An integrated approach for medical abnormality detection using deep patch convolutional neural networks

• Published in: The Visual computer Vol. 36; no. 9; pp. 1869 - 1882
• Main Authors: Xi, Pengcheng, Guan, Haitao, Shu, Chang, Borgeat, Louis, Goubran, Rafik
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer 01.09.2020; Springer Berlin Heidelberg; Springer Nature B.V
• Subjects: Abnormalities; Algorithms; Artificial Intelligence; Artificial neural networks; Calcification; Cancer; class activation mapping; Classification; Computer Graphics; Computer Science; Datasets; deep convolutional neural networks; Deep learning; Detectors; Discriminant analysis; High resolution; Image analysis; Image compression; Image Processing and Computer Vision; Image resolution; Integrated approach; Machine learning; medical abnormality detection; Medical imaging; Neural networks; Object recognition; Original Article; region proposal; Sensors; Sliding; Thyroid gland; Ultrasonic imaging; Deep convolutional neural networks; Medical abnormality detection; Region proposal networks; Class activation mapping

Computer-aided detection of abnormalities in medical images has clinical significance but remains a challenging research topic. Unlike object detection in natural images, the detection of medical abnormalities is unique because they often locate in tiny local regions within a high-resolution medical...