Deep learning-based optimization of field geometry for total marrow irradiation delivered with volumetric modulated arc therapy.

BACKGROUND: Total marrow (lymphoid) irradiation (TMI/TMLI) is a radiotherapy treatment used to selectively target the bone marrow and lymph nodes in conditioning regimens for allogeneic hematopoietic stem cell transplantation. A complex field geometry is needed to cover the large planning target volume (PTV) of TMI/TMLI with volumetric modulated arc therapy (VMAT). Five isocenters and ten overlapping fields are needed for the upper body, while, for patients with large anatomical conformation, two specific isocenters are placed on the arms. The creation of a field geometry is clinically challenging and is performed by a medical physicist (MP) specialized in TMI/TMLI. PURPOSE: To develop convolutional neural networks (CNNs) for automatically generating the field geometry of TMI/TMLI. METHODS: The dataset comprised 117 patients treated with TMI/TMLI between 2011 and 2023 at our Institute. The CNN input image consisted of three channels, obtained by projecting along the sagittal plane: (1) average CT pixel intensity within the PTV; (2) PTV mask; (3) brain, lungs, liver, bowel, and bladder masks. This "averaged" frontal view combined the information analyzed by the MP when setting the field geometry in the treatment planning system (TPS). Two CNNs were trained to predict the isocenters coordinates and jaws apertures for patients with (CNN-1) and without (CNN-2) isocenters on the arms. Local optimization methods were used to refine the models output based on the anatomy of the patient. Model evaluation was performed on a test set of 15 patients in two ways: (1) by computing the root mean squared error (RMSE) between the CNN output and ground truth; (2) with a qualitative assessment of manual and generated field geometries-scale: 1 = not adequate, 4 = adequate-carried out in blind mode by three MPs with different expertise in TMI/TMLI. The Wilcoxon signed-rank test was used to evaluate the independence of the given scores between manual and generated configurations (p < 0.05 significant). RESULTS: The average and standard deviation values of RMSE for CNN-1 and CNN-2 before/after local optimization were 15 ± 2/13 ± 3 mm and 16 ± 2/18 ± 4 mm, respectively. The CNNs were integrated into a planning automation software for TMI/TMLI such that the MPs could analyze in detail the proposed field geometries directly in the TPS. The selection of the CNN model to create the field geometry was based on the PTV width to approximate the decision process of an experienced MP and provide a single option of field configuration. We found no significant differences between the manual and generated field geometries for any MP, with median values of 4 versus 4 (p = 0.92), 3 versus 3 (p = 0.78), 4 versus 3 (p = 0.48), respectively. Starting from October 2023, the generated field geometry has been introduced in our clinical practice for prospective patients. CONCLUSIONS: The generated field geometries were clinically acceptable and adequate, even for an MP with high level of expertise in TMI/TMLI. Incorporating the knowledge of the MPs into the development cycle was crucial for optimizing the models, especially in this scenario with limited data.

Deep learning and atlas-based models to streamline the segmentation workflow of total marrow and lymphoid irradiation.

PURPOSE: To improve the workflow of total marrow and lymphoid irradiation (TMLI) by enhancing the delineation of organs at risk (OARs) and clinical target volume (CTV) using deep learning (DL) and atlas-based (AB) segmentation models. MATERIALS AND METHODS: Ninety-five TMLI plans optimized in our institute were analyzed. Two commercial DL software were tested for segmenting 18 OARs. An AB model for lymph node CTV (CTV_LN) delineation was built using 20 TMLI patients. The AB model was evaluated on 20 independent patients, and a semiautomatic approach was tested by correcting the automatic contours. The generated OARs and CTV_LN contours were compared to manual contours in terms of topological agreement, dose statistics, and time workload. A clinical decision tree was developed to define a specific contouring strategy for each OAR. RESULTS: The two DL models achieved a median [interquartile range] dice similarity coefficient (DSC) of 0.84 [0.71;0.93] and 0.85 [0.70;0.93] across the OARs. The absolute median Dmean difference between manual and the two DL models was 2.0 [0.7;6.6]% and 2.4 [0.9;7.1]%. The AB model achieved a median DSC of 0.70 [0.66;0.74] for CTV_LN delineation, increasing to 0.94 [0.94;0.95] after manual revision, with minimal Dmean differences. Since September 2022, our institution has implemented DL and AB models for all TMLI patients, reducing from 5 to 2 h the time required to complete the entire segmentation process. CONCLUSION: DL models can streamline the TMLI contouring process of OARs. Manual revision is still necessary for lymph node delineation using AB models.

Enhancing Radiotherapy Workflow for Head and Neck Cancer with Artificial Intelligence: A Systematic Review.

BACKGROUND: Head and neck cancer (HNC) is characterized by complex-shaped tumors and numerous organs at risk (OARs), inducing challenging radiotherapy (RT) planning, optimization, and delivery. In this review, we provided a thorough description of the applications of artificial intelligence (AI) tools in the HNC RT process. METHODS: The PubMed database was queried, and a total of 168 articles (2016-2022) were screened by a group of experts in radiation oncology. The group selected 62 articles, which were subdivided into three categories, representing the whole RT workflow: (i) target and OAR contouring, (ii) planning, and (iii) delivery. RESULTS: The majority of the selected studies focused on the OARs segmentation process. Overall, the performance of AI models was evaluated using standard metrics, while limited research was found on how the introduction of AI could impact clinical outcomes. Additionally, papers usually lacked information about the confidence level associated with the predictions made by the AI models. CONCLUSIONS: AI represents a promising tool to automate the RT workflow for the complex field of HNC treatment. To ensure that the development of AI technologies in RT is effectively aligned with clinical needs, we suggest conducting future studies within interdisciplinary groups, including clinicians and computer scientists.

Impact of the Extremities Positioning on the Set-Up Reproducibility for the Total Marrow Irradiation Treatment.

Total marrow (lymph node) irradiation (TMI/TMLI) delivery requires more time than standard radiotherapy treatments. The patient's extremities, through the joints, can experience large movements. The reproducibility of TMI/TMLI patients' extremities was evaluated to find the best positioning and reduce unwanted movements. Eighty TMI/TMLI patients were selected (2013-2022). During treatment, a cone-beam computed tomography (CBCT) was performed for each isocenter to reposition the patient. CBCT-CT pairs were evaluated considering: (i) online vector shift (OVS) that matched the two series; (ii) residual vector shift (RVS) to reposition the patient's extremities; (iii) qualitative agreement (range 1-5). Patients were subdivided into (i) arms either leaning on the frame or above the body; (ii) with or without a personal cushion for foot positioning. The Mann-Whitney test was considered (p < 0.05 significant). Six-hundred-twenty-nine CBCTs were analyzed. The median OVS was 4.0 mm, with only 1.6% of cases ranked < 3, and 24% of RVS > 10 mm. Arms leaning on the frame had significantly smaller RVS than above the body (median: 8.0 mm/6.0 mm, p < 0.05). Using a personal cushion for the feet significantly improved the RVS than without cushions (median: 8.5 mm/1.8 mm, p < 0.01). The role and experience of the radiotherapy team are fundamental to optimizing the TMI/TMLI patient setup.

Multicentric evaluation of a machine learning model to streamline the radiotherapy patient specific quality assurance process.

PURPOSE: Patient-specific quality assurance (PSQA) is performed to ensure that modulated treatment plans can be delivered as intended, but constitutes a substantial workload that could slow down the radiotherapy process and delay the start of clinical treatments. In this study, we investigated a machine learning (ML) tree-based ensemble model to predict the gamma passing rate (GPR) for volumetric modulated arc therapy (VMAT) plans. MATERIALS AND METHODS: 5622 VMAT plans from multiple treatment sites were selected from a database of Institution 1 and the ML model trained using 19 metrics. PSQA analyses were performed automatically using criteria 3%/1 mm (global normalization, absolute dose, 10% threshold) and 95% action limit. Model's performance was evaluated on an out-of-sample test set of Institution 1 and on two independent sets of measurements collected at Institution 2 and Institution 3. Mean absolute error (MAE), as well as the model's sensitivity and specificity, were computed. RESULTS: The model obtained a MAE of 2.33%, 2.54% and 3.91% for the three Institutions, with a specificity of 0.90, 0.90 and 0.68, and a sensitivity of 0.61, 0.25, and 0.55, respectively. Small positive median values of the residuals (i.e., the difference between measurements and predictions) were observed for each Institution (0.95%, 1.66%, and 3.42%). Thus, the model's predictions were, on average, close to the real values and provided a conservative estimation of the GPR. CONCLUSIONS: ML models can be integrated into clinical practice to streamline the radiotherapy workflow, but they should be center-specific or thoroughly verified within centers before clinical use.

Evaluation of plan complexity and dosimetric plan quality of total marrow and lymphoid irradiation using volumetric modulated arc therapy.

PURPOSE: To assess the impact of the planner's experience and optimization algorithm on the plan quality and complexity of total marrow and lymphoid irradiation (TMLI) delivered by means of volumetric modulated arc therapy (VMAT) over 2010-2022 at our institute. METHODS: Eighty-two consecutive TMLI plans were considered. Three complexity indices were computed to characterize the plans in terms of leaf gap size, irregularity of beam apertures, and modulation complexity. Dosimetric points of the target volume (D2%) and organs at risk (OAR) (Dmean) were automatically extracted to combine them with plan complexity and obtain a global quality score (GQS). The analysis was stratified based on the different optimization algorithms used over the years, including a knowledge-based (KB) model. Patient-specific quality assurance (QA) using Portal Dosimetry was performed retrospectively, and the gamma agreement index (GAI) was investigated in conjunction with plan complexity. RESULTS: Plan complexity significantly reduced over the years (r = -0.50, p < 0.01). Significant differences in plan complexity and plan dosimetric quality among the different algorithms were observed. Moreover, the KB model allowed to achieve significantly better dosimetric results to the OARs. The plan quality remained similar or even improved during the years and when moving to a newer algorithm, with GQS increasing from 0.019 ± 0.002 to 0.025 ± 0.003 (p < 0.01). The significant correlation between GQS and time (r = 0.33, p = 0.01) indicated that the planner's experience was relevant to improve the plan quality of TMLI plans. Significant correlations between the GAI and the complexity metrics (r = -0.71, p < 0.01) were also found. CONCLUSION: Both the planner's experience and algorithm version are crucial to achieve an optimal plan quality in TMLI plans. Thus, the impact of the optimization algorithm should be carefully evaluated when a new algorithm is introduced and in system upgrades. Knowledge-based strategies can be useful to increase standardization and improve plan quality of TMLI treatments.

Internal Guidelines for Reducing Lymph Node Contour Variability in Total Marrow and Lymph Node Irradiation.

BACKGROUND: The total marrow and lymph node irradiation (TMLI) target includes the bones, spleen, and lymph node chains, with the latter being the most challenging structures to contour. We evaluated the impact of introducing internal contour guidelines to reduce the inter- and intraobserver lymph node delineation variability in TMLI treatments. METHODS: A total of 10 patients were randomly selected from our database of 104 TMLI patients so as to evaluate the guidelines' efficacy. The lymph node clinical target volume (CTV_LN) was recontoured according to the guidelines (CTV_LN_GL_RO1) and compared to the historical guidelines (CTV_LN_Old). Both topological (i.e., Dice similarity coefficient (DSC)) and dosimetric (i.e., V95 (the volume receiving 95% of the prescription dose) metrics were calculated for all paired contours. RESULTS: The mean DSCs were 0.82 ± 0.09, 0.97 ± 0.01, and 0.98 ± 0.02, respectively, for CTV_LN_Old vs. CTV_LN_GL_RO1, and between the inter- and intraobserver contours following the guidelines. Correspondingly, the mean CTV_LN-V95 dose differences were 4.8 ± 4.7%, 0.03 ± 0.5%, and 0.1 ± 0.1%. CONCLUSIONS: The guidelines reduced the CTV_LN contour variability. The high target coverage agreement revealed that historical CTV-to-planning-target-volume margins were safe, even if a relatively low DSC was observed.

Automatic planning of the lower extremities for total marrow irradiation using volumetric modulated arc therapy.

PURPOSE: Total marrow (and lymphoid) irradiation (TMI-TMLI) is limited by the couch travel range of modern linacs, which forces the treatment delivery to be split into two plans with opposite orientations: a head-first supine upper-body plan, and a feet-first supine lower extremities plan. A specific field junction is thus needed to obtain adequate target coverage in the overlap region of the two plans. In this study, an automatic procedure was developed for field junction creation and lower extremities plan optimization. METHODS: Ten patients treated with TMI-TMLI at our institution were selected retrospectively. The planning of the lower extremities was performed automatically. Target volume parameters (CTV_J­V98% > 98%) at the junction region and several dose statistics (D98%, Dmean, and D2%) were compared between automatic and manual plans. The modulation complexity score (MCS) was used to assess plan complexity. RESULTS: The automatic procedure required 60-90 min, depending on the case. All automatic plans achieved clinically acceptable dosimetric results (CTV_J­V98% > 98%), with significant differences found at the junction region, where Dmean and D2% increased on average by 2.4% (p < 0.03) and 3.0% (p < 0.02), respectively. Similar plan complexity was observed (median MCS = 0.12). Since March 2022, the automatic procedure has been introduced in our clinic, reducing the TMI-TMLI simulation-to-delivery schedule by 2 days. CONCLUSION: The developed procedure allowed treatment planning of TMI-TMLI to be streamlined, increasing efficiency and standardization, preventing human errors, while maintaining the dosimetric plan quality and complexity of manual plans. Automated strategies can simplify the future adoption and clinical implementation of TMI-TMLI treatments in new centers.

A virtual reality classroom to teach and explore crystal solid state structures.

We present an educational application of virtual reality that we created to help students gain an in-depth understanding of the internal structure of crystals and related key concepts. Teachers can use it to give lectures to small groups (10-15) of students in a shared virtual environment, both remotely (with teacher and students in different locations) and locally (while sharing the same physical space). Lectures can be recorded, stored in an online repository, and shared with students who can either review a recorded lecture in the same virtual environment or can use the application for self-studying by exploring a large collection of available crystal structures. We validated our application with human subjects receiving positive feedback. Supplementary Information: The online version contains supplementary material available at 10.1007/s11042-022-13410-0https://doi.org/10.1007/s11042-022-13410-0.

Image Embeddings Extracted from CNNs Outperform Other Transfer Learning Approaches in Classification of Chest Radiographs.

To identify the best transfer learning approach for the identification of the most frequent abnormalities on chest radiographs (CXRs), we used embeddings extracted from pretrained convolutional neural networks (CNNs). An explainable AI (XAI) model was applied to interpret black-box model predictions and assess its performance. Seven CNNs were trained on CheXpert. Three transfer learning approaches were thereafter applied to a local dataset. The classification results were ensembled using simple and entropy-weighted averaging. We applied Grad-CAM (an XAI model) to produce a saliency map. Grad-CAM maps were compared to manually extracted regions of interest, and the training time was recorded. The best transfer learning model was that which used image embeddings and random forest with simple averaging, with an average AUC of 0.856. Grad-CAM maps showed that the models focused on specific features of each CXR. CNNs pretrained on a large public dataset of medical images can be exploited as feature extractors for tasks of interest. The extracted image embeddings contain relevant information that can be used to train an additional classifier with satisfactory performance on an independent dataset, demonstrating it to be the optimal transfer learning strategy and overcoming the need for large private datasets, extensive computational resources, and long training times.

Applications of artificial intelligence in stereotactic body radiation therapy.

This topical review focuses on the applications of artificial intelligence (AI) tools to stereotactic body radiation therapy (SBRT). The high dose per fraction and the limited number of fractions in SBRT require stricter accuracy than standard radiation therapy. The intent of this review is to describe the development and evaluate the possible benefit of AI tools integration into the radiation oncology workflow for SBRT automation. The selected papers were subdivided into four sections, representative of the whole radiotherapy process: 'AI in SBRT target and organs at risk contouring', 'AI in SBRT planning', 'AI during the SBRT delivery', and 'AI for outcome prediction after SBRT'. Each section summarises the challenges, as well as limits and needs for improvement to achieve better integration of AI tools in the clinical workflow.

Distributed learning: a reliable privacy-preserving strategy to change multicenter collaborations using AI.

PURPOSE: The present scoping review aims to assess the non-inferiority of distributed learning over centrally and locally trained machine learning (ML) models in medical applications. METHODS: We performed a literature search using the term "distributed learning" OR "federated learning" in the PubMed/MEDLINE and EMBASE databases. No start date limit was used, and the search was extended until July 21, 2020. We excluded articles outside the field of interest; guidelines or expert opinion, review articles and meta-analyses, editorials, letters or commentaries, and conference abstracts; articles not in the English language; and studies not using medical data. Selected studies were classified and analysed according to their aim(s). RESULTS: We included 26 papers aimed at predicting one or more outcomes: namely risk, diagnosis, prognosis, and treatment side effect/adverse drug reaction. Distributed learning was compared to centralized or localized training in 21/26 and 14/26 selected papers, respectively. Regardless of the aim, the type of input, the method, and the classifier, distributed learning performed close to centralized training, but two experiments focused on diagnosis. In all but 2 cases, distributed learning outperformed locally trained models. CONCLUSION: Distributed learning resulted in a reliable strategy for model development; indeed, it performed equally to models trained on centralized datasets. Sensitive data can get preserved since they are not shared for model development. Distributed learning constitutes a promising solution for ML-based research and practice since large, diverse datasets are crucial for success.

Generalization in the XCSF classifier system: analysis, improvement, and extension.

We analyze generalization in XCSF and introduce three improvements. We begin by showing that the types of generalizations evolved by XCSF can be influenced by the input range. To explain these results we present a theoretical analysis of the convergence of classifier weights in XCSF which highlights a broader issue. In XCSF, because of the mathematical properties of the Widrow-Hoff update, the convergence of classifier weights in a given subspace can be slow when the spread of the eigenvalues of the autocorrelation matrix associated with each classifier is large. As a major consequence, the system's accuracy pressure may act before classifier weights are adequately updated, so that XCSF may evolve piecewise constant approximations, instead of the intended, and more efficient, piecewise linear ones. We propose three different ways to update classifier weights in XCSF so as to increase the generalization capabilities of XCSF: one based on a condition-based normalization of the inputs, one based on linear least squares, and one based on the recursive version of linear least squares. Through a series of experiments we show that while all three approaches significantly improve XCSF, least squares approaches appear to be best performing and most robust. Finally we show how XCSF can be extended to include polynomial approximations.