A morphometrically-based classification rule for the diagnosis of primary mesothelial lesions

Computerized detection of lung nodules in thin-section CT images by use of selective enhancement filters and an automated rule-based classifier

RATIONALE AND OBJECTIVES

We have been developing a computer-aided diagnostic (CAD) scheme for lung nodule detection in order to assist radiologists in the detection of lung cancer in thin-section computed tomography (CT) images.

MATERIALS AND METHODS

Our database consisted of 117 thin-section CT scans with 153 nodules, obtained from a lung cancer screening program at a Japanese university (85 scans, 91 nodules) and from clinical work at an American university (32 scans, 62 nodules). The database included nodules of different sizes (4-28 mm, mean 10.2 mm), shapes, and patterns (solid and ground-glass opacity (GGO)). Our CAD scheme consisted of modules for lung segmentation, selective nodule enhancement, initial nodule detection, feature extraction, and classification. The selective nodule enhancement filter was a key technique for significant enhancement of nodules and suppression of normal anatomic structures such as blood vessels, which are the main sources of false positives. Use of an automated rule-based classifier for reduction of false positives was another key technique; it resulted in a minimized overtraining effect and an improved classification performance. We used a case-based four-fold cross-validation testing method for evaluation of the performance levels of our computerized detection scheme.

RESULTS

Our CAD scheme achieved an overall sensitivity of 86% (small: 76%, medium-sized: 94%, large: 95%; solid: 86%, mixed GGO: 89%, pure GGO: 81%) with 6.6 false positives per scan; an overall sensitivity of 81% (small: 69%, medium-sized: 91%, large: 91%; solid: 79%, mixed GGO: 88%, pure GGO: 81%) with 3.3 false positives per scan; and an overall sensitivity of 75% (small: 60%, medium-sized: 88%, large: 87%; solid: 70%, mixed GGO: 87%, pure GGO: 81%) with 1.6 false positives per scan.

CONCLUSION

The experimental results indicate that our CAD scheme with its two key techniques can achieve a relatively high performance for nodules presenting large variations in size, shape, and pattern.

Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis

Computer-aided diagnostic (CAD) schemes have been developed to assist radiologists detect various lesions in medical images. In CAD schemes, classifiers play a key role in achieving a high lesion detection rate and a low false-positive rate. Although many popular classifiers such as linear discriminant analysis and artificial neural networks have been employed in CAD schemes for reduction of false positives, a rule-based classifier has probably been the simplest and most frequently used one since the early days of development of various CAD schemes. However, with existing rule-based classifiers, there are major disadvantages that significantly reduce their practicality and credibility. The disadvantages include manual design, poor reproducibility, poor evaluation methods such as resubstitution, and a large overtraining effect. An automated rule-based classifier with a minimized overtraining effect can overcome or significantly reduce the extent of the above-mentioned disadvantages. In this study, we developed an "optimal" method for the selection of cutoff thresholds and a fully automated rule-based classifier. Experimental results performed with Monte Carlo simulation and a real lung nodule CT data set demonstrated that the automated threshold selection method can completely eliminate overtraining effect in the procedure of cutoff threshold selection, and thus can minimize overall overtraining effect in the constructed rule-based classifier. We believe that this threshold selection method is very useful in the construction of automated rule-based classifiers with minimized overtraining effect.

Image cytometry: current applications and future trends

Image cytometry has numerous clinical and research applications and is particularly useful in anatomic pathology for the study of malignant lesions. Modern image systems encompass morphometry, densitometry, neural networks, and expert systems. Rapid advances in technology and the development of user-friendly systems have provided pathologists with an alternative to flow cytometry, particularly useful in the evaluation of small or hypocellular specimens. The most common current application of image cytometry is for DNA analysis, followed by quantitation of immunohistochemical staining. Newer uses under active investigation include development of expert systems that may act as diagnostic consultants in the future. Beyond DNA analysis, image cytometry holds great promise for improved tumor classification, for screening and surveillance in high-risk populations, and as a tool to improve diagnostic ability. This article discusses types of image analysis systems, specimen preparation, data acquisition, current applications in specific organ sites, and possible future applications.

Nucleolar and dispersed nucleolar organiser regions (NORs) in differentiating neoplastic from atypical non-neoplastic lesions of the pancreas

Our objective was to compare the accuracy of differentiation of pancreatic carcinoma from the benign ductular aggregation of chronic pancreatitis using two methods, nuclear morphometric analysis and modified argyrophilic nucleolar organiser region (AgNOR) staining for nucleoli and dispersed NORs (AgNU staining). We evaluated 35 metastatic or invasive lesions of pancreatic carcinoma with low-grade atypia, 16 lesions of ductular aggregation and 12 lesions of proper epithelium. Four parameters, consisting of the size of nucleus: mean area, mean minor axis, mean major axis and mean perimeter, and two parameters of AgNu staining: mean number of AgNu-stained dots per nucleus (equal to mean number of nucleoli and dispersed NORs) and mean area of the largest AgNu-stained dot (equal to mean area of the largest nucleolus) of pancreatic carcinomas were significantly larger than those of ductular aggregations and of proper epithelia. In the discriminant analysis of four parameters of nuclear size, the discrimination of carcinomas was correct in 82.9% and that of ductular aggregations in 81.3%. Discriminant analysis by two parameters of AgNu staining showed 2 correct discrimination of lesions in 88.6% and 100%. Thus, AgNu staining was more accurate than nuclear morphometric analysis in discriminating a pancreatic carcinoma from ductular aggregation.