A comparison of the prognostic performance of the Lugano 2014 and RECIL 2017 response criteria in patients with NHL from the phase III GOYA and GALLIUM trials.

The Lugano 2014 criteria are the standard for response assessment in lymphoma. We compared the prognostic performance of Lugano 2014 and the more recently developed response evaluation criteria in lymphoma (RECIL 2017), which relies primarily on computed tomography and uses unidimensional measurements, in patients with previously untreated diffuse large B-cell lymphoma (DLBCL) and follicular lymphoma (FL) from the phase III GOYA and GALLIUM trials, respectively. Concordance between responses according to the Lugano 2014 and RECIL 2017 criteria was analyzed. Landmark analyses of progression-free survival (PFS) and overall survival (OS) by end of treatment (EOT) and end of induction (EOI) response status according to RECIL 2017 and Lugano 2014 criteria, and prognostic value of response at EOT/EOI were also compared. Overall, 1333 patients were included from GOYA and 502 from GALLIUM. Complete response (CR) status according to RECIL 2017 criteria showed high concordance with complete metabolic response (CMR) status by Lugano 2014 criteria in both GOYA (92.5%) and GALLIUM (92.4%). EOT and EOI CR/CMR status by both criteria was highly prognostic for PFS in GOYA (RECIL 2017 [CR]: hazard ratio [HR], 0.35 [95% confidence interval [CI] 0.26-0.46]; Lugano 2014 [CMR]: HR, 0.35 [95% CI 0.26-0.48]; both p < .0001) and GALLIUM (RECIL 2017 [CR]: HR, 0.35 [95% CI 0.23-0.53]; Lugano 2014 [CMR]: HR, 0.21 [95% CI 0.14-0.31]; both p < .0001). In conclusion, response categorization by RECIL 2017 is similar to that by Lugano 2014 criteria, with high concordance observed. Both were prognostic for PFS and OS.

Positron Emission Tomography-Adapted Therapy in Bulky Stage I/II Classic Hodgkin Lymphoma: CALGB 50801 (Alliance).

PURPOSE: Patients with bulky stage I/II classic Hodgkin lymphoma (cHL) are typically treated with chemotherapy followed by radiation. Late effects associated with radiotherapy include increased risk of second cancer and cardiovascular disease. We tested a positron emission tomography (PET)-adapted approach in patients with bulky, early-stage cHL, omitting radiotherapy in patients with interim PET-negative (PET-) disease and intensifying treatment in patients with PET-positive (PET+) disease. METHODS: Eligible patients with bulky disease (mass > 10 cm or 1/3 the maximum intrathoracic diameter on chest x-ray) received two cycles of doxorubicin, bleomycin, vinblastine, and dacarbazine (ABVD) followed by interim fluorodeoxyglucose PET (PET2). Patients with PET2-, defined as 1-3 on the 5-point scale, received four additional cycles of doxorubicin, bleomycin, vinblastine, and dacarbazine. Patients with PET2+ received four cycles of escalated bleomycin, etoposide, doxorubicin, cyclophosphamide, vincristine, procarbazine, and prednisone followed by 30.6 Gy involved-field radiation. RESULTS: Of 94 evaluable patients, 53% were female with median age 30 years (range, 18-58 years). Eight-five (90%) had stage II disease, including 48 (51%) with stage IIB/IIBE. Seventy-eight (78%) were PET2- and 21 (22%) were PET2+. The predominant toxicity was neutropenia, with 9% of patients developing febrile neutropenia and one developing sepsis. The primary end point of 3-year progression-free survival (PFS) was 93.1% in PET2- and 89.7% in PET2+ patients. Three-year overall survival was 98.6% and 94.4%, respectively. The estimated hazard ratio comparing PFS of patients with PET2+ and patients with PET2- was 1.03 (85% upper bound 2.38) and was significantly less than the null hypothesis of 4.1 (one-sided P = .04). CONCLUSION: Our study of PET-adapted therapy in bulky stage I/II cHL met its primary goal and was associated with an excellent 3-year PFS rate of 92.3% in all patients, with the majority being spared radiotherapy and exposure to intensified chemotherapy.

A tumor volume and performance status model to predict outcome before treatment in diffuse large B-cell lymphoma.

Aggressive large B-cell lymphoma (LBCL) has variable outcomes. Current prognostic tools use factors for risk stratification that inadequately identify patients at high risk of refractory disease or relapse before initial treatment. A model associating 2 risk factors, total metabolic tumor volume (TMTV) >220 cm3 (determined by fluorine-18 fluorodeoxyglucose positron emission tomography coupled with computed tomography) and performance status (PS) ≥2, identified as prognostic in 301 older patients in the REMARC trial (#NCT01122472), was validated in 2174 patients of all ages treated in 2 clinical trials, PETAL (Positron Emission Tomography-Guided Therapy of Aggressive Non-Hodgkin Lymphomas; N = 510) and GOYA (N = 1315), and in real-world clinics (N = 349) across Europe and the United States. Three risk categories, low (no factors), intermediate (1 risk factor), and high (2 risk factors), significantly discriminated outcome in most of the series. Patients with 2 risk factors had worse outcomes than patients with no risk factors in the PETAL, GOYA, and real-world series. Patients with intermediate risk also had significantly worse outcomes than patients with no risk factors. The TMTV/Eastern Cooperative Oncology Group-PS combination outperformed the International Prognostic Index with a positive C-index for progression-free survival and overall survival in most series. The combination of high TMTV > 220 cm3 and ECOG-PS ≥ 2 is a simple clinical model to identify aggressive LBCL risk categories before treatment. This combination addresses the unmet need to better predict before treatment initiation for aggressive LBCL the patients likely to benefit the most or not at all from therapy.

PET-CR as a potential surrogate endpoint in untreated DLBCL: meta-analysis and implications for clinical trial design.

This study's focus is the association of end-of-therapy (EOT) PET results with progression-free (PFS) and overall survival (OS) in patients with diffuse large B-cell lymphoma receiving first-line chemoimmunotherapy. We develop a Bayesian hierarchical model for predicting PFS and OS from EOT PET-complete response (PET-CR) using a literature-based meta-analysis of 20 treatment arms and a substudy of 4 treatment arms in 3 clinical trials for which we have patient-level data. The PET-CR rate in our substudy was 72%. The modeled estimates for hazard ratio (PET-CR/non-PET-CR) were 0.13 for PFS (95% CI 0.10, 0.16) and 0.10 for OS (CI 0.07, 0.12). Hazard ratios varied little by patient subtype and were confirmed by the overall meta-analysis. We link these findings to designing future clinical trials and show how our model can be used in adapting the sample size of a trial to accumulating results regarding treatment benefits on PET-CR and a survival endpoint.

A prognostic model integrating PET-derived metrics and image texture analyses with clinical risk factors from GOYA.

Image texture analysis (radiomics) uses radiographic images to quantify characteristics that may identify tumour heterogeneity and associated patient outcomes. Using fluoro-deoxy-glucose positron emission tomography/computed tomography (FDG-PET/CT)-derived data, including quantitative metrics, image texture analysis and other clinical risk factors, we aimed to develop a prognostic model that predicts survival in patients with previously untreated diffuse large B-cell lymphoma (DLBCL) from GOYA (NCT01287741). Image texture features and clinical risk factors were combined into a random forest model and compared with the international prognostic index (IPI) for DLBCL based on progression-free survival (PFS) and overall survival (OS) predictions. Baseline FDG-PET scans were available for 1263 patients, 832 patients of these were cell-of-origin (COO)-evaluable. Patients were stratified by IPI or radiomics features plus clinical risk factors into low-, intermediate- and high-risk groups. The random forest model with COO subgroups identified a clearer high-risk population (45% 2-year PFS [95% confidence interval (CI) 40%-52%]; 65% 2-year OS [95% CI 59%-71%]) than the IPI (58% 2-year PFS [95% CI 50%-67%]; 69% 2-year OS [95% CI 62%-77%]). This study confirms that standard clinical risk factors can be combined with PET-derived image texture features to provide an improved prognostic model predicting survival in untreated DLBCL.

Baseline Total Metabolic Tumor Volume is Prognostic for Refractoriness to Immunochemotherapy in DLBCL: Results From GOYA.

INTRODUCTION: A good response to initial therapy is key to maximizing survival in patients with diffuse large B-cell lymphoma (DLBCL), but patients with chemorefractory disease and early progression have poor outcomes. PATIENTS AND METHODS: Data from the GOYA study in patients with DLBCL who received first-line rituximab or obinutuzumab plus cyclophosphamide, doxorubicin, vincristine, and prednisone (CHOP) were analyzed. Positron emission tomography/computed tomography (PET/CT)-derived characteristics associated with total metabolic tumor volume (TMTV) and clinical risk factors for primary chemorefractory disease and disease progression within 12 months (POD12) were explored. RESULTS: Of those patients fulfilling the criteria for analysis, 108/1126 (10%) were primary chemorefractory and 147/1106 (13%) had POD12. Primary chemorefractory and POD12 status were strongly associated with reduced overall survival. After multivariable analysis of clinical and imaging-based risk factors by backward elimination, only very high TMTV (quartile [Q] 1 vs. Q4 odds ratio [OR]: 0.45; P = .006) and serum albumin levels (low vs. normal OR of 1.86; P = .004) were associated with primary chemorefractoriness. After additionally accounting for BCL2/MYC translocation in a subset of patients, TMTV and BCL2/MYC double-hit status remained as significant predictors of primary chemorefractoriness (Q1 vs. Q4 OR: 0.32, P = .01 and double-hit vs. no-hit OR of 4.47, P = .02, respectively). Risk factors including very high TMTV, high sum of the product of the longest diameters (SPD), geographic region (Asia), short time since diagnosis, extranodal involvement and low serum albumin were retained for POD12. CONCLUSION: PET-derived TMTV has prognostic value in identifying patients at risk of early treatment failure.

Total metabolic tumor volume as a survival predictor for patients with diffuse large B-cell lymphoma in the GOYA study.

This retrospective analysis of the phase III GOYA study investigated the prognostic value of baseline metabolic tumor volume parameters and maximum standardized uptake values for overall and progression-free survival (PFS) in treatment-naïve diffuse large B-cell lymphoma. Baseline total metabolic tumor volume (determined for tumors >1 mL using a threshold of 1.5 times the mean liver standardized uptake value +2 standard deviations), total lesion glycolysis, and maximum standardized uptake value positron emission tomography data were dichotomized based on receiver operating characteristic analysis and divided into quartiles by baseline population distribution. Of 1,418 enrolled patients, 1,305 had a baseline positron emission tomography scan with detectable lesions. Optimal cut-offs were 366 cm3 for total metabolic tumor volume and 3,004 g for total lesion glycolysis. High total metabolic tumor volume and total lesion glycolysis predicted poorer PFS, with associations retained after adjustment for baseline and disease characteristics (high total metabolic tumor volume hazard ratio: 1.71, 95% confidence interval [CI]: 1.35- 2.18; total lesion glycolysis hazard ratio: 1.46; 95% CI: 1.15-1.86). Total metabolic tumor volume was prognostic for PFS in subgroups with International Prognostic Index scores 0-2 and 3-5, and those with different cell-of-origin subtypes. Maximum standardized uptake value had no prognostic value in this setting. High total metabolic tumor volume associated with high International Prognostic Index or non-germinal center B-cell classification identified the highest-risk cohort for unfavorable prognosis. In conclusion, baseline total metabolic tumor volume and total lesion glycolysis are independent predictors of PFS in patients with diffuse large B-cell lymphoma after first-line immunochemotherapy.

Follicular Lymphoma Treated with First-Line Immunochemotherapy: A Review of PET/CT in Patients Who Did Not Achieve a Complete Metabolic Response in the GALLIUM Study.

Complete metabolic response (CMR) on PET/CT was the sole independent predictor of overall survival in the PET substudy of the phase III GALLIUM trial (NCT01332968) in first-line treatment of high-tumor-burden follicular lymphoma. The aim of this analysis was to further investigate the outcome of patients not achieving CMR. Methods: Two international experts rereviewed PET/CT scans from patients failing to achieve CMR assessed by the Independent Review Committee masked otherwise to committee results. Metabolic response category and Deauville score were assigned. Progression-free survival (PFS) was investigator-assessed with contrast-enhanced CT. Kaplan-Meier methodology was used to estimate landmark PFS and time to next treatment from end of induction by Deauville score. Patients who experienced CT-based progressive disease at the end of induction were excluded. Results: Fifty-four patients were reviewed. Six had CMR, 37 had a partial metabolic response, 2 had no metabolic response, and 9 had progressive metabolic disease. Patients were reassigned to CMR because 18F-FDG uptake was considered inflammatory (n = 2), was considered incidental neoplasia (n = 2), or was visually close to liver uptake but quantitatively lower (n = 2). There was a trend for shorter PFS and time to next treatment for patients with a Deauville score of 5 than a score of 4. High-grade mesenteric uptake at the end of induction was common, occurring in 20 patients with non-CMR, 14 of whom achieved CMR at all other sites. Only 3 of 14 (21%) patients with mesenteric uptake as the only site of disease experienced progression or death within 24 mo, whereas 4 of 6 patients (67%) with mesenteric and additional sites of 18F-FDG-avid disease experienced progression or death within 24 mo. All patients with early progression had measurable disease on contrast-enhanced CT at 18F-FDG-avid sites at the end of induction. Conclusion: After induction immunochemotherapy, CMR was assigned after reassessment in some patients, in whom increased 18F-FDG uptake was considered due to inflammation or incidental neoplasia rather than to lymphoma. Quantitative assessment to confirm the visual impression of residual uptake in lesions is suggested. Isolated mesenteric 18F-FDG uptake is likely a common false-positive finding at the end of induction and does not warrant changes in clinical management or disease surveillance unless there is measurable disease on contrast-enhanced CT or clinical suspicion of active disease.

End-of-treatment PET/CT predicts PFS and OS in DLBCL after first-line treatment: results from GOYA.

GOYA was a randomized phase 3 study comparing obinutuzumab plus cyclophosphamide, doxorubicin, vincristine, and prednisone (CHOP) vs standard-of-care rituximab plus CHOP in patients with previously untreated diffuse large B-cell lymphoma (DLBCL). This retrospective analysis of GOYA aimed to assess the association between progression-free survival (PFS) and overall survival (OS) with positron emission tomography (PET)-based complete response (CR) status. Overall, 1418 patients were randomly assigned to receive 8 21-day cycles of obinutuzumab (n = 706) or rituximab (n = 712) plus 6 or 8 cycles of CHOP. Patients received a mandatory fluoro-2-deoxy-d-glucose-PET/computed tomography scan at baseline and end of treatment. After a median follow-up of 29 months, the numbers of independent review committee-assessed PFS and OS events in the entire cohort were 416 (29.3%) and 252 (17.8%), respectively. End-of-treatment PET CR was highly prognostic for PFS and OS according to Lugano 2014 criteria (PFS: hazard ratio [HR], 0.26; 95% confidence interval [CI], 0.19-0.38; P < .0001; OS: HR, 0.12; 95% CI, 0.08-0.17; P < .0001), irrespective of international prognostic index score and cell of origin. In conclusion, the results from this prospectively acquired large cohort corroborated previously published data from smaller sample sizes showing that end-of-treatment PET CR is an independent predictor of PFS and OS and a promising prognostic marker in DLBCL. Long-term survival analysis confirmed the robustness of these data over time. Additional meta-analyses including other prospective studies are necessary to support the substitution of PET CR for PFS as an effective and practical surrogate end point. This trial was registered at www.clinicaltrials.gov as #NCT01287741.

Addition of Lenalidomide to R-CHOP Improves Outcomes in Newly Diagnosed Diffuse Large B-Cell Lymphoma in a Randomized Phase II US Intergroup Study ECOG-ACRIN E1412.

PURPOSE: Lenalidomide combined with rituximab plus cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP) (R2CHOP) in untreated diffuse large B-cell lymphoma (DLBCL) has shown promising activity, particularly in the activated B-cell-like (ABC) subtype. Eastern Cooperative Oncology Group (ECOG)-ACRIN trial E1412 was a randomized phase II study comparing R2CHOP versus R-CHOP in untreated DLBCL. PATIENTS AND METHODS: Patients with newly diagnosed DLBCL, stage II bulky-IV disease, International Prognostic Index (IPI) ≥ 2, and ECOG performance status ≤ 2 were eligible and randomly assigned 1:1 to R2CHOP versus R-CHOP for six cycles. Tumors were analyzed using the NanoString Lymph2Cx for cell of origin. The primary end point was progression-free survival (PFS) in all patients with the co-primary end point of PFS in ABC-DLBCL. Secondary end points included overall response rate (ORR), complete response (CR) rate, and overall survival (OS). RESULTS: Three hundred forty-nine patients were enrolled; 280 patients (145 R2CHOP and 135 R-CHOP) were evaluable: 94 were ABC-DLBCL, 122 germinal center B-cell-like-DLBCL, 18 unclassifiable, and 46 unknowns. Baseline characteristics were well-balanced between arms, and the median age was 66 (range, 24-92); 70% of patients had stage IV disease; 34%, 43%, and 24% had IPI 2, 3, and 4 or 5, respectively. Myelosuppression was more common in the R2CHOP arm. The ORR and CR rate were 92% and 68% in R-CHOP and 97% (P = .06) and 73% (P = .43) in the R2CHOP arm, respectively. The median follow-up was 3.0 years; R2CHOP was associated with a 34% reduction in risk of progression or death versus R-CHOP (hazard ratio [HR], 0.66 95% CI, 0.43 to 1.01) and 3-year PFS of 73% versus 61%, one-sided P = .03, and an improvement in OS (83% and 75% at 3 years; HR, 0.67; one-sided P = .05). The PFS HR for R2CHOP was 0.67 for ABC-DLBCL, one-sided P = .1. CONCLUSION: In this signal-seeking study, the addition of lenalidomide to R-CHOP (R2CHOP) improved outcomes in newly diagnosed DLBCL including patients with ABC-DLBCL.

Brain and blood biomarkers of tauopathy and neuronal injury in humans and rats with neurobehavioral syndromes following blast exposure.

Traumatic brain injury (TBI) is a risk factor for the later development of neurodegenerative diseases that may have various underlying pathologies. Chronic traumatic encephalopathy (CTE) in particular is associated with repetitive mild TBI (mTBI) and is characterized pathologically by aggregation of hyperphosphorylated tau into neurofibrillary tangles (NFTs). CTE may be suspected when behavior, cognition, and/or memory deteriorate following repetitive mTBI. Exposure to blast overpressure from improvised explosive devices (IEDs) has been implicated as a potential antecedent for CTE amongst Iraq and Afghanistan Warfighters. In this study, we identified biomarker signatures in rats exposed to repetitive low-level blast that develop chronic anxiety-related traits and in human veterans exposed to IED blasts in theater with behavioral, cognitive, and/or memory complaints. Rats exposed to repetitive low-level blasts accumulated abnormal hyperphosphorylated tau in neuronal perikarya and perivascular astroglial processes. Using positron emission tomography (PET) and the [18F]AV1451 (flortaucipir) tau ligand, we found that five of 10 veterans exhibited excessive retention of [18F]AV1451 at the white/gray matter junction in frontal, parietal, and temporal brain regions, a typical localization of CTE tauopathy. We also observed elevated levels of neurofilament light (NfL) chain protein in the plasma of veterans displaying excess [18F]AV1451 retention. These findings suggest an association linking blast injury, tauopathy, and neuronal injury. Further study is required to determine whether clinical, neuroimaging, and/or fluid biomarker signatures can improve the diagnosis of long-term neuropsychiatric sequelae of mTBI.

Comparison of 11 automated PET segmentation methods in lymphoma.

Segmentation of lymphoma lesions in FDG PET/CT images is critical in both assessing individual lesions and quantifying patient disease burden. Simple thresholding methods remain common despite the large heterogeneity in lymphoma lesion location, size, and contrast. Here, we assess 11 automated PET segmentation methods for their use in two scenarios: individual lesion segmentation and patient-level disease quantification in lymphoma. Lesions on 18F-FDG PET/CT scans of 90 lymphoma patients were contoured by a nuclear medicine physician. Thresholding, active contours, clustering, adaptive region-growing, and convolutional neural network (CNN) methods were implemented on all physician-identified lesions. Lesion-level segmentation was evaluated using multiple segmentation performance metrics (Dice, Hausdorff Distance). Patient-level quantification of total disease burden (SUVtotal) and metabolic tumor volume (MTV) was assessed using Spearman's correlation coefficients between the segmentation output and physician contours. Lesion segmentation and patient quantification performance was compared to inter-physician agreement in a subset of 20 patients segmented by a second nuclear medicine physician. In total, 1223 lesions with median tumor-to-background ratio of 4.0 and volume of 1.8 cm3, were evaluated. When assessed for lesion segmentation, a 3D CNN, DeepMedic, achieved the highest performance across all evaluation metrics. DeepMedic, clustering methods, and an iterative threshold method had lesion-level segmentation performance comparable to the degree of inter-physician agreement. For patient-level SUVtotal and MTV quantification, all methods except 40% and 50% SUVmax and adaptive region-growing achieved a performance that was similar the agreement of the two physicians. Multiple methods, including a 3D CNN, clustering, and an iterative threshold method, achieved both good lesion-level segmentation and patient-level quantification performance in a population of 90 lymphoma patients. These methods are thus recommended over thresholding methods such as 40% and 50% SUVmax, which were consistently found to be significantly outside the limits defined by inter-physician agreement.

Impact of bone marrow biopsy on response assessment in immunochemotherapy-treated lymphoma patients in GALLIUM and GOYA.

The utility of posttreatment bone marrow biopsy (BMB) histology to confirm complete response (CR) in lymphoma clinical trials is in question. We retrospectively evaluated the impact of BMB on response assessment in immunochemotherapy-treated patients with previously untreated follicular lymphoma (FL) and diffuse large B-cell lymphoma (DLBCL) in the phase 3 Study of Obinutuzumab (RO5072759) Plus Chemotherapy in Comparison With Rituximab Plus Chemotherapy Followed by Obinutuzumab or Rituximab Maintenance in Patients With Untreated Advanced Indolent Non-Hodgkin's Lymphoma (GALLIUM; NCT01332968) and A Study of Obinutuzumab in Combination With CHOP Chemotherapy Versus Rituximab With CHOP in Participants With CD20-Positive Diffuse Large B-Cell Lymphoma (GOYA; NCT01287741) trials, respectively. Baseline BMB was performed in all patients, with repeat BMBs in patients with a CR by computed tomography (CT) at end of induction (EOI) and a positive BMB at baseline, to confirm response. Positron emission tomography imaging was also used in some patients to assess EOI response (Lugano 2014 criteria). Among patients with an EOI CR by CT in GALLIUM and GOYA, 2.8% and 4.1%, respectively, had a BMB-altered response. These results suggest that postinduction BMB histology has minimal impact on radiographically (CT)-defined responses in both FL and DLBCL patients. In GALLIUM and GOYA, respectively, 4.7% of FL patients and 7.1% of DLBCL patients had a repeat BMB result that altered response assessment when applying Lugano 2014 criteria, indicating that bone marrow evaluation appears to add little value to response assessment in FL; however, its evaluation may still have merit in DLBCL.

Prognostic value of interim FDG-PET in diffuse large cell lymphoma: results from the CALGB 50303 Clinical Trial.

As part of a randomized, prospective clinical trial in large cell lymphoma, we conducted serial fluorodeoxyglucose positron emission tomography (FDG-PET) at baseline, after 2 cycles of chemotherapy (interim PET [i-PET]), and at end of treatment (EoT) to identify biomarkers of response that are predictive of remission and survival. Scans were interpreted in a core laboratory by 2 imaging experts, using the visual Deauville 5-point scale (5-PS), and by calculating percent change in FDG uptake (change in standardized uptake value [ΔSUV]). Visual scores of 1 through 3 and ΔSUV ≥66% were prospectively defined as negative. Of 524 patients enrolled in the parent trial, 169 agreed to enroll in the PET substudy and 158 were eligible for final analysis. In this selected population, all had FDG-avid disease at baseline; by 5-PS, 55 (35%) remained positive on i-PET and 28 (18%) on EoT PET. Median ΔSUV on i-PET was 86.2%. With a median follow-up of 5 years, ΔSUV, as continuous variable, was associated with progression-free survival (PFS) (hazard ratio [HR] = 0.99; 95% confidence interval [CI], 0.97-1.00; P = .02) and overall survival (OS) (HR, 0.98; 95% CI, 0.97-0.99; P = .03). ΔSUV ≥66% was predictive of OS (HR, 0.31; 95% CI, 0.11-0.85; P = .02) but not PFS (HR, 0.47; 95% CI, 0.19-1.13; P = .09). Visual 5-PS on i-PET did not predict outcome. ΔSUV, but not visual analysis, on i-PET predicted OS in DLBCL, although the low number of events limited the statistical analysis. These data may help guide future clinical trials using PET response-adapted therapy. This trial was registered at www.clinicaltrials.gov as #NCT00118209.

Convolutional Neural Networks for Automated PET/CT Detection of Diseased Lymph Node Burden in Patients with Lymphoma.

PURPOSE: To automatically detect lymph nodes involved in lymphoma on fluorine 18 (18F) fluorodeoxyglucose (FDG) PET/CT images using convolutional neural networks (CNNs). MATERIALS AND METHODS: In this retrospective study, baseline disease of 90 patients with lymphoma was segmented on 18F-FDG PET/CT images (acquired between 2005 and 2011) by a nuclear medicine physician. An ensemble of three-dimensional patch-based, multiresolution pathway CNNs was trained using fivefold cross-validation. Performance was assessed using the true-positive rate (TPR) and number of false-positive (FP) findings. CNN performance was compared with agreement between physicians by comparing the annotations of a second nuclear medicine physician to the first reader in 20 of the patients. Patient TPR was compared using Wilcoxon signed rank tests. RESULTS: Across all 90 patients, a range of 0-61 nodes per patient was detected. At an average of four FP findings per patient, the method achieved a TPR of 85% (923 of 1087 nodes). Performance varied widely across patients (TPR range, 33%-100%; FP range, 0-21 findings). In the 20 patients labeled by both physicians, a range of 1-49 nodes per patient was detected and labeled. The second reader identified 96% (210 of 219) of nodes with an additional 3.7 per patient compared with the first reader. In the same 20 patients, the CNN achieved a 90% (197 of 219) TPR at 3.7 FP findings per patient. CONCLUSION: An ensemble of three-dimensional CNNs detected lymph nodes at a performance nearly comparable to differences between two physicians' annotations. This preliminary study is a first step toward automated PET/CT assessment for lymphoma.© RSNA, 2020.

End-of-Treatment PET/Computed Tomography Response in Diffuse Large B-Cell Lymphoma.

"PET imaging with fluorodeoxyglucose (FDG), integrated with PET/computed tomography (FDG-PET/CT), is an effective management tool of diffuse large B-cell lymphoma (DLBCL). The results of end-of-treatment (EOT) FDG-PET/CT are more accurate for detection of active disease with residual masses on CT. Complete response defined by EOT FDG-PET/CT (PET-CR) correlates with long-term outcome of patients. Treatment efficacy is determined using EOT PET/CT rather than progression-free survival (PFS) for clinical trials assessing novel drugs. If the correlation of EOT PET/CT with PFS is further proven in large studies and meta-analyses, EOT PET-CR could serve as an expedited novel endpoint replacing PFS."