Accurate breast cancer diagnosis using a stable feature ranking algorithm.

BACKGROUND: Breast cancer (BC) is one of the most common cancers among women. Since diverse features can be collected, how to stably select the powerful ones for accurate BC diagnosis remains challenging. METHODS: A hybrid framework is designed for successively investigating both feature ranking (FR) stability and cancer diagnosis effectiveness. Specifically, on 4 BC datasets (BCDR-F03, WDBC, GSE10810 and GSE15852), the stability of 23 FR algorithms is evaluated via an advanced estimator (S), and the predictive power of the stable feature ranks is further tested by using different machine learning classifiers. RESULTS: Experimental results identify 3 algorithms achieving good stability ([Formula: see text]) on the four datasets and generalized Fisher score (GFS) leading to state-of-the-art performance. Moreover, GFS ranks suggest that shape features are crucial in BC image analysis (BCDR-F03 and WDBC) and that using a few genes can well differentiate benign and malignant tumor cases (GSE10810 and GSE15852). CONCLUSIONS: The proposed framework recognizes a stable FR algorithm for accurate BC diagnosis. Stable and effective features could deepen the understanding of BC diagnosis and related decision-making applications.

[Application value of measurement of the regional pulmonary ventilation by electric impedance pneumograph in the clinical diagnosis of pneumoconiosis].

OBJECTIVE: To study the value of clinical application and distribution character of regional pulmonary ventilation of patients with various type of pneumoconiosis. METHODS: 132 patients with various type of pneumoconiosis were observed by electric impedance pneumograph(EIPV) and routine lung function test. The results were compared with the measured value of 100 healthy cases. RESULTS: The regional pulmonary ventilation of the three kinds of pneumoconiosis(founder's pneumoconiosis, silicosis and asbestosis) was increased in both side of upper pulmonary region and decreased in both of lower pulmonary region. The ventilation distribution showed that the right pulmonary ventilation increased predominantly, accounted for 53.03% (70/132) of total lung ventilation. There was significant difference(P < 0.01) compared with the normal healthy men's EIPV, but no difference(P > 0.05) among various type of pneumoconiosis. There was also no difference(P > 0.05) between pneumoconiosis patients with normal ventilation function and various type of ventilation obstacle of pneumoconiosis. One silicosis patient complicated by atelectasis of the left upper lobe, another silicosis patient complicated by lung cancer and their EIPV accorded with their chest X-rays. CONCLUSION: EIPV could not be measured by routine lung function test. It may be the supplement to latter parameter and as a substitute for radio imaging of pulmonary ventilation in pneumoconiosis complicated by other regional pulmonary disorder.