Facial and Cochlear Nerves Characterization Using Deep Reinforcement Learning for Landmark Detection

Diez, Paula López; Sundgaard, Josefine Vilsbøll; Patou, François; Margeta, Ján; Paulsen, Rasmus Reinhold

doi:10.1007/978-3-030-87202-1_50

Cited by 3 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A cooperative multi-agent reinforcement learning framework (C-MARL) as described in [ 32 ] was used to automatically detect the cochlear apex, center and round window landmarks for each image. Although only the cochlear center landmark was required for further processing, using a three landmark C-MARL approach ensured better detection of the landmark [ 33 ].…”

Section: Methodsmentioning

confidence: 99%

Anatomical Variations of the Human Cochlea Using an Image Analysis Tool

Hussain¹,

Frater²,

Calixto³

et al. 2023

JCM

View full text Add to dashboard Cite

Understanding cochlear anatomy is crucial for developing less traumatic electrode arrays and insertion guidance for cochlear implantation. The human cochlea shows considerable variability in size and morphology. This study analyses 1000+ clinical temporal bone CT images using a web-based image analysis tool. Cochlear size and shape parameters were obtained to determine population statistics and perform regression and correlation analysis. The analysis revealed that cochlear morphology follows Gaussian distribution, while cochlear dimensions A and B are not well-correlated to each other. Additionally, dimension B is more correlated to duct lengths, the wrapping factor and volume than dimension A. The scala tympani size varies considerably among the population, with the size generally decreasing along insertion depth with dimensional jumps through the trajectory. The mean scala tympani radius was 0.32 mm near the 720° insertion angle. Inter-individual variability was four times that of intra-individual variation. On average, the dimensions of both ears are similar. However, statistically significant differences in clinical dimensions were observed between ears of the same patient, suggesting that size and shape are not the same. Harnessing deep learning-based, automated image analysis tools, our results yielded important insights into cochlear morphology and implant development, helping to reduce insertion trauma and preserving residual hearing.

show abstract

Section: Methodsmentioning

confidence: 99%

Anatomical Variations of the Human Cochlea Using an Image Analysis Tool

Hussain¹,

Frater²,

Calixto³

et al. 2023

JCM

View full text Add to dashboard Cite

show abstract

“…A number of approaches have been proposed to estimate the landmarks or the pose, including registration and one-shot learning [28] or using regression forests to vote for the location of the landmarks [29]. More recently, reinforcement learning methods [30][31][32] have also been used to efficiently locate landmarks or to generate clinically meaningful image views [33] and, relevantly for our domain of application, to locate cochlear nerve landmarks [34]. Heatmap-based approaches consistently demonstrate robustness, explainability, and computational efficiency and offer an elegant form of uncertainty modelling and failure detection [35].…”

Section: Cochlear Landmarks and Canonical Pose Estimationmentioning

confidence: 99%

A Web-Based Automated Image Processing Research Platform for Cochlear Implantation-Related Studies

Margeta

Hussain

Diez

et al. 2022

JCM

Self Cite

View full text Add to dashboard Cite

The robust delineation of the cochlea and its inner structures combined with the detection of the electrode of a cochlear implant within these structures is essential for envisaging a safer, more individualized, routine image-guided cochlear implant therapy. We present Nautilus—a web-based research platform for automated pre- and post-implantation cochlear analysis. Nautilus delineates cochlear structures from pre-operative clinical CT images by combining deep learning and Bayesian inference approaches. It enables the extraction of electrode locations from a post-operative CT image using convolutional neural networks and geometrical inference. By fusing pre- and post-operative images, Nautilus is able to provide a set of personalized pre- and post-operative metrics that can serve the exploration of clinically relevant questions in cochlear implantation therapy. In addition, Nautilus embeds a self-assessment module providing a confidence rating on the outputs of its pipeline. We present a detailed accuracy and robustness analyses of the tool on a carefully designed dataset. The results of these analyses provide legitimate grounds for envisaging the implementation of image-guided cochlear implant practices into routine clinical workflows.

show abstract

“…Meanwhile, the shared average weight of the different fully connected layers allows for implicit communication between agents, sharing information of the layers that are used to map the extracted features from the current state to the predicted Q-value of each agent. This setup has been proven especially effective when the different landmarks present a consistent spatial correlation as it is the case with inner ear anatomy [13]. We trained a C-MARL in the normal anatomies of the Synthetic Set and the Real Abnormality Set.…”

Section: Methodsmentioning

confidence: 99%

“…Finally we also trained the MARL model on the normal samples of the Real Abnormality Set as we expect that the explicit communication between agents might influence the variability of the model output when facing an abnormal anatomy. The training configuration employed is the same as presented in [13].…”

Section: Methodsmentioning

confidence: 99%

Deep Reinforcement Learning for Detection of Inner Ear Abnormal Anatomy in Computed Tomography

Diez¹,

Sørensen²,

Sundgaard³

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Detection of abnormalities within the inner ear is a challenging task that, if automated, could provide support for the diagnosis and clinical management of various otological disorders. Inner ear malformations are rare and present great anatomical variation, which challenges the design of deep learning frameworks to automate their detection. We propose a framework for inner ear abnormality detection, based on a deep reinforcement learning model for landmark detection trained in normative data only. We derive two abnormality measurements: the first is based on the variability of the predicted configuration of the landmarks in a subspace formed by the point distribution model of the normative landmarks using Procrustes shape alignment and Principal Component Analysis projection. The second measurement is based on the distribution of the predicted Q-values of the model for the last ten states before the landmarks are located. We demonstrate an outstanding performance for this implementation on both an artificial (0.96 AUC) and a real clinical CT dataset of various malformations of the inner ear (0.87 AUC). Our approach could potentially be used to solve other complex anomaly detection problems.

show abstract

Facial and Cochlear Nerves Characterization Using Deep Reinforcement Learning for Landmark Detection

Cited by 3 publications

References 21 publications

Anatomical Variations of the Human Cochlea Using an Image Analysis Tool

Anatomical Variations of the Human Cochlea Using an Image Analysis Tool

A Web-Based Automated Image Processing Research Platform for Cochlear Implantation-Related Studies

Deep Reinforcement Learning for Detection of Inner Ear Abnormal Anatomy in Computed Tomography

Contact Info

Product

Resources

About