[Detection of multiple gene mutations in non-small-cell lung cancer by suspension microarray].

OBJECTIVE: To construct a high-throughput suspension microarray for detecting the hotspot gene mutations of p53, p16, retinoblastoma (Rb) and epidermal growth factor receptor (EGFR) and to investigate the significance of this multimarker panel in molecular diagnosis of non-small-cell lung cancer (NSCLC). METHODS: The specific probes of normal or mutated sequences targeting the hotspot mutation sites of p53, p16, Rb and EGFR were designed and immobilized to carboxylated Luminex microspheres (micro-beads). Genomic DNA was extracted from 65 specimens of cancer tissues and 20 adjacent normal lung tissues. p53, p16, Rb and EGFR genes were amplified by PCR, hybridized with the specific probes on the beads and measured using Luminex 100. RESULTS: The single gene mutations of p53, p16, Rb or EGFR in NSCLC specimens were 53.8% (35/65), 20.0% (13/65), 7.7% (5/65) or 35.4% (23/65) respectively. The para-tumor normal tissue specimens were 5.0% (1/20), 5.0%(1/20), 0 and 0 respectively. For combined detections of four genes, the sensitivity, specificity and accuracy were 81.5% (53/65), 90.0% (18/20) and 83.5%(71/85) respectively. The mutation rates of this panel in stage I, stage II and stage III were 78.3% (18/23), 80.0% (16/20) and 86.4% (19/22) respectively. CONCLUSIONS: A high-throughput suspension microarray with a higher specificity and sensitivity has been built. It may be used to simultaneously detect the gene mutations of p53, p16, Rb or EGFR in NSCLC specimens. This suspension microarray is helpful to improve the sensitivity of molecular diagnosis of NSCLC and guide the molecular targeting therapy of NSCLC.

[Implementation and application of a digital cytopathological lung cancer diagnosing system].

OBJECTIVE: To evaluate the efficacy of the digital cytopathological lung cancer diagnosing system (DCLCDS) utilizing the latest computer technologies (including reinforcement learning, image segmentation and classifier) and the cytopathological knowledge on lung cancer cells. METHODS: Separate the overlapped lung cancer cells in a slice image applying the improved deBoor-Cox B-Spline algorithm; Segment cell regions in a slice image using an image segmentation algorithm based on reinforcement learning; Ensemble different classifiers, including Decision Tree classifier, Support Vector Machine (SVM) classifier and Bayesian classifier, to achieve an accurate result of cytopathological lung cancer diagnosis. RESULTS: The accurate diagnosis rate for lung cancer identification of 224 images of small lung lesions aspiration biopsy from 120 cases randomly selected was 92.3%. The accurate diagnosis rate for type classification of lung cancer was 82.5%. The identification rate for abnormal nuclear cells was 71.6%. CONCLUSIONS: The DCLCDS achieves a high accuracy on cytopathological lung cancer diagnosis by solving some major problems on the cytology smears, including cell overlapping, uneven coloration and impurity. It provides a relatively objective, standard tool on cytopathological lung cancer diagnosis. It has good efficacy on early diagnosis of lung cancer.