Color radiography in lung nodule detection and characterization: comparison with conventional gray scale radiography

The detection of lung cancer using massive artificial neural network based on soft tissue technique

BACKGROUND

A proposed computer aided detection (CAD) scheme faces major issues during subtle nodule recognition. However, radiologists have not noticed subtle nodules in beginning stage of lung cancer while a proposed CAD scheme recognizes non subtle nodules using x-ray images.

METHOD

Such an issue has been resolved by creating MANN (Massive Artificial Neural Network) based soft tissue technique from the lung segmented x-ray image. A soft tissue image recognizes nodule candidate for feature extortion and classification. X-ray images are downloaded using Japanese society of radiological technology (JSRT) image set. This image set includes 233 images (140 nodule x-ray images and 93 normal x-ray images). A mean size for a nodule is 17.8 mm and it is validated with computed tomography (CT) image. Thirty percent (42/140) abnormal represents subtle nodules and it is split into five stages (tremendously subtle, very subtle, subtle, observable, relatively observable) by radiologists.

RESULT

A proposed CAD scheme without soft tissue technique attained 66.42% (93/140) sensitivity and 66.76% accuracy having 2.5 false positives per image. Utilizing soft tissue technique, many nodules superimposed by ribs as well as clavicles have identified (sensitivity is 72.85% (102/140) and accuracy is 72.96% at one false positive rate).

CONCLUSION

In particular, a proposed CAD system determine sensitivity and accuracy in support of subtle nodules (sensitivity is 14/42 = 33.33% and accuracy is 33.66%) is statistically higher than CAD (sensitivity is 13/42 = 30.95% and accuracy is 30.97%) scheme without soft tissue technique. A proposed CAD scheme attained tremendously minimum false positive rate and it is a promising technique in support of cancerous recognition due to improved sensitivity and specificity.

Fractal Analysis Method for the Complexity of Cell Cluster Staining on Breast FNAB

OBJECTIVE

Because of the increased precision of ultrasound breast cancer screening, early cancer cases with no clear mass or extraction of microcysts on imaging have recently increased, and improvement of the accuracy of breast fine-needle aspiration biopsy (FNAB) cytology is needed. The objective of this study was to investigate the usefulness of cluster gray image-fractal analysis evaluating the darkness of clusters, cluster unevenness, and complexity of hyperchromicity (cluster density) of deep-stained cell clusters, known as hyperchromatic crowded cell groups (HCG), on FNAB as a cytology assistance system for breast FNAB.

STUDY DESIGN

One hundred clusters collected from 10 patients with fibroadenoma (FA), 90 clusters from 9 patients with ductal carcinoma in situ (DCIS), and 122 clusters from 11 patients with invasive breast carcinoma of no special type (IBC-NST) were used. (1) Cluster size classification: clusters were classified into small, middle, and large clusters (small cluster: smaller than 40 × 102 μm2; large cluster: 100 × 102 μm2 or larger; middle cluster: intermediate), and their frequency was calculated. (2) Cluster gray image-fractal analysis: (a) the darkness of clusters (luminance), (b) cluster unevenness (complexity), and (c) complexity of cluster density (roundness-corrected fractal value) were assessed. For statistical analysis, the multiple comparison Steel-Dwass test was used, with a significance level of p < 0.05.

RESULTS

(1) Cluster size classification: in FA, small, middle, and large clusters appeared at a similar frequency, and the frequency (30%) of large clusters was significantly higher than that in other diseases. In IBC-NST, many small clusters (61%) appeared and their frequency was significantly higher than that in other diseases, whereas the frequency of large clusters was significantly lower. (2) Cluster gray image-fractal analysis: in IBC-NST, the luminance of small clusters was low (dark), the cluster unevenness was high, and the complexity of cluster density was high, whereas the luminance of large clusters was high (bright), the cluster unevenness was high, and complexity of cluster density was high compared with those in FA.

CONCLUSION

Cluster gray image-fractal analysis evaluating the darkness of clusters, cluster unevenness, and complexity of cluster density in breast FNAB HCG is a useful cytology assistance system for breast FNA.