Skin lesion segmentation using object scale-oriented fully convolutional neural networks
- 166 Downloads
Melanoma is the deadliest form of skin cancer, and its incidence level is increasing. It is important to obtain a diagnosis at an early stage to increase the patient survival rate. Skin lesion segmentation is a difficult problem in medical image analysis. To address this problem, we propose end-to-end object scale-oriented fully convolutional networks (OSO–FCNs) for skin lesion segmentation. Given a single skin lesion image, the proposed method produces a pixel-level mask for skin lesion areas. We found that the scale of the lesions in the training dataset affects a large number of the segmentation results of the lesions in the testing phase, and thus, a training strategy called object scale-oriented (OSO) training is proposed. First, the pre-trained network of VGG-16 is adapted and is transformed into fully convolutional networks (FCNs). Second, after very simple preprocessing, skin lesion images with boundary-level annotations are fed into the FCNs for fine-tuning training based on the pre-trained model using OSO training. During the OSO training, the training dataset is divided into 2 subsets according to an index called the object occupation ratio, and then the whole training dataset and the 2 subsets are used to train 3 different scale-oriented FCNs. A dataset provided by the International Skin Imaging Collaboration (ISIC), ISIC2016, is used for training and testing. Our algorithm is compared with the state-of-the-art algorithms, and the experimental results demonstrate that the segmentation accuracy of our algorithm is higher or very close to the performances of the other algorithms.
KeywordsSkin lesion Melanoma Fully convolutional neural networks Object scale-oriented Image segmentation
This research was partly supported by the Guangxi Natural Science Foundation (2018JJB170004), the Guangxi Basic Ability Promotion Project for Young and Middle-aged Teachers (2017KY0247), the Project of Cultivating a Thousand Young and Middle-aged Teachers in Guangxi Universities, the Guangxi Key Laboratory Fund of Embedded Technology and Intelligent System (2018A-07), and the Guangxi Universities Key Laboratory Fund of Embedded Technology and Intelligent Information Processing (2017-1-1, 2017-2-4). Additionally, we would like to thank NVIDIA for providing the Titan X GPU used in this research.
- 2.American Cancer Society What are the key statistics about melanoma skin cancer? (2015). http://www.cancer.org/cancer/skincancer-melanoma/detailedguide/melanoma-skin-cancer-key-statistics. Accessed 16 Aug 2015
- 4.Gutman, D., Codella, N.C.F., Celebi, E., Helba, B., Marchetti, M., Mishra, N., Halpern, A.: Skin lesion analysis toward melanoma detection: a challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC). In: IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) (2016). arXiv:1605.01397 [cs.CV]
- 17.Celebi, M.E., Mendonca, T., Marques, J.S. (eds.): A state-of-the- art survey on lesion border detection in dermoscopy images. In: Dermoscopy image analysis, pp. 97-129. CRC Press, Boca Raton, FL (2015). https://www.taylorfrancis.com/books/9781482253269
- 20.Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25(2), 1106–1114 (2012)Google Scholar
- 21.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv.org/abs/1409.1556
- 22.Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 79(10), 1337–1342 (2015)Google Scholar
- 24.Codella, N., Cai, J., Abedini, M., Garnavi, R., Halpern, A., Smith, J.R.: Deep learning, sparse coding, and SVM for melanoma recognition in dermoscopy images. In: International Workshop on Machine Learning in Medical Imaging, pp. 118–126 (2015)Google Scholar
- 25.Yoshida, T., Celebi, M.E., Schaefer, G., Iyatomi, H.: Simple and effective pre-processing for automated melanoma discrimination based on cytological findings. In: 2016 IEEE International Conference on Big Data (Big Data), pp. 3439–3442. (2016)Google Scholar
- 27.Jafari, M.H., Nasresfahani, E., Karimi, N., Soroushmehr, S.M.R., Samavi, S., Najarian, K.: Extraction of skin lesions from non-dermoscopic images using deep learning (2016). arXiv.org/abs/1609.02374
- 30.Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675–678. Orlando, FL (2014)Google Scholar