Automatic Quality Assessment of Transperineal Ultrasound Images of the Male Pelvic Region, Using Deep Learning

Camps, Saskia; Houben, Tim; Carneiro, Gustavo; Edwards, Christopher L.; Antico, Maria; Dunnhofer, Matteo; Martens, Esther; Baeza, J.A.; Vanneste, Ben; Limbergen, Evert J. Van; Verhaegen, Frank; Fontanarosa, Davide

doi:10.1016/j.ultrasmedbio.2019.10.027

Cited by 11 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recommendation 1 : Increase use of emerging technologies to automate and simplify probe positioning [37] , [38] . These tools make US-IGRT systems easier to use, improves image quality and reduces both residual and observer errors.…”

Section: Discussionmentioning

confidence: 99%

Factors affecting accuracy and precision in ultrasound guided radiotherapy

Grimwood

Thomas

Kember

et al. 2021

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

Background and purpose Transperineal ultrasound (TPUS) is used clinically for directly assessing prostate motion. Factors affecting accuracy and precision in TPUS motion estimation must be assessed to realise its full potential. Methods and materials Patients were imaged using volumetric TPUS during the Clarity-Pro trial (NCT02388308). Prostate motion was measured online at patient set-up and offline by experienced observers. Cone beam CT with markers was used as a comparator and observer performance was also quantified. The influence of different clinical factors was examined to establish specific recommendations towards efficacious ultrasound guided radiotherapy. Results From 330 fractions in 22 patients, offline observer random errors were 1.5 mm, 1.3 mm, 1.9 mm (left–right, superior-inferior, anteroposterior respectively). Errors increased in fractions exhibiting poor image quality to 3.3 mm, 3.3 mm and 6.8 mm. Poor image quality was associated with inconsistent probe placement, large anatomical changes and unfavourable imaging conditions within the patient. Online matching exhibited increased observer errors of: 3.2 mm, 2.9 mm and 4.7 mm. Four patients exhibited large systematic residual errors, of which three had poor quality images. Patient habitus showed no correlation with observer error, residual error, or image quality. Conclusions TPUS offers the unique potential to directly assess inter- and intra-fraction motion on conventional linacs. Inconsistent image quality, inexperienced operators and the pressures of the clinical environment may degrade precision and accuracy. Experienced operators are essential and cross-centre standards for training and QA should be established that build upon current guidance. Greater use of automation technologies may further minimise uncertainties.

show abstract

Section: Discussionmentioning

confidence: 99%

Factors affecting accuracy and precision in ultrasound guided radiotherapy

Grimwood

Thomas

Kember

et al. 2021

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

show abstract

“…The number of arthroscope and non-arthroscope images varied per volume, so this split could not be done randomly. Therefore, an algorithm based on simulated annealing [41], similarly to the one proposed by Camps et al [42], was used. In brief, the dataset splitting algorithm starts with putting 80% of the volumes in the training set and 20% of the volumes in the test set.…”

Section: Methodsmentioning

confidence: 99%

Arthroscope Localization in 3D Ultrasound Volumes Using Weakly Supervised Deep Learning

Burgt¹,

Camps²,

Antico

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

This work presents an algorithm based on weak supervision to automatically localize an arthroscope on 3D ultrasound (US). The ultimate goal of this application is to combine 3D US with the 2D arthroscope view during knee arthroscopy, to provide the surgeon with a comprehensive view of the surgical site. The implemented algorithm consisted of a weakly supervised neural network, which was trained on 2D US images of different phantoms mimicking the imaging conditions during knee arthroscopy. Image-based classification was performed and the resulting class activation maps were used to localize the arthroscope. The localization performance was evaluated visually by three expert reviewers and by the calculation of objective metrics. Finally, the algorithm was also tested on a human cadaver knee. The algorithm achieved an average classification accuracy of 88.6% on phantom data and 83.3% on cadaver data. The localization of the arthroscope based on the class activation maps was correct in 92–100% of all true positive classifications for both phantom and cadaver data. These results are relevant because they show feasibility of automatic arthroscope localization in 3D US volumes, which is paramount to combining multiple image modalities that are available during knee arthroscopies.

show abstract

“…Image quality assessment criteria for transperineal ultrasound images of the male pelvic region. The table was adapted from Camps et al (2020) [15]. PICS and CPR, these differences were not significant (p < 0.05 -see Supplementary Fig.…”

Section: Tablementioning

confidence: 99%

“…Each ultrasound image was categorised into ratings of 1, 2 or 3 according to an image quality assessment criteria (Table 1) defined by Camps et al (2020) [15]. One investigator (KDS) rated all images, with another investigator (AB) independently rating a subset (n = 15) as quality assurance.…”

Section: Image Ratingmentioning

confidence: 99%