Computed tomography radiomics-based cross-sectional detection of mandibular osteoradionecrosis in head and neck cancer survivors.

Purpose: This study aims to identify radiomic features extracted from contrast-enhanced CT scans that differentiate osteoradionecrosis (ORN) from normal mandibular bone in patients with head and neck cancer (HNC) treated with radiotherapy (RT). Materials and Methods: Contrast-enhanced CT (CECT) images were collected for 150 patients (80% train, 20% test) with confirmed ORN diagnosis at The University of Texas MD Anderson Cancer Center between 2008 and 2018. Using PyRadiomics, radiomic features were extracted from manually segmented ORN regions and the corresponding automated control regions, the later defined as the contralateral healthy mandible region. A subset of pre-selected features was obtained based on correlation analysis (r > 0.95) and used to train a Random Forest (RF) classifier with Recursive Feature Elimination. Model explainability SHapley Additive exPlanations (SHAP) analysis was performed on the 20 most important features identified by the trained RF classifier. Results: From a total of 1316 radiomic features extracted, 810 features were excluded due to high collinearity. From a set of 506 pre-selected radiomic features, the optimal subset resulting on the best discriminative accuracy of the RF classifier consisted of 67 features. The RF classifier was well calibrated (Log Loss 0.296, ECE 0.125) and achieved an accuracy of 88% and a ROC AUC of 0.96. The SHAP analysis revealed that higher values of Wavelet-LLH First-order Mean and Median were associated with ORN of the jaw (ORNJ). Conversely, higher Exponential GLDM Dependence Entropy and lower Square First-order Kurtosis were more characteristic of normal mandibular tissue. Conclusion: This study successfully developed a CECT-based radiomics model for differentiating ORNJ from healthy mandibular tissue in HNC patients after RT. Future work will focus on the detection of subclinical ORNJ regions to guide earlier interventions.

Artificial Intelligence and Machine Learning in Cancer Pain: A Systematic Review.

BACKGROUND/OBJECTIVES: Pain is a challenging multifaceted symptom reported by most cancer patients. This systematic review aims to explore applications of artificial intelligence/machine learning (AI/ML) in predicting pain-related outcomes and pain management in cancer. METHODS: A comprehensive search of Ovid MEDLINE, EMBASE and Web of Science databases was conducted using terms: "Cancer," "Pain," "Pain Management," "Analgesics," "Artificial Intelligence," "Machine Learning," and "Neural Networks" published up to September 7, 2023. AI/ML models, their validation and performance were summarized. Quality assessment was conducted using PROBAST risk-of-bias andadherence to TRIPOD guidelines. RESULTS: Forty four studies from 2006 to 2023 were included. Nineteen studies used AI/ML for classifying pain after cancer therapy [median AUC 0.80 (range 0.76-0.94)]. Eighteen studies focused on cancer pain research [median AUC 0.86 (range 0.50-0.99)], and 7 focused on applying AI/ML for cancer pain management, [median AUC 0.71 (range 0.47-0.89)]. Median AUC (0.77) of models across all studies. Random forest models demonstrated the highest performance (median AUC 0.81), lasso models had the highest median sensitivity (1), while Support Vector Machine had the highest median specificity (0.74). Overall adherence to TRIPOD guidelines was 70.7%. Overall, high risk-of-bias (77.3%), lack of external validation (14%) and clinical application (23%) was detected. Reporting of model calibration was also missing (5%). CONCLUSION: Implementation of AI/ML tools promises significant advances in the classification, risk stratification, and management decisions for cancer pain. Further research focusing on quality improvement, model calibration, rigorous external clinical validation in real healthcare settings is imperative for ensuring its practical and reliable application in clinical practice.

Mechanical regulation to interfacial thermal transport in GaN/diamond heterostructures for thermal switch.

Gallium nitride offers an ideal material platform for next-generation high-power electronics devices, which enable a spectrum of applications. The thermal management of the ever-growing power density has become a major bottleneck in the performance, reliability, and lifetime of the devices. GaN/diamond heterostructures are usually adopted to facilitate heat dissipation, given the extraordinary thermal conduction properties of diamonds. However, thermal transport is limited by the interfacial conductance at the material interface between GaN and diamond, which is associated with significant mechanical stress at the atomic level. In this work, we investigate the effect of mechanical strain perpendicular to the GaN/diamond interface on the interfacial thermal conductance of heterostructures using full-atom non-equilibrium molecular dynamics simulations. We found that the heterostructure exhibits severe mechanical stress at the interface in the absence of loading, which is due to lattice mismatch. Upon tensile/compressive loading, the interfacial stress is more pronounced, and the strain is not identical across the interface owing to the contrasting elastic moduli of GaN and diamond. In addition, the interfacial thermal conductance can be notably enhanced and suppressed by tensile and compressive strains, respectively, leading to a 400% variation in thermal conductance. More detailed analyses reveal that the change in interfacial thermal conductance is related to the surface roughness and interfacial bonding strength, as described by a generalized relationship. Moreover, phonon analyses suggest that the unequal mechanical deformation under compressive strain in GaN and diamond induces different frequency shifts in the phonon spectra, leading to an enhancement in phonon overlapping energy, which promotes phonon transport at the interface and elevates the thermal conductance and vice versa for tensile strain. The effect of strain on interface thermal conductance was investigated at various temperatures. Based on the mechanical tunability of thermal conductance, we propose a conceptual design for a mechanical thermal switch that regulates thermal conductance with excellent sensitivity and high responsiveness. This study offers a fundamental understanding of how mechanical strain can adjust interface thermal conductance in GaN/diamond heterostructures with respect to mechanical stress, deformation, and phonon properties. These results and findings lay the theoretical foundation for designing thermal management devices in a strain environment and shed light on developing intelligent thermal devices by leveraging the interplay between mechanics and thermal transport.

An ultra-efficient pretreatment method adopted LPUV/CoFe2O4/PMS-based photolysis for accurate detection of Cd(II) and Pb(II) in water via SWASV.

Dissolved organic matter (DOM) is a widely occurring substance in rivers that can strongly complex with heavy metal ions (HMIs), severely interfering with the electrochemical signal of anodic stripping voltammetry (ASV) and reducing the detection accuracy of HMIs in water. In this study, we investigated a novel advanced oxidation process (AOP) that involves the activation of peroxymonosulfate (PMS) using low-pressure ultraviolet (LPUV) radiation and CoFe2O4 photocatalysis. This novel AOP was used for the first time as an effective pretreatment method to break or weaken the complexation between HMIs and DOM, thereby restoring the electrochemical signals of HMIs. The key parameters, including the PMS concentration, CoFe2O4 concentration, and photolysis time, were optimized to be 6 mg/L, 12 mg/L, and 30 s for eliminating DOM interference during the electrochemical analysis of HMIs via LPUV/CoFe2O4-based photolysis. Investigations of the microstructure, surface morphology, specific surface area, and pore volume of CoFe2O4 were conducted to reveal the exceptional signal recovery capability of LPUV/CoFe2O4/PMS-based photolysis in mitigating interference from DOM during HMIs analysis. The PMS activation mechanism, which is critical to the signal recovery process, was elucidated by analyzing the reactive oxygen species (ROS) and the surface elemental composition of CoFe2O4. Additionally, the degradation and transformation behavior of humus-HMIs complexes were analyzed to study the mechanism of ASV signal recovery further. Notably, the detection results of HMIs in actual water samples obtained using the proposed pretreatment method were compared with those obtained from ICP-MS, yielding an RMSE less than 0.04 µg/L, which indicated the satisfactory performance of the proposed pretreatment method for the ASV detection of HMIs in complex actual samples.

Application of simultaneous uncertainty quantification and segmentation for oropharyngeal cancer use-case with Bayesian deep learning.

BACKGROUND: Radiotherapy is a core treatment modality for oropharyngeal cancer (OPC), where the primary gross tumor volume (GTVp) is manually segmented with high interobserver variability. This calls for reliable and trustworthy automated tools in clinician workflow. Therefore, accurate uncertainty quantification and its downstream utilization is critical. METHODS: Here we propose uncertainty-aware deep learning for OPC GTVp segmentation, and illustrate the utility of uncertainty in multiple applications. We examine two Bayesian deep learning (BDL) models and eight uncertainty measures, and utilize a large multi-institute dataset of 292 PET/CT scans to systematically analyze our approach. RESULTS: We show that our uncertainty-based approach accurately predicts the quality of the deep learning segmentation in 86.6% of cases, identifies low performance cases for semi-automated correction, and visualizes regions of the scans where the segmentations likely fail. CONCLUSIONS: Our BDL-based analysis provides a first-step towards more widespread implementation of uncertainty quantification in OPC GTVp segmentation.

Radiotherapy is used as a treatment for people with oropharyngeal cancer. It is important to distinguish the areas where cancer is present so the radiotherapy treatment can be targeted at the cancer. Computational methods based on artificial intelligence can automate this task but need to be able to distinguish areas where it is unclear whether cancer is present. In this study we compare these computational methods that are able to highlight areas where it is unclear whether or not cancer is present. Our approach accurately predicts how well these areas are distinguished by the models. Our results could be applied to improve the computational methods used during radiotherapy treatment. This could enable more targeted treatment to be used in the future, which could result in better outcomes for people with oropharyngeal cancer.

Associations Between Radiation Oncologist Demographic Factors and Segmentation Similarity Benchmarks: Insights From a Crowd-Sourced Challenge Using Bayesian Estimation.

PURPOSE: The quality of radiotherapy auto-segmentation training data, primarily derived from clinician observers, is of utmost importance. However, the factors influencing the quality of clinician-derived segmentations are poorly understood; our study aims to quantify these factors. METHODS: Organ at risk (OAR) and tumor-related segmentations provided by radiation oncologists from the Contouring Collaborative for Consensus in Radiation Oncology data set were used. Segmentations were derived from five disease sites: breast, sarcoma, head and neck (H&N), gynecologic (GYN), and GI. Segmentation quality was determined on a structure-by-structure basis by comparing the observer segmentations with an expert-derived consensus, which served as a reference standard benchmark. The Dice similarity coefficient (DSC) was primarily used as a metric for the comparisons. DSC was stratified into binary groups on the basis of structure-specific expert-derived interobserver variability (IOV) cutoffs. Generalized linear mixed-effects models using Bayesian estimation were used to investigate the association between demographic variables and the binarized DSC for each disease site. Variables with a highest density interval excluding zero were considered to substantially affect the outcome measure. RESULTS: Five hundred seventy-four, 110, 452, 112, and 48 segmentations were used for the breast, sarcoma, H&N, GYN, and GI cases, respectively. The median percentage of segmentations that crossed the expert DSC IOV cutoff when stratified by structure type was 55% and 31% for OARs and tumors, respectively. Regression analysis revealed that the structure being tumor-related had a substantial negative impact on binarized DSC for the breast, sarcoma, H&N, and GI cases. There were no recurring relationships between segmentation quality and demographic variables across the cases, with most variables demonstrating large standard deviations. CONCLUSION: Our study highlights substantial uncertainty surrounding conventionally presumed factors influencing segmentation quality relative to benchmarks.

Dataset of weekly intra-treatment diffusion weighted imaging in head and neck cancer patients treated with MR-Linac.

Radiation therapy (RT) is a crucial treatment for head and neck squamous cell carcinoma (HNSCC); however, it can have adverse effects on patients' long-term function and quality of life. Biomarkers that can predict tumor response to RT are being explored to personalize treatment and improve outcomes. While tissue and blood biomarkers have limitations, imaging biomarkers derived from magnetic resonance imaging (MRI) offer detailed information. The integration of MRI and a linear accelerator in the MR-Linac system allows for MR-guided radiation therapy (MRgRT), offering precise visualization and treatment delivery. This data descriptor offers a valuable repository for weekly intra-treatment diffusion-weighted imaging (DWI) data obtained from head and neck cancer patients. By analyzing the sequential DWI changes and their correlation with treatment response, as well as oncological and survival outcomes, the study provides valuable insights into the clinical implications of DWI in HNSCC.

ZnO/g-C3N4 photocatalyst activated by low-pressure ultraviolet for restoring the SWASV signals: A fast pretreatment method for electrochemically detecting Cd2+ and Pb2+ in soil extracts.

Soil organic matter (SOM) significantly impacts the detection accuracy of Cd2+ and Pb2+ using square wave anodic stripping voltammetry (SWASV) due to the complexation of SOM to heavy metal ions (HMIs), thereby attenuating SWASV signals. This study explored an effective pretreatment method that combined low-pressure ultraviolet (LPUV) photolysis with the ZnO/g-C3N4 photocatalyst, activating the photocatalyst to generate highly oxidative •OH radicals and O2•- radicals, which effectively disrupted this complexation, consequently restoring the electroactivity of HMIs and achieving high-fidelity SWASV signals. The parameters of the LPUV-ZnO/g-C3N4 photocatalytic system were meticulously optimized, including the pH of photolysis, duration of photolysis, g-C3N4 mass fraction, and concentration of the photocatalyst. Furthermore, the ZnO/g-C3N4 photocatalyst was thoroughly characterized, with an in-depth investigation on the synergistic interaction between ZnO and g-C3N4 and the mechanisms contributing to the restoration of SWASV signals. This synergistic interaction effectively separated charge carriers and reduced charge transfer resistance, enabling photogenerated electrons (e-) from the conduction band of g-C3N4 to be quickly transferred to the conduction band of ZnO, preventing the recombination of e- and hole (h+) and generating more radicals to disrupt complexation and restore the SWASV signals. Finally, the analysis of HMIs in real soil extracts using the proposed pretreatment method demonstrated high detection accuracy of 94.9% for Cd2+ and 99.8% for Pb2+, which validated the feasibility and effectiveness of the proposed method in environmental applications.

Enhancing Electrode Performance through Triple Distribution Modulation of Active Material, Conductive Agent, and Porosity.

The increasing demand for large-scale energy storage propels the development of lithium-ion batteries with high energy and high power density. Low tortuosity electrodes with aligned straight channels have proved to be effective in building such batteries. However, manufacturing such low tortuosity electrodes in large scale remains extremely challenging. In contrast, high-performance electrodes with customized gradients of materials and porosity are possible to be made by industrial roll-to-roll coating process. Yet, the desired design of gradients combining materials and porosity is unclear for high-performance gradient electrodes. Here, triple gradient LiFePO4 electrodes (TGE) are fabricated featuring distribution modulation of active material, conductive agent, and porosity by combining suction filtration with the phase inversion method. The effects and mechanism of active material, conductive agent, and porosity distribution on electrode performance are analyzed by experiments. It is found that the electrode with a gradual increase of active material content from current collector to separator coupled with the distribution of conductive agent and porosity in the opposite direction, demonstrates the best rate capability, the fastest electrochemical reaction kinetics, and the highest utilization of active material. This work provides valuable insights into the design of gradient electrodes with high performance and high potential in application.