Medical Imaging
This is just a preliminary collation of the relevant TCGA datasets collated and used in our methodology. We will continue to upload the full dataset later for your reference and use. We hope to make a small contribution to the study of automatic 3D MRI classification of gliomas and the problem of domain adaptation on medical images.
- Categories:
227 Views
Due to the complex and unstructured nature of the intestine, 3D reconstruction and visual navigation are imperative for clinical endoscopists performing the skill-intensive colonoscopy. Unsupervised 3D reconstruction methods, as a mainstream paradigm in auto-driving scenarios, exploit warping loss to predict 6-DOF pose and depth information jointly. However, owing to illumination inconsistency, repeated texture regions, and non-Lambertian reflection, the geometry warping constraint cannot be efficiently applied to the colonic environment.
- Categories:
85 Views
Data diversity and volume are crucial to the success of training deep learning models, while in the medical imaging field, the difficulty and cost of data collection and annotation are especially huge. Specifically in robotic surgery, data scarcity and imbalance have heavily affected the model accuracy and limited the design and deployment of deep learning-based surgical applications such as surgical instrument segmentation.
- Categories:
204 Views
Synaptic vesicle glycoprotein 2A (SV2A) is the most widely distributed transmembrane glycoprotein present on secretory vesicles in the pre-synaptic terminal of neurons throughout the central nervous system (Bajjalieh et al., 1994). SV2A can be used as a marker to visualize pre-synaptic density distribution in vivo using positron emission tomography (PET) imaging thanks to the SV2A radioligands available, including [11C]UCB-J (Nabulsi et al., 2016). Given the brain-wide distribution of SV2A, regional analysis of SV2A PET data may be limiting the amount of information that can be obtained.
- Categories:
61 Views
The dataset includes annotated Computed Tomography (CT) scanned images. The labels consist of three types:
- Categories:
165 Views
Relaxation mechanism of magnetic particles is crucial in differentiating particles and estimating temperature and viscosity for diagnosis and treatment. The magnetization recovery process in field flat phase of pulsed excitation generates decay signals that can be fitted by a bi-exponential model. The relaxation time spectrum can be generated by using inverse Laplace transform.
- Categories:
106 Views
Hydrogel scaffolds have attracted attention to develop cellular therapy and tissue engineering platforms for regenerative medicine applications. Among factors, local mechanical properties of scaffolds drive the functionalities of cell niche. Dynamic mechanical analysis (DMA), the standard method to characterize mechanical properties of hydrogels, restricts development in tissue engineering because the measurement provides a single elasticity value for the sample, requires direct contact, and represents a destructive evaluation preventing longitudinal studies on the same sample.
- Categories:
88 Views
The data is divided into a training set of 999 images and a test set of 335 images. The size of each 2D ultrasound image is 800 by 540 pixels with a pixel size ranging from 0.052 to 0.326 mm. The pixel size for each image can be found in the csv files: ‘training_set_pixel_size_and_HC.csv’ and ‘test_set_pixel_size.csv’. The training set also includes an image with the manual annotation of the head circumference for each HC, which was made by a trained sonographer.
- Categories:
851 Views
This dataset includes four sub-datasets: Drishti-GS, RIM-ONE-r3, ORIGA and REFUGE. Each image is cropped around the optic disc area for joint optic disc and cup segmentation. The size of all images is 512×512. The manual pixel-wise annotation is stored as a PNG image with the same size as the corresponding fundus image with the following labels:
128: Optic Disc (Grey color)
0: Optic Cup (Black color)
255: Background (White color)
- Categories:
748 Views
Early detection of retinal diseases is one of the most important means of preventing partial or permanent blindness in patients. One of the major stumbling blocks for manual retinal examination is the lack of a sufficient number of qualified medical personnel per capita to diagnose diseases.
- Categories:
4617 Views