RESUMEN
In recent years, deep learning (DL) has shown great potential in the field of dermatological image analysis. However, existing datasets in this domain have significant limitations, including a small number of image samples, limited disease conditions, insufficient annotations, and non-standardized image acquisitions. To address these shortcomings, we propose a novel framework called DermSynth3D. DermSynth3D blends skin disease patterns onto 3D textured meshes of human subjects using a differentiable renderer and generates 2D images from various camera viewpoints under chosen lighting conditions in diverse background scenes. Our method adheres to top-down rules that constrain the blending and rendering process to create 2D images with skin conditions that mimic in-the-wild acquisitions, ensuring more meaningful results. The framework generates photo-realistic 2D dermatological images and the corresponding dense annotations for semantic segmentation of the skin, skin conditions, body parts, bounding boxes around lesions, depth maps, and other 3D scene parameters, such as camera position and lighting conditions. DermSynth3D allows for the creation of custom datasets for various dermatology tasks. We demonstrate the effectiveness of data generated using DermSynth3D by training DL models on synthetic data and evaluating them on various dermatology tasks using real 2D dermatological images. We make our code publicly available at https://github.com/sfu-mial/DermSynth3D.
Asunto(s)
Enfermedades de la Piel , Humanos , Enfermedades de la Piel/diagnóstico por imagen , Imagenología Tridimensional/métodos , Aprendizaje Profundo , Interpretación de Imagen Asistida por Computador/métodosRESUMEN
The use of real-time magnetic resonance imaging (rt-MRI) of speech is increasing in clinical practice and speech science research. Analysis of such images often requires segmentation of articulators and the vocal tract, and the community is turning to deep-learning-based methods to perform this segmentation. While there are publicly available rt-MRI datasets of speech, these do not include ground-truth (GT) segmentations, a key requirement for the development of deep-learning-based segmentation methods. To begin to address this barrier, this work presents rt-MRI speech datasets of five healthy adult volunteers with corresponding GT segmentations and velopharyngeal closure patterns. The images were acquired using standard clinical MRI scanners, coils and sequences to facilitate acquisition of similar images in other centres. The datasets include manually created GT segmentations of six anatomical features including the tongue, soft palate and vocal tract. In addition, this work makes code and instructions to implement a current state-of-the-art deep-learning-based method to segment rt-MRI speech datasets publicly available, thus providing the community and others with a starting point for developing such methods.
Asunto(s)
Articuladores Dentales , Habla , Adulto , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodosRESUMEN
Objective: Dynamic magnetic resonance (MR) imaging enables visualisation of articulators during speech. There is growing interest in quantifying articulator motion in two-dimensional MR images of the vocal tract, to better understand speech production and potentially inform patient management decisions. Image registration is an established way to achieve this quantification. Recently, segmentation-informed deformable registration frameworks have been developed and have achieved state-of-the-art accuracy. This work aims to adapt such a framework and optimise it for estimating displacement fields between dynamic two-dimensional MR images of the vocal tract during speech. Methods: A deep-learning-based registration framework was developed and compared with current state-of-the-art registration methods and frameworks (two traditional methods and three deep-learning-based frameworks, two of which are segmentation informed). The accuracy of the methods and frameworks was evaluated using the Dice coefficient (DSC), average surface distance (ASD) and a metric based on velopharyngeal closure. The metric evaluated if the fields captured a clinically relevant and quantifiable aspect of articulator motion. Results: The segmentation-informed frameworks achieved higher DSCs and lower ASDs and captured more velopharyngeal closures than the traditional methods and the framework that was not segmentation informed. All segmentation-informed frameworks achieved similar DSCs and ASDs. However, the proposed framework captured the most velopharyngeal closures. Conclusions: A framework was successfully developed and found to more accurately estimate articulator motion than five current state-of-the-art methods and frameworks. Significance: The first deep-learning-based framework specifically for registering dynamic two-dimensional MR images of the vocal tract during speech has been developed and evaluated.
RESUMEN
BACKGROUND AND OBJECTIVE: Magnetic resonance (MR) imaging is increasingly used in studies of speech as it enables non-invasive visualisation of the vocal tract and articulators, thus providing information about their shape, size, motion and position. Extraction of this information for quantitative analysis is achieved using segmentation. Methods have been developed to segment the vocal tract, however, none of these also fully segment any articulators. The objective of this work was to develop a method to fully segment multiple groups of articulators as well as the vocal tract in two-dimensional MR images of speech, thus overcoming the limitations of existing methods. METHODS: Five speech MR image sets (392 MR images in total), each of a different healthy adult volunteer, were used in this work. A fully convolutional network with an architecture similar to the original U-Net was developed to segment the following six regions in the image sets: the head, soft palate, jaw, tongue, vocal tract and tooth space. A five-fold cross-validation was performed to investigate the segmentation accuracy and generalisability of the network. The segmentation accuracy was assessed using standard overlap-based metrics (Dice coefficient and general Hausdorff distance) and a novel clinically relevant metric based on velopharyngeal closure. RESULTS: The segmentations created by the method had a median Dice coefficient of 0.92 and a median general Hausdorff distance of 5mm. The method segmented the head most accurately (median Dice coefficient of 0.99), and the soft palate and tooth space least accurately (median Dice coefficients of 0.92 and 0.93 respectively). The segmentations created by the method correctly showed 90% (27 out of 30) of the velopharyngeal closures in the MR image sets. CONCLUSIONS: An automatic method to fully segment multiple groups of articulators as well as the vocal tract in two-dimensional MR images of speech was successfully developed. The method is intended for use in clinical and non-clinical speech studies which involve quantitative analysis of the shape, size, motion and position of the vocal tract and articulators. In addition, a novel clinically relevant metric for assessing the accuracy of vocal tract and articulator segmentation methods was developed.
Asunto(s)
Aprendizaje Profundo , Articuladores Dentales , Adulto , Humanos , Procesamiento de Imagen Asistido por Computador , Imagen por Resonancia Magnética , HablaRESUMEN
Dynamic and real-time MRI (rtMRI) of human speech is an active field of research, with interest from both the linguistics and clinical communities. At present, different research groups are investigating a range of rtMRI acquisition and reconstruction approaches to visualise the speech organs. Similar to other moving organs, it is difficult to create a physical phantom of the speech organs to optimise these approaches; therefore, the optimisation requires extensive scanner access and imaging of volunteers. As previously demonstrated in cardiac imaging, realistic numerical phantoms can be useful tools for optimising rtMRI approaches and reduce reliance on scanner access and imaging volunteers. However, currently, no such speech rtMRI phantom exists. In this work, a numerical phantom for optimising speech rtMRI approaches was developed and tested on different reconstruction schemes. The novel phantom comprised a dynamic image series and corresponding k-space data of a single mid-sagittal slice with a temporal resolution of 30 frames per second (fps). The phantom was developed based on images of a volunteer acquired at a frame rate of 10 fps. The creation of the numerical phantom involved the following steps: image acquisition, image enhancement, segmentation, mask optimisation, through-time and spatial interpolation and finally the derived k-space phantom. The phantom was used to: (1) test different k-space sampling schemes (Cartesian, radial and spiral); (2) create lower frame rate acquisitions by simulating segmented k-space acquisitions; (3) simulate parallel imaging reconstructions (SENSE and GRAPPA). This demonstrated how such a numerical phantom could be used to optimise images and test multiple sampling strategies without extensive scanner access.
RESUMEN
PURPOSE: To investigate: (1) the feasibility of using through-time radial GeneRalized Autocalibrating Partially Parallel Acquisitions (rGRAPPA) and hybrid radial GRAPPA (h-rGRAPPA) in single- and multislice dynamic speech MRI; (2) whether single-slice dynamic speech MRI at a rate of 15 frames per second (fps) or higher and with adequate image quality can be achieved using these radial GRAPPA techniques. METHODS: Seven healthy adult volunteers were imaged at 3T using a 16-channel neurovascular coil and 2 spoiled gradient echo sequences (radial trajectory, field of view = 192 × 192 mm2 , acquired pixel size = 2.4 × 2.4 mm2 ). One sequence imaged a single slice at 16.8 fps, the other imaged 2 interleaved slices at 7.8 fps per slice. Image sets were reconstructed using rGRAPPA and h-rGRAPPA, and their image quality was compared using the root mean square error, structural similarity index, and visual assessments. RESULTS: Image quality deteriorated when fewer than 170 calibration frames were used in the rGRAPPA reconstruction. rGRAPPA image sets demonstrated: (1) in 97% of cases, a similar image quality to h-rGRAPPA image sets reconstructed using a k-space segment size of 4, (2) in 98% of cases, a better image quality than h-rGRAPPA image sets reconstructed using a k-space segment size of 32. CONCLUSION: This study confirmed: (1) the feasibility of using rGRAPPA and h-rGRAPPA in single- and multislice dynamic speech MRI, (2) that single-slice speech imaging at a frame rate higher than 15 fps and with adequate image quality can be achieved using these radial GRAPPA techniques.
Asunto(s)
Cabeza/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética/métodos , Habla/fisiología , Adulto , Femenino , Humanos , Imagen por Resonancia Magnética/instrumentación , Masculino , Adulto JovenRESUMEN
PURPOSE: This study aims to improve clinical reliability of real-time Magnetic Resonance Imaging (rt-MRI) in the visualisation of velopharyngeal motion during speech. METHODS: Seven subjects were imaged at 3T during natural phonation. Speech rt-MRI methodologies were investigated with (i) a comparison of commercial Cartesian and non-Cartesian (radial and spiral) rt-MRI sequences and (ii) investigation of further improvement with accelerated radial acquisition and offline reconstruction methodology. RESULTS: Cartesian and non-Cartesian protocols were implemented with temporal resolutions between 10 frames per second (fps) and 27â¯fps and voxel sizes between 1.5â¯×â¯1.5â¯×â¯10â¯mm3 and 2.7â¯×â¯2.7â¯×â¯10â¯mm3. Commercial spiral acquisitions provided superior contrast-to-noise ratio (CNR) than otherwise equivalent Cartesian and radial. Spirals at 22â¯fps allowed for improved spatial resolution (1.9â¯×â¯1.9â¯mm2) when compared to similar Cartesian protocols (20â¯fps), limited to a lower spatial resolution (2.7â¯×â¯2.7â¯mm2). Cartesian protocols were on average scored higher than spiral protocols in visual quality. However, some variability was found on choice of recommended imaging protocol between subjects. Accelerated radial data reconstructed offline with a Total Generalized Variation (TGV) scheme showed improved visual sharpness of velum motion. DISCUSSION/CONCLUSION: Adequate visualisation of velopharyngeal motion with commercial rt-MRI at 3T was possible. Both Cartesian and spiral protocols demonstrated adequate temporal depiction and overall image quality. However, choice of optimal imaging protocol at 3T was more subject-dependent than in previously published 1.5T data and additional care should be taken when selecting an adequate protocol. Offline TGV reconstruction of radial data has shown potential to improve temporal sharpness.
Asunto(s)
Procesamiento de Imagen Asistido por Computador/métodos , Imagen por Resonancia Magnética , Movimiento , Faringe/diagnóstico por imagen , Faringe/fisiología , Adulto , Estudios de Factibilidad , Femenino , Humanos , Masculino , Factores de TiempoRESUMEN
OBJECTIVE: The purpose of this work was to assess heating and radiofrequency (RF) deposition and image quality effects of a prototype three-section carbon fibre flatbed insert for use in MRI. METHODS: RF deposition was assessed using two different thermometry techniques, infrared thermometry and Bragg-grating thermometry. Image quality effects were assessed with and without the flatbed insert in place by using mineral oil phantoms and a human subject. RESULTS: Neither technique detected heating of the insert in typical MRI examinations. We found that the insert was less suitable for MRI applications owing to severe RF shielding artefact. For spin-echo (SE), turbo spin-echo (TSE) and gradient-echo sequences, the reduction in signal-to-noise ratio (SNR) was as much as 89% when the insert was in place compared with the standard couch, making it less suitable as a patient-support material. Turning on the MultiTransmit switch together with using the scanner's quadrature body coil improved the reduction in SNR from 89% to 39% for the SE sequence and from 82% to 12% for the TSE sequence. CONCLUSION: No evidence was found to support reports in the literature that carbon fibre is an unsuitable material for use in MRI because of heating. ADVANCES IN KNOWLEDGE: This study suggests that carbon fibre is less suitable for large-scale MRI applications owing to it causing severe RF shading. Further research is needed to establish the suitability of the flatbed for treatment planning using alternative sequences or whether an alternative carbon fibre composite for large-scale MRI applications or a design that can minimize shielding can be found.