Utilizing Artificial Intelligence for Head and Neck Cancer Outcomes Prediction From Imaging.

Artificial intelligence (AI)-based models have become a growing area of interest in predictive medicine and have the potential to aid physician decision-making to improve patient outcomes. Imaging and radiomics play an increasingly important role in these models. This review summarizes recent developments in the field of radiomics for AI in head and neck cancer. Prediction models for oncologic outcomes, treatment toxicity, and pathological findings have all been created. Exploratory studies are promising; however, validation studies that demonstrate consistency, reproducibility, and prognostic impact remain uncommon. Prospective clinical trials with standardized procedures are required for clinical translation.

Assessment of function and quality of life in a phase II multi-institutional clinical trial of fractionated simultaneous in-field boost radiotherapy for patients with 1-3 metastases.

We examined functional outcomes and quality of life of whole brain radiotherapy (WBRT) with integrated fractionated stereotactic radiotherapy boost (FSRT) for brain metastases treatment. Eighty seven people with 1-3 brain metastases (54/87 lung primary, 42/87 single brain metastases) were enrolled on this Phase II trial of WBRT (30 Gy/10) + simultaneous FSRT, (60 Gy/10). Median overall follow-up and survival was 5.4 months, 6 month actuarial intra-lesional control was 78 %; only 1 patient exhibited grade 4 toxicity (worsened seizures); most treatment related toxicity was grade 1 or 2; 2/87 patients demonstrated asymptomatic radiation necrosis on follow-up imaging. Mean (Min-Max) baseline KPS, Mini Mental Status Exam (MMSE) and FACT-BR quality of life were 83 (70-100), 28 (21-30) and 143 (98-153). Lower baseline MMSE (but not KPS or FACT-Br) was associated with worse survival after adjusting for age, number of metastases, primary and extra-cranial disease status. Crude rates of deterioration (>10 points decrease from baseline for KPS and FACT-Br, MMSE fall to <27) ranged from 26 to 38 % for KPS, 32-59 % for FACT-Br and 0-16 % for MMSE depending on the time-point assessed with higher rates generally noted at earlier time points (≤6 months post-treatment). Using a linear mixed models analysis, significant declines from baseline were noted for KPS and FACT-Br (largest effects at 6 weeks to 3 months) with no significant change in MMSE. The effects on function and quality of life of this integrated treatment of WBRT + simultaneous FSRT were similar to other published series combining WBRT + radiosurgery.

Evaluating the impact of an integrated multidisciplinary head & neck competency-based anatomy & radiology teaching approach in radiation oncology: a prospective cohort study.

BACKGROUND: Modern radiation oncology demands a thorough understanding of gross and cross-sectional anatomy for diagnostic and therapeutic applications. Complex anatomic sites present challenges for learners and are not well-addressed in traditional postgraduate curricula. A multidisciplinary team (MDT) based head-and-neck gross and radiologic anatomy program for radiation oncology trainees was developed, piloted, and empirically assessed for efficacy and learning outcomes. METHODS: Four site-specific MDT head-and-neck seminars were implemented, each involving a MDT delivering didactic and case-based instruction, supplemented by cadaveric presentations. There was no dedicated contouring instruction. Pre- and post-testing were performed to assess knowledge, and ability to apply knowledge to the clinical setting as defined by accuracy of contouring. Paired analyses of knowledge pretests and posttests were performed by Wilcoxon matched-pair signed-rank test. RESULTS: Fifteen post-graduate trainees participated. A statistically significant (p < 0.001) mean absolute improvement of 4.6 points (17.03%) was observed between knowledge pretest and posttest scores. Contouring accuracy was analyzed quantitatively by comparing spatial overlap of participants' pretest and posttest contours with a gold standard through the dice similarity coefficient. A statistically significant improvement in contouring accuracy was observed for 3 out of 20 anatomical structures. Qualitative and quantitative feedback revealed that participants were more confident at contouring and were enthusiastic towards the seminars. CONCLUSIONS: MDT seminars were associated with improved knowledge scores and resident satisfaction; however, increased gross and cross-sectional anatomic knowledge did not translate into improvements in contouring accuracy. Further research should evaluate the impact of hands-on contouring sessions in addition to dedicated instructional sessions to develop competencies.

Cervical spine abnormalities in 22q11.2 deletion syndrome.

OBJECTIVE: The 22q11.2 deletion syndrome is among the most common head-and-neck-related syndromes. The literature has examined many of the phenotypic features of 22q11.2 deletion syndrome; however, few studies have explored the manifestation of cervical spine abnormalities. In this study, we compared the cervical spines of individuals with and without 22q11.2 deletion syndrome using diagnostic imaging. DESIGN: A retrospective case-control study, with age- and sex-matched control participants who underwent flexion/extension x-rays and either a computed tomography or MRI scan. SETTING: PARTICIPANTS presented to the velopharyngeal insufficiency clinic at Victoria Hospital in London, Ontario, Canada, a tertiary care center. PARTICIPANTS: Sixteen pediatric patients (

Long-term follow-up of an attenuated presentation of NAXE-related disease, a potentially actionable neurometabolic disease: a case report.

Background: Early-onset progressive encephalopathy with brain edema and/or leukoencephalopathy (PEBEL-1) is an autosomal recessive disorder whereby a fluctuating clinical course is exacerbated by febrile illnesses. Pathogenic NAD(P)HX epimerase (NAXE) gene mutations underpin this disorder. This mutation damages the metabolite repair system involved in regenerating crucial redox carriers. Longer survival has rarely been reported in this potentially actionable entity. Objectives: This case study aims to report a milder phenotype of a patient with NAXE gene mutation and his longitudinal follow-up of more than 20 years. Case report: A 24-year-old man first became symptomatic in infancy with frequent initial neurological decompensations in the setting of infections with subsequent clinical improvement followed by stability with residual cerebellar dysfunction. Clinical features noted over the years include chronic ataxia, nystagmus, ptosis, mild spasticity of lower limbs, and neuropsychiatric symptoms. Cerebellar and spinal cord atrophy were noted in cranial and spinal MR imaging. Biallelic homozygous variants in the NAXE gene (c.733 A>C) were identified on whole exome sequencing. Symptom management included the initiation of a mitochondrial cocktail with carnitine, coenzyme Q, and thiamine. Subsequently, niacin (Vitamin B3), which is involved in the cellular biosynthesis of NAD+, was added, given its potentially beneficial therapeutic impact. Conclusion: A missense homozygous variant in the NAXE gene is described in this patient with a milder clinical phenotype of the disease. Supplementation with niacin in addition to a mitochondrial cocktail presents a potential supportive therapeutic option to reduce disease progression.

Bloom Syndrome Complicated by Low-Grade Lymphoma and Non-small Cell Lung Cancer: A Case Report.

Bloom syndrome (BS) is a rare autosomal recessive genetic disorder characterized by photosensitivity, rashes on the nose and cheeks, short stature, and a predisposition to develop cancers. In this report, we discuss the diagnosis and management of a 34-year-old Canadian male BS patient, originally from Honduras, who developed B-cell lymphoma and a subsequent non-small cell lung carcinoma (NSCLC). Given the radiosensitivity of the patient due to his BS diagnosis and the early stage of the low-grade B-cell lymphoma, we relied on surveillance as the clinical approach to his management. The treatment for NSCLC was initiated in stage III of the disease and was palliative in intent. Chemotherapy (12 rounds of paclitaxel, with the dosage gradually increasing from 48 mg to 58 mg and finally to 72 mg) was employed to shrink the left upper lobe (LUL) lung mass. Subsequently, radiotherapy (3000 cGY in 20 fractions) was administered to improve symptoms further. The radiotherapy dose schedule was modified given the patient's BS diagnosis to avoid excessive toxicity. The palliative treatment course was well tolerated by the patient and resulted in symptom relief. However, his cancer progressed over the course of the treatment, ultimately resulting in his death 18 months after the initial diagnosis of NSCLC; no autopsy was performed. We believe this report will spur clinicians to engage in fruitful discussions about tailoring chemotherapy and radiation therapy regimens for treating cancer in BS patients.

A milder form of molybdenum cofactor deficiency type A presenting as Leigh's syndrome-like phenotype highlighting the secondary mitochondrial dysfunction: a case report.

Background: Molybdenum cofactor deficiency (MoCD) (OMIM# 252150) is an autosomal-recessive disorder caused by mutations in four genes involved in the molybdenum cofactor (MOCO) biosynthesis pathway. Objectives: We report a milder phenotype in a patient with MOCS1 gene mutation who presented with a Leigh-like presentation. Case report: We present the case of a 10-year-old boy who was symptomatic at the age of 5 months with sudden onset of dyskinesia, nystagmus, and extrapyramidal signs following a febrile illness. Initial biochemical, radiological, and histopathological findings a Leigh syndrome-like phenotype; however, whole-exome sequencing detected compound heterozygous mutations in MOCS1 gene, c.1133 G>C and c.217C>T, confirming an underlying MoCD. This was biochemically supported by low uric acid level of 80 (110-282 mmol/L) and low cystine level of 0 (3-49), and a urine S-sulfocysteine at 116 (0-15) mmol/mol creatinine. The patient was administered methionine- and cystine-free formulas. The patient has remained stable, with residual intellectual, speech, and motor sequelae. Conclusion: This presentation expands the phenotypic variability of late-onset MoCD A and highlights the role of secondary mitochondrial dysfunction in its pathogenesis.

Unusual presentation of Chiari I in toddlers: case reports and review of the literature.

Toddlers with Chiari malformations can present with common symptoms, such as cough or drooling, which are associated with respiratory illnesses, delaying a correct diagnosis. Presentation does vary with age, and therefore can be different in older children when compared to infants. We present two cases of unusual presentations in toddlers and review the literature with an emphasis on acute presentation of Chiari in different age groups in children.

Demographic and pathologic factor regression to a growth rate model of p16-negative oral cavity squamous cell carcinoma.

Objectives: The current study aims to quantify the growth rate of p16-negative oral cavity squamous cell carcinoma, characterize causative relationships between demographic risk factors and tumor growth, and examine pathologic findings associated with the tumor growth rate at a tertiary care institution. It is hypothesized that causative relationships will be drawn between the individual sociodemographic and pathologic factors and oral cavity p16-negative squamous cell carcinoma growth rate. Methods: Prospectively recruited participants, receiving surgical intervention only, were followed from initial staging CT scan to surgical resection. Interval growth was calculated in cm3/week. Demographic information including age, sex, smoking history, alcohol consumption history, previous all-type malignancy, previous chemotherapy treatment, previous head or neck radiation exposure, and time interval elapsed between diagnosis and surgery was collected from each participant, and regression analysis was applied to determine causality. Results: Summary statistics revealed a mean growth rate for the study sample of 1.385cm3/week. Statistically significant regression correlations were detected between tumor growth and alcohol consumption, origination at the retromolar trigone, and clinical nodal stage. Conclusions: Through a small prospective cohort sample, the current study suggests clinical associations between alcohol consumption, origination at the retromolar trigone, and clinical nodal stage with rate of tumor growth. Future work will validate these relationships in a larger patient cohort, and against stronger modeling techniques. Level of Evidence: Prospective non-random cohort design.

Can We Identify Predictors of Success in Contouring Education for Radiation Oncology Trainees? An Analysis of the Anatomy and Radiology Contouring Bootcamp.

PURPOSE: Although several different contouring instructional programs are available to radiation oncologists and trainees, very little is known about which methods and resources benefit learners most, and whether some learners may need alternate forms of instruction. This study aimed to determine the factors that were predictors of learners' success in anatomy, radiology, and contouring education. METHODS AND MATERIALS: Participants in the online and face-to-face Anatomy and Radiology Contouring (ARC) Bootcamp completed pre- and postintervention evaluations that assessed anatomy/radiology knowledge, contouring skills, self-confidence, and spatial ability. Baseline factors were assessed as predictors of outcomes across multiple educational domains. RESULTS: One hundred and eighty (face-to-face: n = 40; online: n = 140) participants enrolled in the ARC Bootcamp, and 57 (face-to-face: n = 30; online: n = 27) participants completed both evaluations. Of the participants enrolled, 37% were female, and most were radiation oncology residents (62%). In the anatomy/radiology knowledge testing, all quartiles (based on baseline performance) improved numerically; however, the largest improvements occurred in learners with the lowest baseline scores (P < .001). At the end of the Bootcamp, learners with lower-performing scores did not reach the level of learners with the highest baseline scores (Bonferroni-corrected P < .001). Regarding the contouring assessment, improvements were only evident for the participants with lower-performing baseline scores (P < .05). Spatial anatomy skills, as measured by the spatial anatomy task, were correlated to contouring ability. Overall, the greatest improvements were seen for learners in postgraduate year 1 to 3, those with no previous rotation experience in a given discipline, and those who attended from other programs (ie, medical physics residents and medical students). CONCLUSIONS: The ARC Bootcamp improved all levels of performers' anatomy and radiology knowledge but only lower-performers' contouring ability. The course alone does not help lower-performing learners reach the abilities of higher-performers. The ARC Bootcamp tends to be most beneficial for participants with less radiation oncology experience. Curriculum modifications can be made to help support ARC Bootcamp participants with lower performing scores.

Is Remote Learning as Effective as In-Person Learning for Contouring Education? A Prospective Comparison of Face-to-Face versus Online Delivery of the Anatomy and Radiology Contouring Bootcamp.

PURPOSE: The Anatomy and Radiology Contouring (ARC) Bootcamp was a face-to-face (F2F) intervention providing integrated education for radiation oncology (RO) residents and medical physicists. To increase access, we launched an online offering in 2019. We evaluated the effect of the online course on participants' knowledge acquisition, contouring skills, and self-confidence by comparing it with the F2F course. METHODS AND MATERIALS: Using modules, the online course offers content similar to that of the F2F comparator. Participants from the 2019 F2F and the 2019-2020 online course completed pre- and postevaluations assessing anatomy and radiology knowledge, contouring skills, self-confidence, and course satisfaction. RESULTS: There were 180 individuals enrolled (F2F: n = 40; online: n = 140); 57 participants (F2F: n = 30; online: n = 27) completed both evaluations. The online course had a wider geographic participation (19 countries) than F2F (4 countries). F2F had primarily RO resident participation (80%), compared with online (41%). Both cohorts demonstrated similar improvements in self-confidence pertaining to anatomy and radiology knowledge, contouring skills, and interpreting radiology images (all P < .001). Both the online (mean ± SD improvement: 6.6 ± 6.7 on a 40-point scale; P < .001) and F2F (3.7 ± 5.7; P = .002) groups showed anatomy and radiology knowledge improvement. Only the F2F group demonstrated improvement with the contouring assessment (F2F: 0.10 ± 0.17 on a 1-point Dice scale; P = .004; online: 0.07 ± 0.16; P = .076). Both cohorts perceived the course as a positive experience (F2F: 4.8 ± 0.4 on a 5-point scale; online: 4.5 ± 0.6), stated it would improve their professional practice (F2F: 4.6 ± 0.5; online: 4.2 ± 0.8), and said they would recommend it to others (F2F: 4.8 ± 0.4; online: 4.4 ± 0.6). CONCLUSIONS: The online ARC Bootcamp demonstrated improved self-confidence, knowledge scores, and high satisfaction levels among participants. The offering had lower completion rates but was more accessible to geographic regions, provided a flexible learning experience, and allowed for ongoing education during the COVID-19 pandemic.

Implementation and evaluation of an online anatomy, radiology and contouring bootcamp for radiation therapists.

BACKGROUND: As new treatments and technologies have been introduced in radiation oncology, the clinical roles of radiation therapists (RTs) have expanded. However, there are few formal learning opportunities for RTs. An online, anatomy, radiology and contouring bootcamp (ARC Bootcamp) originally designed for medical residents was identified as a prospective educational tool for RTs. The purpose of this study was to evaluate an RT edition of the ARC Bootcamp on knowledge, contouring, and confidence, as well as to identify areas for future modification. METHODS: Fifty licensed RTs were enrolled in an eight-week, multidisciplinary, online RT ARC Bootcamp. Contouring practice was available throughout the course using an online contouring platform. Outcomes were evaluated using a pre-course and post-course multiple-choice quiz (MCQ), contouring evaluation and qualitative self-efficacy and satisfaction survey. RESULTS: Of the fifty enrolled RTs, 30 completed the course, and 26 completed at least one of the post-tests. Nineteen contouring dice similarity coefficient (DSC) scores were available for paired pre- and post-course analysis. RTs demonstrated a statistically significant increase in mean DSC scoring pooled across all contouring structures (mean ± SD improvement: 0.09 ± 0.18 on a scale from 0 to 1, p=0.020). For individual contouring structures, 3/15 reached significance in contouring improvement. MCQ scores were available for 26 participants and increased after RT ARC Bootcamp participation with a mean ± SD pre-test score of 18.6 ± 4.2 (46.5%); on a 40-point scale vs. post-test score of 24.5 ± 4.3 (61.4%) (p < 0.001). RT confidence in contouring, anatomy knowledge and radiographic identification improved after course completion (p < 0.001). Feedback from RTs recommended more contouring instruction, less in-depth anatomy review and more time to complete the course. CONCLUSIONS: The RT ARC Bootcamp was an effective tool for improving anatomy and radiographic knowledge among RTs. The course demonstrated improvements in contouring and overall confidence. However, only approximately half of the enrolled RTs completed the course, limiting statistical power. Future modifications will aim to increase relevance to RTs and improve completion rates.

A Phase II Multi-institutional Clinical Trial Assessing Fractionated Simultaneous In-Field Boost Radiotherapy for Brain Oligometastases.

Purpose/Objective Published preclinical and phase I clinical trial data suggest that fractionated lesional radiotherapy with 60 Gy in 10 fractions can serve as an alternative approach to single fraction radiosurgical boost for brain oligometastases.  Methods and Materials A phase II clinical trial (NCT01543542) of a total of 60 Gy in 10 fractions of lesional (one to three) radiotherapy (given simultaneously with whole-brain helical tomotherapy with 30 Gy in 10 fractions) was conducted at five institutions. We hypothesized that fractionated radiotherapy would be considered unsuitable if the median overall survival (OS) was degraded by two months or if six-month intracranial control (ICC) and intracranial lesion (ILC) were inferior by 10% compared with the published RTOG 9508 results. Results A total of 87 patients were enrolled over a 4.5-year accrual period. Radiological lesion and extralesional central nervous system progression were documented in 15/87 (17%) and 11/87 (13%) patients, respectively. Median OS for all patients was 5.4 months. Six-month actuarial estimates of ICC and ILC were 78% and 89%, respectively. However, only the ILC estimate achieved statistical significance (p=0.02), demonstrating non-inferiority to the a priori historical controls (OS: p=0.09, ICC=0.31). Two patients developed suspected asymptomatic radionecrosis. Conclusions The phase II estimates of ILC were demonstrated to be non-inferior to the results of the RTOG 9508.

Magnetic resonance imaging in the diagnosis of white matter signal abnormalities.

Background White matter abnormalities (WMAs) pose a diagnostic challenge when trying to establish etiologic diagnoses. During childhood and adult years, genetic disorders, metabolic disorders and acquired conditions are included in differential diagnoses. To assist clinicians and radiologists, a structured algorithm using cranial magnetic resonance imaging (MRI) has been recommended to aid in establishing working diagnoses that facilitate appropriate biochemical and genetic investigations. This retrospective pilot study investigated the validity and diagnostic utility of this algorithm when applied to white matter signal abnormalities (WMSAs) reported on imaging studies of patients seen in our clinics. Methods The MRI algorithm was applied to 31 patients selected from patients attending the neurometabolic/neurogenetic/metabolic/neurology clinics at a tertiary care hospital. These patients varied in age from 5 months to 79 years old, and were reported to have WMSAs on cranial MRI scans. Twenty-one patients had confirmed WMA diagnoses and 10 patients had non-specific WMA diagnoses (etiology unknown). Two radiologists, blinded to confirmed diagnoses, used clinical abstracts and the WMSAs present on patient MRI scans to classify possible WMA diagnoses utilizing the algorithm. Results The MRI algorithm displayed a sensitivity of 100%, a specificity of 30.0% and a positive predicted value of 74.1%. Cohen's kappa statistic for inter-radiologist agreement was 0.733, suggesting "good" agreement between radiologists. Conclusions Although a high diagnostic utility was not observed, results suggest that this MRI algorithm has promise as a clinical tool for clinicians and radiologists. We discuss the benefits and limitations of this approach.

Thymoma-associated Myasthenia Gravis in a Young Adult with Development of Paraneoplastic Limbic Encephalitis and Systemic Lupus Erythematosus Post-thymectomy: A Case Report.

We report a young adult with thymoma-associated myasthenia gravis (MG) who, following thymectomy, developed paraneoplastic limbic encephalitis (LE) and systemic lupus erythematosus (SLE). Although thymomas commonly co-occur with MG, LE is an uncommon autoimmune sequela. Herein, we discuss the pathophysiology of paraneoplastic LE and its management. Our report also highlights an unusual case of a thymoma patient who presented with multiple autoimmune disorders. The treatment of such a patient is therefore challenging and requires care from multiple specialized teams.