A pilot study of machine-learning based automated planning for primary brain tumours.

PURPOSE: High-quality radiotherapy (RT) planning for children and young adults with primary brain tumours is essential to minimize the risk of late treatment effects. The feasibility of using automated machine-learning (ML) to aid RT planning in this population has not previously been studied. METHODS AND MATERIALS: We developed a ML model that identifies learned relationships between image features and expected dose in a training set of 95 patients with a primary brain tumour treated with focal radiotherapy to a dose of 54 Gy in 30 fractions. This ML method was then used to create predicted dose distributions for 15 previously-treated brain tumour patients across two institutions, as a testing set. Dosimetry to target volumes and organs-at-risk (OARs) were compared between the clinically-delivered (human-generated) plans versus the ML plans. RESULTS: The ML method was able to create deliverable plans in all 15 patients in the testing set. All ML plans were generated within 30 min of initiating planning. Planning target volume coverage with 95% of the prescription dose was attained in all plans. OAR doses were similar across most structures evaluated; mean doses to brain and left temporal lobe were lower in ML plans than manual plans (mean difference to left temporal, - 2.3 Gy, p = 0.006; mean differences to brain, - 1.3 Gy, p = 0.017), whereas mean doses to right cochlea and lenses were higher in ML plans (+ 1.6-2.2 Gy, p < 0.05 for each). CONCLUSIONS: Use of an automated ML method to aid RT planning for children and young adults with primary brain tumours is dosimetrically feasible and can be successfully used to create high-quality 54 Gy RT plans. Further evaluation after clinical implementation is planned.

Neurocognitive Performance in Adults Treated With Radiation for a Primary Brain Tumor.

Purpose: The contributory effects of radiation dose to different brain regions on neurocognitive performance after radiation therapy (RT) for primary brain tumors is not well known. Methods and Materials: In this retrospective cohort study, 30 patients with brain tumors treated with photon RT were identified, and radiation dosimetric parameters across brain regions were calculated. All patients had longitudinal neurocognitive evaluations at baseline and after treatment. Generalized estimating equations were used to model each neurocognitive endpoint over time in a multivariable analysis, while adjusted for multiple comparisons of brain regions. Results: Median follow-up from RT to last assessment was 4.1 years. Fewer years of formal education and older age at the time of RT were associated with lower scores in language, verbal memory, and working memory, after adjustment for baseline scores in multivariable analyses. Higher radiation dose to specific brain regions was not associated with declines in any of the evaluated cognitive domains. On average, there was no clinically significant decline (magnitude of z score change >1) between first and last neurocognitive evaluation. Across each individual cognitive domain, fewer than 15% of patients were impaired at most recent follow-up. Conclusions: In this small study of 30 patients treated with RT for a primary brain tumor, brain region dosimetry was not associated with decline in cognitive performance. Older age at time of RT and fewer years of formal education were associated with declines in cognitive performance, suggesting that effects of nondosimetric factors on cognitive performance should be considered alongside treatment factors and dosimetry in neuro-oncology research.

Hearing Loss After Radiation and Chemotherapy for CNS and Head-and-Neck Tumors in Children.

PURPOSE: Hearing loss (HL) is a serious secondary effect of treatment for CNS and head-and-neck tumors in children. The goal of this study was to evaluate incidence and risk factors for HL in patients with multiple ototoxic exposures. PATIENTS AND METHODS: We evaluated 340 ears from 171 patients with CNS or head-and-neck tumors treated with radiation, with or without chemotherapy, who had longitudinal audiologic evaluation. International Society of Pediatric Oncology-Boston grades were assigned to 2,420 hearing assessments. Multivariable weighted ordinal logistic regression was fitted to evaluate the effect of clinicopathologic features on HL. RESULTS: Mean cochlea dose (odds ratio [OR] 1.04 per Gy, P < .001), time since radiotherapy (RT; OR 1.21 per year, P < .001), cisplatin dose (OR 1.48 per 100 mg/m2, P < .001), and carboplatin dose (OR 1.41 per 1,000 mg/m2, P = .002) were associated with increasing International Society of Pediatric Oncology-Boston grade of HL. There was no synergistic effect of RT and cisplatin (interaction term, P = .53) or RT and carboplatin (interaction term, P = .85). Cumulative incidence of high-frequency HL (> 4 kHz) was 50% or greater at 5 years after RT if mean cochlea dose was > 30 Gy, while incidence of HL across all frequencies continued to increase beyond 5 years after RT. CONCLUSION: Children treated with radiation and chemotherapy experience a high incidence of HL over time, with associations found between more severe HL and cisplatin or carboplatin dose as well as mean cochlea dose. Mean cochlea dose of ≤ 30 Gy is proposed as a goal to reduce the risk of HL; a lower threshold (20-25 Gy) may be considered in patients receiving platinum chemotherapy to reduce cumulative HL burden.

Intellectual changes after radiation for children with brain tumors: which brain structures are most important?

BACKGROUND: The objective of this study was to evaluate the contribution of radiation dose to different intracranial structures on changes in intellectual function for children with brain tumors. METHODS: We evaluated children with brain tumors treated in 2005-2017 who had longitudinal neuropsychological assessments and available photon dosimetric data (if radiation therapy [RT] given). Full Scale Intelligence Quotient (FSIQ) and index scores were evaluated (perceptual reasoning index [PRI], processing speed index [PSI], verbal comprehension index [VCI], and working memory index [WMI]). Multivariable linear mixed effects models were used to model endpoints, with age at RT and dose to different brain regions as fixed effects and patient-specific random intercepts. P-values (P*) were adjusted for multiple comparisons. RESULTS: Sixty-nine patients were included, 56 of whom received RT. Median neuropsychological follow-up was 3.2 years. Right temporal lobe mean dose was strongly associated with decline in FSIQ (P* = 0.005); with each gray increase in mean dose, there was a decrease of 0.052 FSIQ points per year. Dose to 50% (D50) of the supratentorial brain was associated with decline in PSI (P* = 0.006) and WMI (P* = 0.001). Right and left hippocampus D50 were individually strongly associated with declines in VCI (P* = 0.009 for each). Presence of a ventriculoperitoneal shunt decreased FSIQ by 10 points. CONCLUSIONS: We reported associations between dosimetry to specific brain regions and intellectual outcomes, with suggested avoidance structures during RT planning. These models can help clinicians anticipate changes in neurocognition post-RT and guide selection of an optimal RT plan.

From uncertainty to pathogenicity: clinical and functional interrogation of a rare TP53 in-frame deletion.

Li-Fraumeni syndrome (LFS) is a highly penetrant cancer predisposition syndrome caused by heterozygous germline mutations in the TP53 gene. Although more than 200 missense and null TP53 mutations are well established as disease-causing, little is known about the pathogenicity and cancer risks associated with small in-frame deletions. This leads to challenges in variant classification and subsequent difficulty making a molecular diagnosis. We report the genetic testing process for a pediatric patient diagnosed with an undifferentiated high-grade brain tumor following his mother's diagnosis of early-onset bilateral breast cancer. Sequential testing revealed that both harbored a heterozygous three-nucleotide deletion in exon 7 of TP53 (c.764_766delTCA; I255del), which was classified as a variant of uncertain significance. Because the maternal family history was void of any other LFS spectrum tumors, additional information was needed to effectively classify the variant. Targeted TP53 testing of the patient's maternal grandparents confirmed that neither carried the variant; this new de novo data upgraded the variant classification to likely pathogenic. To assess the impact of this mutation on the encoded p53 protein, additional in vitro analyses were performed. Structural modeling predicted that the deletion of isoleucine at codon 255 would disrupt the architecture of the DNA-binding domain, suggesting that it might negatively impact p53 function. Consistent with this notion, the I255del mutant protein exhibited significantly impaired transcriptional activity and greatly reduced growth suppressive properties, similar to more well-characterized LFS-associated p53 mutants. This report illustrates the importance of seeking additional evidence to assign proper pathogenicity classification, which enables optimal genetic counseling and medical management of individuals with LFS and their at-risk relatives.

Elective single embryo transfer and perinatal outcomes: a systematic review and meta-analysis.

OBJECTIVE: To determine whether elective single embryo transfer (eSET) lowers the risk of poor perinatal outcomes associated with IVF, when [1] compared with double embryo transfer (DET) or multiple embryo transfer (MET), and separately, [2] compared with spontaneous conceptions. DESIGN: Systematic review and meta-analysis. SETTING: Centers for reproductive care. PATIENT(S): Infertility patients. INTERVENTION(S): MEDLINE, Embase, and bibliographies were searched for the period 1978-2011. Two reviewers independently assessed titles, abstracts, and full studies, extracted data, and assessed quality. Dichotomous data were pooled using relative risks and continuous data with mean differences using a random effects model. Randomized controlled trials (RCTs), case-control studies, and cohort studies that examined any of the primary or secondary outcomes in singleton, twin, or multiple-order infants conceived by eSET as compared with [1] those conceived by DET or MET or [2] spontaneously conceived singleton gestations were included. MAIN OUTCOME MEASURE(S): Primary outcomes were preterm birth (PTB, <37 weeks' gestation) and low birth weight (LBW, <2,500 g). RESULT(S): Sixteen studies were included (eight RCTs, eight cohort studies). Compared with DET-conceived infants, eSET-conceived singletons were less likely to be born either preterm (RCT-based relative risk [RR] 0.37, 95% confidence interval [CI] 0.25-0.55) or with LBW (RCT-based RR 0.25, 95% CI 0.15-0.45; cohort study RR 0.51, 95% CI 0.29-0.91). However, compared with spontaneously conceived singletons, eSET gestations had higher risks of PTB (RR 2.13, 95% CI 1.26-3.61), placenta previa (RR 6.02, 95% CI 2.79-13.01), gestational diabetes (RR 1.69, 95% CI 1.19-2.42), and ectopic pregnancy (RR 6.40, 95% CI 4.38-9.35). CONCLUSION(S): Elective single embryo transfer is associated with decreased risks of PTB and LBW compared with DET but higher risks of PTB compared with spontaneously conceived singletons.