Evolutionary Strategies Enable Systematic and Reliable Uncertainty Quantification: A Proof-of-Concept Pilot Study on Resting-State Functional MRI Language Lateralization.

Reliable and trustworthy artificial intelligence (AI), particularly in high-stake medical diagnoses, necessitates effective uncertainty quantification (UQ). Existing UQ methods using model ensembles often introduce invalid variability or computational complexity, rendering them impractical and ineffective in clinical workflow. We propose a UQ approach based on deep neuroevolution (DNE), a data-efficient optimization strategy. Our goal is to replicate trends observed in expert-based UQ. We focused on language lateralization maps from resting-state functional MRI (rs-fMRI). Fifty rs-fMRI maps were divided into training/testing (30:20) sets, representing two labels: "left-dominant" and "co-dominant." DNE facilitated acquiring an ensemble of 100 models with high training and testing set accuracy. Model uncertainty was derived from distribution entropies over the 100 model predictions. Expert reviewers provided user-based uncertainties for comparison. Model (epistemic) and user-based (aleatoric) uncertainties were consistent in the independently and identically distributed (IID) testing set, mainly indicating low uncertainty. In a mostly out-of-distribution (OOD) holdout set, both model and user-based entropies correlated but displayed a bimodal distribution, with one peak representing low and another high uncertainty. We also found a statistically significant positive correlation between epistemic and aleatoric uncertainties. DNE-based UQ effectively mirrored user-based uncertainties, particularly highlighting increased uncertainty in OOD images. We conclude that DNE-based UQ correlates with expert assessments, making it reliable for our use case and potentially for other radiology applications.

Temporal Lobe Necrosis in Head and Neck Cancer Patients after Proton Therapy to the Skull Base.

PURPOSE: To demonstrate temporal lobe necrosis (TLN) rate and clinical/dose-volume factors associated with TLN in radiation-naïve patients with head and neck cancer treated with proton therapy where the field of radiation involved the skull base. MATERIALS AND METHODS: Medical records and dosimetric data for radiation-naïve patients with head and neck cancer receiving proton therapy to the skull base were retrospectively reviewed. Patients with <3 months of follow-up, receiving <45 GyRBE or nonconventional fractionation, and/or no follow-up magnetic resonance imaging (MRI) were excluded. TLN was determined using MRI and graded using Common Terminology Criteria for Adverse Events (CTCAE) v5.0. Clinical (gender, age, comorbidities, concurrent chemotherapy, smoking, radiation techniques) and dose-volume parameters were analyzed for TLN correlation. The receiver operating characteristic curve and area under the curve (AUC) were performed to determine the cutoff points of significant dose-volume parameters. RESULTS: Between 2013 and 2019, 234 patients were included. The median follow-up time was 22.5 months (range = 3.2-69.3). Overall TLN rates of any grade, ≥ grade 2, and ≥ grade 3 were 5.6% (N = 13), 2.1%, and 0.9%, respectively. The estimated 2-year TLN rate was 4.6%, and the 2-year rate of any brain necrosis was 6.8%. The median time to TLN was 20.9 months from proton completion. Absolute volume receiving 40, 50, 60, and 70 GyRBE (absolute volume [aV]); mean and maximum dose received by the temporal lobe; and dose to the 0.5, 1, and 2 cm3 volume receiving the maximum dose (D0.5cm3, D1cm3, and D2cm3, respectively) of the temporal lobe were associated with greater TLN risk while clinical parameters showed no correlation. Among volume parameters, aV50 gave maximum AUC (0.921), and D2cm3 gave the highest AUC (0.935) among dose parameters. The 11-cm3 cutoff value for aV50 and 62 GyRBE for D2cm3 showed maximum specificity and sensitivity. CONCLUSION: The estimated 2-year TLN rate was 4.6% with a low rate of toxicities ≥grade 3; aV50 ≤11 cm3, D2cm3 ≤62 GyRBE and other cutoff values are suggested as constraints in proton therapy planning to minimize the risk of any grade TLN. Patients whose temporal lobe(s) unavoidably receive higher doses than these thresholds should be carefully followed with MRI after proton therapy.

Use of Larynx-Preservation Strategies in the Treatment of Laryngeal Cancer: American Society of Clinical Oncology Clinical Practice Guideline Update.

Purpose To update the guideline recommendations on the use of larynx-preservation strategies in the treatment of laryngeal cancer. Methods An Expert Panel updated the systematic review of the literature for the period from January 2005 to May 2017. Results The panel confirmed that the use of a larynx-preservation approach for appropriately selected patients does not compromise survival. No larynx-preservation approach offered a survival advantage compared with total laryngectomy and adjuvant therapy as indicated. Changes were supported for the use of endoscopic surgical resection in patients with limited disease (T1, T2) and for initial total laryngectomy in patients with T4a disease or with severe pretreatment laryngeal dysfunction. New recommendations for positron emission tomography imaging for the evaluation of regional nodes after treatment and best measures for evaluating voice and swallowing function were added. Recommendations Patients with T1, T2 laryngeal cancer should be treated initially with intent to preserve the larynx by using endoscopic resection or radiation therapy, with either leading to similar outcomes. For patients with locally advanced (T3, T4) disease, organ-preservation surgery, combined chemotherapy and radiation, or radiation alone offer the potential for larynx preservation without compromising overall survival. For selected patients with extensive T3 or large T4a lesions and/or poor pretreatment laryngeal function, better survival rates and quality of life may be achieved with total laryngectomy. Patients with clinically involved regional cervical nodes (N+) who have a complete clinical and radiologic imaging response after chemoradiation do not require elective neck dissection. All patients should undergo a pretreatment baseline assessment of voice and swallowing function and receive counseling with regard to the potential impact of treatment options on voice, swallowing, and quality of life. Additional information is available at www.asco.org/head-neck-cancer-guidelines and www.asco.org/guidelineswiki .

Evaluation of sinus computed tomography scans: a collaborative approach between radiology and otolaryngology.

PURPOSE OF REVIEW: Sinus computed tomography (CT) interpretation is subject to individual variation. We propose a template-driven approach as a method to ensure CT interpretation that is complete and efficient. RECENT FINDINGS: Recent years have seen the description of newly noted anatomic abnormalities in the paranasal sinuses that should be noted during sinus CT interpretation. SUMMARY: There exists significant variation in the methodology by which sinus CT scans are interpreted and the findings are reported. We believe that it will benefit radiologists and otolaryngologists alike to use a simple, template-driven approach to describe the findings encountered on a sinus CT. In this study, we present one such approach.

American Society of Clinical Oncology clinical practice guideline for the use of larynx-preservation strategies in the treatment of laryngeal cancer.

PURPOSE: To develop a clinical practice guideline for treatment of laryngeal cancer with the intent of preserving the larynx (either the organ itself or its function). This guideline is intended for use by oncologists in the care of patients outside of clinical trials. METHODS: A multidisciplinary Expert Panel determined the clinical management questions to be addressed and reviewed the literature available through November 2005, with emphasis given to randomized controlled trials of site-specific disease. Survival, rate of larynx preservation, and toxicities were the principal outcomes assessed. The guideline underwent internal review and approval by the Panel, as well as external review by additional experts, members of the American Society of Clinical Oncology (ASCO) Health Services Committee, and the ASCO Board of Directors. RESULTS: Evidence supports the use of larynx-preservation approaches for appropriately selected patients without a compromise in survival; however, no larynx-preservation approach offers a survival advantage compared with total laryngectomy and adjuvant therapy with rehabilitation as indicated. RECOMMENDATIONS: All patients with T1 or T2 laryngeal cancer, with rare exception, should be treated initially with intent to preserve the larynx. For most patients with T3 or T4 disease without tumor invasion through cartilage into soft tissues, a larynx-preservation approach is an appropriate, standard treatment option, and concurrent chemoradiotherapy therapy is the most widely applicable approach. To ensure an optimum outcome, special expertise and a multidisciplinary team are necessary, and the team should fully discuss with the patient the advantages and disadvantages of larynx-preservation options compared with treatments that include total laryngectomy.