Body Contour Research Articles

Anterior Bone Loss after Cervical Baguera C Disc versus Bryan Disc Arthroplasty.

The objectives of this study were to identify the risk factors and incidence of anterior bone loss (ABL) after Baguera C cervical disc arthroplasty (CDA) and identify whether design differences in artificial discs affect ABL. In this retrospective radiological review of patients who underwent single-level Baguera C CDA in a medical center, the extent of ABL and the following radiological parameters were recorded: global and segmental alignment angle, lordotic angle (or functional spinal unit angle), shell angle, global range of motion (ROM), and ROM of the index level. ABL at the index level was grade 0-2. Grade 0 was defined as no remodeling, grade 1 as spur disappearance or mild change in body contour, and grade 2 as obvious bone regression with Baguera C Disc exposure. Combining grade 1 and grade 2, ABL was found in 56 upper adjacent vertebrae and 52 lower adjacent vertebrae of the 77 patients. Only 18 patients (23.4%) had no ABL. Shell angle differed significantly between ABL grades of both the upper and lower adjacent level: 0.0° in grade 0 and 1 ABL vs. 2.0° in grade 2 ABL of the upper adjacent level (p < 0.05); and 0.0° in grade 0 and 1 ABL vs. 3.5° in grade 2 ABL of the lower adjacent level (p < 0.05). A female predominance of ABL was found. Hybrid surgery and artificial disc size were also related to ABL. ABL is more common in Baguera C Disc arthroplasty than Bryan Disc arthroplasty. Larger shell angle was related to ABL after CDA with Baguera C Discs, which may indicate that shell angle is pivotal in determining the incidence of ABL after CDA. Females had more ABL with Baguera C Disc arthroplasty; this might be related to shorter endplate lengths as well as a smaller endplate-implant mismatch.

A new needle nematode, Longidorus zanjanensis sp. nov. (Nematoda: Longidoridae) from north-western Iran.

During a survey of soil nematodes in 2022, a new species of the genus Longidorus, described here as Longidorus zanjanensis sp. nov., was discovered in the rhizosphere of Astragalus sp. in Zanjan Province, Iran. The new needle nematode is described and illustrated based on morphological, morphometric, and molecular traits. Further, its females are characterized by having a long body ranging 5.6-7.7 mm long, lip region anteriorly flattened and almost continuous or slightly offset by a depression with body contour, ca 16.5-18.5 μm wide, amphidial fovea pouch-like without basal lobes, guiding ring at 35-41 μm distance from the anterior end, and an odontostyle and odontophore ranging 102-115 and 47-75 μm long, respectively. The pharyngeal bulb is 123-153 μm long, female reproductive system didelphic-amphidelphic containing sperm, vulva almost equatorial, located at 46.7-51.4% of body length, tail short, rounded to bluntly conoid, bearing two pairs of caudal pores and terminus widely rounded with distinct radial lines in hyaline region (39-50 μm long, c = 122.4-189.4, c' = 0.6-0.8). Males are common, making up to 60% of the adults, and are functional, with spicules 68.0-80.0 μm long, as well as having 8-14 ventromedian copulatory supplements. All four juvenile life developmental stages were present, with the tail of first-stage juvenile conoid shape, dorso-ventrally curved with rounded terminus. The polytomous codes delimiting the new species are: A4-B3-C3-D3-E1-F34-G12-H1-I2-J1-K6. Morphologically, the new species comes close to eight known species of the genus, namely L. apulus, L. armeniacae, L. crassus, L. kheirii, L. soosanae, L. proximus, L. pauli, and L. ferrisi. The morphological differences between the new species and the aforementioned species are discussed. Molecular phylogenetic analyses based on D2-D3 of large subunit (LSU) and internal transcribed spacer 1 (ITS1) rRNA sequences indicate that Longidorus zanjanensis sp. nov. is closely related to L. hyrcanus, L. soosanae, and L. elongatus.

Cozinhando mudanças: o ato de cozinhar como ferramenta de enfrentamento aos desafios do Antropoceno

Abstract Cooking encompasses cultural, environmental, social, economic, and political dimensions, as well as composes the activities contained in a food system and promoting dialogues and transformations. This study aims to describe and to analyze everyday elements related to cooking and its relationship with the food system based on the experience of a group of female urban farmers in the east side of the city of São Paulo. Body-map storytelling was used, a creative visual research method, in which, by drawing the participant’s body contours, visual and oral data were produced on the meanings of cooking. Seven women participated in this study, who develop actions related to agriculture and cooking. The generated data were analyzed using thematic analysis. Cooking proved to be a connector from the field to the table, strengthening and being strengthened by the practices of urban and peri-urban farming, and is an interesting tool to promote health, contemplating biopsychosocial well-being in line with issues of social, economic, and environmental sustainability. Understanding this connection enables to support public policies to promote sustainable food systems and facing the challenges of the Anthropocene.

Revisiting Body Contour Outlining Procedures in Nuclear Medicine

Obtaining clear localization images in nuclear medicine can be challenging when radiotracers are administered locally. This lack of anatomical information can make it difficult to relate the scintigraphic findings to specific body structures. Various localization techniques such as point source, cobalt wires, transmission scans using Cobalt-57 (57Co) and Gadolinium-153 (153Gd), and hybrid imaging (SPECT-CT) can be employed to overcome this issue. The primary goal of this communication is to summarize the available body contour outlining methods in nuclear medicine and provide a comprehensive guide for nuclear medicine trainees to obtain high-quality localization images that can facilitate better evaluation of nuclear medicine scans.

Unsupervised Human Contour Extraction From Through-Wall Radar Images Using Dual UNet

Through-wall radar (TWR) can image the target of interest and capture the human sensing information. However, the poor human interpretability of TWR images and the lack of effective supervision make the extraction of complete body contour intractable. This letter proposes dual UNet, an unsupervised human contour extraction method for TWR images. Specifically, the method adopts two UNets with the same structure. One serves as the encoder to convert the TWR images into the latent representation. Another serves as the decoder to reconstruct the latent representation into the original images. Reconstruction loss and smooth normalized cut loss are optimized together to offset the dependence on labels and supplement global segment constraints. After training and post-processing, the latent representation can be used as the result of contour extraction. Experimental results show that dual UNet stands out among unsupervised human contour extraction methods in both free space and wall-occlusive scenarios, opening the possibility of learning useful human sensing information from raw TWR images without manual annotations.

Fast, Fully-Automatic Characterization of Metallic and Water-Based Threat Objects for Millimeter-Wave Personnel Screening Systems

Efficient characterization of concealed person-worn objects enhances the security of air travel and reduces the inspection time. Mm-wave nearfield radar can detect metallic objects such as guns or knives, as well as water-based materials that might be associated with peroxide threats. However, it cannot discriminate these potential threats from benign objects to decrease the nuisance alarm rate. Moreover, distinguishing these potential threats from benign objects in the presence of human skin is even more challenging. The authors have previously developed a method using mm-wave imaging to estimate the nominal body contour (NBC) with attached objects. This paper extends the image-processing-based algorithm to identify concealed metallic and water-based objects, as thin as 1 cm, attached to arms, legs, torso, and the pelvic region. The algorithm determines if the anomaly in the image is due to lossless or conductive material seen respectively as a depression or protrusion relative to the NBC. Next, high-loss water-based objects are distinguished from metallic and benign low-loss objects. The developed method is verified experimentally via actual images of human subjects, with foreign attached objects of various types and sizes. The images were captured by the High Definition-Advanced Imaging Technology (HD-AIT) scanner, a laboratory prototype system developed recently by the U.S. Department of Homeland Security (DHS). The developed codes resulted in zero miss and 7% rate of false alarm, while the rest of objects were either characterized correctly or referred to for a secondary pat down. Our method is performed fully-automatically and within a few seconds.

Description of Hemicycliophora geraerti n. sp. (Tylenchida: Hemicycliophoridae) associated with Prunus persica L. from China

Summary Hemicycliophora species are migratory root ectoparasites of higher plants, commonly known as sheath nematodes. The present study describes a new species, Hemicycliophora geraerti n. sp., recovered from the rhizosphere of peach tree (Prunus persica) in Zhejiang Province, China. This species is characterised by a cuticular sheath loosely fitting to the body, a lip region slightly set-off with body contour bearing 3-4 annuli, oral plate narrow, ovate, and non-protruding, amphidial apertures plugged, dorsoventrally flanked in the first lip annulus, stylet 110 (103-116) μm long and flexible, excretory pore located 4-7 annuli posterior to the base of the pharyngeal bulb; vulval lips modified with a small vulval sleeve, anus located 16 (13-21) annuli posterior to vulva, tail elongated, having a narrowly rounded slightly offset spike. The molecular characterisation and phylogenetic analyses based on D2-D3 expansion segments of the 28S rRNA, ITS rRNA, and COI mtDNA gene indicated the unique status and support the novelty of this population of Hemicycliophora, therefore herein described as H. geraerti n. sp.

Ensemble learning and personalized training for the improvement of unsupervised deep learning-based synthetic CT reconstruction.

The growing adoption of magnetic resonance imaging (MRI)-guided radiation therapy (RT) platforms and a focus on MRI-only RT workflows have brought the technical challenge of synthetic computed tomography (sCT) reconstruction to the forefront. Unpaired-data deep learning-based approaches to the problem offer the attractive characteristic of not requiring paired training data, but the gap between paired- and unpaired-data results can belimiting. We present two distinct approaches aimed at improving unpaired-data sCT reconstruction results: a cascade ensemble that combines multiple models and a personalized training strategy originally designed for the paired-datasetting. Comparisons are made between the following models: (1) the paired-data fully convolutional DenseNet (FCDN), (2) the FCDN with the Intentional Deep Overfit Learning (IDOL) personalized training strategy, (3) the unpaired-data CycleGAN, (4) the CycleGAN with the IDOL training strategy, and (5) the CycleGAN as an intermediate model in a cascade ensemble approach. Evaluation of the various models over 25 total patients is carried out using a five-fold cross-validation scheme, with the patient-specific IDOL models being trained for the five patients of fold 3, chosen atrandom. In both the paired- and unpaired-data settings, adopting the IDOL training strategy led to improvements in the mean absolute error (MAE) between true CT images and sCT outputs within the body contour (mean improvement, paired- and unpaired-data approaches, respectively: 38%, 9%) and in regions of bone (52%, 5%), the peak signal-to-noise ratio (PSNR; 15%, 7%), and the structural similarity index (SSIM; 6%, <1%). The ensemble approach offered additional benefits over the IDOL approach in all three metrics (mean improvement over unpaired-data approach in fold 3; MAE: 20%; bone MAE: 16%; PSNR: 10%; SSIM: 2%), and differences in body MAE between the ensemble approach and the paired-data approach are statisticallyinsignificant. We have demonstrated that both a cascade ensemble approach and a personalized training strategy designed initially for the paired-data setting offer significant improvements in image quality metrics for the unpaired-data sCT reconstruction task. Closing the gap between paired- and unpaired-data approaches is a step toward fully enabling these powerful and attractive unpaired-dataframeworks.

High-Definition Liposculpture 18-Year Evolution: Patient Safety and Aesthetic Outcomes.

High-definition liposculpture (HDL) emerged as an innovative surgical technique that allowed plastic surgeons to achieve improved aesthetic results with a natural and athletic appearance using minimal incisions and with imperceptible scarring. Its targets are high aesthetic standards and patient safety. This article summarizes the evolution of HDL by explaining upgrades to the original technique and comparing the complication rates among them. The authors retrospectively reviewed records from four private medical centers (Evolution Medical Center, Santa Barbara Medical Center, and Dhara Clinic in Bogota and FOSCAL in Bucaramanga, Colombia) of patients who underwent HDL performed by the senior author (A.E.H) over an 18-year period (2002 through 2019). Patients were classified into three groups: suction-assisted lipoplasty (period 1), vibration amplification of sound energy at resonance-assisted HDL (period 2), and dynamic definition liposculpture (period 3). The authors established a cohort of 5052 patients (4300 women and 752 men): 923 in period 1, 1272 in period 2, and 2857 in period 3. The most common complications included seroma, bruising, hematoma, acute anemia, hyperchromia, wrinkled skin, wound dehiscence, and local infections. HDL and dynamic-definition liposculpture procedures are safe and reproducible techniques to achieve an athletic and natural body contour. Complication rates, especially those related to bleeding, decreased as the technique evolved. These procedures are aimed toward patient safety to provide higher aesthetic outcomes using extensive medical, anatomic, artistic, and technological knowledge. Therapeutic, III.

Human Bas-Relief Generation From a Single Photograph

We present a semi-automatic method for producing human bas-relief from a single photograph. Given an input photo of one or multiple persons, our method first estimates a 3D skeleton for each person in the image. SMPL models are then fitted to the 3D skeletons to generate a 3D guide model. To align the 3D guide model with the image, we compute a 2D warping field to non-rigidly register the projected contours of the guide model with the body contours in the image. Then the normal map of the 3D guide model is warped by the 2D deformation field to reconstruct an overall base shape. Finally, the base shape is integrated with a fine-scale normal map to produce the final bas-relief. To tackle the complex intra- and inter-body interactions, we design an occlusion relationship resolution method that operates at the level of 3D skeletons with minimal user inputs. To tightly register the model contours to the image contours, we propose a non-rigid point matching algorithm harnessing user-specified sparse correspondences. Experiments demonstrate that our human bas-relief generation method is capable of producing perceptually realistic results on various single-person and multi-person images, on which the state-of-the-art depth and pose estimation methods often fail.

Three wound types: common challenges with exudate, gaps and anatomical positioning

Complex wounds require combinations of technologies and regimes to match laboratory tests and address challenges of physiological processes, body contours, movement and ease of use during life-long self-management. Wound management for vascular and lymphatic disorders incorporate wound dressings, skin care and compression to address local wound needs and underlying pathologies, while allowing functionality for movement. In a similar manner, acute inflammatory conditions that become chronic require skin care and local conformable and absorbent wound management, but with simple, atraumatic retention methods without compression. Three types of conditions will be discussed in this article-venous leg ulcers with chronic oedema (VLU), hidradenitis suppurativa (HS) and pilonidal sinuses (PS). It focuses on overcoming challenges associated with excess exudate, compromised skin, dressing awkward areas and contours, while also demonstrating wound care similarities when administered by patients themselves.

Attention-based gait recognition network with novel partial representation PGOFI based on prior motion information

Compared to other recognition tasks, gait recognition has two unique scenarios, i.e., camera-pedestrian angle change scenario and body contour change (e.g., clothing change) scenario. The current gait recognition methods suffer from feature dilution and fail to extract accurate and highly robust gait features, therefore encounter serious performance degradation when facing these scenarios. In this paper, we propose an attention-based gait recognition network with novel gait representation. First, we design a novel partial gait representation: Part-based Gait Optical Flow Image. During the generation of representation, different parts of the body are separated according to their movement patterns and the optical flow of each part is extracted separately. Second, we propose Prior-Information-based Attention Module to highlight gait features of body parts with distinct motion based on prior information. In terms of appearance features, we propose Attention-based Frame Selection Module to acquire and high-light the key frames. These two modules extract and enhance local features in terms of motion and appearance respectively, avoiding unfocused global feature extraction and solving the feature dilution problem. Finally, our network uses a fusion optimization strategy to allow the network to adaptively balance the contributions of the motion feature and appearance feature, enhancing the robustness of the network under multiple angles. Experiments demonstrate that the method proposed in this paper achieves the best performance on both CASIA-B and OU-MVLP datasets.

Description and molecular characterisation of Ditylenchus pedrami n. sp. (Rhabditida: Anguinidae) from Iran

Summary Ditylenchus pedrami n. sp., recovered from the rhizospheric soil of date palm in Khuzestan province, southwest Iran, is described and illustrated based upon morphological and molecular data. The new species is characterised by having six lines in the lateral field, lip region smooth and continuous with body contour, stylet 9-11 μm long, median pharyngeal bulb oval with small valve, pharyngeal bulb offset from the intestine, V = 83.9 (80.2-88.1), conoid tail with a pointed, dull or rounded tip and males with 20.1 (17-24) μm long spicules. Morphologically, the new species comes close to D. africanus, D. anchilisposomus, D. australiae, D. clarus, D. clavicaudatus and D. parcevivens, mainly by having shared features like six lines in the lateral fields, stylet length and somewhat similar tail tip. The new species was also compared with D. stenurus and D. sarvarae, two species with close phylogenetic affinities to it. The phylogenetic relationships of the new species with representatives of the family Anguinidae were reconstructed and discussed using partial sequences of the small subunit, D2-D3 expansion segments of the large subunit, and internal transcribed spacer regions of ribosomal DNA (SSU, LSU D2-D3 and ITS rDNA) based on Bayesian inference (BI).

A Self-Pumping Dressing with Multiple Liquid Transport Channels for Wound Microclimate Management.

A microclimate with ventilation and proper wettability near the wound is vital for wound healing. In the case of pressure or absorption of large amounts of wound exudate, maintaining air circulation around the wound is currently a challenge for wound dressings. In this study, a novel self-pumping dressing (FAED) with multiple liquid transport channels is designed by combining a 3D spacer fabric, sodium alginate aerogel, and electrospun membrane. This unique structural design allows FAED to unidirectionally rapidly remove excess biofluid from the wound and transfer it through a special liquid transport channel to a liquid storage layer with a high absorption ratio. Importantly, the air circulation layer of FAED composed of liquid transport channels and spacer yarns provides excellent air permeability in both the horizontal (12.3 L min-1 ) and vertical (272.02 mm s-1 ) directions. Additionally, a lower compression modulus (0.14MPa) and higher compression strength (0.15MPa) enable the novel dressing to adapt to body contours and provide good supporting performance, as compared to foam dressings. Combined with its high biocompatibility, this unique dressing has significant potential for wound treatment and intensive care.

To sleep tight you should sleep right.

The impact of environmental context and lifestyle to our health is crucial. Balancing physical activity and rest, especially sleep, is the key to healthier ageing and greater functional capacity. Humans spend about 1/3 of their lives sleeping, usually in the recumbent position. Favourable sleeping environment is not only a quiet place but also an adjustable sleep system may hold one of the keys to sleep right and tight. All systems deteriorate with ageing, and the vascular system is particularly affected, which in turn aggravates the natural limitations that occur in the musculoskeletal system. In this paper we will see why sleeping system should be addressed to meet the increased impairment of the musculoskeletal system and the sleep function. The age-related decrease in vascular function affects all body systems, and also exposes the musculoskeletal system to greater risk factors for chronic pain conditions. Changes occurs also in sleep architecture, the decreasing shifting of positions while asleep, the adoption of side lying and less posture options due to health conditions alone are some of the risk factors for sustained compression on all the musculoskeletal structures, particularly in the side of the body in contact with the bed. Shoulders and hips are the regions of the body that suffer greater pressure and impaired blood perfusion. Musculoskeletal conditions and sleep disorders in the United States alone affect about 50%of the 126.6 million American adults; about 40% of those subjects who suffer from low back/neck pain, sustain pain and sleep disturbances despite analgesic treatment. Women are more susceptible to these complaints, especially those with more prominent body contours, or frail people with severe muscle atrophy. Ageing increases the demand for a better contextual environment, not only during activity but also at rest and especially during sleep. This paper based on the records of a case-series study of 19 subjects focusing only on paraesthesia and comorbid insomnia and their evolution with the systematic application of a customised topper.

Deep Learning-based calculation of patient size and attenuation surrogates from localizer Image: Toward personalized chest CT protocol optimization

PurposeExtracting water equivalent diameter (DW), as a good descriptor of patient size, from the CT localizer before the spiral scan not only minimizes truncation errors due to the limited scan field-of-view but also enables prior size-specific dose estimation as well as scan protocol optimization. This study proposed a unified methodology to measure patient size, shape, and attenuation parameters from a 2D anterior-posterior localizer image using deep learning algorithms without the need for labor-intensive vendor-specific calibration procedures. Methods3D CT chest images and 2D localizers were collected for 4005 patients. A modified U-NET architecture was trained to predict the 3D CT images from their corresponding localizer scans. The algorithm was tested on 648 and 138 external cases with fixed and variable table height positions. To evaluate the performance of the prediction model, structural similarity index measure (SSIM), body area, body contour, Dice index, and water equivalent diameter (DW) were calculated and compared between the predicted 3D CT images and the ground truth (GT) images in a slicewise manner. ResultsThe average age of the patients included in this study (1827 male and 1554 female) was 53.8 ± 17.9 (18–120) years. The DW, tube current ,and CTDIvol measured on original axial images in the external 138 cases group were significantly larger than those of the external 648 cases (P < 0.05). The SSIM and Dice index calculated between the prediction and GT for body contour were 0.998 ± 0.001 and 0.950 ± 0.016, respectively. The average percentage error in the calculation of DW was 2.7 ± 3.5 %. The error in the DW calculation was more considerable in larger patients (p-value < 0.05). ConclusionsWe developed a model to predict the patient size, shape, and attenuation factors slice-by-slice prior to spiral scanning. The model exhibited remarkable robustness to table height variations. The estimated parameters are helpful for patient dose reduction and protocol optimization.

Coverage probability planning for simultaneously integrated boosts of inguinal lymph nodes in vulvar cancer

Background and purpose Strategies for minimizing irradiation of organs at risk (OARs) from pathological inguinal lymph node (PILN) boosting are needed to minimize the risk of morbidity. Coverage probability (CovP) is a conformal planning strategy for simultaneously integrated boost (SIB). Our aim was to investigate if SIB of PILN using CovP can be delivered safely in vulvar cancer. Materials and methods Ten consecutive patients treated with definitive radiotherapy (RT) including SIB of PILN and with daily cone beam CT (CBCT) were included. Dose prescription was 51.2/32 fx to the elective target and 64 Gy/32 fx to the gross disease at the vulva and to positive lymph nodes (LN). PILN were contoured on both planning CT and MRI (GTV-N) and combined to form ITV-N. Each PILN GTV-N was contoured on every third CBCT, in total 11 CBCT for each patient. OARs were subcutaneous tissue (SC), inguinal vessels, skin rim, bowel, and body contour. Three plans were created for every patient: A) Standard CT-based planning; PTV-N based on GTV-NCT with a 10 mm isotropic margin. B) CT and MRI-based planning with smaller margins: PTV-N based on ITV-N with a 5 mm isotropic margin. C) CovP. The total delivered dose to GTV-Ns was estimated by accumulating dose across all fractions based on GTV-Ns contoured on CBCT. Results Thirty-five PILNs were boosted. There was no significant difference in accumulated GTV-N D98% between the three plans. CovP delivered a higher mean dose to the GTV-N D50% and D2% (p < 0.001). The planned mean doses to the OARs were reduced when applying CovP. Conclusions SIB of PILN in vulvar cancer based on CovP and a 5 mm PTV margin does not compromise target coverage during RT and reduces the dose to normal tissues in the groin.

Addressing New and Unexpected Failure Modes in a CBCT-Guided, Online Adaptive Radiotherapy Platform

<h3>Purpose/Objective(s)</h3> Our department has recently commissioned a CBCT-guided online adaptive radiation therapy (ART) platform, one of the first of its kind in the United States. The implementation of this novel technology has revealed unique failure modes to the workflow with on-couch ART. We have performed root-cause analyses (RCA) on three unexpected failure modes, quantified the impact to patient care and clinical workflow, and implemented quality control measures to mitigate the likelihood of these failure modes from impacting patient care. <h3>Materials/Methods</h3> We identified three unique failure modes in the first three months of operating the machine clinically. Each failure mode underwent RCA with a team of physicists, dosimetrists, therapists, and oncologists. Key items that contributed to the events reaching the patient were identified at each step in the planning and treatment workflow. Impact on patient treatment was rated following the guidance of TG-100. Mitigation measures were identified and implemented within our clinical workflows. <h3>Results</h3> The three unique failure modes identified were: incorrect on-couch target contouring, automated structures failing to propagate, and OAR contours existing outside the body resulting in on-couch session failures. RCA identified that the on-couch target contouring was a risk at each adaptive session, while the other two failure modes originated in the planning stage. Incorrect on-couch target contouring was rated as the highest risk for ART by our team as it was the most difficult failure to detect in real-time and prone to several contributing factors, such as poor initial target propagation and artifacts on the daily CBCT. Team familiarity with the new technology was a contributing factor, coupled with a lack of global warning messages within the system reporting. Mitigation strategies included establishing easily-identifiable anatomic landmarks for target extent, modification of existing checklists to systematically incorporate the RT Intent Report generated by the ART platform into our pre-existing Oncology Information System, and trimming of specific organs at risk away from the body contour. Product improvement requests for the on-couch structures outside of body and failure of derived structures to propagate failure modes have been lodged with the vendor to improve warnings presented to the user during final clinical review. We have not encountered further failures following implementation of these control measures. <h3>Conclusion</h3> Unique and unanticipated failure modes will exist in any new technology. We have identified three failure modes unique to this CBCT-guided, online ART platform and implemented systematic controls to mitigate future failures. Periodic review and team learning from encountering failures is an important step in continual quality improvement for emerging techniques.

Dose Predictions for Head and Neck Cancers Using Hybrid Structure Sets Containing Manual and Automated Contours

<h3>Purpose/Objective(s)</h3> The purpose of this study was to create a deep learning dose prediction model for head and neck (H&N) cancer treatments using computed tomography (CT) images, planning target volumes (PTV), and hybrid organ at risk (OAR) contour sets containing manually defined structures from historical treatments and artificial intelligence (AI) generated structures. The aim of this work was to enhance dose prediction models by including AI generated contours. <h3>Materials/Methods</h3> 140 H&N patients were selected for model training and testing. All patients had a PTV treated to 6996 cGy and possibly contained one or more of six lower-dose PTVs ranging from 6600 cGy to 5400 cGy. 9 OARs were selected as important critical structures for dose planning and included the total parotids, total submandibular glands, brainstem, cerebellum, mandible, spinal cord, esophagus, oral cavity, and body. In instances where one or more of the OARs was not contoured for the treated plan, an automated contour was inserted in the vacancy. A U-Net architecture was developed for training the dose prediction model and contained 17 input channels including CT images, 7 PTVs, and 9 OARs. Dose was normalized using a maximum dose point such that the objective dose for training the model was between zero and one. The model used five convolution layers with 32, 64, 128, 256, and 512 filters, respectively. After each convolution, 2 × 2 max pooling was performed to down sample the input matrix. 117 patient data sets were used for training and 23 patients were used for testing. Due to computational memory constraints, the model was trained using individual shuffled slices and in batches of 32 slices. Mean square error (MSE) was used as the loss function and a linear activation function was used for generating the predicted dose. <h3>Results</h3> The predicted mean dose to PTV₆₉₉₆ was 1.9 ± 2.7% lower than the actual mean dose. The mean percent differences between the predicted and actual D_95% and D_2% values for PTV6996 were -8.1 ± 5.1% and 1.5 ± 2.9 %, respectively. The maximum predicted dose to the spinal cord was 11.0 ± 10.8% lower than the actual dose. The percent difference and deviation for the mean dose to the total parotids was 15.0 ±17.7% lower than the actual dose. The mean predicted dose to the external body contour was 5.8 ± 10.1% lower than the actual dose. <h3>Conclusion</h3> The model was able to predict a dose distribution that agreed with treatment planning principles for H&N cancers, with target volumes receiving high dose and OARs receiving lower doses. The current model is a work in progress. More work is needed to validate and refine the prediction accuracy, which predicted lower doses to structures than the delivered dose. After refinement, the model will be used to assess the effects of AI generated contours on the predicted dose.

Simulation-Free Online Adaption: An Accelerated Pathway to Palliative Radiotherapy

<h3>Purpose/Objective(s)</h3> Novel AI-assisted on-line adaptive radiotherapy, combined with a simulation-free planning approach, might provide rapid palliative radiotherapy treatment which will accommodate patient shape on day of treatment. This would eliminate the simulation appointment, reducing patient wait-time, as well as allow sophisticated treatment options (such as IMRT/VMAT, boost, dose escalation). This study reports on the feasibility of this novel pathway as well as early experience. We report on AI contouring accuracy, accuracy of synthetic CT, evaluation of auto-planning quality, and efficiency of this novel pathway. <h3>Materials/Methods</h3> A commercial on-line adaptive system that generates a plan of the day with AI contours and auto-planning was used for this work in combination with a test environment that replicated the system. Reference contours and planning was conducted on diagnostic CT, while on-couch adaptive sessions utilized the daily CBCT and generated synthetic CT. AI contouring accuracy was determined by comparing target and organ at risk (OAR) contours reviewed by a Clinician (supervised), to the AI-derived (unsupervised) contours using the Dice Similarity Co-efficient (DSC). The fidelity of the synthetic CT created for daily on-couch treatment planning was assessed by comparing AI contours (body and bones) to the CBCT structures as a surrogate for the underlying deformable registration using a Likert scale. Daily plan generation was evaluated against reference plan quality metrics for target and OAR structures. Efficiency of the adaptive treatment was measured for each human and system task in the treatment delivery pathway. <h3>Results</h3> Data is reported for 10 retrospective patients in our test system and 6 prospective patients treated at our Institution with an online adaptive system. These were abdominopelvic palliative lesions. Mean DSC for unsupervised targets and OAR (kidney, liver, bladder, rectum) were above 0.9, while duodenum and stomach contours required user intervention. The synthetic CT registration of diagnostic CT to CBCT was scored as locally aligned within 2mm for all prospective patients for body contour, however the bones did not replicate as well. This indicates for diagnostic CTs bones are not deformed well. The daily plans were generated were determined to have a conformity index and PTV V95% equivalent to reference plans. The adaptive process averaged 20 min (range 14 to 27 min). <h3>Conclusion</h3> Early results are encouraging and suggest that this novel AI-assisted online adaptive radiotherapy may be feasible for simulation-free dynamic palliative radiotherapy.