Artificial intelligence in immunotherapy PET/SPECT imaging.

OBJECTIVE: Immunotherapy has dramatically altered the therapeutic landscape for oncology, but more research is needed to identify patients who are likely to achieve durable clinical benefit and those who may develop unacceptable side effects. We investigated the role of artificial intelligence in PET/SPECT-guided approaches for immunotherapy-treated patients. METHODS: We performed a scoping review of MEDLINE, CENTRAL, and Embase databases using key terms related to immunotherapy, PET/SPECT imaging, and AI/radiomics through October 12, 2022. RESULTS: Of the 217 studies identified in our literature search, 24 relevant articles were selected. The median (interquartile range) sample size of included patient cohorts was 63 (157). Primary tumors of interest were lung (n = 14/24, 58.3%), lymphoma (n = 4/24, 16.7%), or melanoma (n = 4/24, 16.7%). A total of 28 treatment regimens were employed, including anti-PD-(L)1 (n = 13/28, 46.4%) and anti-CTLA-4 (n = 4/28, 14.3%) monoclonal antibodies. Predictive models were built from imaging features using univariate radiomics (n = 7/24, 29.2%), radiomics (n = 12/24, 50.0%), or deep learning (n = 5/24, 20.8%) and were most often used to prognosticate (n = 6/24, 25.0%) or describe tumor phenotype (n = 5/24, 20.8%). Eighteen studies (75.0%) performed AI model validation. CONCLUSION: Preliminary results suggest broad potential for the application of AI-guided immunotherapy management after further validation of models on large, prospective, multicenter cohorts. CLINICAL RELEVANCE STATEMENT: This scoping review describes how artificial intelligence models are built to make predictions based on medical imaging and explores their application specifically in the PET and SPECT examination of immunotherapy-treated cancers. KEY POINTS: • Immunotherapy has drastically altered the cancer treatment landscape but is known to precipitate response patterns that are not accurately accounted for by traditional imaging methods. • There is an unmet need for better tools to not only facilitate in-treatment evaluation but also to predict, a priori, which patients are likely to achieve a good response with a certain treatment as well as those who are likely to develop side effects. • Artificial intelligence applied to PET/SPECT imaging of immunotherapy-treated patients is mainly used to make predictions about prognosis or tumor phenotype and is built from baseline, pre-treatment images. Further testing is required before a true transition to clinical application can be realized.

Emerging and Evolving Concepts in Cancer Immunotherapy Imaging.

Criteria based on measurements of lesion diameter at CT have guided treatment with historical therapies due to the strong association between tumor size and survival. Clinical experience with immune checkpoint modulators shows that editing immune system function can be effective in various solid tumors. Equally, novel immune-related phenomena accompany this novel therapeutic paradigm. These effects of immunotherapy challenge the association of tumor size with response or progression and include risks and adverse events that present new demands for imaging to guide treatment decisions. Emerging and evolving approaches to immunotherapy highlight further key issues for imaging evaluation, such as dissociated response following local administration of immune checkpoint modulators, pseudoprogression due to immune infiltration in the tumor environment, and premature death due to hyperprogression. Research that may offer tools for radiologists to meet these challenges is reviewed. Different modalities are discussed, including immuno-PET, as well as new applications of CT, MRI, and fluorodeoxyglucose PET, such as radiomics and imaging of hematopoietic tissues or anthropometric characteristics. Multilevel integration of imaging and other biomarkers may improve clinical guidance for immunotherapies and provide theranostic opportunities.

A machine-learning-based combination of criteria to detect bladder cancer lymph node metastasis on [18F]FDG PET/CT: a pathology-controlled study.

OBJECTIVES: Initial pelvic lymph node (LN) staging is pivotal for treatment planification in patients with muscle-invasive bladder cancer (MIBC), but [18F]FDG PET/CT provides insufficient and variable diagnostic performance. We aimed to develop and validate a machine-learning-based combination of criteria on [18F]FDG PET/CT to accurately identify pelvic LN involvement in bladder cancer patients. METHODS: Consecutive patients with localized MIBC who performed preoperative [18F]FDG PET/CT between 2010 and 2017 were retrospectively assigned to training (n = 129) and validation (n = 44) sets. The reference standard was the pathological status after extended pelvic LN dissection. In the training set, a random forest algorithm identified the combination of criteria that best predicted LN status. The diagnostic performances (AUC) and interrater agreement of this combination of criteria were compared to a consensus of experts. RESULTS: The overall prevalence of pelvic LN involvement was 24% (n = 41/173). In the training set, the top 3 features were derived from pelvic LNs (SUVmax of the most intense LN, and product of diameters of the largest LN) and primary bladder tumor (product of diameters). In the validation set, diagnostic performance did not differ significantly between the combination of criteria (AUC = 0.59 95%CI [0.43-0.73]) and the consensus of experts (AUC = 0.64 95%CI [0.48-0.78], p = 0.54). The interrater agreement was equally good with Κ = 0.66 for both. CONCLUSION: The developed machine-learning-based combination of criteria performs as well as a consensus of experts to detect pelvic LN involvement on [18F]FDG PET/CT in patients with MIBC. KEY POINTS: • The developed machine-learning-based combination of criteria performs as well as experts to detect pelvic LN involvement on [18F]FDG PET/CT in patients with muscle-invasive bladder cancer. • The top 3 features to predict LN involvement were the SUVmax of the most intense LN, the product of diameters of the largest LN, and the product of diameters of the primary bladder tumor.

Ethnic diversity in treatment response for colorectal cancer: proof of concept for radiomics-driven enrichment trials.

BACKGROUND: Several barriers hamper recruitment of diverse patient populations in multicenter clinical trials which determine efficacy of new systemic cancer therapies. PURPOSE: We assessed if quantitative analysis of computed tomography (CT) scans of metastatic colorectal cancer (mCRC) patients using imaging features that predict overall survival (OS) can unravel the association between ethnicity and efficacy. METHODS: We retrospectively analyzed CT images from 1584 mCRC patients in two phase III trials evaluating FOLFOX ± panitumumab (n = 331, 350) and FOLFIRI ± aflibercept (n = 437, 466) collected from August 2006 to March 2013. Primary and secondary endpoints compared RECIST1.1 response at month-2 and delta tumor volume at month-2, respectively. An ancillary study compared imaging phenotype using a peer-reviewed radiomics-signature combining 3 imaging features to predict OS landmarked from month-2. Analysis was stratified by ethnicity. RESULTS: In total, 1584 patients were included (mean age, 60.25 ± 10.57 years; 969 men). Ethnicity was as follows: African (n = 50, 3.2%), Asian (n = 66, 4.2%), Caucasian (n = 1413, 89.2%), Latino (n = 27, 1.7%), Other (n = 28, 1.8%). Overall baseline tumor volume demonstrated Africans and Caucasians had more advanced disease (p < 0.001). Ethnicity was associated with treatment response. Response per RECIST1.1 at month-2 was distinct between ethnicities (p = 0.048) with higher response rate (55.6%) in Latinos. Overall delta tumor volume at month-2 demonstrated that Latino patients more likely experienced response to treatment (p = 0.021). Radiomics phenotype was also distinct in terms of tumor radiomics heterogeneity (p = 0.023). CONCLUSION: This study highlights how clinical trials that inadequately represent minority groups may impact associated translational work. In appropriately powered studies, radiomics features may allow us to unravel associations between ethnicity and treatment efficacy, better elucidate mechanisms of resistance, and promote diversity in trials through predictive enrichment. CLINICAL RELEVANCE STATEMENT: Radiomics could promote clinical trial diversity through predictive enrichment, hence benefit to historically underrepresented racial/ethnic groups that may respond variably to treatment due to socioeconomic factors and built environment, collectively referred to as social determinants of health. KEY POINTS: •Findings indicate ethnicity was associated with treatment response across all 3 endpoints. First, response per RECIST1.1 at month-2 was distinct between ethnicities (p = 0.048) with higher response rate (55.6%) in Latinos. •Second, the overall delta tumor volume at month-2 demonstrated that Latino patients were more likely to experience response to treatment (p = 0.021). Radiomics phenotype was also distinct in terms of tumor radiomics heterogeneity (p = 0.023).

Prognostic factors of the synovial sarcoma of the extremities: imaging does matter.

OBJECTIVES: Synovial sarcomas (SS) of the extremities are rare soft tissue sarcomas that are more common in young adults. We deciphered the imaging phenotype of SS with the aim to determine if imaging could provide an incremental value to currently known prognostic factors (PF)-age and histological grade-to predict long-term overall survival (OS). METHODS: This retrospective multicenter study included consecutive pediatric and adult patients with synovial sarcomas of the extremities from December 2002 to August 2020. Inclusion criteria were (i) a follow-up greater than 5 years and (ii) available pre-therapeutic MRI. A subset analysis included MRI and CT-scan. Clinical, pathological, and imaging variables were collected in all patients. The primary endpoint was to evaluate the association of these variables with OS using univariate and multivariate Cox regressions. RESULTS: Out of 428 patients screened for eligibility, 98 patients (mean age: 37.1 ± 15.2 years) were included (MRI: n = 98/98, CT scan: n = 34/98; 35%). The median OS was 75.25 months (IQR = 55.50-109.12) and thirty-six patients (n = 36/98;37%) died during follow-up. The recurrence rate was 12.2% (n =12/98). SS lesions were mostly grade 2 (57/98; 58%). On MRI, SS had a mean long-axis diameter of 67.5 ± 38.3 mm. On CT scan, 44% (15/34) were calcified. Grade (hazard ratio [HR] = 2.71; 95%CI = 1.30-5.66; p = 0.008), size of the lesions evaluated on MRI (HR = 1.02; 95% CI = 1.01-1.03; p < 0.001), and calcifications on CT scan (HR = 0.10; 95% CI = 0.02-0.50; p = 0.005) were independent PF of OS. CONCLUSIONS: This study demonstrated that imaging biomarkers can be used to predict long-term outcome in patients with SS. Strikingly, the presence of calcifications on CT scan is associated with favorable outcome and provides an incremental value over existing PF such as age, grade, and size. KEY POINTS: • Beyond its diagnostic value, MRI is a pre-operative prognostic tool in synovial sarcomas of the extremities since the size of the lesion is an important prognostic factor. • Calcifications on CT scans are independently and significantly associated with prolonged overall survival.

Interpretation of 2-[18F]FDG PET/CT in Hodgkin lymphoma patients treated with immune checkpoint inhibitors.

The development of immunotherapy has revolutionized cancer treatment, improving the outcome and survival of many patients. Immune checkpoint inhibitors (ICIs), the most common form of immunotherapy, use antibodies to restore T-cells' anti-tumor activity. Immune checkpoint inhibitors are gaining ground in the therapeutic strategy across various cancers. Although widely used in solid tumors, ICIs have shown remarkable efficacy in patients with Hodgkin lymphoma. 2-[18F]Fluoro-2-deoxy-D-glucose (FDG)-positron emission tomography (PET)/CT is the gold standard to stage and monitor responses in Hodgkin lymphoma. This article reviewed the use of 2-[18F]FDG-PET/CT in patients with Hodgkin lymphoma treated with ICI, focusing on image interpretation for response monitoring and detecting adverse events. Key Points • Immune checkpoint inhibitors have dramatically improved the outcome of patients with cancer. Their mechanisms of action induce inflammatory processes that might translate into a high 2-[18F]FDG uptake visible on 2-[18F]FDG-PET/CT, requiring an adaptation of the evaluation criteria. • PET readers should be aware of new patterns of response observed with immunotherapy in assessing treatment response in HL patients. • -[18F]FDG-PET/CT has an unparalleled ability of assessing tumor response, visualizing signs of immune activation as well as immune-related adverse events in a one-stop-shop examination.

Predicting death or recurrence of portal hypertension symptoms after TIPS procedures.

BACKGROUND: Accurate prediction of portal hypertension recurrence after transjugular intrahepatic portosystemic shunt (TIPS) placement will improve clinical decision-making. PURPOSE: To evaluate if perioperative variables could predict disease-free survival (DFS) in cirrhotic patients with portal hypertension (PHT) treated with TIPS. MATERIALS AND METHODS: We recruited 206 cirrhotic patients with PHT treated with TIPS, randomly assigned to training (n = 138) and validation (n = 68) sets. We recorded 7 epidemiological, 4 clinical, and 9 radiological variables. TIPS-distal end positioning (TIPS-DEP) measured the distance between the distal end of the stent and the hepatocaval junction on contrast-enhanced CT scans. In the training set, the signature was defined as the random forest for survival algorithm achieving the lowest error rate for the prediction of DFS which was landmarked 4 weeks after the TIPS procedure. In the training set, a simple to use scoring system was derived from variables selected by the signature. The primary endpoint was to assess if TIPS-DEP was associated with DFS. The secondary endpoint was to validate the scoring system in the validation set. RESULTS: Overall, patients with TIPS-DEP ≥ 6 mm (n = 49) had a median DFS of 24.5 months vs. 72.8 months otherwise (n = 157, p = 0.004). In the training set, the scoring system was calculated by adding age ≥ 60 years old, Child-Pugh B or C, and TIPS-DEP ≥ 6 mm (1 point each) since the signature showed high DFS probability at 6.5 months post-landmark in patients that did not meet these criteria: 86%, 80%, and 78%, respectively. The hazard ratio [95 CI] between patients determined to be low-risk (< 2 points) and high-risk (≥ 2 points) was 2.30 [1.35-3.93] (p = 0.002) in the training set and 2.01 [0.94-4.32] (p = 0.072) in the validation set. CONCLUSION: TIPS-DEP is an actionable radiological biomarker which can be combined with age and Child-Pugh score to predict death or PHT symptom recurrence after TIPS procedure. KEY POINTS: • TIPS-DEP measurement was the third most important but only actionable variable for predicting DFS. • TIPS-DEP < 6 mm was associated with a DFS probability of 78% at 6.5 months post-landmark. • A simple scoring system calculated using age, Child-Pugh score, and TIPS-DEP predicted DFS after TIPS.

Reinventing radiation therapy with machine learning and imaging bio-markers (radiomics): State-of-the-art, challenges and perspectives.

Radiation therapy is a pivotal cancer treatment that has significantly progressed over the last decade due to numerous technological breakthroughs. Imaging is now playing a critical role on deployment of the clinical workflow, both for treatment planning and treatment delivery. Machine-learning analysis of predefined features extracted from medical images, i.e. radiomics, has emerged as a promising clinical tool for a wide range of clinical problems addressing drug development, clinical diagnosis, treatment selection and implementation as well as prognosis. Radiomics denotes a paradigm shift redefining medical images as a quantitative asset for data-driven precision medicine. The adoption of machine-learning in a clinical setting and in particular of radiomics features requires the selection of robust, representative and clinically interpretable biomarkers that are properly evaluated on a representative clinical data set. To be clinically relevant, radiomics must not only improve patients' management with great accuracy but also be reproducible and generalizable. Hence, this review explores the existing literature and exposes its potential technical caveats, such as the lack of quality control, standardization, sufficient sample size, type of data collection, and external validation. Based upon the analysis of 165 original research studies based on PET, CT-scan, and MRI, this review provides an overview of new concepts, and hypotheses generating findings that should be validated. In particular, it describes evolving research trends to enhance several clinical tasks such as prognostication, treatment planning, response assessment, prediction of recurrence/relapse, and prediction of toxicity. Perspectives regarding the implementation of an AI-based radiotherapy workflow are presented.

Comparing RECIST 1.1 and iRECIST in advanced melanoma patients treated with pembrolizumab in a phase II clinical trial.

OBJECTIVES: To compare tumor best overall response (BOR) by RECIST 1.1 and iRECIST, to explore the incidence of pseudoprogression in melanoma treated with pembrolizumab, and to assess the impact of pseudoprogression on overall survival (OS). METHODS: A total of 221 patients with locally advanced/unresectable melanoma who received pembrolizumab as part of KEYNOTE-002 trial were included in this study. Radiological assessment of imaging was centrally reviewed to assess tumor response. Incidence of discordance in BOR between RECIST 1.1 and iRECIST as well as rate of pseudoprogression were measured. OS of patients with pseudoprogression was compared with that of those with uncontrolled disease. RESULTS: Of the 221 patients in this cohort, 136 patients developed PD as per RECIST v1.1 and 78 patients with PD continued treatment and imaging beyond initial RECIST 1.1-defined PD. Among the 78 patients who continued therapy and imaging post-progression, RECIST 1.1 and iRECIST were discordant in 10 patients (12.8%) and pseudoprogression was encountered in 14 patients (17.9%). OS of patients with pseudoprogression was longer than that of patients with uncontrolled disease/true progression (29.9 months versus 8.0 months, p value < 0.001). CONCLUSIONS: Effectiveness of immunotherapy in clinical trials depends on the criterion used to assess tumor response (RECIST 1.1 vs iRECIST) with iRECIST being more appropriate to detect pseudoprogression and potentially prevent premature termination of effective therapy. Pseudoprogression was associated with improved OS in comparison with that of patients with uncontrolled disease. KEY POINTS: • Discordance between iRECIST and RECIST 1.1 was found in 12.8% of unresectable melanoma patients on pembrolizumab who continued therapy beyond initial RECIST 1.1-defined progression. • Pseudoprogression, captured with iRECIST, occurred in 17.9% and was significantly associated with improved overall survival in comparison with uncontrolled disease.

Performance of CT Compared with 18F-FDG PET in Predicting the Efficacy of Nivolumab in Relapsed or Refractory Hodgkin Lymphoma.

Background CT and fluorine 18 (18F) fluorodeoxyglucose (FDG) PET/CT performances following immune therapy are not well known in patients with relapsed or refractory Hodgkin lymphoma (RRHL). Purpose To compare CT and PET/CT for prognostic value of early response evaluation following nivolumab therapy. Materials and Methods This retrospective study included patients from 34 institutions who underwent early imaging response evaluation from July 2013 to April 2017. Three experienced readers classified imaging response by using Cheson et al and 2016 Lymphoma Response to Immunomodulatory Therapy Criteria as follows: complete (metabolic) response, partial (metabolic) response, stable disease or no metabolic response, or progressive (metabolic) disease. Primary CT and PET assessments were performed at a median of 2.0 months (interquartile range, 1.7-3.7 months) after nivolumab initiation. Kaplan-Meier analysis was used to determine the relationship of primary CT and PET assessment response categories to overall survival (OS). Agreements between primary and secondary imaging assessments were assessed by using κ analysis. Results A total of 45 patients (median age, 37 years; range, 18-77 years; 25 men) underwent a primary assessment using CT and PET/CT; 36 patients also underwent a subsequent assessment. Eleven patients (24%) died after a median follow-up of 21.2 months. CT and PET response categories were associated with OS (P = .03 for primary CT assessment; P = .02 for primary PET assessment). There was no pseudoprogression at primary CT and PET assessments. At the primary assessment, response categories by using CT were reclassified by using PET in 44% (20 of 45) of patients. Among these, 55% (11 of 20) were reclassified to complete metabolic response (complete metabolic response rate: 29% [13 of 45 patients] vs complete response rate: 4% [two of 45 patients]), with a 2-year OS probability of 100%. At the secondary assessment, complete response rate using CT increased to 17% (six of 36 patients), hence a better agreement with PET (κ = 0.78; P < .001). Conclusion Early CT and PET/CT at a median of 2 months after initiation of nivolumab predicted overall survival in relapsed or refractory Hodgkin lymphoma. Early PET detected additional patients with complete metabolic response. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Scott and Wang in this issue.

Prognostic 18F-FDG PET biomarkers in metastatic mucosal and cutaneous melanoma treated with immune checkpoint inhibitors targeting PD-1 and CTLA-4.

PURPOSE: To compare the prognostic value of imaging biomarkers derived from a quantitative analysis of baseline 18F-FDG-PET/CT in patients with mucosal melanoma (Muc-M) or cutaneous melanoma (Cut-M) treated with immune checkpoint inhibitors (ICIs). METHODS: In this retrospective monocentric study, we included 56 patients with non-resectable Muc-M (n = 24) or Cut-M (n = 32) who underwent baseline 18F-FDG-PET/CT before treatment with ICIs between 2011 and 2017. Parameters were extracted from (i) tumoral tissues: SUVmax, SUVmean, TMTV (total metabolic tumor volume), and TLG (total lesion glycolysis) and (ii) lymphoid tissues: BLR (bone marrow-to-liver SUVmax ratio) and SLR (spleen-to-liver SUVmax ratio). Association with survival and response was evaluated using Cox prediction models, Student's t tests, and Spearman's correlation respectively. p < 0.05 was considered significant. RESULTS: Majority of ICIs were anti-PD1 (92.9%, n = 52/56). All 18F-FDG-PET/CT were positive. Overall (Muc-M to Cut-M), ORR was 33%:42%, DCR was 56%:69%, median follow-up was 25.0:28.9 months, median PFS was 4.7:10.7 months, and median OS was 23.9:28.3 months. In Muc-M, increased tumor SUVmax was associated with shorter OS while it was not correlated with PFS, ORR, or DCR. In Cut-M, increased TMTV and increased BLR were independently associated with shorter OS, shorter PFS, and lower response (ORR, DCR). CONCLUSION: While all Muc-M and Cut-M were FDG avid, prognostic imaging biomarkers differed. For Muc-M patients treated with ICI, the only prognostic imaging biomarker was a high baseline maximal glycolytic activity (SUVmax), whereas for Cut-M patients, baseline metabolic tumor burden or bone marrow metabolism was negatively correlated to ICI response duration.

Baseline metabolic tumor burden on FDG PET/CT scans predicts outcome in advanced NSCLC patients treated with immune checkpoint inhibitors.

PURPOSE: We aimed to evaluate if imaging biomarkers on FDG PET are associated with clinical outcomes in patients with advanced non-small cell lung cancer (NSCLC) treated with immune checkpoint inhibitors (ICIs). METHODS: In this retrospective monocentric study, we included 109 patients with advanced NSCLC who underwent baseline FDG PET/CT before ICI initiation between July 2013 and September 2018. Clinical, biological (including dNLR = neutrophils/[leukocytes minus neutrophils]), pathological and PET parameters (tumor SUVmax, total metabolic tumor volume [TMTV]) were evaluated. A multivariate prediction model was developed using Cox models for progression-free survival (PFS) and overall survival (OS). The association between biomarkers on FDG PET/CT and disease clinical benefit (DCB) was tested using logistic regression. RESULTS: Eighty patients were eligible. Median follow-up was 11.6 months (95%CI 7.7-15.5). Sixty-four and 52 patients experienced progression and death, respectively. DCB was 40%. In multivariate analyses, TMTV > 75 cm3 and dNLR > 3 were associated with shorter OS (HR 2.5, 95%CI 1.3-4.7 and HR 3.3, 95%CI 1.6-6.4) and absence of DCB (OR 0.3, 95%CI 0.1-0.9 and OR 0.4, 95%CI 0.2-0.9). Unlike TMTV, dNLR was a significant prognostic factor for PFS (HR 1.9, 95%CI 1.1-3.3) along with anemia (HR 1.9, 95%CI 1.2-3.8). No association was observed between tumor SUVmax and PFS or OS. CONCLUSION: Baseline tumor burden (TMTV) on FDG PET/CT scans and inflammatory status (dNLR) were associated with poor OS and absence of DCB for ICI treatment in advanced NSCLC patients, unlike tumor SUVmax, and may be used together to improve the selection of appropriate candidates.

Radiomics machine-learning signature for diagnosis of hepatocellular carcinoma in cirrhotic patients with indeterminate liver nodules.

PURPOSE: To enhance clinician's decision-making by diagnosing hepatocellular carcinoma (HCC) in cirrhotic patients with indeterminate liver nodules using quantitative imaging features extracted from triphasic CT scans. MATERIAL AND METHODS: We retrospectively analyzed 178 cirrhotic patients from 27 institutions, with biopsy-proven liver nodules classified as indeterminate using the European Association for the Study of the Liver (EASL) guidelines. Patients were randomly assigned to a discovery cohort (142 patients (pts.)) and a validation cohort (36 pts.). Each liver nodule was segmented on each phase of triphasic CT scans, and 13,920 quantitative imaging features (12 sets of 1160 features each reflecting the phenotype at one single phase or its change between two phases) were extracted. Using machine-learning techniques, the signature was trained and calibrated (discovery cohort), and validated (validation cohort) to classify liver nodules as HCC vs. non-HCC. Effects of segmentation and contrast enhancement quality were also evaluated. RESULTS: Patients were predominantly male (88%) and CHILD A (65%). Biopsy was positive for HCC in 77% of patients. LI-RADS scores were not different between HCC and non-HCC patients. The signature included a single radiomics feature quantifying changes between arterial and portal venous phases: DeltaV-A_DWT1_LL_Variance-2D and reached area under the receiver operating characteristic curve (AUC) of 0.70 (95%CI 0.61-0.80) and 0.66 (95%CI 0.64-0.84) in discovery and validation cohorts, respectively. The signature was influenced neither by segmentation nor by contrast enhancement. CONCLUSION: A signature using a single feature was validated in a multicenter retrospective cohort to diagnose HCC in cirrhotic patients with indeterminate liver nodules. Artificial intelligence could enhance clinicians' decision by identifying a subgroup of patients with high HCC risk. KEY POINTS: • In cirrhotic patients with visually indeterminate liver nodules, expert visual assessment using current guidelines cannot accurately differentiate HCC from differential diagnoses. Current clinical protocols do not entail biopsy due to procedural risks. Radiomics can be used to non-invasively diagnose HCC in cirrhotic patients with indeterminate liver nodules, which could be leveraged to optimize patient management. • Radiomics features contributing the most to a better characterization of visually indeterminate liver nodules include changes in nodule phenotype between arterial and portal venous phases: the "washout" pattern appraised visually using EASL and EASL guidelines. • A clinical decision algorithm using radiomics could be applied to reduce the rate of cirrhotic patients requiring liver biopsy (EASL guidelines) or wait-and-see strategy (AASLD guidelines) and therefore improve their management and outcome.

Evaluation of the efficacy of immunotherapy for non-resectable mucosal melanoma.

BACKGROUND: Immune checkpoint inhibitors are now standard-of-care treatments for metastatic cutaneous melanoma. However, for rare sub-groups, such as mucosal melanomas, few published data are available, and with no established therapeutic guidelines. Our objective was to assess the response to anti-CTLA4 and anti-PD1 immunotherapy in patients with mucosal melanomas. METHODS: We performed a single-center, prospective cohort analysis of patients with non-surgical locally advanced and/or metastatic mucosal melanoma receiving anti-CTLA4 and/or anti-PD1 immunotherapy from 2010 to 2016. RESULTS: Forty-four patients were enrolled, including 18 (40.9%) with head and neck, 12 (27.3%) with vulvo-vaginal and 14 (31.8%) with ano-rectal primary tumours. Eleven (25%) patients had stage 3 disease, and 11 (25%) had distant metastases. The first-line immunotherapy was ipilimumab in 24 patients and pembrolizumab in 20. The objective response rate (ORR) was 8.2% (one complete response) for ipilimumab and 35% (four complete responses) for pembrolizumab. No significant difference was observed for primary tumour location. The median follow-up was 24 months (range 4-73). The median progression-free survival (PFS) in the first-line ipilimumab and pembrolizumab groups was 3 months [95% confidence interval (CI) 2.5-4.6] and 5 months (95% CI 2.6-33.1), respectively (p = 0.0147). CONCLUSION: In the patients with unresectable and/or metastatic mucosal melanoma, we found ORR and PFS rates comparable to those in patients with cutaneous melanoma, with no significant differences in the types of mucosal surfaces involved. Anti-PD1 therapy has a more favorable benefit-risk ratio than ipilimumab and should be used preferentially.

Diagnostic Performance of 4D CT and Sestamibi SPECT/CT in Localizing Parathyroid Adenomas in Primary Hyperparathyroidism.

Background There currently is no consensus on the optimal localization procedure and imaging protocol for parathyroid adenoma. Parathyroid four-dimensional (4D) CT has emerged as a promising method for preoperative localization. Purpose To evaluate the diagnostic performance of parathyroid 4D CT and technetium 99m-sestamibi (hereafter, referred to as sestamibi) SPECT/CT in preoperative localization in patients with primary hyperparathyroidism. Materials and Methods This was a single-institution retrospective study of patients with primary hyperparathyroidism who underwent a combined imaging protocol of sestamibi SPECT/CT and 4D CT (noncontrast, contrast agent-enhanced, arterial, and delayed venous phases) acquired in a single setting from February 2013 to May 2016, with subsequent parathyroidectomy within 6 months. Reference standard for correct localization was on the basis of location denoted on operative reports, with pathologic confirmation of parathyroid adenoma or hyperplasia. By using a four-quadrant analysis, sensitivity, specificity, and area under the curve (AUC) for localization of the hyperfunctioning parathyroid gland or glands at sestamibi SPECT/CT and 4D CT were compared, per modality and in combination. Results Four hundred patients (319 women, 81 men; mean age, 61 years ± 14 [standard deviation]) were evaluated. Similar diagnostic performance was found in both combined 4D CT with sestamibi SPECT/CT and 4D CT alone (area under the curve [AUC], 0.88 [95% CI: 0.86, 0.90] and 0.87 [95% CI: 0.85, 0.90], respectively; P = .82). Both modalities outperformed sestamibi SPECT/CT (AUC, 0.78; 95% CI: 0.76, 0.81; P < .001). Four-dimensional CT showed higher sensitivity than did sestamibi SPECT/CT (sensitivity, 79.3% [414 of 522] vs 58.0% [303 of 522], respectively; P < .001). In a subset analysis, 4D CT had higher sensitivity than sestamibi SPECT/CT in patients with single-gland disease (sensitivity, 92.5% [297 of 321] vs 75.1% [241 of 321], respectively; P < .001) and with multigland disease (sensitivity, 58.2% [117 of 201] vs 30.8% [62 of 201], respectively; P < .001). Conclusion Four-dimensional CT provided superior preoperative localization compared with sestamibi SPECT/CT in patients with single and multigland disease. The combination of the two modalities did not improve diagnostic performance compared with four-dimensional CT alone. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Sinha and Oates in this issue.

Prognostic and theranostic 18F-FDG PET biomarkers for anti-PD1 immunotherapy in metastatic melanoma: association with outcome and transcriptomics.

PURPOSE: An imaging-based stratification tool is needed to identify melanoma patients who will benefit from anti Programmed Death-1 antibody (anti-PD1). We aimed at identifying biomarkers for survival and response evaluated in lymphoid tissue metabolism in spleen and bone marrow before initiation of therapy. METHODS: This retrospective study included 55 patients from two institutions who underwent 18F-FDG PET/CT before anti-PD1. Parameters extracted were SUVmax, SUVmean, HISUV (SUV-based Heterogeneity Index), TMTV (total metabolic tumor volume), TLG (total lesion glycolysis), BLR (Bone marrow-to-Liver SUVmax ratio), and SLR (Spleen-to-Liver SUVmax ratio). Each parameter was dichotomized using the median as a threshold. Association with survival, best overall response (BOR), and transcriptomic analyses (NanoString assay) were evaluated using Cox prediction models, Wilcoxon tests, and Spearman's correlation, respectively. RESULTS: At 20.7 months median follow-up, 33 patients had responded, and 29 patients died. Median PFS and OS were 11.4 (95%CI 2.7-20.2) and 28.5 (95%CI 13.4-43.8) months. TMTV (>25cm3), SLR (>0.77), and BLR (>0.79) correlated with shorter survival. High TMTV (>25 cm3), SLR (>0.77), and BLR (>0.79) correlated with shorter survival, with TMTV (HR PFS 2.2, p = 0.02, and HR OS 2.5, p = 0.02) and BLR (HR OS 2.3, p = 0.04) remaining significant in a multivariable analysis. Low TMTV and TLG correlated with BOR (p = 0.03). Increased glucose metabolism in bone marrow (BLR) was associated with transcriptomic profiles including regulatory T cell markers (p < 0.05). CONCLUSION: Low tumor burden correlates with survival and objective response while hematopoietic tissue metabolism correlates inversely with survival. These biomarkers should be further evaluated for potential clinical application.

Evaluation of 2 diuretic 18fluorine-fluorodeoxyglucose positron emission tomography/computed tomography imaging protocols for intrapelvic cancer.

BACKGROUND: 18F-Fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) plays an important part in the oncological evaluation of the abdomen and pelvis, but the interpretation and quantification is often hampered by intense physiological urinary activity. We evaluate 2 different diuretic imaging protocols by comparing intensity of urinary activity and we look at the impact of multiple variables on the final urinary activity. METHODS: Comparative analysis of 102 patients (median age: 64) having intrapelvic carcinoma. After full body acquisition, 58 patients were administered 20 mg of furosemide 90 min post injection of FDG (P90). For 44 patients, 20 mg of furosemide was administered 30 min post injection of FDG (P30). Comparisons between groups were performed using the Mann-Whitney Test and χ2. The BMI, creatinine, clearance, age, injected activity, diuretic protocol, gender and glycemia were evaluated with multivariate analysis for their impact on the final urinary activity. RESULTS: Concerning the comparison of the urinary activity we observe a significant difference (P=0.0029) between P90 and P30 for the SUVmax (median 4.3 [range 1.6: 17.7] vs. 6.0 [range 2.9: 15.1]), and for the SUVmean (P<0.001) (median 2.4 [range 1.1; 9.9] vs. 3.8 [range 2.0; 10.1]). For 2 patients of P30, the acquisition was interrupted because the patient needed to void. Multivariate analysis shows that creatinine and creatinine clearance do not have a significant independent impact on the final bladder activity. CONCLUSIONS: By comparing the 2 diuretic imaging protocols, we found a significant lower urinary activity for the P90 protocol and the regression decision tree shows that the P90 protocol is mostly superior. The P30 protocol, which seems to be less well tolerated, is adequate in the group of patients with an injected activity of less than 240 MBq and older than 65 years, if P90 is not feasible. For most patients with injected activity ≥240 MBq or BMI of ≥25 and a glycemia >120 mg/dL, a significant amount of residual urinary activity remains for both protocols.

A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study.

BACKGROUND: Because responses of patients with cancer to immunotherapy can vary in success, innovative predictors of response to treatment are urgently needed to improve treatment outcomes. We aimed to develop and independently validate a radiomics-based biomarker of tumour-infiltrating CD8 cells in patients included in phase 1 trials of anti-programmed cell death protein (PD)-1 or anti-programmed cell death ligand 1 (PD-L1) monotherapy. We also aimed to evaluate the association between the biomarker, and tumour immune phenotype and clinical outcomes of these patients. METHODS: In this retrospective multicohort study, we used four independent cohorts of patients with advanced solid tumours to develop and validate a radiomic signature predictive of immunotherapy response by combining contrast-enhanced CT images and RNA-seq genomic data from tumour biopsies to assess CD8 cell tumour infiltration. To develop the radiomic signature of CD8 cells, we used the CT images and RNA sequencing data of 135 patients with advanced solid malignant tumours who had been enrolled into the MOSCATO trial between May 1, 2012, and March 31, 2016, in France (training set). The genomic data, which are based on the CD8B gene, were used to estimate the abundance of CD8 cells in the samples and data were then aligned with the images to generate the radiomic signatures. The concordance of the radiomic signature (primary endpoint) was validated in a Cancer Genome Atlas [TGCA] database dataset including 119 patients who had available baseline preoperative imaging data and corresponding transcriptomic data on June 30, 2017. From 84 input variables used for the machine-learning method (78 radiomic features, five location variables, and one technical variable), a radiomics-based predictor of the CD8 cell expression signature was built by use of machine learning (elastic-net regularised regression method). Two other independent cohorts of patients with advanced solid tumours were used to evaluate this predictor. The immune phenotype internal cohort (n=100), were randomly selected from the Gustave Roussy Cancer Campus database of patient medical records based on previously described, extreme tumour-immune phenotypes: immune-inflamed (with dense CD8 cell infiltration) or immune-desert (with low CD8 cell infiltration), irrespective of treatment delivered; these data were used to analyse the correlation of the immune phenotype with this biomarker. Finally, the immunotherapy-treated dataset (n=137) of patients recruited from Dec 1, 2011, to Jan 31, 2014, at the Gustave Roussy Cancer Campus, who had been treated with anti-PD-1 and anti-PD-L1 monotherapy in phase 1 trials, was used to assess the predictive value of this biomarker in terms of clinical outcome. FINDINGS: We developed a radiomic signature for CD8 cells that included eight variables, which was validated with the gene expression signature of CD8 cells in the TCGA dataset (area under the curve [AUC]=0·67; 95% CI 0·57-0·77; p=0·0019). In the cohort with assumed immune phenotypes, the signature was also able to discriminate inflamed tumours from immune-desert tumours (0·76; 0·66-0·86; p<0·0001). In patients treated with anti-PD-1 and PD-L1, a high baseline radiomic score (relative to the median) was associated with a higher proportion of patients who achieved an objective response at 3 months (vs those with progressive disease or stable disease; p=0·049) and a higher proportion of patients who had an objective response (vs those with progressive disease or stable disease; p=0·025) or stable disease (vs those with progressive disease; p=0·013) at 6 months. A high baseline radiomic score was also associated with improved overall survival in univariate (median overall survival 24·3 months in the high radiomic score group, 95% CI 18·63-42·1; vs 11·5 months in the low radiomic score group, 7·98-15·6; hazard ratio 0·58, 95% CI 0·39-0·87; p=0·0081) and multivariate analyses (0·52, 0·35-0·79; p=0·0022). INTERPRETATION: The radiomic signature of CD8 cells was validated in three independent cohorts. This imaging predictor provided a promising way to predict the immune phenotype of tumours and to infer clinical outcomes for patients with cancer who had been treated with anti-PD-1 and PD-L1. Our imaging biomarker could be useful in estimating CD8 cell count and predicting clinical outcomes of patients treated with immunotherapy, when validated by further prospective randomised trials. FUNDING: Fondation pour la Recherche Médicale, and SIRIC-SOCRATE 2.0, French Society of Radiation Oncology.

A score combining baseline neutrophilia and primary tumor SUVpeak measured from FDG PET is associated with outcome in locally advanced cervical cancer.

PURPOSE: We investigated whether a score combining baseline neutrophilia and a PET biomarker could predict outcome in patients with locally advanced cervical cancer (LACC). METHODS: Patients homogeneously treated with definitive chemoradiation plus image-guided adaptive brachytherapy (IGABT) between 2006 and 2013 were analyzed retrospectively. We divided patients into two groups depending on the PET device used: a training set (TS) and a validation set (VS). Primary tumors were semi-automatically delineated on PET images, and 11 radiomics features were calculated (LIFEx software). A PET radiomic index was selected using the time-dependent area under the curve (td-AUC) for 3-year local control (LC). We defined the neutrophil SUV grade (NSG = 0, 1 or 2) score as the number of risk factors among (i) neutrophilia (neutrophil count >7 G/L) and (ii) high risk defined from the PET radiomic index. The NSG prognostic value was evaluated for LC and overall survival (OS). RESULTS: Data from 108 patients were analyzed. Estimated 3-year LC was 72% in the TS (n = 69) and 65% in the VS (n = 39). In the TS, SUVpeak was selected as the most LC-predictive biomarker (td-AUC = 0.75), and was independent from neutrophilia (p = 0.119). Neutrophilia (HR = 2.6), high-risk SUVpeak (SUVpeak > 10, HR = 4.4) and NSG = 2 (HR = 9.2) were associated with low probability of LC in TS. In multivariate analysis, NSG = 2 was independently associated with low probability of LC (HR = 7.5, p < 0.001) and OS (HR = 5.8, p = 0.001) in the TS. Results obtained in the VS (HR = 5.2 for OS and 3.5 for LC, p < 0.02) were promising. CONCLUSION: This innovative scoring approach combining baseline neutrophilia and a PET biomarker provides an independent prognostic factor to consider for further clinical investigations.