Evaluation of Feature Selection Methods for Mammographic Breast Cancer Diagnosis in a Unified Framework.

Over recent years, feature selection (FS) has gained more attention in intelligent diagnosis. This study is aimed at evaluating FS methods in a unified framework for mammographic breast cancer diagnosis. After FS methods generated rank lists according to feature importance, the framework added features incrementally as the input of random forest which performed as the classifier for breast lesion classification. In this study, 10 FS methods were evaluated and the digital database for screening mammography (1104 benign and 980 malignant lesions) was analyzed. The classification performance was quantified with the area under the curve (AUC), and accuracy, sensitivity, and specificity were also considered. Experimental results suggested that both infinite latent FS method (AUC, 0.866 ± 0.028) and RELIEFF (AUC, 0.855 ± 0.020) achieved good prediction (AUC ≥ 0.85) when 6 features were used, followed by correlation-based FS method (AUC, 0.867 ± 0.023) using 7 features and WILCOXON (AUC, 0.887 ± 0.019) using 8 features. The reliability of the diagnosis models was also verified, indicating that correlation-based FS method was generally superior over other methods. Identification of discriminative features among high-throughput ones remains an unavoidable challenge in intelligent diagnosis, and extra efforts should be made toward accurate and efficient feature selection.

[Clinical observation of soft tissue wire rivets in the treatment of large patellar cartilage fracture].

OBJECTIVE: To explore the clinical curative effect of soft tissue wire rivet for the treatment of fracture of patella cartilage. METHODS: A retrospective study was conducted in 25 patients(25 knees) from June 2015 to February 2017 in patients with patellar cartilage fractures. Among them, 19 were male, 6 were female, 11 were left knee, 14 were right knee. The accident occurred in 2 cases, 23 cases of sprained athletes; the average age was(25.12±6.02) years old, the average weight was (62.48±7.91) kg, and the average body mass index was(23.25±1.51) kg/m². The average time from injury to admission was (1.96±1.51) d. The clinical manifestations were swelling of knee joint, positive floating patella sign, severe pain, occasional joint strangulation, limited flexion and extension, obvious tenderness of lateral patella, positive patellar extrapolation test and positive extrapolation fear test. X-ray and CT examination were performed before operation. X-ray showed the continuity of patellar bone and a loose body in the joint cavity. CT and 3D reconstruction showed patellar cartilage and facial defects. All 25 patients were fixed with soft tissue wire rivet. The clinical efficacy included preoperative Lysholm score and Insall evaluation. RESULTS: All the patients were followed up, and the duration ranged from 3 to 15 months, with an average of(9.72±4.07) months. The preoperative Lysholm score was 60.32±5.08, and the final follow-up was 88.24±4.37. The postoperative score was better than that before operation(t=-22.926, P<0.05). According to Insall criteria, 21 cases were excellent, 4 cases were good, no fracture fragments were found and knee joint adhesion was found. Six weeks after operation, X-ray and CT showed that the fracture was well positioned, the cartilage surface was smooth without obvious steps, and the patella was in good shape. MRI showed the smooth articular surface of patellar cartilage at the 6th month after operation. CONCLUSIONS: Soft tissue wire rivet for the treatment of massive patellar cartilage fracture has the advantages of simple operation, rapid postoperative recovery, no need for secondary operation pain, fewer complications, and definite effect, which is worthy of clinical promotion.