To develop automated diagnosis of melanoma, the deadliest form of skin cancer, from dermoscopic images, International Skin Imaging Collaboration (ISIC) hosted the ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challenge at MICCAI. Participated in the challenge, we proposed deep learning methods to solve semantic segmentation and classification problems of melanoma.
PDFTo develop algorithms for automated detection and grading of diabetic retinopathy, the Indian Diabetic Retinopathy Image Dataset (IDRiD) organized the IDRiD Diabetic Retinopathy Segmentation and Grading Challenge at ISBI. Participated in the challenge, we proposed a deep learning method to detect the retinal lesions associated with diabetic retinopathy.
CodeDetect common thoracic diseases from chest X-ray images. We use the ChestX-ray8 dataset to train our deep learning model.
Code