학술논문
Discriminating basal cell carcinoma and Bowen's disease from benign skin lesions with a 3D hyperspectral imaging system and convolutional neural networks.
Document Type
Article
Author
Source
Subject
*HYPERSPECTRAL imaging systems
*BASAL cell carcinoma
*BOWEN'S disease
*CONVOLUTIONAL neural networks
*THREE-dimensional imaging
*MULTISPECTRAL imaging
*IMAGE recognition (Computer vision)
*SKIN
*
*
*
*
*
*
*
Language
ISSN
0909-752X
Abstract
A study published in the journal Skin Research & Technology examines the use of a 3D hyperspectral imaging system and convolutional neural networks (CNN) for the diagnosis of skin lesions. The study involved 175 lesions from 73 patients and found that the novel imaging system showed promising diagnostic performance. The researchers compared the outcomes of the CNN analysis to traditional imaging methods and found that the HSI-CNN system achieved higher specificities and did not require expertise from the user. The study suggests that the HSI-CNN system has potential for skin cancer diagnosis in primary healthcare settings and may be a useful tool for specialists in ambiguous cases. However, further studies and comparisons with other imaging modalities are needed to validate the system's performance in clinical practice. [Extracted from the article]