Hi all,
I am working on Medical Imaging, I used Multi-scaled approach by using DenseNet, ResNet, Inception module etc.. to gain more contextual information from images (BRATS, iSeg, ISLES). Please let me know, what factors more affects to exploit image information and what would be recent approach for skin lesion type dataset? Please let me know about recent useful CNN architecture for Skin dataset and factors to make changes in them? your suggestion will be highly appreciable..
Thanks
Hi Saqib,
As you may know that the contextual information depends on the neighborhood of the pixels, e.g. how central pixel value correlated with its neighborhood in a 3x3 or 5x5 region, etc. By saying that, the researchers are using dilated convolutions which increases receptive field of CNN kernals/filters. If you have not tried that in your research, go for it. However, I can not comment about dataset being used for skin lesion.
Dear Saqib Qamar,
Look the link, maybe useful.
Article Medical Image Analysis using Convolutional Neural Networks: A Review
https://arxiv.org/pdf/1708.00377.pdf
Regards,
Shafagat
- Badges
- Science topic
- Similar topics
- Computer Science
- Images