Robust prediction of mortality of COVID-19 patients based on quantitative,operator-independent,lung CT densitometry

PurposeTo train and validate a predictive model of mortality for hospitalized COVID-19 patients based on lung densitometry.MethodsTwo-hundred-fifty-one patients with respiratory symptoms underwent CT few days after hospitalization. “Aerated” (AV), “consolidated” (CV) and “intermediate” (IV) lung sub-volumes were quantified by an operator-independent method based on individual HU maximum gradient recognition. AV, CV, IV, CV/AV, IV/AV, and HU of the first peak position were extracted. Relevant clinical parameters were prospectively collected. The population was composed by training (n = 166) and validation (n = 85) consecutive cohorts, and backward multi-variate logistic regression was applied on the training group to build a CT_model. Similarly, models including only clinical parameters (CLIN_model) and both CT/clinical parameters (COMB_model) were developed. Model’s performances were assessed by goodness-of-fit (H&L-test), calibration and discrimination. Model’s performances were tested in the validation group.ResultsForty-three patients died (25/18 in training/validation). CT_model included AVmax (i.e. maximum AV between lungs), CV and CV/AE, while CLIN_model included random glycemia, C-reactive protein and biological drugs (protective). Goodness-of-fit and discrimination were similar (H&L:0.70 vs 0.80; AUC:0.80 vs 0.80). COMB_model including AVmax, CV, CV/AE, random glycemia, biological drugs and active cancer, outperformed both models (H&L:0.91; AUC:0.89, 95%CI:0.82–0.93). All models showed good calibration (R²:0.77–0.97). Despite several patient's characteristics were different between training and validation cohorts, performances in the validation cohort confirmed good calibration (R²:0–70-0.81) and discrimination for CT_model/COMB_model (AUC:0.72/0.76), while CLIN_model performed worse (AUC:0.64).ConclusionsFew automatically extracted densitometry parameters with clear functional meaning predicted mortality of COVID-19 patients. Combined with clinical features, the resulting predictive model showed higher discrimination/calibration.     

Deep learning methods to generate synthetic CT from MRI in radiotherapy: A literature review

PurposeIn radiotherapy, MRI is used for target volume and organs-at-risk delineation for its superior soft-tissue contrast as compared to CT imaging. However, MRI does not provide the electron density of tissue necessary for dose calculation. Several methods of synthetic-CT (sCT) generation from MRI data have been developed for radiotherapy dose calculation. This work reviewed deep learning (DL) sCT generation methods and their associated image and dose evaluation, in the context of MRI-based dose calculation.MethodsWe searched the PubMed and ScienceDirect electronic databases from January 2010 to March 2021. For each paper, several items were screened and compiled in figures and tables.ResultsThis review included 57 studies. The DL methods were either generator-only based (45% of the reviewed studies), or generative adversarial network (GAN) architecture and its variants (55% of the reviewed studies). The brain and pelvis were the most commonly investigated anatomical localizations (39% and 28% of the reviewed studies, respectively), and more rarely, the head-and-neck (H&N) (15%), abdomen (10%), liver (5%) or breast (3%). All the studies performed an image evaluation of sCTs with a diversity of metrics, with only 36 studies performing dosimetric evaluations of sCT.ConclusionsThe median mean absolute errors were around 76 HU for the brain and H&N sCTs and 40 HU for the pelvis sCTs. For the brain, the mean dose difference between the sCT and the reference CT was <2%. For the H&N and pelvis, the mean dose difference was below 1% in most of the studies. Recent GAN architectures have advantages compared to generator-only, but no superiority was found in term of image or dose sCT uncertainties. Key challenges of DL-based sCT generation methods from MRI in radiotherapy is the management of movement for abdominal and thoracic localizations, the standardization of sCT evaluation, and the investigation of multicenter impacts.     

Application of radiography of computed tomography in non-small cell lung cancer using prognosis model

ObjectiveStudying the diagnostic value of CT imaging in non-small cell lung cancer (NSCLC), and establishing a prognosis model combined with clinical characteristics is the objective, so as to provide a reference for the survival prediction of NSCLC patients.MethodCT scan data of NSCLC 200 patients were taken as the research object. Through image segmentation, the radiology features of CT images were extracted. The reliability and performance of the prognosis model based on the optimal feature number of specific algorithm and the prognosis model based on the global optimal feature number were compared.Results30-RELF-NB (30 optimal features, RELF feature selection algorithm and NB classifier) has the highest accuracy and AUC (area under the subject characteristic curve) in the prognosis model based on the optimal features of specific algorithm. Among the prognosis models based on global optimal features, 25-NB (25 global optimal features, naive Bayes classification algorithm classifier) has the highest accuracy and AUC. Compared with the prediction model based on feature training of specific feature selection algorithm, the overall performance and stability of the prediction model based on global optimal feature are higher.ConclusionThe prognosis model based on the global optimal feature established in this paper has good reliability and performance, and can be applied to the CT radiology of NSCLC.     

Dose calculation accuracy of different image value to density tables for cone-beam CT planning in head & neck and pelvic localizations

PurposeWe aimed to identify the most accurate combination of phantom and protocol for image value to density table (IVDT) on volume-modulated arc therapy (VMAT) dose calculation based on kV-Cone-beam CT imaging, for head and neck (H&N) and pelvic localizations.MethodsThree phantoms (Catphan^®600, CIRS^®062M (inner phantom for head and outer phantom for body), and TomoTherapy^® “Cheese” phantom) were used to create IVDT curves of CBCT systems with two different CBCT protocols (Standard-dose Head and Standard Pelvis). Hounsfield Unit (HU) time stability and repeatability for a single On-Board-Imager (OBI) and compatibility of two distinct devices were assessed with Catphan^®600. Images from the anthropomorphic phantom CIRS ATOM^® for both CT and CBCT modalities were used for VMAT dose calculation from different IVDT curves. Dosimetric indices from CT and CBCT imaging were compared.ResultsIVDT curves from CBCT images were highly different depending on phantom used (up to 1000 HU for high densities) and protocol applied (up to 200 HU for high densities). HU time stability was verified over seven weeks. A maximum difference of 3% on the dose calculation indices studied was found between CT and CBCT VMAT dose calculation across the two localizations using appropriate IVDT curves. One IVDT curve per localization can be established with a bi-monthly verification of IVDT-CBCT.ConclusionsThe IVDT-CBCT_CIRS-Head phantom with the Standard-dose Head protocol was the most accurate combination for dose calculation on H&N CBCT images. For pelvic localizations, the IVDT-CBCT_Cheese established with the Standard Pelvis protocol provided the best accuracy.     

Evaluation of a cycle-generative adversarial network-based cone-beam CT to synthetic CT conversion algorithm for adaptive radiation therapy

PurposeImage-guided radiation therapy could benefit from implementing adaptive radiation therapy (ART) techniques. A cycle-generative adversarial network (cycle-GAN)-based cone-beam computed tomography (CBCT)-to-synthetic CT (sCT) conversion algorithm was evaluated regarding image quality, image segmentation and dosimetric accuracy for head and neck (H&N), thoracic and pelvic body regions.MethodsUsing a cycle-GAN, three body site-specific models were priorly trained with independent paired CT and CBCT datasets of a kV imaging system (XVI, Elekta). sCT were generated based on first-fraction CBCT for 15 patients of each body region. Mean errors (ME) and mean absolute errors (MAE) were analyzed for the sCT. On the sCT, manually delineated structures were compared to deformed structures from the planning CT (pCT) and evaluated with standard segmentation metrics. Treatment plans were recalculated on sCT. A comparison of clinically relevant dose-volume parameters (D₉₈, D₅₀ and D₂ of the target volume) and 3D-gamma (3%/3mm) analysis were performed.ResultsThe mean ME and MAE were 1.4, 29.6, 5.4 Hounsfield units (HU) and 77.2, 94.2, 41.8 HU for H&N, thoracic and pelvic region, respectively. Dice similarity coefficients varied between 66.7 ± 8.3% (seminal vesicles) and 94.9 ± 2.0% (lungs). Maximum mean surface distances were 6.3 mm (heart), followed by 3.5 mm (brainstem). The mean dosimetric differences of the target volumes did not exceed 1.7%. Mean 3D gamma pass rates greater than 97.8% were achieved in all cases.ConclusionsThe presented method generates sCT images with a quality close to pCT and yielded clinically acceptable dosimetric deviations. Thus, an important prerequisite towards clinical implementation of CBCT-based ART is fulfilled.     

Effects of remedies made in patient setup process on residual setup errors and margins in head and neck cancer radiotherapy based on 2D image guidance

AimPatient setup errors were aimed to be reduced in radiotherapy (RT) of head-and-neck (H&N) cancer. Some remedies in patient setup procedure were proposed for this purpose.BackgroundRT of H&N cancer has challenges due to patient rotation and flexible anatomy. Residual position errors occurring in treatment situation and required setup margins were estimated for relevant bony landmarks after the remedies made in setup process and compared with previous results.Materials and methodsThe formation process for thermoplastic masks was improved. Also image matching was harmonized to the vertebrae in the middle of the target and a 5 mm threshold was introduced for immediate correction of systematic errors of the landmarks. After the remedies, residual position errors of bony landmarks were retrospectively determined from 748 orthogonal X-ray images of 40 H&N cancer patients. The landmarks were the vertebrae C1–2, C5–7, the occiput bone and the mandible. The errors include contributions from patient rotation, flexible anatomy and inter-observer variation in image matching. Setup margins (3D) were calculated with the Van Herk formula.ResultsSystematic residual errors of the landmarks were reduced maximally by 49.8% (p ≤ 0.05) and the margins by 3.1 mm after the remedies. With daily image guidance the setup margins of the landmarks were within 4.4 mm, but larger margins of 6.4 mm were required for the mandible.ConclusionsRemarkable decrease in the residual errors of the bony landmarks and setup margins were achieved through the remedies made in the setup process. The importance of quality assurance of the setup process was demonstrated.     

Modeling of couch transmission in the RayStation treatment planning system

PurposeTo present our methods and results regarding the modeling of a carbon fiber couch (Varian Exact IGRT) in the RayStation treatment planning system (TPS).MethodsThree geometrical-models (GMs) were implemented in the TPS to represent the three different regions of the couch (thick, medium and thin). The materials and densities of each GM component were tuned to maximize the agreement between measured and calculated attenuations. Moreover, a couch computed-tomography (CT) scan was acquired and dosimetrically compared with the GMs. For validation, plan-specific quality assurance (QA) of VMAT plans (TG-119 cases, 5 prostate and 5 H&N clinical cases) was performed by comparing measured dose distributions with doses computed with and without including the GMs in the TPS.ResultsCouch attenuations up to 4.3% were measured (energy: 6MV). Compared to couch CT, GMs could be modified to optimize the agreement with measurements and reduce dependence on the dose grid resolution. For both couch CT and GM, absolute deviations between measured and calculated attenuations were within 1.0%. When including the GMs in plan-specific QA, global 2%/2 mm γ-pass rates showed an average improvement of 4.8% (p-value < 0.001, max +18.6%). The couch reduced the mean dose to targets by up to 2.4% of the prescribed dose for prostate cases and up to 1.4% for H&N cases.ConclusionsRayStation accurately considers the implemented couch GMs replicating measured attenuations within an uncertainty of 1.0%. Materials and densities are proposed for the Varian Exact IGRT couch. The results obtained justify introducing couch GMs in clinical routine.     

Segmentation and Tracking of Adherens Junctions in 3D for the Analysis of Epithelial Tissue Morphogenesis

Epithelial morphogenesis generates the shape of tissues, organs and embryos and is fundamental for their proper function. It is a dynamic process that occurs at multiple spatial scales from macromolecular dynamics, to cell deformations, mitosis and apoptosis, to coordinated cell rearrangements that lead to global changes of tissue shape. Using time lapse imaging, it is possible to observe these events at a system level. However, to investigate morphogenetic events it is necessary to develop computational tools to extract quantitative information from the time lapse data. Toward this goal, we developed an image-based computational pipeline to preprocess, segment and track epithelial cells in 4D confocal microscopy data. The computational pipeline we developed, for the first time, detects the adherens junctions of epithelial cells in 3D, without the need to first detect cell nuclei. We accentuate and detect cell outlines in a series of steps, symbolically describe the cells and their connectivity, and employ this information to track the cells. We validated the performance of the pipeline for its ability to detect vertices and cell-cell contacts, track cells, and identify mitosis and apoptosis in surface epithelia of Drosophila imaginal discs. We demonstrate the utility of the pipeline to extract key quantitative features of cell behavior with which to elucidate the dynamics and biomechanical control of epithelial tissue morphogenesis. We have made our methods and data available as an open-source multiplatform software tool called TTT (http://github.com/morganrcu/TTT)     

The importance of evaluating the complete automated knowledge-based planning pipeline

We determine how prediction methods combine with optimization methods in two-stage knowledge-based planning (KBP) pipelines to produce radiation therapy treatment plans. We trained two dose prediction methods, a generative adversarial network (GAN) and a random forest (RF) with the same 130 treatment plans. The models were applied to 87 out-of-sample patients to create two sets of predicted dose distributions that were used as input to two optimization models. The first optimization model, inverse planning (IP), estimates weights for dose-objectives from a predicted dose distribution and generates new plans using conventional inverse planning. The second optimization model, dose mimicking (DM), minimizes the sum of one-sided quadratic penalties between the predictions and the generated plans using several dose-objectives. Altogether, four KBP pipelines (GAN-IP, GAN-DM, RF-IP, and RF-DM) were constructed and benchmarked against the corresponding clinical plans using clinical criteria; the error of both prediction methods was also evaluated. The best performing plans were GAN-IP plans, which satisfied the same criteria as their corresponding clinical plans (78%) more often than any other KBP pipeline. However, GAN did not necessarily provide the best prediction for the second-stage optimization models. Specifically, both the RF-IP and RF-DM plans satisfied the same criteria as the clinical plans 25% and 15% more often than GAN-DM plans (the worst performing plans), respectively. GAN predictions also had a higher mean absolute error (3.9 Gy) than those from RF (3.6 Gy). We find that state-of-the-art prediction methods when paired with different optimization algorithms, produce treatment plans with considerable variation in quality.     

Variations in rest-activity rhythm are associated with clinically measured disease severity in Parkinson’s disease

ABSTRACT

The continuous, longitudinal nature of accelerometry monitoring is well-suited to capturing the regular 24-hour oscillations in human activity across the day, the cumulative effect of our circadian rhythm and behavior. Disruption of the circadian rhythm in turn disrupts rest-activity rhythms. Although circadian disruption is a major feature of Parkinson’s disease (PD), rest-activity rhythms and their relationship with disease severity have not been well characterized in PD. 13 PD participants (Hoehn & Yahr Stage [H&Y] 1–3) wore a Philips Actiwatch Spectrum PRO continuously for two separate weeks. Rest-activity rhythms were quantified by fitting an oscillating 24-hour cosinor model to each participant-day of activity data. One-way ANOVAs adjusted for demographics revealed significant variation in the amount (MESOR, F = 12.76, p < .01), range (Amplitude, F = 9.62, p < .01), and timing (Acrophase, F = 2.7, p = .05) of activity across H&Y Stages. Those with higher H&Y Stages were significantly more likely to be active later in the day, where-as those who shifted between H&Y Stages during the study were significantly more active than those who did not change H&Y Stage. Being active later in the day was also significantly associated with higher scores on the Movement Disorder Society’s Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) Section III (motor symptom severity, p = .02), Section II (self-reported impact of motor symptoms on daily living, p = .01), and Total Score (p = .01) in an adjusted linear regression model; significant associations between MDS-UPDRS scores and activity levels were observed only in the unadjusted model. These findings demonstrate that continuous actigraphy is capable of detecting rest-activity disruption in PD, and provides preliminary evidence that rest-activity rhythms are associated with motor symptom severity and H&Y Stage.     

X线片和多层螺旋CT诊断及鉴别周围型肺癌的对比研究

目的:对比X线平片和多层螺旋CT诊断及鉴别周围型肺癌的效果。方法:选取了100例周围型肺癌患者,所有患者入院后先行X线片检查,后进行多层螺旋CT检查。通过观察并记录X线片与多层螺旋CT对周围型肺癌的影像学特征、临床TNM分期的诊断效果,评价X线平片和多层螺旋CT对周围型肺癌的诊断效果。结果:多层螺旋CT对周围型肺癌的肿块、分叶征、支气管气象征、空洞、胸膜凹陷、血管集束征,胸腔积液的检出率均高于X线片(P0.05)。根据外科病理TNM分期结果,多层螺旋CT对周围型肺癌的临床TNM分期诊断符合率为92.0%,X线对周围型肺癌的临床TNM分期诊断符合率为61.0%,多层螺旋CT对周围型肺癌的临床TNM分期诊断符合率明显高于X线(P0.05)。结论:多层螺旋CT对于周围型肺癌各类型影像学征象具有较好的检出率,对周围型肺癌临床TNM分期诊断准确性接近病理诊断结果。     

Neck emphysema in a HNSCC cancer patient undergoing concurrent radiotherapy and cetuximab

BackgroundLung toxicity in patients undergoing cetuximab and radiotherapy (Cetux-RT) for head and neck squamous cell carcinoma (HNSCC) has been reported in literature and represents a serious side effect of concurrent therapies.MethodsWe report a case of a HNSCC patient that developed neck emphysema during the course of Cetux-RT. The patient was an old male (80 years old) in a good performance status, with an oropharyngeal cancer (T4aN3a).ResultsDuring RT, cone-beam computed tomography (CBCT) showed bilateral neck emphysema that was confirmed at restaging CT. We decided to stop the treatment and to treat the neck emphysema with conservative strategies. After one week CT was repeated and the neck emphysema had improved, so we decided to complete the RT treatment.ConclusionsPatients undergoing Cetux-RT must be properly selected, whereas IGRT imaging must be viewed carefully in order to permit an early diagnosis and careful management of the patients.     

A deep learning approach to gold nanoparticle quantification in computed tomography

IntroductionDeep learning (DL) is used to classify, detect, and quantify gold nanoparticles (AuNPs) in a human-sized phantom with a clinical MDCT scanner.MethodsAuNPs were imaged at concentrations between 0.0274 and 200 mgAu/mL in a 33 cm phantom. 1 mm-thick CT image slices were acquired at 120 kVp with a CTDI_vol of 23.6 mGy. A convolutional neural network (CNN) was trained on 544 images to classify 17 different tissue types and AuNP concentrations. A second set of 544 images was then used for testing.ResultsAuNPs were classified with 95% accuracy at 0.1095 mgAu/mL and 97% accuracy at 0.2189 mgAu/mL. Both these concentrations are lower than what humans can visually perceive (0.3–1.4 mgAu/mL). AuNP concentrations were also classified with 95% accuracy at 150 and 200 mgAu/mL. These high concentrations result in CT numbers that are at or above the 12-bit limit for CT’s dynamic range where extended Hounsfield scales are otherwise required for measuring differences in contrast.ConclusionsWe have shown that DL can be used to detect AuNPs at concentrations lower than what humans can visually perceive and can also quantify very high AuNP concentrations that exceed the typical 12-bit dynamic range of clinical MDCT scanners. This second finding is possible due to inhomogeneous AuNP distributions and characteristic streak artifacts. It may even be possible to extend this approach beyond AuNP imaging in CT for quantifying high density objects without extended Hounsfield scales.     

Evaluation of automated pipelines for tree and plot metric estimation from TLS data in tropical forest areas

Background and AimsTerrestrial LiDAR scanning (TLS) data are of great interest in forest ecology and management because they provide detailed 3-D information on tree structure. Automated pipelines are increasingly used to process TLS data and extract various tree- and plot-level metrics. With these developments comes the risk of unknown reliability due to an absence of systematic output control. In the present study, we evaluated the estimation errors of various metrics, such as wood volume, at tree and plot levels for four automated pipelines.MethodsWe used TLS data collected from a 1-ha plot of tropical forest, from which 391 trees >10 cm in diameter were fully processed using human assistance to obtain control data for tree- and plot-level metrics.Key ResultsOur results showed that fully automated pipelines led to median relative errors in the quantitative structural model (QSM) volume ranging from 39 to 115 % at the tree level and 10 to 134 % at the 1-ha plot level. For tree-level metrics, the median error for the crown-projected area ranged from 46 to 59 % and that for the crown-hull volume varied from 72 to 88 %. This result suggests that the tree isolation step is the weak link in automated pipeline methods. We further analysed how human assistance with automated pipelines can help reduce the error in the final QSM volume. At the tree scale, we found that isolating trees using human assistance reduced the error in wood volume by a factor of 10. At the 1-ha plot scale, locating trees with human assistance reduced the error by a factor of 3.ConclusionsOur results suggest that in complex tropical forests, fully automated pipelines may provide relatively unreliable metrics at the tree and plot levels, but limited human assistance inputs can significantly reduce errors.     

DEMAT: A multi-institutional dosimetry audit of rotational and static intensity-modulated radiotherapy

PurposeStatic beam intensity-modulated-radiation-therapy (IMRT) and/or Volumetric-Modulated-Arc-Therapy (VMAT) are now available in many regional radiotherapy departments. The aim of this multi-institutional audit was to design a new methodology based on radiochromic films to perform an independent quality control.MethodsA set of data were sent to all participating centres for two clinical localizations: prostate and Head and Neck (H&N) cancers. The agreement between calculations and measurements was verified in the Octavius phantom (PTW) by point measurements using ionization chambers and by 2D measurements using EBT3 radiochromic films. Due to uncertainties in the whole procedure, criteria were set to 5% and 3% in local dose and 3 mm in distance excluding doses lower than 10% of the maximum doses. No normalization point or area was used for the quantitative analysis.Results13 radiotherapy centres participated in this audit involving 28 plans (12 IMRT, 16 VMAT). For point measurements, mean errors were −0.18 ± 1.54% and 0.00 ± 1.58% for prostate and H&N cases respectively. For 2D measurements with 5%/3 mm criteria, gamma map analysis showed a pixel pass rate higher than 95% for prostate and H&N. Mean gamma index was lower than 0.4 for prostate and 0.5 for H&N. Both techniques yielded similar results.ConclusionThis study showed the feasibility of an independent quality control by peers for conventional IMRT and VMAT. Results from all participating centres were found to be in good agreement. This regional study demonstrated the feasibility of our new methodology based on radiochromic films without dose normalization on a specific point.     

Dosimetric and Monte Carlo verification of jaws-only IMRT plans calculated by the Collapsed Cone Convolution algorithm for head and neck cancers

AimThe aim of this study is to verify the Prowess Panther jaws-only intensity modulated radiation therapy (JO-IMRT) treatment planning (TP) by comparing the TP dose distributions for head-and-neck (H&N) cancer with the ones simulated by Monte Carlo (MC).BackgroundTo date, dose distributions planned using JO-IMRT for H&N patients were found superior to the corresponding three-dimensional conformal radiotherapy (3D-CRT) plans. Dosimetry of the JO-IMRT plans were also experimentally verified using an ionization chamber, MapCHECK 2, and Octavius 4D and good agreements were shown.Materials and methodsDose distributions of 15 JO-IMRT plans of nasopharyngeal patients were recalculated using the EGSnrc Monte Carlo code. The clinical photon beams were simulated using the BEAMnrc. The absorbed dose to patients treated by fixed-field IMRT was computed using the DOSXYZnrc. The simulated dose distributions were then compared with the ones calculated by the Collapsed Cone Convolution (CCC) algorithm on the TPS, using the relative dose error comparison and the gamma index using global methods implemented in PTW-VeriSoft with 3%/3 mm, 2%/2 mm, 1%/1 mm criteria.ResultsThere is a good agreement between the MC and TPS dose. The average gamma passing rates were 93.3 ± 3.1%, 92.8 ± 3.2%, 92.4 ± 3.4% based on the 3%/3 mm, 2%/2 mm, 1%/1 mm criteria, respectively.ConclusionsAccording to the results, it is concluded that the CCC algorithm was adequate for most of the IMRT H&N cases where the target was not immediately adjacent to the critical structures.