Autosegmentation based on different-sized training datasets of consistently-curated volumes and impact on rectal contours in prostate cancer radiation therapy

Olsson, Caroline; Suresh, Rahul; Niemelä, Jarkko; Akram, Saad Ullah; Valdman, Alexander

doi:10.1016/j.phro.2022.04.007

Cited by 5 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of note, one issue remains on the dataset used, mainly represented by the inter-RO variability of expert contours used for the DL-tool training and validation. Olsson et al (19) showed for a single VOI (i.e., rectum) that, the DSCs of retrained MVision model were 0.89 ± 0.07 while the one of the clinical and the original MVision tool were 0.87 ± 0.07 and 0.86 ± 0.06, respectively, thus suggesting that the DSC variability remains similar after the model retraining. Based on these results, our study focused on assessing the performance of the MVision algorithm using an external validation dataset, considering the inter-RO variability of several expert ROs, all applying the ESTRO and international delineation guidelines.…”

Section: Potential Applications Of Our Resultsmentioning

confidence: 99%

See 1 more Smart Citation

How smart is artificial intelligence in organs delineation? Testing a CE and FDA-approved Deep-Learning tool using multiple expert contours delineated on planning CT images

et al. 2023

View full text Add to dashboard Cite

BackgroundA CE- and FDA-approved cloud-based Deep learning (DL)-tool for automatic organs at risk (OARs) and clinical target volumes segmentation on computer tomography images is available. Before its implementation in the clinical practice, an independent external validation was conducted.MethodsAt least a senior and two in training Radiation Oncologists (ROs) manually contoured the volumes of interest (VOIs) for 6 tumoral sites. The auto-segmented contours were retrieved from the DL-tool and, if needed, manually corrected by ROs. The level of ROs satisfaction and the duration of contouring were registered. Relative volume differences, similarity indices, satisfactory grades, and time saved were analyzed using a semi-automatic tool.ResultsSeven thousand seven hundred sixty-five VOIs were delineated on the CT images of 111 representative patients. The median (range) time for manual VOIs delineation, DL-based segmentation, and subsequent manual corrections were 25.0 (8.0-115.0), 2.3 (1.2-8) and 10.0 minutes (0.3-46.3), respectively. The overall time for VOIs retrieving and modification was statistically significantly lower than for manual contouring (p<0.001). The DL-tool was generally appreciated by ROs, with 44% of vote 4 (well done) and 43% of vote 5 (very well done), correlated with the saved time (p<0.001). The relative volume differences and similarity indexes suggested a better inter-agreement of manually adjusted DL-based VOIs than manually segmented ones.ConclusionsThe application of the DL-tool resulted satisfactory, especially in complex delineation cases, improving the ROs inter-agreement of delineated VOIs and saving time.

show abstract

Section: Potential Applications Of Our Resultsmentioning

confidence: 99%

“…All the OARs and targets available in the versions mentioned above of the software were used for the subsequent VOI comparisons. Details about MVision model architecture and libraries are reported by Olsson et al (19).…”

Section: Methodsmentioning

confidence: 99%

How smart is artificial intelligence in organs delineation? Testing a CE and FDA-approved Deep-Learning tool using multiple expert contours delineated on planning CT images

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Further, data extraction from multiple sites can be associated with difference in delineation guidelines. For optimal DL segmentation quality it is crucial that the data contains low noise, is of high quality, 16,17 and that delineation guidelines are coherent, as demonstrated in this paper.…”

Section: Introductionmentioning

confidence: 93%

Deep learning‐based classification of organs at risk and delineation guideline in pelvic cancer radiation therapy

Lempart

Scherman

Nilsson

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

Deep learning (DL) models for radiation therapy (RT) image segmentation require accurately annotated training data. Multiple organ delineation guidelines exist; however, information on the used guideline is not provided with the delineation. Extraction of training data with coherent guidelines can therefore be challenging. We present a supervised classification method for pelvis structure delineations where bowel cavity, femoral heads, bladder, and rectum data, with two guidelines, were classified. The impact on DL‐based segmentation quality using mixed guideline training data was also demonstrated. Bowel cavity was manually delineated on CT images for anal cancer patients (n = 170) according to guidelines Devisetty and RTOG. The DL segmentation quality from using training data with coherent or mixed guidelines was investigated. A supervised 3D squeeze‐and‐excite SENet‐154 model was trained to classify two bowel cavity delineation guidelines. In addition, a pelvis CT dataset with manual delineations from prostate cancer patients (n = 1854) was used where data with an alternative guideline for femoral heads, rectum, and bladder were generated using commercial software. The model was evaluated on internal (n = 200) and external test data (n = 99). By using mixed, compared to coherent, delineation guideline training data mean DICE score decreased 3% units, mean Hausdorff distance (95%) increased 5 mm and mean surface distance (MSD) increased 1 mm. The classification of bowel cavity test data achieved 99.8% unweighted classification accuracy, 99.9% macro average precision, 97.2% macro average recall, and 98.5% macro average F1. Corresponding metrics for the pelvis internal test data were all 99% or above and for the external pelvis test data they were 96.3%, 96.6%, 93.3%, and 94.6%. Impaired segmentation performance was observed for training data with mixed guidelines. The DL delineation classification models achieved excellent results on internal and external test data. This can facilitate automated guideline‐specific data extraction while avoiding the need for consistent and correct structure labels.

show abstract

“…: prostate and seminal vesicles) as well as OARs [1] , [2] , [3] , [4] , [5] . Automatic tools aiming to both reduce contouring time and improve contouring consistency have been developed over the past 10–15 years [6] , [7] , [8] , [9] , [10] , [11] , [12] , [13] , [14] , [15] .…”

Section: Introductionmentioning

confidence: 99%

Real-world validation of Artificial Intelligence-based Computed Tomography auto-contouring for prostate cancer radiotherapy planning

Palazzo,

Mangili,

Deantoni

et al. 2023

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

Autosegmentation based on different-sized training datasets of consistently-curated volumes and impact on rectal contours in prostate cancer radiation therapy

Cited by 5 publications

References 21 publications

How smart is artificial intelligence in organs delineation? Testing a CE and FDA-approved Deep-Learning tool using multiple expert contours delineated on planning CT images

How smart is artificial intelligence in organs delineation? Testing a CE and FDA-approved Deep-Learning tool using multiple expert contours delineated on planning CT images

Deep learning‐based classification of organs at risk and delineation guideline in pelvic cancer radiation therapy

Real-world validation of Artificial Intelligence-based Computed Tomography auto-contouring for prostate cancer radiotherapy planning

Contact Info

Product

Resources

About