Although artificial intelligence algorithms are often developed and applied for narrow tasks, their implementation in other medical settings could help to improve patient care. Here we assess whether ...a deep-learning system for volumetric heart segmentation on computed tomography (CT) scans developed in cardiovascular radiology can optimize treatment planning in radiation oncology. The system was trained using multi-center data (n = 858) with manual heart segmentations provided by cardiovascular radiologists. Validation of the system was performed in an independent real-world dataset of 5677 breast cancer patients treated with radiation therapy at the Dana-Farber/Brigham and Women's Cancer Center between 2008-2018. In a subset of 20 patients, the performance of the system was compared to eight radiation oncology experts by assessing segmentation time, agreement between experts, and accuracy with and without deep-learning assistance. To compare the performance to segmentations used in the clinic, concordance and failures (defined as Dice < 0.85) of the system were evaluated in the entire dataset. The system was successfully applied without retraining. With deep-learning assistance, segmentation time significantly decreased (4.0 min IQR 3.1-5.0 vs. 2.0 min IQR 1.3-3.5; p < 0.001), and agreement increased (Dice 0.95 IQR = 0.02; vs. 0.97 IQR = 0.02, p < 0.001). Expert accuracy was similar with and without deep-learning assistance (Dice 0.92 IQR = 0.02 vs. 0.92 IQR = 0.02; p = 0.48), and not significantly different from deep-learning-only segmentations (Dice 0.92 IQR = 0.02; p ≥ 0.1). In comparison to real-world data, the system showed high concordance (Dice 0.89 IQR = 0.06) across 5677 patients and a significantly lower failure rate (p < 0.001). These results suggest that deep-learning algorithms can successfully be applied across medical specialties and improve clinical care beyond the original field of interest.
Coronary artery calcium (CAC) quantified on computed tomography (CT) scans is a robust predictor of atherosclerotic coronary disease; however, the feasibility and relevance of quantitating CAC from ...lung cancer radiotherapy planning CT scans is unknown. We used a previously validated deep learning (DL) model to assess whether CAC is a predictor of all-cause mortality and major adverse cardiac events (MACEs).
Retrospective analysis of non-contrast-enhanced radiotherapy planning CT scans from 428 patients with locally advanced lung cancer is performed. The DL-CAC algorithm was previously trained on 1,636 cardiac-gated CT scans and tested on four clinical trial cohorts. Plaques ≥ 1 cubic millimeter were measured to generate an Agatston-like DL-CAC score and grouped as DL-CAC = 0 (very low risk) and DL-CAC ≥ 1 (elevated risk). Cox and Fine and Gray regressions were adjusted for lung cancer and cardiovascular factors.
The median follow-up was 18.1 months. The majority (61.4%) had a DL-CAC ≥ 1. There was an increased risk of all-cause mortality with DL-CAC ≥ 1 versus DL-CAC = 0 (adjusted hazard ratio, 1.51; 95% CI, 1.01 to 2.26;
= .04), with 2-year estimates of 56.2% versus 45.4%, respectively. There was a trend toward increased risk of major adverse cardiac events with DL-CAC ≥ 1 versus DL-CAC = 0 (hazard ratio, 1.80; 95% CI, 0.87 to 3.74;
= .11), with 2-year estimates of 7.3% versus 1.2%, respectively.
In this proof-of-concept study, CAC was effectively measured from routinely acquired radiotherapy planning CT scans using an automated model. Elevated CAC, as predicted by the DL model, was associated with an increased risk of mortality, suggesting a potential benefit for automated cardiac risk screening before cancer therapy begins.
Most localized hepatocellular carcinoma (HCC) patients are not surgically operable or transplantation candidates, increasing the role for nonsurgical therapies. Ablative external beam radiotherapy ...(XRT) and transarterial radioembolization (TARE) are emerging radiotherapeutic treatments for localized HCC. We sought to evaluate their utilization and efficacy in a large nationwide cohort.
We conducted an observational study of 2685 patients from the National Cancer Database (NCDB) diagnosed with American Joint Committee on Cancer 7th edition clinical stage I to III HCC between 2004 and 2015, treated with definitive-intent XRT delivered in 1 to 15 fractions or TARE. The association between treatment modality (XRT vs. TARE) and overall survival (OS) was defined using propensity score-weighted Kaplan-Meier estimators and propensity score-weighted multivariable Cox regressions.
Among 2685 patients, 2007 (74.7%) received TARE and 678 (25.3%) received XRT, with increasing usage for both from 2004 to 2015 (Ptrend<0.001), but with overall greater uptake and absolute usage of TARE. Patients who received TARE were more likely to have elevated alpha fetoprotein and more advanced stage (P<0.05 for all). Median OS was 14.5 months for the entire cohort. XRT was associated with an OS advantage compared with TARE on propensity score-unadjusted analysis (adjusted hazard ratio AHR, 0.89; 95% confidence interval, 0.79-1.00; P=0.049), but not on propensity score-adjusted analysis (AHR, 0.99; 95% confidence interval, 0.86-1.13; P=0.829).
Our study demonstrates that while both XRT and TARE usage have increased with time, there was greater uptake and absolute use of TARE. We found no difference in survival between XRT and TARE after propensity score adjustment.
1. Urban-rural transects can be utilized as natural gradients of temperature and also as a tool to predict how plant ecology and physiology might respond to expected global change variables such as ...elevated temperatures, CO₂ and inorganic nitrogen deposition. 2. We investigated differences in respiration (R) and the balance of electron partitioning through the cytochrome (CP) and alternative (AP) pathways in leaves of mature Quercus rubra L. trees along a transect from New York City to the Catskill Mountains over the course of one growing season. In addition, we investigated the effects of elevated temperature on Q. rubra seedlings in a controlled environment study. 3. In the field study, we found that urban-grown leaves often respired at greater rates than leaves grown at other sites and that this was likely due to higher leaf nitrogen. At each site, R at the prevailing growth temperature declined steadily throughout the growing season despite higher temperatures at the end of the summer. Differences in R were associated with changes in the relative abundances of cytochrome and alternative oxidase proteins. Oxygen isotope discrimination (D), which reflects relative changes in AP and CP partitioning, was negatively correlated with daily minimum temperature in trees grown at the colder rural sites, but not at the warmer urban sites. 4. In the growth cabinet study, we found that R acclimated to elevated temperatures and that this was accompanied by a steady increase in D. 5. These findings that AP partitioning increases with both high and low temperatures show that the AP may play an important role in plant responses to environmental conditions that elicit stress, and not simply to specific conditions such as low temperature.
In August 2022, the Cancer Informatics for Cancer Centers brought together cancer informatics leaders for its biannual symposium, Precision Medicine Applications in Radiation Oncology, co-chaired by ...Quynh-Thu Le, MD (Stanford University), and Walter J. Curran, MD (GenesisCare). Over the course of 3 days, presenters discussed a range of topics relevant to radiation oncology and the cancer informatics community more broadly, including biomarker development, decision support algorithms, novel imaging tools, theranostics, and artificial intelligence (AI) for the radiotherapy workflow. Since the symposium, there has been an impressive shift in the promise and potential for integration of AI in clinical care, accelerated in large part by major advances in generative AI. AI is now poised more than ever to revolutionize cancer care. Radiation oncology is a field that uses and generates a large amount of digital data and is therefore likely to be one of the first fields to be transformed by AI. As experts in the collection, management, and analysis of these data, the informatics community will take a leading role in ensuring that radiation oncology is prepared to take full advantage of these technological advances. In this report, we provide highlights from the symposium, which took place in Santa Barbara, California, from August 29 to 31, 2022. We discuss lessons learned from the symposium for data acquisition, management, representation, and sharing, and put these themes into context to prepare radiation oncology for the successful and safe integration of AI and informatics technologies.
To compare clinical and treatment characteristics and outcomes in locally advanced anal cancer, a potentially curable disease, in patients referred from a public or private hospital.
We ...retrospectively reviewed 112 anal cancer patients from a public and a private hospital who received definitive chemoradiotherapy at the same cancer center between 2004 and 2013. Tumor stage, radiotherapy delay, radiotherapy duration, and unplanned treatment breaks ≥10 days were compared using t-test and χ(2) test. Overall survival (OS), disease free survival (DFS), and colostomy free survival (CFS) were examined using the Kaplan-Meier method and compared with the log-rank test. Cox proportional hazard models for OS and DFS were developed.
The follow-up was 14.9 months (range, 0.7-94.8 months). Public hospital patients presented with significantly higher clinical T stage (P<0.05) and clinical stage group (P<0.05), had significantly longer radiotherapy delays (P<0.05) and radiotherapy duration (P<0.05), and had more frequent radiation therapy (RT) breaks ≥10 days (P<0.05). Three-year OS showed a marked trend in favor of private hospital patients for 3-year OS (72.8% vs. 48.9%; P=0.171), 3-year DFS (66.3% vs. 42.7%, P=0.352), and 3-year CFS (86.4% vs. 68.9%, P=0.299). Referral hospital was not predictive of OS or DFS on multivariate analysis.
Public hospital patients presented at later stage and experienced more delays in initiating and completing radiotherapy, which may contribute to the trend in poorer DFS and OS. These findings emphasize the need for identifying clinical and treatment factors that contribute to decreased survival in low socioeconomic status (SES) populations.