论文信息 - Deep Learning Techniques for Real Time Computer-Aided Diagnosis in Colorectal Cancer

Deep Learning Techniques for Real Time Computer-Aided Diagnosis in Colorectal Cancer

Colorectal cancer is one of the most common types of cancer. The development of this cancer starts with the presence of polyps or neoplastic lesions in the colon which can evolve to malignant processes. When a polyp is detected during endoscopy, a resection is carried out and a biopsy is done afterwards. Sometimes, resections that have been done are not really necessary, performing an unnecessary procedure over the patient. The PhD project presented here aims develop a real-time colon polyp detection, localization and classification system based on Deep Learning techniques. The creation of this system could help endoscopist in the optical diagnosis of colon lesions, giving an observer-independent aid when making decisions over colorectal cancers.

[1] Bram van Ginneken,et al. A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[2] Jun Ki Min,et al. Overview of Deep Learning in Gastrointestinal Endoscopy , 2019, Gut and liver.

[3] Jonathan H. Chen,et al. Machine Learning and Prediction in Medicine - Beyond the Peak of Inflated Expectations. , 2017, The New England journal of medicine.

[4] Sebastian Thrun,et al. Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[5] Kazufumi Kaneda,et al. Computer-Aided Colorectal Tumor Classification in NBI Endoscopy Using CNN Features , 2016, ArXiv.

[6] Carmen C. Y. Poon,et al. Automatic Detection and Classification of Colorectal Polyps by Transferring Low-Level CNN Features From Nonmedical Domain , 2017, IEEE Journal of Biomedical and Health Informatics.

[7] P. Baldi,et al. Deep Learning Localizes and Identifies Polyps in Real Time With 96% Accuracy in Screening Colonoscopy. , 2018, Gastroenterology.

[8] T. Berzin,et al. Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy , 2018, Nature Biomedical Engineering.