Applications of machine learning techniques to a sensor-network-based prosthesis training system.

In the past, the utilization of the limb prosthesis has improved the daily life of amputees or patients with movement disorders. However, a leg-amputee has to take a series of training after wearing a limb prosthesis, and the training results determine whether a patient can use the limb prosthesis correctly in her/his daily life. Limb prosthesis vendors thus desire to offer the leg-amputee a complete and well-organized training process, but they often fail to do so owing to the factors such as the limited support of human resource and financial condition of the amputee. This work proposes a prosthesis training system that the amputees can borrow or buy from the limb prosthesis vendors and train themselves at home. Instant feedback messages provided by the prosthesis training system are used to correct their walking postures during the self-training process. An embedded chip is used as a core to establish a body area sensor network for the prosthesis training system. RFID readers and tags are employed to acquire the 3D positioning information of the amputee's limbs in this work to assist in diagnosing the amputee's walking problem. A series of simulations were conducted and the simulation results exhibit the effectiveness and practicability of the proposed prosthesis training system.

[Relationship between D2-40-labeled lymphatic vessel invasion and lymph node metastasis of breast cancer].

OBJECTIVE: To investigate the feasibility of D2-40 labeling for detecting lymphatic vessels in breast cancer tissues and the clinicopathological implications of lymphatic vessel invasion (LVI). METHODS: Immunohistochemistry was used to detect the expression of D2-40 and lymphatic invasion in 72 cases of breast cancer and 15 benign breast tumor tissues, and their correlations to the clinicopathological factors were analyzed. RESULTS: The positivity rate of LVI was 69.4% in breast cancer tissue. In patients with lymph node metastasis, the positivity rate of LVI was significantly higher than that in patients without lymph node involvement (85.7% vs 54.1%, P<0.01), and LVI was found to be positively correlated to axillary lymph node metastasis (r=0.382). CONCLUSION: D2-40 can specially and reliably mark the lymphatic vessels in breast cancer tissues. LVI is positively correlated to axillary lymph node metastasis and occurs earlier than the latter, therefore should be included in routine clinicopathological testing.

[Expressions of D2-40 and CD34 in invasive ductal carcinoma of the breast and the clinical implications].

OBJECTIVE: To investigate the expression of D2-40 and CD34 in invasive ductal carcinoma of the breast and the clinical significance. METHODS: D2-40 and CD34 expressions were detected immunohistochemically in 108 cases of invasive ductal carcinoma of the breast and 30 cases of breast fibroadenoma. The lymphatic microvessel density (LMD) and the microvessel density (MD), marked by D2-40 and CD34, respectively, were calculated and their relationship with the clinicopathological factors was analyzed. RESULTS: The LMD and MD for invasive ductal carcinoma of the breast were significantly higher than those of breast fibroadenoma (P<0.01). One-way ANOVA indicated that the LMD differed significantly between tumors of different histological grades, status of lymph node metastasis and TNM stages; the MD also varied significantly with the tumor size, histological grade, lymph node metastasis and TNM stage. The LMD and MD showed a positive correlation to the tumor size (r=0.335, 0.337), histological grade (r=0.580, 0.671), lymph node metastasis (r=0.690, 0.721) and TNM stage (r=0.623, 0.634), but not to ER, PR or Her-2 status (P>0.05). CONCLUSIONS: D2-40 can specifically mark the lymphatic endothelial cells in invasive ductal carcinoma of the breast. The LMD and MD are positively correlated to the clinicopathological factors of the malignancy. D2-40 and CD34 has the potential for use as the predictors to evaluate the tumor progression and metastasis.