Machine Learning in Computer-Aided Diagnosis of the Thorax and Colon in CT: A Survey

Abstract

SUMMARY Computer-aided detection (CADe) and diagnosis (CAD) has been a rapidly growing, active area of research in medical imaging. Machine leaning (ML) plays an essential role in CAD, because objects such as lesions and organs may not be represented accurately by a simple equation; thus, medical pattern recognition essentially require “learning from examples.” One of the most popular uses of ML is the classification of objects such as lesion candidates into certain classes (e.g., abnormal or normal, and lesions or non-lesions) based on input features (e.g., contrast and area) obtained from segmented lesion candidates. The task of ML is to determine “optimal” boundaries for separating classes in the multidimensional feature space which is formed by the input features. ML algorithms for classification include linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), multilayer perceptrons, and support vector machines (SVM). Recently, pixel/voxel-based ML (PML) emerged in medical image processing/analysis, which uses pixel/voxel values in images directly, instead of features calculated from segmented lesions, as input information; thus, feature calculation or segmentation is not required. In this paper, ML techniques used in CAD schemes for detection and diagnosis of lung nodules in thoracic CT and for detection of polyps in CT colonography (CTC) are surveyed and reviewed.

Using Supervised Machine Learning to Classify Real Alerts and Artifact in Online Multisignal Vital Sign Monitoring Data*

“…Machine learning (ML) techniques learn models encapsulating differential patterns through training on a set of known data(17, 18), and the models then classify new, unseen examples (19). ML-based automated pattern recognition is used to successfully classify abnormal and normal patterns in ultrasound, echocardiographic and computerized tomography images (20-22), electroencephalogram signals (23), intracranial pressure waveforms (24), and word patterns in electronic health record text (25). We hypothesized that ML could learn and automatically classify VS patterns as they evolve in real time online to minimize false positives (artifacts counted as true instability) and false negatives (true instability not captured).…”

Artificial intelligence in radiology

“…The chief hindering factor for further CAD development was its training, namely supervised learning, which restrained the machine from finding new, subtle patterns, relying instead on the ones visible to the human eye, missing the same discreet features as their trainers. Coupled with technologies such as deep learning, CADs may represent solid foundations for future development of AI image analysis [12][13][14][15][16][17] . Another important use of AI technologies in radiology would be workflow optimization.…”

Progress in Fully Automated Abdominal CT Interpretation

“…Review articles cover this topic in more detail [85–87]. Advances in CAD of the colon are leading to improved polyp and mass detection accuracy [88–96].…”