Integrating predictive coding and a user-centric interface for enhanced auditing and quality in cancer registry data.

Data curation for a hospital-based cancer registry heavily relies on the labor-intensive manual abstraction process by cancer registrars to identify cancer-related information from free-text electronic health records. To streamline this process, a natural language processing system incorporating a hybrid of deep learning-based and rule-based approaches for identifying lung cancer registry-related concepts, along with a symbolic expert system that generates registry coding based on weighted rules, was developed. The system is integrated with the hospital information system at a medical center to provide cancer registrars with a patient journey visualization platform. The embedded system offers a comprehensive view of patient reports annotated with significant registry concepts to facilitate the manual coding process and elevate overall quality. Extensive evaluations, including comparisons with state-of-the-art methods, were conducted using a lung cancer dataset comprising 1428 patients from the medical center. The experimental results illustrate the effectiveness of the developed system, consistently achieving F1-scores of 0.85 and 1.00 across 30 coding items. Registrar feedback highlights the system's reliability as a tool for assisting and auditing the abstraction. By presenting key registry items along the timeline of a patient's reports with accurate code predictions, the system improves the quality of registrar outcomes and reduces the labor resources and time required for data abstraction. Our study highlights advancements in cancer registry coding practices, demonstrating that the proposed hybrid weighted neural-symbolic cancer registry system is reliable and efficient for assisting cancer registrars in the coding workflow and contributing to clinical outcomes.

Exploring Deep Learning for Estimating the Isoeffective Dose of FLASH Irradiation From Mouse Intestinal Histological Images.

PURPOSE: Ultrahigh-dose-rate (FLASH) irradiation has been reported to reduce normal tissue damage compared with conventional dose rate (CONV) irradiation without compromising tumor control. This proof-of-concept study aims to develop a deep learning (DL) approach to quantify the FLASH isoeffective dose (dose of CONV that would be required to produce the same effect as the given physical FLASH dose) with postirradiation mouse intestinal histology images. METHODS AND MATERIALS: Eighty-four healthy C57BL/6J female mice underwent 16 MeV electron CONV (0.12 Gy/s; n = 41) or FLASH (200 Gy/s; n = 43) single fraction whole abdominal irradiation. Physical dose ranged from 12 to 16 Gy for FLASH and 11 to 15 Gy for CONV in 1 Gy increments. Four days after irradiation, 9 jejunum cross-sections from each mouse were hematoxylin and eosin stained and digitized for histological analysis. CONV data set was randomly split into training (n = 33) and testing (n = 8) data sets. ResNet101-based DL models were retrained using the CONV training data set to estimate the dose based on histological features. The classical manual crypt counting (CC) approach was implemented for model comparison. Cross-section-wise mean squared error was computed to evaluate the dose estimation accuracy of both approaches. The validated DL model was applied to the FLASH data set to map the physical FLASH dose into the isoeffective dose. RESULTS: The DL model achieved a cross-section-wise mean squared error of 0.20 Gy2 on the CONV testing data set compared with 0.40 Gy2 of the CC approach. Isoeffective doses estimated by the DL model for FLASH doses of 12, 13, 14, 15, and 16 Gy were 12.19 ± 0.46, 12.54 ± 0.37, 12.69 ± 0.26, 12.84 ± 0.26, and 13.03 ± 0.28 Gy, respectively. CONCLUSIONS: Our proposed DL model achieved accurate CONV dose estimation. The DL model results indicate that in the physical dose range of 13 to 16 Gy, the biologic dose response of small intestinal tissue to FLASH irradiation is represented by a lower isoeffective dose compared with the physical dose. Our DL approach can be a tool for studying isoeffective doses of other radiation dose modifying interventions.

Framework for Quality Assurance of Ultrahigh Dose Rate Clinical Trials Investigating FLASH Effects and Current Technology Gaps.

FLASH radiation therapy (FLASH-RT), delivered with ultrahigh dose rate (UHDR), may allow patients to be treated with less normal tissue toxicity for a given tumor dose compared with currently used conventional dose rate. Clinical trials are being carried out and are needed to test whether this improved therapeutic ratio can be achieved clinically. During the clinical trials, quality assurance and credentialing of equipment and participating sites, particularly pertaining to UHDR-specific aspects, will be crucial for the validity of the outcomes of such trials. This report represents an initial framework proposed by the NRG Oncology Center for Innovation in Radiation Oncology FLASH working group on quality assurance of potential UHDR clinical trials and reviews current technology gaps to overcome. An important but separate consideration is the appropriate design of trials to most effectively answer clinical and scientific questions about FLASH. This paper begins with an overview of UHDR RT delivery methods. UHDR beam delivery parameters are then covered, with a focus on electron and proton modalities. The definition and control of safe UHDR beam delivery and current and needed dosimetry technologies are reviewed and discussed. System and site credentialing for large, multi-institution trials are reviewed. Quality assurance is then discussed, and new requirements are presented for treatment system standard analysis, patient positioning, and treatment planning. The tables and figures in this paper are meant to serve as reference points as we move toward FLASH-RT clinical trial performance. Some major questions regarding FLASH-RT are discussed, and next steps in this field are proposed. FLASH-RT has potential but is associated with significant risks and complexities. We need to redefine optimization to focus not only on the dose but also on the dose rate in a manner that is robust and understandable and that can be prescribed, validated, and confirmed in real time. Robust patient safety systems and access to treatment data will be critical as FLASH-RT moves into the clinical trials.

Automating quality assurance of digital linear accelerators using a radioluminescent phosphor coated phantom and optical imaging.

Performing mechanical and geometric quality assurance (QA) tests for medical linear accelerators (LINAC) is a predominantly manual process that consumes significant time and resources. In order to alleviate this burden this study proposes a novel strategy to automate the process of performing these tests. The autonomous QA system consists of three parts: (1) a customized phantom coated with radioluminescent material; (2) an optical imaging system capable of visualizing the incidence of the radiation beam, light field or lasers on the phantom; and (3) software to process the captured signals. The radioluminescent phantom, which enables visualization of the radiation beam on the same surface as the light field and lasers, is placed on the couch and imaged while a predefined treatment plan is delivered from the LINAC. The captured images are then processed to self-calibrate the system and perform measurements for evaluating light field/radiation coincidence, jaw position indicators, cross-hair centering, treatment couch position indicators and localizing laser alignment. System accuracy is probed by intentionally introducing errors and by comparing with current clinical methods. The accuracy of self-calibration is evaluated by examining measurement repeatability under fixed and variable phantom setups. The integrated system was able to automatically collect, analyze and report the results for the mechanical alignment tests specified by TG-142. The average difference between introduced and measured errors was 0.13 mm. The system was shown to be consistent with current techniques. Measurement variability increased slightly from 0.1 mm to 0.2 mm when the phantom setup was varied, but no significant difference in the mean measurement value was detected. Total measurement time was less than 10 minutes for all tests as a result of automation. The system's unique features of a phosphor-coated phantom and fully automated, operator independent self-calibration offer the potential to streamline the QA process for modern LINACs.

Entry into vocational rehabilitation program following work-related hand injury: Potential candidates.

OBJECTIVES: This case-control study aimed to investigate the predictors of return to work (RTW) following work-related major forearm, wrist or hand injury at the preparation stage of return to work. MATERIAL AND METHODS: A total of 80 clients were recruited and divided into 2 groups depending on their readiness of RTW. The groups were compared with each other with regard to their demographics, compensation status, hand injury severity, health perception, and time off work (TOW) using correlation coefficient. Predictors of RTW were measured by logistic regression analysis. RESULTS: There were no significant differences in demographics and the severity of hand injury between 2 groups. Self-perceived physical functioning (p = 0.04), vitality (p = 0.01), mental health (p = 0.03) and TOW (p = 0.001) were significantly different between Action group and Preparation group. With binary logistic regression analysis, self-perceived vitality (odds ratio (OR) = 1.041) and TOW (OR = 0.996) were shown to be strongly predictive of RTW at the preparation stage of return to work. CONCLUSIONS: This study has shown that shorter TOW and better self-perceived vitality could predict early readiness for RTW after major work-related forearm, wrist or hand injury.

Comprehensive Analysis of the Incidence and Survival Patterns of Lung Cancer by Histologies, Including Rare Subtypes, in the Era of Molecular Medicine and Targeted Therapy: A Nation-Wide Cancer Registry-Based Study From Taiwan.

Lung cancer is the third most common cancer in the world and has the highest cancer mortality rate. A worldwide increasing trend of lung adenocarcinoma has been noted. In addition, the identification of epidermal growth factor receptor (EGFR) mutations and the introduction of EGFR inhibitors to successfully treat EGFR mutated non-small cell lung cancers are breakthroughs for lung cancer treatment. The current study evaluated the incidence and survival of lung cancer using data collected by the Taiwan Cancer Registry between 1996 and 2008. The results showed that the most common histologic subtype of lung cancer was adenocarcinoma, followed by squamous cell carcinoma, small cell carcinoma, large cell carcinoma, neuroendocrine tumors, lymphoma, and sarcoma. Overall, the incidence of lung cancer in Taiwan increased significantly from 1996 to 2008. An increased incidence was observed for adenocarcinoma, particularly for women, with an annual percentage change of 5.9, whereas the incidence of squamous cell carcinoma decreased. Among the subtypes of lung cancer, the most rapid increase occurred in neuroendocrine tumors with an annual percentage change of 15.5. From 1996-1999 to 2005-2008, the 1-year survival of adenocarcinoma increased by 10% for men, whereas the 1-, 3-, and 5-year survivals of adenocarcinoma for women increased by 18%, 11%, and 5%, respectively. Overall, the incidence of lung cancer has been increasing in Taiwan, although the trends were variable by subtype. The introduction of targeted therapies was associated with a significantly improved survival for lung adenocarcinoma in Taiwan; however, more studies are needed to explain the rising incidence of lung adenocarcinoma. In addition, it is important to investigate the molecular pathogenesis of the various subtypes of lung cancer to develop novel therapeutic agents.

Monitoring external beam radiotherapy using real-time beam visualization.

PURPOSE: To characterize the performance of a novel radiation therapy monitoring technique that utilizes a flexible scintillating film, common optical detectors, and image processing algorithms for real-time beam visualization (RT-BV). METHODS: Scintillating films were formed by mixing Gd2O2S:Tb (GOS) with silicone and casting the mixture at room temperature. The films were placed in the path of therapeutic beams generated by medical linear accelerators (LINAC). The emitted light was subsequently captured using a CMOS digital camera. Image processing algorithms were used to extract the intensity, shape, and location of the radiation field at various beam energies, dose rates, and collimator locations. The measurement results were compared with known collimator settings to validate the performance of the imaging system. RESULTS: The RT-BV system achieved a sufficient contrast-to-noise ratio to enable real-time monitoring of the LINAC beam at 20 fps with normal ambient lighting in the LINAC room. The RT-BV system successfully identified collimator movements with sub-millimeter resolution. CONCLUSIONS: The RT-BV system is capable of localizing radiation therapy beams with sub-millimeter precision and tracking beam movement at video-rate exposure.

A study of non-invasive Patlak quantification for whole-body dynamic FDG-PET studies of mice.

Physiological changes in dynamic PET images can be quantitatively estimated by kinetic modeling technique. The process of PET quantification usually requires an input function in the form of a plasma-time activity curve (PTAC), which is generally obtained by invasive arterial blood sampling. However, invasive arterial blood sampling poses many challenges especially for small animal studies, due to the subjects' limited blood volume and small blood vessels. A simple non-invasive quantification method based on Patlak graphical analysis (PGA) has been recently proposed to use a reference region to derive the relative influx rate for a target region without invasive blood sampling, and evaluated by using the simulation data of human brain FDG-PET studies. In this study, the non-invasive Patlak (nPGA) method was extended to whole-body dynamic small animal FDG-PET studies. The performance of nPGA was systematically investigated by using experimental mouse studies and computer simulations. The mouse studies showed high linearity of relative influx rates between the nPGA and PGA for most pairs of reference and target regions, when an appropriate underlying kinetic model was used. The simulation results demonstrated that the accuracy of the nPGA method was comparable to that of the PGA method, with a higher reliability for most pairs of reference and target regions. The results proved that the nPGA method could provide a non-invasive and indirect way for quantifying the FDG kinetics of tumor in small animal studies.

Bright fluorescent nanodiamonds: no photobleaching and low cytotoxicity.

Diamond nanocrystals emit bright fluorescence at 600-800 nm after irradiation by a 3 MeV proton beam (5 x 1015 ions/cm2) and annealing at 800 degrees C (2 h) in vacuum. The irradiation/annealing process yields high concentrations of nitrogen-vacancy defect centers ( approximately 107 centers/mum3), making possible visualization of the individual 100 nm diamond crystallites using a fluorescence microscope. The fluorescent nanodiamonds (FND) show no sign of photobleaching and can be taken up by mammalian cells with minimal cytotoxicity. The nanomaterial can have far-reaching biological applications.