RESUMO
Background and purpose: Accurate and automated segmentation of targets and organs-at-risk (OARs) is crucial for the successful clinical application of online adaptive radiotherapy (ART). Current methods for cone-beam computed tomography (CBCT) auto-segmentation face challenges, resulting in segmentations often failing to reach clinical acceptability. Current approaches for CBCT auto-segmentation overlook the wealth of information available from initial planning and prior adaptive fractions that could enhance segmentation precision. Materials and methods: We introduce a novel framework that incorporates data from a patient's initial plan and previous adaptive fractions, harnessing this additional temporal context to significantly refine the segmentation accuracy for the current fraction's CBCT images. We present LSTM-UNet, an innovative architecture that integrates Long Short-Term Memory (LSTM) units into the skip connections of the traditional U-Net framework to retain information from previous fractions. The models underwent initial pre-training with simulated data followed by fine-tuning on a clinical dataset. Results: Our proposed model's segmentation predictions yield an average Dice similarity coefficient of 79% from 8 Head & Neck organs and targets, compared to 52% from a baseline model without prior knowledge and 78% from a baseline model with prior knowledge but no memory. Conclusions: Our proposed model excels beyond baseline segmentation frameworks by effectively utilizing information from prior fractions, thus reducing the effort of clinicians to revise the auto-segmentation results. Moreover, it works together with registration-based methods that offer better prior knowledge. Our model holds promise for integration into the online ART workflow, offering precise segmentation capabilities on synthetic CT images.
RESUMO
Background Clinical trial matching, essential for advancing medical research, involves detailed screening of potential participants to ensure alignment with specific trial requirements. Research staff face challenges due to the high volume of eligible patients and the complexity of varying eligibility criteria. The traditional manual process, both time-consuming and error-prone, often leads to missed opportunities. Recently, large language models (LLMs), specifically generative pre-trained transformers (GPTs), have become impressive and impactful tools. Utilizing such tools from artificial intelligence (AI) and natural language processing (NLP) may enhance the accuracy and efficiency of this process through automated patient screening against established criteria. Methods Utilizing data from the National NLP Clinical Challenges (n2c2) 2018 Challenge, we utilized 202 longitudinal patient records. These records were annotated by medical professionals and evaluated against 13 selection criteria encompassing various health assessments. Our approach involved embedding medical documents into a vector database to determine relevant document sections and then using an LLM (OpenAI's GPT-3.5 Turbo and GPT-4) in tandem with structured and chain-of-thought prompting techniques for systematic document assessment against the criteria. Misclassified criteria were also examined to identify classification challenges. Results This study achieved an accuracy of 0.81, sensitivity of 0.80, specificity of 0.82, and a micro F1 score of 0.79 using GPT-3.5 Turbo, and an accuracy of 0.87, sensitivity of 0.85, specificity of 0.89, and micro F1 score of 0.86 using GPT-4. Notably, some criteria in the ground truth appeared mislabeled, an issue we couldn't explore further due to insufficient label generation guidelines on the website. Conclusion Our findings underscore the potential of AI and NLP technologies, including LLMs, in the clinical trial matching process. The study demonstrated strong capabilities in identifying eligible patients and minimizing false inclusions. Such automated systems promise to alleviate the workload of research staff and improve clinical trial enrollment, thus accelerating the process and enhancing the overall feasibility of clinical research. Further work is needed to determine the potential of this approach when implemented on real clinical data.
RESUMO
Background/purpose: The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack of clinician trust in AI models, underscoring the need for effective uncertainty quantification (UQ) methods. The purpose of this study was to scope existing literature related to UQ in RT, identify areas of improvement, and determine future directions. Methods: We followed the PRISMA-ScR scoping review reporting guidelines. We utilized the population (human cancer patients), concept (utilization of AI UQ), context (radiotherapy applications) framework to structure our search and screening process. We conducted a systematic search spanning seven databases, supplemented by manual curation, up to January 2024. Our search yielded a total of 8980 articles for initial review. Manuscript screening and data extraction was performed in Covidence. Data extraction categories included general study characteristics, RT characteristics, AI characteristics, and UQ characteristics. Results: We identified 56 articles published from 2015-2024. 10 domains of RT applications were represented; most studies evaluated auto-contouring (50%), followed by image-synthesis (13%), and multiple applications simultaneously (11%). 12 disease sites were represented, with head and neck cancer being the most common disease site independent of application space (32%). Imaging data was used in 91% of studies, while only 13% incorporated RT dose information. Most studies focused on failure detection as the main application of UQ (60%), with Monte Carlo dropout being the most commonly implemented UQ method (32%) followed by ensembling (16%). 55% of studies did not share code or datasets. Conclusion: Our review revealed a lack of diversity in UQ for RT applications beyond auto-contouring. Moreover, there was a clear need to study additional UQ methods, such as conformal prediction. Our results may incentivize the development of guidelines for reporting and implementation of UQ in RT.
RESUMO
Background: Adaptive radiotherapy (ART) can compensate for the dosimetric impact of anatomic change during radiotherapy of head neck cancer (HNC) patients. However, implementing ART universally poses challenges in clinical workflow and resource allocation, given the variability in patient response and the constraints of available resources. Therefore, early identification of head and neck cancer (HNC) patients who would experience significant anatomical change during radiotherapy (RT) is of importance to optimize patient clinical benefit and treatment resources. Purpose: The purpose of this study is to assess the feasibility of using a vision-transformer (ViT) based neural network to predict radiotherapy induced anatomic change of HNC patients. Methods: We retrospectively included 121 HNC patients treated with definitive RT/CRT. We collected the planning CT (pCT), planned dose, CBCTs acquired at the initial treatment (CBCT01) and fraction 21 (CBCT21), and primary tumor volume (GTVp) and involved nodal volume (GTVn) delineated on both pCT and CBCTs for model construction and evaluation. A UNet-style ViT network was designed to learn the spatial correspondence and contextual information from embedded image patches of CT, dose, CBCT01, GTVp, and GTVn. The deformation vector field between CBCT01 and CBCT21 was estimated by the model as the prediction of anatomic change, and deformed CBCT01 was used as the prediction of CBCT21. We also generated binary masks of GTVp, GTVn and patient body for volumetric change evaluation. We used data from 100 patients for training and validation, and the remaining 21 patients for testing. Image and volumetric similarity metrics including mean square error (MSE), structural similarity index (SSIM), dice coefficient, and average surface distance were used to measure the similarity between the target image and predicted CBCT. Results: The predicted image from the proposed method yielded the best similarity to the real image (CBCT21) over pCT, CBCT01, and predicted CBCTs from other comparison models. The average MSE and SSIM between the normalized predicted CBCT to CBCT21 are 0.009 and 0.933, while the average dice coefficient between body mask, GTVp mask, and GTVn mask are 0.972, 0.792, and 0.821 respectively. Conclusions: The proposed method showed promising performance for predicting radiotherapy induced anatomic change, which has the potential to assist in the decision making of HNC Adaptive RT.
RESUMO
Background and purpose: Radiation-induced erectile dysfunction (RiED) commonly affects prostate cancer patients, prompting clinical trials across institutions to explore dose-sparing to internal-pudendal-arteries (IPA) for preserving sexual potency. IPA, challenging to segment, isn't conventionally considered an organ-at-risk (OAR). This study proposes a deep learning (DL) auto-segmentation model for IPA, using Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) or CT alone to accommodate varied clinical practices. Materials and methods: A total of 86 patients with CT and MRI images and noisy IPA labels were recruited in this study. We split the data into 42/14/30 for model training, testing, and a clinical observer study, respectively. There were three major innovations in this model: 1) we designed an architecture with squeeze-and-excite blocks and modality attention for effective feature extraction and production of accurate segmentation, 2) a novel loss function was used for training the model effectively with noisy labels, and 3) modality dropout strategy was used for making the model capable of segmentation in the absence of MRI. Results: Test dataset metrics were DSC 61.71 ± 7.7 %, ASD 2.5 ± .87 mm, and HD95 7.0 ± 2.3 mm. AI segmented contours showed dosimetric similarity to expert physician's contours. Observer study indicated higher scores for AI contours (mean = 3.7) compared to inexperienced physicians' contours (mean = 3.1). Inexperienced physicians improved scores to 3.7 when starting with AI contours. Conclusion: The proposed model achieved good quality IPA contours to improve uniformity of segmentation and to facilitate introduction of standardized IPA segmentation into clinical trials and practice.
RESUMO
OBJECTIVE: We explore the potential dosimetric benefits of reducing treatment volumes through daily adaptive radiation therapy for head and neck cancer (HNC) patients using the Ethos system/Intelligent Optimizer Engine (IOE). We hypothesize reducing treatment volumes afforded by daily adaption will significantly reduce the dose to adjacent organs at risk. We also explore the capability of the Ethos IOE to accommodate this highly conformal approach in HNC radiation therapy. METHODS: Ten HNC patients from a phase II trial were chosen, and their cone-beam CT (CBCT) scans were uploaded to the adaptive RT (ART) emulator. A new initial reference plan was generated using both a 1 mm and 5 mm planning target volume (PTV) expansion. Daily adaptive ART plans (1 mm) were simulated from the clinical CBCT taken every fifth fraction. Additionally, using physician-modified ART contours the larger 5 mm plan was recalculated on this recontoured on daily anatomy. Changes in target and OAR contours were measured using Dice coefficients as a surrogate of clinician effort. PTV coverage and organ-at-risk (OAR) doses were statistically compared, and the robustness of each ART plan was evaluated at fractions 5 and 35 to observe if OAR doses were within 3 Gy of pre-plan. RESULTS: This study involved six patients with oropharynx and four with larynx cancer, totaling 70 adaptive fractions. The primary and nodal gross tumor volumes (GTV) required the most adjustments, with median Dice scores of 0.88 (range: 0.80-0.93) and 0.83 (range: 0.66-0.91), respectively. For the 5th and 35th fraction plans, 80 % of structures met robustness criteria (quartile 1-3: 67-100 % and 70-90 %). Adaptive planning improved median PTV V100% coverage for doses of 70 Gy (96 % vs. 95.6 %), 66.5 Gy (98.5 % vs. 76.5 %), and 63 Gy (98.9 % vs. 74.9 %) (p < 0.03). Implementing ART with total volume reduction yielded median dose reductions of 7-12 Gy to key organs-at-risk (OARs) like submandibular glands, parotids, oral cavity, and constrictors (p < 0.05). CONCLUSIONS: The IOE enables feasible daily ART treatments with reduced margins while enhancing target coverage and reducing OAR doses for HNC patients. A phase II trial recently finished accrual and forthcoming analysis will determine if these dosimetric improvements correlate with improved patient-reported outcomes.
Assuntos
Tomografia Computadorizada de Feixe Cônico , Estudos de Viabilidade , Neoplasias de Cabeça e Pescoço , Órgãos em Risco , Dosagem Radioterapêutica , Planejamento da Radioterapia Assistida por Computador , Humanos , Neoplasias de Cabeça e Pescoço/radioterapia , Neoplasias de Cabeça e Pescoço/diagnóstico por imagem , Planejamento da Radioterapia Assistida por Computador/métodos , Órgãos em Risco/efeitos da radiação , Simulação por ComputadorRESUMO
Background and Purpose: Online cone-beam-based adaptive radiotherapy (ART) adjusts for anatomical changes during external beam radiotherapy. However, limited cone-beam image quality complicates nodal contouring. Despite this challenge, artificial-intelligence guided deformation (AID) can auto-generate nodal contours. Our study investigated the optimal use of such contours in cervical online cone-beam-based ART. Materials and Methods: From 136 adaptive fractions across 21 cervical cancer patients with nodal disease, we extracted 649 clinically-delivered and AID clinical target volume (CTV) lymph node boost structures. We assessed geometric alignment between AID and clinical CTVs via dice similarity coefficient, and 95% Hausdorff distance, and geometric coverage of clinical CTVs by AID planning target volumes by false positive dice. Coverage of clinical CTVs by AID contour-based plans was evaluated using D100, D95, V100%, and V95%. Results: Between AID and clinical CTVs, the median dice similarity coefficient was 0.66 and the median 95 % Hausdorff distance was 4.0 mm. The median false positive dice of clinical CTV coverage by AID planning target volumes was 0. The median D100 was 1.00, the median D95 was 1.01, the median V100% was 1.00, and the median V95% was 1.00. Increased nodal volume, fraction number, and daily adaptation were associated with reduced clinical CTV coverage by AID-based plans. Conclusion: In one of the first reports on pelvic nodal ART, AID-based plans could adequately cover nodal targets. However, physician review is required due to performance variation. Greater attention is needed for larger, daily-adapted nodes further into treatment.
RESUMO
PURPOSE: Elective neck irradiation (ENI) has long been considered mandatory when treating head and neck squamous cell carcinoma (HNSCC) with definitive radiotherapy, but it is associated with significant dose to normal organs-at-risk (OAR). In this prospective phase II study, we investigated the efficacy and tolerability of eliminating ENI and strictly treating involved and suspicious lymph nodes (LN) with intensity-modulated radiotherapy. PATIENTS AND METHODS: Patients with newly diagnosed HNSCC of the oropharynx, larynx, and hypopharynx were eligible for enrollment. Each LN was characterized as involved or suspicious based on radiologic criteria and an in-house artificial intelligence (AI)-based classification model. Gross disease received 70 Gray (Gy) in 35 fractions and suspicious LNs were treated with 66.5 Gy, without ENI. The primary endpoint was solitary elective volume recurrence, with secondary endpoints including patterns-of-failure and patient-reported outcomes. RESULTS: Sixty-seven patients were enrolled, with 18 larynx/hypopharynx and 49 oropharynx cancer. With a median follow-up of 33.4 months, the 2-year risk of solitary elective nodal recurrence was 0%. Gastrostomy tubes were placed in 14 (21%), with median removal after 2.9 months for disease-free patients; no disease-free patient is chronically dependent. Grade I/II dermatitis was seen in 90%/10%. There was no significant decline in composite MD Anderson Dysphagia Index scores after treatment, with means of 89.1 and 92.6 at 12 and 24 months, respectively. CONCLUSIONS: These results suggest that eliminating ENI is oncologically sound for HNSCC, with highly favorable quality-of-life outcomes. Additional prospective studies are needed to support this promising paradigm before implementation in any nontrial setting.
Assuntos
Neoplasias de Cabeça e Pescoço , Radioterapia de Intensidade Modulada , Humanos , Inteligência Artificial , Neoplasias de Cabeça e Pescoço/radioterapia , Estudos Prospectivos , Qualidade de Vida , Radioterapia de Intensidade Modulada/efeitos adversos , Carcinoma de Células Escamosas de Cabeça e Pescoço/radioterapiaRESUMO
Importance: Oncologic outcomes are similar for patients with oropharyngeal squamous cell carcinoma (OPSCC) treated with primary surgery or radiotherapy. However, comparative differences in long-term patient-reported outcomes (PROs) between modalities are less well established. Objective: To determine the association between primary surgery or radiotherapy and long-term PROs. Design, Setting, and Participants: This cross-sectional study used the Texas Cancer Registry to identify survivors of OPSCC treated definitively with primary radiotherapy or surgery between January 1, 2006, and December 31, 2016. Patients were surveyed in October 2020 and April 2021. Exposures: Primary radiotherapy and surgery for OPSCC. Main Outcomes and Measures: Patients completed a questionnaire that included demographic and treatment information, the MD Anderson Symptom Inventory-Head and Neck (MDASI-HN) module, the Neck Dissection Impairment Index (NDII), and the Effectiveness of Auditory Rehabilitation (EAR) scale. Multivariable linear regression models were performed to evaluate the association of treatment (surgery vs radiotherapy) with PROs while controlling for additional variables. Results: Questionnaires were mailed to 1600 survivors of OPSCC identified from the Texas Cancer Registry, with 400 responding (25% response rate), of whom 183 (46.2%) were 8 to 15 years from their initial diagnosis. The final analysis included 396 patients (aged ≤57 years, 190 [48.0%]; aged >57 years, 206 [52.0%]; female, 72 [18.2%]; male, 324 [81.8%]). After multivariable adjustment, no significant differences were found between surgery and radiotherapy outcomes as measured by the MDASI-HN (ß, -0.1; 95% CI, -0.7 to 0.6), NDII (ß, -1.7; 95% CI, -6.7 to 3.4), and EAR (ß, -0.9; 95% CI -7.7 to 5.8). In contrast, less education, lower household income, and feeding tube use were associated with significantly worse MDASI-HN, NDII, and EAR scores, while concurrent chemotherapy with radiotherapy was associated with worse MDASI-HN and EAR scores. Conclusions and Relevance: This population-based cohort study found no associations between long-term PROs and primary radiotherapy or surgery for OPSCC. Lower socioeconomic status, feeding tube use, and concurrent chemotherapy were associated with worse long-term PROs. Further efforts should focus on the mechanism, prevention, and rehabilitation of these long-term treatment toxicities. The long-term outcomes of concurrent chemotherapy should be validated and may inform treatment decision making.
Assuntos
Neoplasias de Cabeça e Pescoço , Neoplasias Orofaríngeas , Humanos , Masculino , Feminino , Estudos de Coortes , Estudos Transversais , Neoplasias Orofaríngeas/radioterapia , Neoplasias Orofaríngeas/cirurgia , Neoplasias Orofaríngeas/patologia , Medidas de Resultados Relatados pelo Paciente , Carcinoma de Células Escamosas de Cabeça e PescoçoRESUMO
Objective. Accurate diagnosis of lymph node metastasis (LNM) is critical in treatment management for patients with head and neck cancer. Positron emission tomography and computed tomography are routinely used for identifying LNM status. However, for small or less fluorodeoxyglucose (FDG) avid nodes, there are always uncertainties in LNM diagnosis. We are aiming to develop a reliable prediction model is for identifying LNM.Approach. In this study, a new automated and reliable multi-objective learning model (ARMO) is proposed. In ARMO, a multi-objective model is introduced to obtain balanced sensitivity and specificity. Meanwhile, confidence is calibrated by introducing individual reliability, whilst the model uncertainty is estimated by a newly defined overall reliability in ARMO. In the training stage, a Pareto-optimal model set is generated. Then all the Pareto-optimal models are used, and a reliable fusion strategy that introduces individual reliability is developed for calibrating the confidence of each output. The overall reliability is calculated to estimate the model uncertainty for each test sample.Main results. The experimental results demonstrated that ARMO obtained more promising results, which the area under the curve, accuracy, sensitivity and specificity can achieve 0.97, 0.93, 0.88 and 0.94, respectively. Meanwhile, based on calibrated confidence and overall reliability, clinicians could pay particular attention to highly uncertain predictions.Significance. In this study, we developed a unified model that can achieve balanced prediction, confidence calibration and uncertainty estimation simultaneously. The experimental results demonstrated that ARMO can obtain accurate and reliable prediction performance.
Assuntos
Neoplasias de Cabeça e Pescoço , Tomografia por Emissão de Pósitrons combinada à Tomografia Computadorizada , Humanos , Tomografia por Emissão de Pósitrons combinada à Tomografia Computadorizada/métodos , Metástase Linfática , Reprodutibilidade dos Testes , Linfonodos/patologia , Neoplasias de Cabeça e Pescoço/patologia , Estudos RetrospectivosRESUMO
Cone-beam CT (CBCT)-based online adaptive radiotherapy calls for accurate auto-segmentation to reduce the time cost for physicians. However, deep learning (DL)-based direct segmentation of CBCT images is a challenging task, mainly due to the poor image quality and lack of well-labelled large training datasets. Deformable image registration (DIR) is often used to propagate the manual contours on the planning CT (pCT) of the same patient to CBCT. In this work, we undertake solving the problems mentioned above with the assistance of DIR. Our method consists of three main components. First, we use deformed pCT contours derived from multiple DIR methods between pCT and CBCT as pseudo labels for initial training of the DL-based direct segmentation model. Second, we use deformed pCT contours from another DIR algorithm as influencer volumes to define the region of interest for DL-based direct segmentation. Third, the initially trained DL model is further fine-tuned using a smaller set of true labels. Nine patients are used for model evaluation. We found that DL-based direct segmentation on CBCT without influencer volumes has much poorer performance compared to DIR-based segmentation. However, adding deformed pCT contours as influencer volumes in the direct segmentation network dramatically improves segmentation performance, reaching the accuracy level of DIR-based segmentation. The DL model with influencer volumes can be further improved through fine-tuning using a smaller set of true labels, achieving mean Dice similarity coefficient of 0.86, Hausdorff distance at the 95th percentile of 2.34 mm, and average surface distance of 0.56 mm. A DL-based direct CBCT segmentation model can be improved to outperform DIR-based segmentation models by using deformed pCT contours as pseudo labels and influencer volumes for initial training, and by using a smaller set of true labels for model fine tuning.
Assuntos
Aprendizado Profundo , Planejamento da Radioterapia Assistida por Computador , Humanos , Planejamento da Radioterapia Assistida por Computador/métodos , Processamento de Imagem Assistida por Computador/métodos , Tomografia Computadorizada de Feixe Cônico/métodos , AlgoritmosRESUMO
PURPOSE: A reliable locoregional recurrence (LRR) prediction model is important for the personalized management of head and neck cancers (HNC) patients who received radiotherapy. This work aims to develop a delta-radiomics feature-based multi-classifier, multi-objective, and multi-modality (Delta-mCOM) model for post-treatment HNC LRR prediction. Furthermore, we aim to adopt a learning with rejection option (LRO) strategy to boost the reliability of Delta-mCOM model by rejecting prediction for samples with high prediction uncertainties. METHODS: In this retrospective study, we collected PET/CT image and clinical data from 224 HNC patients who received radiotherapy (RT) at our institution. We calculated the differences between radiomics features extracted from PET/CT images acquired before and after radiotherapy and used them in conjunction with pre-treatment radiomics features as the input features. Using clinical parameters, PET radiomics features, and CT radiomics features, we built and optimized three separate single-modality models. We used multiple classifiers for model construction and employed sensitivity and specificity simultaneously as the training objectives for each of them. Then, for testing samples, we fused the output probabilities from all these single-modality models to obtain the final output probabilities of the Delta-mCOM model. In the LRO strategy, we estimated the epistemic and aleatoric uncertainties when predicting with a trained Delta-mCOM model and identified patients associated with prediction of higher reliability (low uncertainty estimates). The epistemic and aleatoric uncertainties were estimated using an AutoEncoder-style anomaly detection model and test-time augmentation (TTA) with predictions made from the Delta-mCOM model, respectively. Predictions with higher epistemic uncertainty or higher aleatoric uncertainty than given thresholds were deemed unreliable, and they were rejected before providing a final prediction. In this study, different thresholds corresponding to different low-reliability prediction rejection ratios were applied. Their values are based on the estimated epistemic and aleatoric uncertainties distribution of the validation data. RESULTS: The Delta-mCOM model performed significantly better than the single-modality models, whether trained with pre-, post-treatment radiomics features or concatenated BaseLine and Delta-Radiomics Features (BL-DRFs). It was numerically superior to the PET and CT fused BL-DRF model (nonstatistically significant). Using the LRO strategy for the Delta-mCOM model, most of the evaluation metrics improved as the rejection ratio increased from 0% to around 25%. Utilizing both epistemic and aleatoric uncertainty for rejection yielded nonstatistically significant improved metrics compared to each alone at approximately a 25% rejection ratio. Metrics were significantly better than the no-rejection method when the reject ratio was higher than 50%. CONCLUSIONS: The inclusion of the delta-radiomics feature improved the accuracy of HNC LRR prediction, and the proposed Delta-mCOM model can give more reliable predictions by rejecting predictions for samples of high uncertainty using the LRO strategy.
Assuntos
Neoplasias de Cabeça e Pescoço , Tomografia por Emissão de Pósitrons combinada à Tomografia Computadorizada , Humanos , Estudos Retrospectivos , Reprodutibilidade dos Testes , Neoplasias de Cabeça e Pescoço/diagnóstico por imagem , Neoplasias de Cabeça e Pescoço/radioterapia , Sensibilidade e EspecificidadeRESUMO
Purpose: To present a concept called artificial intelligence-assisted contour editing (AIACE) and demonstrate its feasibility. Materials and Methods: The conceptual workflow of AIACE is as follows: Given an initial contour that requires clinician editing, the clinician indicates where large editing is needed, and a trained deep learning model uses this input to update the contour. This process repeats until a clinically acceptable contour is achieved. In this retrospective, proof-of-concept study, the authors demonstrated the concept on two-dimensional (2D) axial CT images from three head-and-neck cancer datasets by simulating the interaction with the AIACE model to mimic the clinical environment. The input at each iteration was one mouse click on the desired location of the contour segment. Model performance is quantified with the Dice similarity coefficient (DSC) and 95th percentile of Hausdorff distance (HD95) based on three datasets with sample sizes of 10, 28, and 20 patients. Results: The average DSCs and HD95 values of the automatically generated initial contours were 0.82 and 4.3 mm, 0.73 and 5.6 mm, and 0.67 and 11.4 mm for the three datasets, which were improved to 0.91 and 2.1 mm, 0.86 and 2.5 mm, and 0.86 and 3.3 mm, respectively, with three mouse clicks. Each deep learning-based contour update required about 20 msec. Conclusion: The authors proposed the newly developed AIACE concept, which uses deep learning models to assist clinicians in editing contours efficiently and effectively, and demonstrated its feasibility by using 2D axial CT images from three head-and-neck cancer datasets.Keywords: Segmentation, Convolutional Neural Network (CNN), CT, Deep Learning Algorithms Supplemental material is available for this article. © RSNA, 2022.
RESUMO
(1) We hypothesized that adding concurrent stereotactic ablative radiotherapy (SAbR) would increase the time to progression in patients with metastatic castrate-resistant prostate cancer (mCRPCA) treated with sipuleucel-T. (2) Patients with a history of prostate cancer (PC), radiographic evidence of metastatic disease, and rising prostate-specific antigen (PSA) > 0.2 ng/dL on castrate testosterone levels were enrolled in this single-arm phase II clinical trial and treated with sipuleucel-T and SAbR. The primary endpoint was time to progression (TTP). Cellular and humoral responses were measured using ELISpot and Luminex multiplex assays, respectively. (3) Twenty patients with mCRPC were enrolled and treated with SAbR to 1−3 sites. Treatment was well tolerated with 51, 8, and 4 treatment-related grade 1, 2, and 3 toxicities, respectively, and no grade 4 or 5 adverse events. At a median follow-up of 15.5 months, the median TTP was 11.2 weeks (95% CI; 6.8−14.0 weeks). Median OS was 76.8 weeks (95% CI; 41.6−130.8 weeks). This regimen induced both humoral and cellular immune responses. Baseline M-MDSC levels were elevated in mCRPC patients compared to healthy donors (p = 0.004) and a decline in M-MDSC was associated with biochemical response (p = 0.044). Responders had lower baseline uric acid levels (p = 0.05). No clear correlation with radiographic response was observed. (4) While the regimen was safe, the PC-antigen-specific immune response induced by SAbR did not yield a synergistic clinical benefit for patients treated with sipuleucel-T compared to the historically reported outcomes.
RESUMO
Purpose. Real-time three-dimensional (3D) magnetic resonance (MR) imaging is challenging because of slow MR signal acquisition, leading to highly under-sampled k-space data. Here, we proposed a deep learning-based, k-space-driven deformable registration network (KS-RegNet) for real-time 3D MR imaging. By incorporating prior information, KS-RegNet performs a deformable image registration between a fully-sampled prior image and on-board images acquired from highly-under-sampled k-space data, to generate high-quality on-board images for real-time motion tracking.Methods. KS-RegNet is an end-to-end, unsupervised network consisting of an input data generation block, a subsequent U-Net core block, and following operations to compute data fidelity and regularization losses. The input data involved a fully-sampled, complex-valued prior image, and the k-space data of an on-board, real-time MR image (MRI). From the k-space data, under-sampled real-time MRI was reconstructed by the data generation block to input into the U-Net core. In addition, to train the U-Net core to learn the under-sampling artifacts, the k-space data of the prior image was intentionally under-sampled using the same readout trajectory as the real-time MRI, and reconstructed to serve an additional input. The U-Net core predicted a deformation vector field that deforms the prior MRI to on-board real-time MRI. To avoid adverse effects of quantifying image similarity on the artifacts-ridden images, the data fidelity loss of deformation was evaluated directly in k-space.Results. Compared with Elastix and other deep learning network architectures, KS-RegNet demonstrated better and more stable performance. The average (±s.d.) DICE coefficients of KS-RegNet on a cardiac dataset for the 5- , 9- , and 13-spoke k-space acquisitions were 0.884 ± 0.025, 0.889 ± 0.024, and 0.894 ± 0.022, respectively; and the corresponding average (±s.d.) center-of-mass errors (COMEs) were 1.21 ± 1.09, 1.29 ± 1.22, and 1.01 ± 0.86 mm, respectively. KS-RegNet also provided the best performance on an abdominal dataset.Conclusion. KS-RegNet allows real-time MRI generation with sub-second latency. It enables potential real-time MR-guided soft tissue tracking, tumor localization, and radiotherapy plan adaptation.
Assuntos
Artefatos , Imageamento por Ressonância Magnética , Abdome , Processamento de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Movimento (Física)RESUMO
PURPOSE/OBJECTIVES: Radiation therapy (RT) for the treatment of patients with head and neck cancer (HNC) leads to side effects that can limit a person's oral intake. Early identification of patients who need aggressive nutrition supplementation via a feeding tube (FT) could improve outcomes. We hypothesize that traditional machine learning techniques used in combination with deep learning techniques could identify patients early during RT who will later need a FT. MATERIALS/METHODS: We evaluated 271 patients with HNC treated with RT. Sixteen clinical features, planning computed tomography (CT) scans, 3-dimensional dose, and treatment cone-beam CT scans were gathered for each patient. The outcome predicted was the need for a FT or ≥10% weight loss during RT. Three conventional classifiers, including logistic regression (LR), support vector machine, and multilayer perceptron, used the 16 clinical features for clinical modeling. A convolutional neural network (CNN) analyzed the imaging data. Five-fold cross validation was performed. The area under the curve (AUC) values were used to compare models' performances. ROC analyses were performed using a paired DeLong Test in R-4.1.2. The clinical and imaging model outcomes were combined to make a final prediction via evidential reasoning rule-based fusion. RESULTS: The LR model performed the best on the clinical dataset (AUC 0.69). The MedicalNet CNN trained via transfer learning performed the best on the imaging dataset (AUC 0.73). The combined clinical and image-based model obtained an AUC of 0.75. The combined model was statistically better than the clinical model alone (p = 0.001). CONCLUSIONS: An artificial intelligence model incorporating clinical parameters, dose distributions and on-treatment CBCT achieved the highest performance to identify the need to place a reactive feeding tube.
Assuntos
Aprendizado Profundo , Neoplasias de Cabeça e Pescoço , Inteligência Artificial , Tomografia Computadorizada de Feixe Cônico/métodos , Suplementos Nutricionais , Neoplasias de Cabeça e Pescoço/diagnóstico por imagem , Neoplasias de Cabeça e Pescoço/radioterapia , Humanos , Redes Neurais de ComputaçãoRESUMO
Purpose: Stereotactic ablative radiation (SAbR) has been increasingly used in prostate cancer (PCa) given its convenience and cost efficacy. Optimal doses remain poorly defined with limited prospective comparative trials and long-term safety/efficacy data at higher dose levels. We analyzed toxicity and outcomes for SAbR in men with localized PCa at escalated 45 Gy in 5 fractions. Methods and Materials: This study retrospectively analyzed men from 2015 to 2019 with PCa who received linear-accelerator-based SAbR to 45 Gy in 5 fractions, along with perirectal hydrogel spacer, fiducial placement, and MRI-based planning. Disease control outcomes were calculated from end of treatment. Minimally important difference (MID) assessing patient-reported quality of life was defined as greater than a one-half standard deviation increase in American Urological Association (AUA) symptom score after SAbR. Results: Two-hundred and forty-nine (249) low-, intermediate-, and high-risk PCa patients with median follow-up of 14.9 months for clinical toxicity were included. Acute urinary grade II toxicity occurred in 20.4% of patients. Acute grade II GI toxicity occurred in 7.3% of patients. For follow-up > 2 years (n = 69), late GU and GI grade ≥III toxicity occurred in 5.8% and 1.5% of patients, respectively. MID was evident in 31.8%, 23.4%, 35.8%, 37.0%, 33.3%, and 26.7% of patients at 3, 6, 12, 24, 36, and 48 months, respectively. The median follow-up for biochemical recurrence was 22.6 months with biochemical failure-free survival of 100% at 1 year (n = 226) and 98.7% for years 2 (n = 113) and 3 (n = 54). Conclusions: SAbR for PCa at 45 Gy in 5 fractions shows an encouraging safety profile. Prospective studies with longer follow-up are warranted to establish this dose regimen as standard of care for PCa.
RESUMO
BACKGROUND: Local failure (LF) following chemoradiation (CRT) for head and neck cancer is associated with poor overall survival. If machine learning techniques could stratify patients at risk of treatment failure based on baseline and intra-treatment imaging, such a model could facilitate response-adapted approaches to escalate, de-escalate, or switch therapy. METHODS: A 1:2 retrospective case control cohort of patients treated at a single institution with definitive radiotherapy for head and neck cancer who failed locally, in-field at a primary or nodal structure were included. Radiomic features were extracted from baseline CT and CBCT scans at fractions 1 and 21 (delta) of radiotherapy with PyRadiomics and were selected for by: reproducibility (intra-class correlation coefficients ≥0.95), redundancy [maximum relevance and minimum redundancy (mRMR)], and informativeness [recursive feature elimination (RFE)]. Separate models predicting LF of primaries or nodes were created using the explainable boosting machine (EBM) classifier with 5-fold cross-validation for (I) clinical only, (II) radiomic only (CT1 and delta features), and (III) fused models (clinical + radiomic). Twenty-five iterations were performed, and predicted scores were averaged with a parallel ensemble design. Receiver operating characteristic curves were compared between models with paired-samples t-tests. RESULTS: The fused ensemble model for primaries (using clinical, CT1, and delta features) achieved an AUC of 0.871 with a sensitivity of 78.3% and specificity of 90.9% at the maximum Youden J statistic. The fused ensemble model trended towards improvement when compared to the clinical only ensemble model (AUC =0.788, P=0.134) but reached significance when compared to the radiomic ensemble model (AUC =0.770, P=0.017). The fused ensemble model for nodes achieved an AUC of 0.910 with a sensitivity of 100.0% and specificity of 68.0%, which also trended towards improvement when compared to the clinical model (AUC =0.865, P=0.080). CONCLUSIONS: The fused ensemble EBM model achieved high discriminatory ability at predicting LF for head and neck cancer in independent primary and nodal structures. Although an additive benefit of delta radiomics over clinical factors could not be proven, the results trended towards improvement with the fused ensemble model, which are promising and worthy of prospective investigation in a larger cohort.