A pilot study of probe-based confocal laser endomicroscopy for computer-aided diagnosis of bile duct cancer by using the deep learning technology

Computed tomography (CT) scanning is a non-invasive diagnostic imaging technique that provides more detailed information about the liver than standard X-rays. Unlike ultrasound (US) examination, the quality of the CT image is not highly operator dependent. Plenty of works has been done using computer-aided diagnosis (CAD) for liver using conventional machine learning algorithms with better results. Recent advances especially in deep learning technology, can detect, classify, segment patterns in medical images where the advancements in deep learning has been shifted to medical domain also. One of the core abilities of deep learning is that they could learn feature representations automatically from data instead of feeding hand crafted features based on application. In this review, the basics of deep learning is introduced and their success in liver segmentation and lesion detection, classification using CT imaging modality is reviewed and their different network architectures is also discussed. Transfer learning is an interesting approach in deep learning which is also discussed. So, deep learning and CAD system has made a huge impact and has produced enhanced performance in healthcare industry.

Download Full-text

P.10.1 COMPUTER AIDED DIAGNOSIS OF BARRETT'S ESOPHAGUS USING CONFOCAL LASER ENDOMICROSCOPY: PRELIMINARY DATA

Digestive and Liver Disease ◽

10.1016/s1590-8658(12)60411-3 ◽

2012 ◽

Vol 44 ◽

pp. S147-S148 ◽

Cited By ~ 1

Author(s):

E. Grisan ◽

E. Veronese ◽

G. Diamantis ◽

C. Trovato ◽

C. Crosta ◽

...

Keyword(s):

Barrett’S Esophagus ◽

Preliminary Data ◽

Barrett's Esophagus ◽

Computer Aided Diagnosis ◽

Confocal Laser Endomicroscopy ◽

Confocal Laser ◽

Computer Aided ◽

Aided Diagnosis

Download Full-text

Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey

BioMed Research International ◽

10.1155/2018/5137904 ◽

2018 ◽

Vol 2018 ◽

pp. 1-10 ◽

Cited By ~ 36

Author(s):

Qinghua Huang ◽

Fan Zhang ◽

Xuelong Li

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Performance Improvement ◽

Ultrasound Imaging ◽

Low Cost ◽

Learning Technology ◽

Diagnostic Systems ◽

Cad System ◽

Computer Aided ◽

Aided Diagnosis

The ultrasound imaging is one of the most common schemes to detect diseases in the clinical practice. There are many advantages of ultrasound imaging such as safety, convenience, and low cost. However, reading ultrasound imaging is not easy. To support the diagnosis of clinicians and reduce the load of doctors, many ultrasound computer-aided diagnosis (CAD) systems are proposed. In recent years, the success of deep learning in the image classification and segmentation led to more and more scholars realizing the potential of performance improvement brought by utilizing the deep learning in the ultrasound CAD system. This paper summarized the research which focuses on the ultrasound CAD system utilizing machine learning technology in recent years. This study divided the ultrasound CAD system into two categories. One is the traditional ultrasound CAD system which employed the manmade feature and the other is the deep learning ultrasound CAD system. The major feature and the classifier employed by the traditional ultrasound CAD system are introduced. As for the deep learning ultrasound CAD, newest applications are summarized. This paper will be useful for researchers who focus on the ultrasound CAD system.

Download Full-text