Evaluating Outcome Prediction via Baseline, End-of-Treatment, and Delta Radiomics on PET-CT Images of Primary Mediastinal Large B-Cell Lymphoma.

OBJECTIVES: Accurate outcome prediction is important for making informed clinical decisions in cancer treatment. In this study, we assessed the feasibility of using changes in radiomic features over time (Delta radiomics: absolute and relative) following chemotherapy, to predict relapse/progression and time to progression (TTP) of primary mediastinal large B-cell lymphoma (PMBCL) patients. MATERIAL AND METHODS: Given the lack of standard staging PET scans until 2011, only 31 out of 103 PMBCL patients in our retrospective study had both pre-treatment and end-of-treatment (EoT) scans. Consequently, our radiomics analysis focused on these 31 patients who underwent [18F]FDG PET-CT scans before and after R-CHOP chemotherapy. Expert manual lesion segmentation was conducted on their scans for delta radiomics analysis, along with an additional 19 EoT scans, totaling 50 segmented scans for single time point analysis. Radiomics features (on PET and CT), along with maximum and mean standardized uptake values (SUVmax and SUVmean), total metabolic tumor volume (TMTV), tumor dissemination (Dmax), total lesion glycolysis (TLG), and the area under the curve of cumulative standardized uptake value-volume histogram (AUC-CSH) were calculated. We additionally applied longitudinal analysis using radial mean intensity (RIM) changes. For prediction of relapse/progression, we utilized the individual coefficient approximation for risk estimation (ICARE) and machine learning (ML) techniques (K-Nearest Neighbor (KNN), Linear Discriminant Analysis (LDA), and Random Forest (RF)) including sequential feature selection (SFS) following correlation analysis for feature selection. For TTP, ICARE and CoxNet approaches were utilized. In all models, we used nested cross-validation (CV) (with 10 outer folds and 5 repetitions, along with 5 inner folds and 20 repetitions) after balancing the dataset using Synthetic Minority Oversampling TEchnique (SMOTE). RESULTS: To predict relapse/progression using Delta radiomics between the baseline (staging) and EoT scans, the best performances in terms of accuracy and F1 score (F1 score is the harmonic mean of precision and recall, where precision is the ratio of true positives to the sum of true positives and false positives, and recall is the ratio of true positives to the sum of true positives and false negatives) were achieved with ICARE (accuracy = 0.81 ± 0.15, F1 = 0.77 ± 0.18), RF (accuracy = 0.89 ± 0.04, F1 = 0.87 ± 0.04), and LDA (accuracy = 0.89 ± 0.03, F1 = 0.89 ± 0.03), that are higher compared to the predictive power achieved by using only EoT radiomics features. For the second category of our analysis, TTP prediction, the best performer was CoxNet (LASSO feature selection) with c-index = 0.67 ± 0.06 when using baseline + Delta features (inclusion of both baseline and Delta features). The TTP results via Delta radiomics were comparable to the use of radiomics features extracted from EoT scans for TTP analysis (c-index = 0.68 ± 0.09) using CoxNet (with SFS). The performance of Deauville Score (DS) for TTP was c-index = 0.66 ± 0.09 for n = 50 and 0.67 ± 03 for n = 31 cases when using EoT scans with no significant differences compared to the radiomics signature from either EoT scans or baseline + Delta features (p-value> 0.05). CONCLUSION: This work demonstrates the potential of Delta radiomics and the importance of using EoT scans to predict progression and TTP from PMBCL [18F]FDG PET-CT scans.

Outcome of primary mediastinal large B-cell lymphoma using R-CHOP: impact of a PET-adapted approach.

Cure rates for primary mediastinal large B-cell lymphoma (PMBCL) have improved with the integration of rituximab. However, the type of primary therapy and role of radiotherapy (RT) remains ill-defined. Herein, we evaluated the outcome of PMBCL primarily treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP) and the impact of an end-of-treatment (EOT) 18F-fluorodeoxyglucose positron emission tomography (PET) scan to guide consolidative RT. Patients ≥18 years of age with PMBCL treated with curative intent rituximab-chemotherapy were identified. Prior to 2005, patients were recommended to receive R-CHOP + RT (RT era). Beginning in 2005, EOT PET was used to guide RT and only those with a PET-positive scan received RT (PET era). In total, 159 patients were identified, 94% were treated with R-CHOP and 44% received RT (78% in RT era, 28% in PET era). The 5-year time to progression (TTP) and overall survival (OS) for the entire cohort were 80% and 89%, respectively, similar across treatment eras. Overall, 10% had refractory disease. In total, 113 patients had an EOT PET scan: 63% negative and 37% positive with a 5-year TTP of 90% vs 71% and 5-year OS of 97% vs 88%, respectively. For those with Deauville (D)-scored PET scans (n = 103), the 5-year TTP for PET-negative cases by Deauville criteria (D1-D3, DX) was 91%, with inferior outcomes for D5 vs D4 (5-year TTP 33% vs 87%, P = .0002). Outcomes for PMBCL treated with RCHOP are favorable and use of a PET-adapted approach reduces RT in the majority of patients. A small proportion have refractory disease and may benefit from an alternate treatment.

Etoposide-based treatment of adult HLH is associated with high biochemical response but poor survival outcomes.

Etoposide-based treatment is the standard of care for adult HLH in many centers, yet there remains a paucity of data regarding treatment outcomes. We conducted a retrospective study of 23 adults treated with etoposide-based therapy compared to 10 pediatric HLH cases at a single center. At diagnosis, the median serum ferritin was 20,071 µg/L and 937 µg/L in adults and children, respectively; median sIL-2r was 14,524 U/mL and 4,478 U/mL. Biochemical response to treatment was high, with 21/23 adults achieving >75% reduction in serum ferritin, but one year survival was only 7/21 compared to 7/10 in pediatric cases.

Validation of a simplified international prognostic score (IPS-3) in patients with advanced-stage classic Hodgkin lymphoma.

A novel prognostic score (IPS-3), comprised of only three of the seven IPS-7 indicators (age ≥45, stage IV, haemoglobin <105 g/l), was recently proposed as a simplified model for advanced-stage classic Hodgkin lymphoma (cHL). We aimed to validate this model in advanced-stage cHL patients treated with doxorubicin, bleomycin, vinblastine, dacarbazine (ABVD) in British Columbia. The estimated five-year freedom from progression (FFP) for scores of 0, 1, 2 and 3 were very similar to the original report at 84%, 76%, 72% and 68% respectively. The IPS-3 score is highly reproducible in this independent dataset and its simplicity makes it appealing for everyday clinical practice.

HTT haplotypes contribute to differences in Huntington disease prevalence between Europe and East Asia.

Huntington disease (HD) results from CAG expansion in the huntingtin (HTT) gene. Although HD occurs worldwide, there are large geographic differences in its prevalence. The prevalence in populations derived from Europe is 10-100 times greater than in East Asia. The European general population chromosomes can be grouped into three major haplogroups (group of similar haplotypes): A, B and C. The majority of HD chromosomes in Europe are found on haplogroup A. However, in the East-Asian populations of China and Japan, we find the majority of HD chromosomes are associated with haplogroup C. The highest risk HD haplotypes (A1 and A2), are absent from the general and HD populations of China and Japan, and therefore provide an explanation for why HD prevalence is low in East Asia. Interestingly, both East-Asian and European populations share a similar low level of HD on haplogroup C. Our data are consistent with the hypothesis that different HTT haplotypes have different mutation rates, and geographic differences in HTT haplotypes explain the difference in HD prevalence. Further, the bias for expansion on haplogroup C in the East-Asian population cannot be explained by a higher average CAG size, as haplogroup C has a lower average CAG size in the general East-Asian population compared with other haplogroups. This finding suggests that CAG-tract size is not the only factor important for CAG instability. Instead, the expansion bias may be because of genetic cis-elements within the haplotype that influence CAG instability in HTT, possibly through different mutational mechanisms for the different haplogroups.

CAG expansion in the Huntington disease gene is associated with a specific and targetable predisposing haplogroup.

Huntington disease (HD) is an autosomal-dominant disorder that results from >or=36 CAG repeats in the HD gene (HTT). Approximately 10% of patients inherit a chromosome that underwent CAG expansion from an unaffected parent with <36 CAG repeats. This study is a comprehensive analysis of genetic diversity in HTT and reveals that HD patients of European origin (n = 65) have a significant enrichment (95%) of a specific set of 22 tagging single nucleotide polymorphisms (SNPs) that constitute a single haplogroup. The disease association of many SNPs is much stronger than any previously reported polymorphism and was confirmed in a replication cohort (n = 203). Importantly, the same haplogroup is also significantly enriched (83%) in individuals with 27-35 CAG repeats (intermediate alleles, n = 66), who are unaffected by the disease, but have increased CAG tract sizes relative to the general population (n = 116). These data support a stepwise model for CAG expansion into the affected range (>or=36 CAG) and identifies specific haplogroup variants in the general population associated with this instability. The specific variants at risk for CAG expansion are not present in the general population in China, Japan, and Nigeria where the prevalence of HD is much lower. The current data argue that cis-elements have a major predisposing influence on CAG instability in HTT. The strong association between specific SNP alleles and CAG expansion also provides an opportunity of personalized therapeutics in HD where the clinical development of only a small number of allele-specific targets may be sufficient to treat up to 88% of the HD patient population.