Contour Dice Loss for Structures with Fuzzy and Complex Boundaries in Fetal MRI

Specktor-Fadida, Bella; Yehuda, Bossmat; Link-Sourani, Daphna; Ben‐Sira, Liat; Bashat, Dafna Ben; Joskowicz, Leo

doi:10.1007/978-3-031-25066-8_19

Cited by 1 publication

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A batch size of 1 was used to increase the generalization and to be able to fit the image on the available GPU memory. The sum of the boundary dice loss, boundary binary-cross entropy, and focal Tversky loss (α=0.7, β=0.3, γ=1.5) were used as the loss functions, and the Adam optimizer (learning rate=0.001) was used for training 41,42 . The input data (bone segmentation and the corresponding metadata) was split into ∼70% training and ∼30% validation.…”

Section: Methodsmentioning

confidence: 99%

“…The sum of the boundary dice loss, boundary binary-cross entropy, and focal Tversky loss (α = 0.7, β = 0.3, γ = 1.5) were used as the loss functions, and the Adam optimizer (learning rate = 0.001) was used for training. 41,42 The input data (bone segmentation and the corresponding metadata) was split into ∼70% training and ∼30% validation. The models were trained for 40…”

Section: Training Parametersmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence–Based Modeling Can Predict Face Shape Based on Underlying Craniomaxillofacial Bone

Arjmand,

Clement,

Hardisty

et al. 2023

Journal of Craniofacial Surgery

View full text Add to dashboard Cite

Reconstructing facial deformities is often challenging due to the complex 3-dimensional (3D) anatomy of the craniomaxillofacial skeleton and overlying soft tissue structures. Bilateral injuries cannot benefit from mirroring techniques and as such preinjury information (eg, 2D pictures or 3D imaging) may be utilized to determine or estimate the desired 3D face shape. When patient-specific information is not available, other options such as statistical shape models may be employed; however, these models require registration to a consistent orientation which may be challenging. Artificial intelligence (AI) has been used to identify facial features and generate highly realistic simulated faces. As such, it was hypothesized that AI can be used to predict 3D face shape by learning its relationship with the underlying bone surface anatomy in a subject-specific manner. An automated image processing and AI modeling workflow using a modified 3D UNet was generated to estimate 3D face shape using the underlying bone geometry and additional metadata (eg, body mass index and age) obtained from 5 publicly available computed tomography imaging datasets. Visually, the trained models provided a reasonable prediction of the contour and geometry of the facial tissues. The pipeline achieved a validation dice=0.89 when trained on the combined 5 datasets, with the highest dice=0.925 achieved with the single HNSCC dataset. Estimated predefect facial geometry may ultimately be used to aid preoperative craniomaxillofacial surgical planning, providing geometries for intraoperative templates, guides, navigation, molds, and forming tools. Automated face shape prediction may additionally be useful in forensic studies to aid in the identification of unknown skull remains.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Training Parametersmentioning

confidence: 99%