Auto-segmentation for total marrow irradiation

Watkins, W.T.; Qing, Kun; Han, Chunhui; Song, Hui; Liu, An

doi:10.3389/fonc.2022.970425

Cited by 9 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Structure Previously Reported DICE (Mean ± Std.) Mandible 0.86 ± 0.12 1 [ 56 ], 0.90 ± 0.04 [ 54 ], 0.91 ± 0.02 [ 55 ], 0.94 ± 0.02 [ 57 ], 0.94 ± 0.01 [ 52 ], 0.99 ± 0.01 [ 55 ] Submandibular Gland (r) 0.73 ± 0.09 [ 54 ], 0.78 ± 0.10 [ 52 ], 0.79 [ 51 ], 0.95 ± 0.07 [ 55 ], 0.98 ± 0.03 [ 55 ] Submandibular Gland (l) 0.70 ± 0.13 [ 54 ], 0.77 ± 0.12 [ 52 ], 0.79 [ 51 ], 0.91 ± 0.08 [ 55 ], 0.97 ± 0.05 [ 55 ] Thyroid Gland 0.83 ± 0.08 [ 52 ], 0.90 ± 0.02 [ 57 ] Internal Carotid Artery (r) 0.81 [ 49 ], 0.86 ± 0.02 [ 50 ] Internal Carotid Artery (l) 0.81 [ 49 ], 0.86 ± 0.02 [ 50 ] Superior Constrictor 0.67 ± 0.11 [ 60 ], 0.76 ± 0.13 [ 55 ], 0.83 ± 0.15 [ 55 ] Middle Constrictor 0.60 ± 0.19 [ …”

Section: Appendix A1 Standard Operation Proceduresmentioning

confidence: 99%

“…Region growing' with upper threshold = −300 and 'remove holes', but avoid including trachea/air outside the patient (sometimes segmented, correct manually) Previously reported DICE values (mean ± standard deviation) between contours predicted by different deep learning methods and manual labels. Mandible 0.86 ± 0.12 1[56], 0.90 ± 0.04[54], 0.91 ± 0.02[55], 0.94 ± 0.02[57], 0.94 ± 0.01[52], 0.99 ± 0.01[55] Submandibular Gland (r) 0.73 ± 0.09[54], 0.78 ± 0.10 [52], 0.79[51], 0.95 ± 0.07[55], 0.98 ± 0.03[55] …”

mentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of 71 Anatomical Structures Necessary for the Evaluation of Guideline-Conforming Clinical Target Volumes in Head and Neck Cancers

Walter,

Hoegen-Saßmannshausen,

Stanic

et al. 2024

Cancers

View full text Add to dashboard Cite

The delineation of the clinical target volumes (CTVs) for radiation therapy is time-consuming, requires intensive training and shows high inter-observer variability. Supervised deep-learning methods depend heavily on consistent training data; thus, State-of-the-Art research focuses on making CTV labels more homogeneous and strictly bounding them to current standards. International consensus expert guidelines standardize CTV delineation by conditioning the extension of the clinical target volume on the surrounding anatomical structures. Training strategies that directly follow the construction rules given in the expert guidelines or the possibility of quantifying the conformance of manually drawn contours to the guidelines are still missing. Seventy-one anatomical structures that are relevant to CTV delineation in head- and neck-cancer patients, according to the expert guidelines, were segmented on 104 computed tomography scans, to assess the possibility of automating their segmentation by State-of-the-Art deep learning methods. All 71 anatomical structures were subdivided into three subsets of non-overlapping structures, and a 3D nnU-Net model with five-fold cross-validation was trained for each subset, to automatically segment the structures on planning computed tomography scans. We report the DICE, Hausdorff distance and surface DICE for 71 + 5 anatomical structures, for most of which no previous segmentation accuracies have been reported. For those structures for which prediction values have been reported, our segmentation accuracy matched or exceeded the reported values. The predictions from our models were always better than those predicted by the TotalSegmentator. The sDICE with 2 mm margin was larger than 80% for almost all the structures. Individual structures with decreased segmentation accuracy are analyzed and discussed with respect to their impact on the CTV delineation following the expert guidelines. No deviation is expected to affect the rule-based automation of the CTV delineation.

show abstract

Section: Appendix A1 Standard Operation Proceduresmentioning

confidence: 99%

mentioning

confidence: 99%

Segmentation of 71 Anatomical Structures Necessary for the Evaluation of Guideline-Conforming Clinical Target Volumes in Head and Neck Cancers

Walter,

Hoegen-Saßmannshausen,

Stanic

et al. 2024

Cancers

View full text Add to dashboard Cite

show abstract

“…Watkins et al evaluated an AI segmentation software for total body contouring of 27 organs at risk (OARs) and four planning target volumes (PTVs), finding good spatial and dosimetric agreement with manual contours. 9 Ahn et al developed an AI-based model for plan optimization of VMAT-TMI, which improved dosimetric quality while reducing dependence on planner experience. 10 However, other technological difficulties remain unanswered.…”

Section: Introductionmentioning

confidence: 99%

“…Watkins et al. evaluated an AI segmentation software for total body contouring of 27 organs at risk (OARs) and four planning target volumes (PTVs), finding good spatial and dosimetric agreement with manual contours 9 . Ahn et al.…”

Section: Introductionmentioning

confidence: 99%

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

Lambri,

Longari,

Loiacono

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundTotal 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.PurposeTo develop convolutional neural networks (CNNs) for automatically generating the field geometry of TMI/TMLI.MethodsThe 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).ResultsThe 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.ConclusionsThe 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.

show abstract

“…Recent advancements in AI have led to the development of auto-segmentation algorithms capable of delineating anatomical structures with a precision that challenges the expertise of human radiation oncologists. Watkins et al explored the efficiency gains of unedited AI contours in total marrow irradiation, highlighting the potential of AI to achieve a 100% efficiency gain over traditional methods [3]. This leap in efficiency is not only a testament to the capabilities of AI but also the significance of its role in future The accuracy of AI contouring is paramount, as the slightest deviation can lead to suboptimal treatment or increased toxicity.…”

Section: Introductionmentioning

confidence: 99%

Integrating Artificial Intelligence Into Radiation Oncology: Can Humans Spot AI?

Shanbhag,

Bin Sumaida,

Binz

et al. 2023

Cureus

View full text Add to dashboard Cite

Introduction Artificial intelligence (AI) is transforming healthcare, particularly in radiation oncology. AI-based contouring tools like Limbus are designed to delineate Organs at Risk (OAR) and Target Volumes quickly. This study evaluates the accuracy and efficiency of AI contouring compared to human radiation oncologists and the ability of professionals to differentiate between AI-generated and human-generated contours. Methods At a recent AI conference in Abu Dhabi, a blind comparative analysis was performed to assess AI's performance in radiation oncology. Participants included four human radiation oncologists and the Limbus® AI software. They contoured specific regions from CT scans of a breast cancer patient. The audience, consisting of healthcare professionals and AI experts, was challenged to identify the AI-generated contours. The exercise was repeated twice to observe any learning effects. Time taken for contouring and audience identification accuracy were recorded. Results Initially, only 28% of the audience correctly identified the AI contours, which slightly increased to 31% in the second attempt. This indicated a difficulty in distinguishing between AI and human expertise. The AI completed contouring in up to 60 seconds, significantly faster than the human average of 8 minutes. Discussion The results indicate that AI can perform radiation contouring comparably to human oncologists but much faster. The challenge faced by professionals in identifying AI versus human contours highlights AI's advanced capabilities in medical tasks. Conclusion AI shows promise in enhancing radiation oncology workflow by reducing contouring time without quality compromise. Further research is needed to confirm AI contouring's clinical efficacy and its integration into routine practice.

show abstract

Auto-segmentation for total marrow irradiation

Cited by 9 publications

References 47 publications

Segmentation of 71 Anatomical Structures Necessary for the Evaluation of Guideline-Conforming Clinical Target Volumes in Head and Neck Cancers

Segmentation of 71 Anatomical Structures Necessary for the Evaluation of Guideline-Conforming Clinical Target Volumes in Head and Neck Cancers

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

Integrating Artificial Intelligence Into Radiation Oncology: Can Humans Spot AI?

Contact Info

Product

Resources

About