of the winner neoadjuvant combination scheme identified in OpACIN-neo; to investigate whether TLND can be safely omitted in patients achieving MPR; and to investigate whether RFS at 24 months can be improved for patients achieving pNR. ILN resection and ILN-response-tailored treatment were feasible. The pRR was 72%, including 61% MPR. Grade 3-4 toxicity within the first 12 weeks was observed in 22 (22%) patients. TLND was omitted in 59 of 60 patients with MPR, resulting in significantly lower surgical morbidity and better quality of life. The 24-month relapse-free survival and distant metastasis-free survival rates were 93% and 98% in patients with MPR, 64% and 64% in patients with pPR, and 71% and 76% in patients with pNR, respectively. These findings provide a strong rationale for randomized clinical trials testing response-directed treatment personalization after neoadjuvant ipilimumab and nivolumab. Show less
IMPORTANCE Neoadjuvant checkpoint inhibition in patients with high-risk stage III melanoma shows high pathologic response rates associated with a durable relapse-free survival. Whether a... Show moreIMPORTANCE Neoadjuvant checkpoint inhibition in patients with high-risk stage III melanoma shows high pathologic response rates associated with a durable relapse-free survival. Whether a therapeutic lymph node dissection (TLND) can be safely omitted when a major pathologic response in the largest lymph node metastasis at baseline (index lymph node; ILN) is obtained is currently being investigated. A previous small pilot study (n = 12) showed that the response in the ILN may be representative of the pathologic response in the entire TLND specimen.OBJECTIVE To assess the concordance of response between the ILN and the total lymph node bed in a larger clinical trial population.DESIGN, SETTING, AND PARTICIPANTS Retrospective pathologic response analysis of a multicenter clinical trial population of patients from the randomized Study to Identify the Optimal Adjuvant Combination Scheme of Ipilimumab and Nivolumab in Melanoma Patients (OpACIN) and Optimal Neo-Adjuvant Combination Scheme of Ipilimumab and Nivolumab (OpACIN-neo) trials. Included patients were treated with 6 weeks neoadjuvant ipilimumab plus nivolumab. Patient inclusion into the trials was conducted from August 12, 2015, to October 24, 2016 (OpACIN), and November 24, 2016, and June 28, 2018 (OpACIN-neo). Data were analyzed from April 1, 2020, to August 31, 2021.MAIN OUTCOMES AND MEASURES Concordance of the pathologic response between the ILN and the TLND tumor bed. The pathologic response of the ILN was retrospectively assessed according to the International Neoadjuvant Melanoma Consortium criteria and compared with the pathologic response of the entire TLND specimen.RESULTS A total of 82 patients treated with neoadjuvant ipilimumab and nivolumab followed by TLND (48 [59%] were male; median age, 58.5 [range, 18-80] years) were included. The pathologic response in the ILN was concordant with the entire TLND specimen response in 81 of 82 patients (99%) and in 79 of 82 patients (96%) concordant when comparing the ILN response with the response in every individual lymph node. In the single patient with a discordant response, the ILN response (20% viable tumor, partial pathologic response) underestimated the entire TLND specimen response (5% viable, near-complete pathologic response). Two other patients each had 1 small nonindex node that contained 80% viable tumor (pathologic nonresponse) whereas all other lymph nodes (including the ILN) showed a partial pathologic response. In these 2 patients, the risk of regional relapse might potentially have been increased if TLND had been omitted.CONCLUSIONS AND RELEVANCE The results of this study suggest that the pathologic response of the ILN may be considered a reliable indicator of the entire TLND specimen response and may support the ILN response-directed omission of TLND in a prospective trial. Show less
Neoadjuvant ipilimumab and nivolumab induces high pathologic response rates (pRRs) in clinical stage III nodal melanoma, and pathologic response is strongly associated with prolonged relapse-free... Show moreNeoadjuvant ipilimumab and nivolumab induces high pathologic response rates (pRRs) in clinical stage III nodal melanoma, and pathologic response is strongly associated with prolonged relapse-free survival (RFS). The PRADO extension cohort of the OpACIN-neo trial ( NCT02977052 ) addressed the feasibility and effect on clinical outcome of using pathologic response after neoadjuvant ipilimumab and nivolumab as a criterion for further treatment personalization. In total, 99 patients with clinical stage IIIb-d nodal melanoma were included and treated with 6 weeks of neoadjuvant ipilimumab 1 mg kg-1 and nivolumab 3 mg kg-1. In patients achieving major pathologic response (MPR, ≤10% viable tumor) in their index lymph node (ILN, the largest lymph node metastasis at baseline), therapeutic lymph node dissection (TLND) and adjuvant therapy were omitted. Patients with pathologic partial response (pPR; >10 to ≤50% viable tumor) underwent TLND only, whereas patients with pathologic non-response (pNR; >50% viable tumor) underwent TLND and adjuvant systemic therapy ± synchronous radiotherapy. Primary objectives were confirmation of pRR (ILN, at week 6) of the winner neoadjuvant combination scheme identified in OpACIN-neo; to investigate whether TLND can be safely omitted in patients achieving MPR; and to investigate whether RFS at 24 months can be improved for patients achieving pNR. ILN resection and ILN-response-tailored treatment were feasible. The pRR was 72%, including 61% MPR. Grade 3-4 toxicity within the first 12 weeks was observed in 22 (22%) patients. TLND was omitted in 59 of 60 patients with MPR, resulting in significantly lower surgical morbidity and better quality of life. The 24-month relapse-free survival and distant metastasis-free survival rates were 93% and 98% in patients with MPR, 64% and 64% in patients with pPR, and 71% and 76% in patients with pNR, respectively. These findings provide a strong rationale for randomized clinical trials testing response-directed treatment personalization after neoadjuvant ipilimumab and nivolumab. Show less
As a subset of advanced melanoma patients derive long-term benefit from anti-PD-1 therapy, early identification of non-responsiveness would enable an early switch to next line therapies. This study... Show moreAs a subset of advanced melanoma patients derive long-term benefit from anti-PD-1 therapy, early identification of non-responsiveness would enable an early switch to next line therapies. This study assessed if an early increase in S100B or lactate dehydrogenase (LDH) could be predictive for non-responsiveness to anti-PD-1. We retrospectively analysed advanced melanoma patients treated with anti-PD-1 monotherapy. Serum S100B and LDH levels were measured at baseline and before every infusion. Non-response was defined as progression or death at 6 months. Marker cut-offs were defined based on > 95% specificity and feasibility in clinical practice. For validation an independent cohort was analysed. In total, 313 patients were included (166 patients in training cohort, 147 patients in validation cohort). Increase of > 50% in LDH or > 100% in S100B above upper limit of normal at week 6 compared to baseline was determined as criterion to positively test for non-responsiveness. In the validation cohort, obtained specificity of the combination test was > 95% with a positive predictive value of 82%; obtained sensitivity was lower (21%), with a negative predictive value of 55%. Early increase in S100B or LDH is a strong parameter for non-responsiveness to anti-PD-1 in advanced melanoma. Prospective confirmation is needed before clinical implementation. Show less
Background: Guidelines for pathological evaluation of neoadjuvant specimens and pathological response categories have been developed by the International Neoadjuvant Melanoma Consortium (INMC). As... Show moreBackground: Guidelines for pathological evaluation of neoadjuvant specimens and pathological response categories have been developed by the International Neoadjuvant Melanoma Consortium (INMC). As part of the Optimal Neo-adjuvant Combination Scheme of Ipilimumab and Nivolumab (OpACIN-neo) clinical trial of neoadjuvant combination anti-programmed cell death protein 1/anti-cytotoxic T-Iymphocyte-associated protein 4 immunotherapy for stage III melanoma, we sought to determine interobserver reproducibility of INMC histopathological assessment principles, identify specific tumour bed histopathological features of immunotherapeutic response that correlated with recurrence and relapse-free survival (RFS) and evaluate proposed INMC pathological response categories for predicting recurrence and RFS.Patients and methods: Clinicopathological characteristics of lymph node dissection specimens of 83 patients enrolled in the OpACIN-neo clinical trial were evaluated. Two methods of assessing histological features of immunotherapeutic response were evaluated: the previously described immune-related pathologic response (irPR) score and our novel immunotherapeutic response score (ITRS). For a subset of cases (n = 29), cellular composition of the tumour bed was analysed by flow cytometry.Results: There was strong interobserver reproducibility in assessment of pathological response (kappa = 0.879) and percentage residual viable melanoma (intraclass correlation coefficient = 0.965). The immunotherapeutic response subtype with high fibrosis had the strongest association with lack of recurrence (P = 0.008) and prolonged RFS (P = 0.019). Amongst patients with criteria for pathological non-response (pNR, >50% viable tumour), all who recurred had >= 70% viable melanoma. Higher ITRS and irPR scores correlated with lack of recurrence in the entire cohort (P = 0.002 and P <= 0.0001). The number of B lymphocytes was significantly increased in patients with a high fibrosis subtype of treatment response (P = 0.046).Conclusions: There is strong reproducibility for assessment of pathological response using INMC criteria. Immunotherapeutic response of fibrosis subtype correlated with improved RFS, and may represent a biomarker. Potential B-cell contribution to fibrosis development warrants further study. Reclassification of pNR to a threshold of >= 70% viable melanoma and incorporating additional criteria of <10% fibrosis subtype of response may identify those at highest risk of recurrence, but requires validation. Show less
Background: Patients with synchronous clinical stage III melanoma can present with primary melanoma lesions, locally recurrent melanoma or in-transit metastases. Neoad-juvant ipilimumab plus... Show moreBackground: Patients with synchronous clinical stage III melanoma can present with primary melanoma lesions, locally recurrent melanoma or in-transit metastases. Neoad-juvant ipilimumab plus nivolumab induces high pathologic response rates and an impressive relapse-free survival in patients with nodal macroscopic stage III melanoma. Whether primary site melanoma and in-transit metastases respond similarly to lymph node metastases with neoadjuvant immunotherapy is largely unknown. Such data would clarify whether surgical excision of these melanoma lesions should be performed before neoadjuvant therapy or whether it could be deferred and performed in conjunction with lymphadenectomy following neoadjuvant immunotherapy. Patients: Patients with synchronous clinical stage III melanoma were identified from the OpA-CIN, OpACIN-neo and PRADO neoadjuvant trials, where all patients were treated with ipi-limumab plus nivolumab. An additional case treated outside those clinical trials was included. Results: Seven patients were identified; six patients had a concordant response in primary site melanoma lesions or in-transit metastasis and the lymph node metastases. One patient had concordant progression in both the primary and nodal tumour lesions and developed stage IV disease during neoadjuvant treatment, and thus, no resection was performed. Conclusion: Pathologic response following neoadjuvant ipilimumab plus nivolumab in pri-mary site melanoma lesions or in-transit metastasis is concordant with a response in the lymph node metastases, indicating that there may be no need to perform upfront surgery to these melanoma lesions prior to neoadjuvant treatment. (c) 2021 Elsevier Ltd. All rights reserved. Show less
Background: Patients with synchronous clinical stage III melanoma can present with primary melanoma lesions, locally recurrent melanoma or in-transit metastases. Neoadjuvant ipilimumab plus... Show moreBackground: Patients with synchronous clinical stage III melanoma can present with primary melanoma lesions, locally recurrent melanoma or in-transit metastases. Neoadjuvant ipilimumab plus nivolumab induces high pathologic response rates and an impressive relapse-free survival in patients with nodal macroscopic stage III melanoma. Whether primary site melanoma and in-transit metastases respond similarly to lymph node metastases with neoadjuvant immunotherapy is largely unknown. Such data would clarify whether surgical excision of these melanoma lesions should be performed before neoadjuvant therapy or whether it could be deferred and performed in conjunction with lymphadenectomy following neoadjuvant immunotherapy.Patients: Patients with synchronous clinical stage III melanoma were identified from the OpACIN, OpACIN-neo and PRADO neoadjuvant trials, where all patients were treated with ipilimumab plus nivolumab. An additional case treated outside those clinical trials was included.Results: Seven patients were identified; six patients had a concordant response in primary site melanoma lesions or in-transit metastasis and the lymph node metastases. One patient had concordant progression in both the primary and nodal tumour lesions and developed stage IV disease during neoadjuvant treatment, and thus, no resection was performed.Conclusion: Pathologic response following neoadjuvant ipilimumab plus nivolumab in primary site melanoma lesions or in-transit metastasis is concordant with a response in the lymph node metastases, indicating that there may be no need to perform upfront surgery to these melanoma lesions prior to neoadjuvant treatment. Show less
Neoadjuvant ipilimumab plus nivolumab showed high pathologic response rates (pRRs) in patients with macroscopic stage III melanoma in the phase 1b OpACIN () and phase 2 OpACIN-neo () studies(1,2).... Show moreNeoadjuvant ipilimumab plus nivolumab showed high pathologic response rates (pRRs) in patients with macroscopic stage III melanoma in the phase 1b OpACIN () and phase 2 OpACIN-neo () studies(1,2). While the results are promising, data on the durability of these pathologic responses and baseline biomarkers for response and survival were lacking. After a median follow-up of 4 years, none of the patients with a pathologic response (n = 7/9 patients) in the OpACIN study had relapsed. In OpACIN-neo (n = 86), the 2-year estimated relapse-free survival was 84% for all patients, 97% for patients achieving a pathologic response and 36% for nonresponders (P < 0.001). High tumor mutational burden (TMB) and high interferon-gamma-related gene expression signature score (IFN-gamma score) were associated with pathologic response and low risk of relapse; pRR was 100% in patients with high IFN-gamma score/high TMB; patients with high IFN-gamma score/low TMB or low IFN-gamma score/high TMB had pRRs of 91% and 88%; while patients with low IFN-gamma score/low TMB had a pRR of only 39%. These data demonstrate long-term benefit in patients with a pathologic response and show the predictive potential of TMB and IFN-gamma score. Our findings provide a strong rationale for a randomized phase 3 study comparing neoadjuvant ipilimumab plus nivolumab versus standard adjuvant therapy with antibodies against the programmed cell death protein-1 (anti-PD-1) in macroscopic stage III melanoma. Show less
Background: Checkpoint inhibitors have changed overall survival for patients with advanced melanoma. However, there is a lack of data on health-related quality of life (HRQoL) of long-term advanced... Show moreBackground: Checkpoint inhibitors have changed overall survival for patients with advanced melanoma. However, there is a lack of data on health-related quality of life (HRQoL) of long-term advanced melanoma survivors, years after treatment. Therefore, we evaluated HRQoL in long-term advanced melanoma survivors and compared the study outcomes with matched controls without cancer.Material and methods: Ipilimumab-treated advanced melanoma survivors without evidence of disease and without subsequent systemic therapy for a minimum of two years following last administration of ipilimumab were eligible for this study. The European Organization for Research and Treatment of Cancer quality of life questionnaire Core 30 (EORTC QLQ-C30), the Multidimensional Fatigue Inventory (MFI), the Hospital Anxiety and Depression Scale (HADS), and the Functional Assessment of Cancer Therapy-Melanoma questionnaire (FACT-M) were administered. Controls were individually matched for age, gender, and educational status. Outcomes of survivors and controls were compared using generalized estimating equations, and differences were interpreted as clinically relevant according to published guidelines.Results: A total of 89 survivors and 265 controls were analyzed in this study. After a median follow-up of 39 (range, 17-121) months, survivors scored significantly lower on physical (83.7vs. 89.8, difference (diff) = -5.80,p=.005), role (83.5vs.90, diff = -5.97,p=.02), cognitive (83.7vs.91.9, diff = -8.05,p=.001), and social functioning (86.5vs.95.1, diff = -8.49,p= <.001) and had a higher symptom burden of fatigue (23.0vs.15.5, diff = 7.48,p=.004), dyspnea (13.3vs.6.7, diff = 6.47p=.02), diarrhea (7.9vs.4.0, diff = 3.78,p=.04), and financial impact (10.5vs.2.5, diff = 8.07,p=.001) than matched controls. Group differences were indicated as clinically relevant.Discussion: Compared to matched controls, long-term advanced melanoma survivors had overall worse functioning scores, more physical symptoms, and financial difficulties. These data may contribute to the development of appropriate survivorship care. Show less
Approximately, 50% of patients with uveal melanoma develop distant metastasis for which no standard therapy is established. In contrast to cutaneous melanoma, the anti-CTLA-4 antibody ipilimumab... Show moreApproximately, 50% of patients with uveal melanoma develop distant metastasis for which no standard therapy is established. In contrast to cutaneous melanoma, the anti-CTLA-4 antibody ipilimumab showed no clinical activity in uveal melanoma. Liver directed therapies improve local control, but fail to show overall survival (OS) benefit. Preclinical experiments demonstrated that radiofrequency ablation (RFA) induced durable responses in combination with anti-CTLA-4. The aim of this phase Ib/II study was to assess safety and efficacy of RFA plus ipilimumab in uveal melanoma. Patients underwent RFA of one liver lesion and subsequently received four courses ipilimumab 0.3, 3 or 10 mg/kg every 3 weeks in a 3 + 3 design. Primary endpoints were safety in terms of dose limiting toxicities per cohort to define the recommended phase II dose (RP2D) in the phase Ib part and confirmed the objective response rate and disease control rate (DCR) of non-RFA lesions in the phase II part. Secondary endpoints were progression-free survival (PFS) and OS. Ipilimumab 10 mg/kg + RFA was initially defined as the RP2D. However, after 19 patients, the study was amended to adjust the RP2D to ipilimumab 3 mg/kg + RFA, because 47% of patients treated with 10 mg/kg had developed grade 3 colitis. In the 3 mg/kg cohort, also 19 patients have been treated. Immunotherapy-related grade >= 3 adverse events were observed in 53% of patients in the 10 mg/kg cohort versus 32% in the 3 mg/kg cohort. No confirmed objective responses were observed; the confirmed DCR was 5% in the 10 mg/kg cohort and 11% in the 3 mg/kg cohort. Median PFS was 3 months and comparable for both cohorts, median OS was 14.2 months for the 10 mg/kg cohort versus 9.7 months for the 3 mg/kg cohort. Combining RFA with ipilimumab 3 mg/kg was well tolerated, but showed very limited clinical activity in uveal melanoma. Show less
Multiomic profiling of several cohorts of patients treated with immune checkpoint blockade highlights the presence and potential role of B cells and tertiary lymphoid structures in promoting... Show moreMultiomic profiling of several cohorts of patients treated with immune checkpoint blockade highlights the presence and potential role of B cells and tertiary lymphoid structures in promoting therapy response.Treatment with immune checkpoint blockade (ICB) has revolutionized cancer therapy. Until now, predictive biomarkers(1-10) and strategies to augment clinical response have largely focused on the T cell compartment. However, other immune subsets may also contribute to anti-tumour immunity(11-15), although these have been less well-studied in ICB treatment(16). A previously conducted neoadjuvant ICB trial in patients with melanoma showed via targeted expression profiling(17) that B cell signatures were enriched in the tumours of patients who respond to treatment versus non-responding patients. To build on this, here we performed bulk RNA sequencing and found that B cell markers were the most differentially expressed genes in the tumours of responders versus non-responders. Our findings were corroborated using a computational method (MCP-counter(18)) to estimate the immune and stromal composition in this and two other ICB-treated cohorts (patients with melanoma and renal cell carcinoma). Histological evaluation highlighted the localization of B cells within tertiary lymphoid structures. We assessed the potential functional contributions of B cells via bulk and single-cell RNA sequencing, which demonstrate clonal expansion and unique functional states of B cells in responders. Mass cytometry showed that switched memory B cells were enriched in the tumours of responders. Together, these data provide insights into the potential role of B cells and tertiary lymphoid structures in the response to ICB treatment, with implications for the development of biomarkers and therapeutic targets. Show less
Background The profound disparity in response to immune checkpoint blockade (ICB) by cutaneous melanoma (CM) and uveal melanoma (UM) patients is not well understood. Therefore, we characterized... Show moreBackground The profound disparity in response to immune checkpoint blockade (ICB) by cutaneous melanoma (CM) and uveal melanoma (UM) patients is not well understood. Therefore, we characterized metastases of CM and UM from the same metastatic site (liver), in order to dissect the potential underlying mechanism in differential response on ICB. Methods Tumor liver samples from CM (n=38) and UM (n=28) patients were analyzed at the genomic (whole exome sequencing), transcriptional (RNA sequencing) and protein (immunohistochemistry and GeoMx Digital Spatial Profiling) level. Results Comparison of CM and UM metastases from the same metastatic site revealed that, although originating from the same melanocyte lineage, CM and UM differed in somatic mutation profile, copy number profile, tumor mutational burden (TMB) and consequently predicted neoantigens. A higher melanin content and higher expression of the melanoma differentiation antigen MelanA was observed in liver metastases of UM patients. No difference in B2M and human leukocyte antigen-DR (HLA-DR) expression was observed. A higher expression of programmed cell death ligand 1 (PD-L1) was found in CM compared with UM liver metastases, although the majority of CM and UM liver metastases lacked PD-L1 expression. There was no difference in the extent of immune infiltration observed between CM and UM metastases, with the exception of a higher expression of CD163 (p<0.0001) in CM liver samples. While the extent of immune infiltration was similar for CM and UM metastases, the ratio of exhausted CD8 T cells to cytotoxic T cells, to total CD8 T cells and to Th1 cells, was significantly higher in UM metastases. Conclusions While TMB was different between CM and UM metastases, tumor immune infiltration was similar. The greater dependency on PD-L1 as an immune checkpoint in CM and the identification of higher exhaustion ratios in UM may both serve as explanations for the difference in response to ICB. Consequently, in order to improve current treatment for metastatic UM, reversal of T cell exhaustion beyond programmed cell death 1 blockade should be considered. Show less
Unprecedented successes regarding cancer immunotherapy have been achieved, in which therapeutic agents are used to target immune cells rather than cancer cells. The most effective immunotherapy to... Show moreUnprecedented successes regarding cancer immunotherapy have been achieved, in which therapeutic agents are used to target immune cells rather than cancer cells. The most effective immunotherapy to date is the group of immune checkpoint inhibitors (CPI), targeting, for example, cytotoxic T-lymphocyte-associated antigen 4 (CTLA-4) or programmed cell death protein (PD-1). TThe combination of these therapies (anti-PD-1 with anti-CTLA-4) induces high response rates, and seem to be increased further when applied in early-stage disease. However, combined CTLA-4 plus PD-1 blockade causes frequent high-grade immune-related adverse events (irAE). To date, research on biological mechanism of irAEs is scarce and no widely accepted biomarkers predicting onset of severe irAEs have been identified. The similarity of irAEs to autoimmune disorders fuels the hypothesis that irAEs may be linked to susceptible genetic loci related to various autoimmune diseases. In this review, we extensively searched for susceptible loci associated with various autoimmune diseases, and pooled them in groups most likely to be associated with CPI-induced irAEs. These sets could be used in future research on predicting irAEs and guide physicians in a more refined and personal manner. Show less
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.... Show moreIntroduction: 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. Show less
