Abstract
In skin lesion detection systems, a large number of labeled images are usually required to achieve high segmentation accuracy (ACC), which hinders the effectiveness and timeliness of disease diagnosis. To this end, a high-precision skin lesion detection system is proposed in this article. The hardware part of the system adopts a modular design, fully considering ergonomics, portability, and miniaturization. In the software part, an active learning ensemble with a multimodel fusion method (ALEM) is proposed to achieve efficient and accurate skin lesion region segmentation. The core idea of ALEM is to use multiple uncertainty strategies of active learning to obtain the most uncertain pixels to be marked in the skin lesion image when marking image pixels. The experiment shows that the average Dice coefficient (DIC) and average Jaccard index (JAI) of ALEM on International Skin Imaging Collaboration (ISIC)-2016 are 82.81% and 92.4%, respectively, and that on ISIC-2017 are 87.51% and 79.26%, respectively. It is worth noting that ALEM still outperforms in tests with only 80% of the training data and no more than 15% pixel annotation per image on average. Our system achieves an average AUC of 91.01% on the ISIC2017 and is tested for effectiveness on real skin. The skin lesion detection system developed in this article is expected to bring convenience to doctors and patients and speed up the diagnosis of diseases.
Original language | English |
---|---|
Pages (from-to) | 9898-9908 |
Number of pages | 11 |
Journal | IEEE Sensors Journal |
Volume | 23 |
Issue number | 9 |
DOIs | |
Publication status | Published - 1 May 2023 |
Externally published | Yes |
Keywords
- Active learning
- multimodel fusion
- multiple uncertainty strategies
- portable detection system
- skin lesion segmentation (SLS)
ASJC Scopus subject areas
- Instrumentation
- Electrical and Electronic Engineering