Transfer Learning-Based Multi-Scale Denoising Convolutional Neural Network for Prostate Cancer Detection.

BACKGROUND: Prostate cancer is the 4th most common type of cancer. To reduce the workload of medical personnel in the medical diagnosis of prostate cancer and increase the diagnostic accuracy in noisy images, a deep learning model is desired for prostate cancer detection. METHODS: A multi-scale denoising convolutional neural network (MSDCNN) model was designed for prostate cancer detection (PCD) that is capable of noise suppression in images. The model was further optimized by transfer learning, which contributes domain knowledge from the same domain (prostate cancer data) but heterogeneous datasets. Particularly, Gaussian noise was introduced in the source datasets before knowledge transfer to the target dataset. RESULTS: Four benchmark datasets were chosen as representative prostate cancer datasets. Ablation study and performance comparison between the proposed work and existing works were performed. Our model improved the accuracy by more than 10% compared with the existing works. Ablation studies also showed average improvements in accuracy using denoising, multi-scale scheme, and transfer learning, by 2.80%, 3.30%, and 3.13%, respectively. CONCLUSIONS: The performance evaluation and comparison of the proposed model confirm the importance and benefits of image noise suppression and transfer of knowledge from heterogeneous datasets of the same domain.

Improving Efficiency Assessment of Psychiatric Halfway Houses: A Context-Dependent Data Envelopment Analysis Approach.

This study proposes the approach of context-dependent data envelopment analysis (DEA) to measure operating performance in halfway houses to enable suitable adjustments at the current economic scale. The proposed approach can be used to discriminate the performance of efficient halfway houses and provide more accurate DEA results related to the performance of all halfway houses in a region or a country. The relative attractiveness and progress were also evaluated, and individual halfway houses' competitive advantage and potential competitors could be determined. A case study of 38 halfway houses in Taiwan was investigated by our proposed approach. Findings suggest that fifteen halfway houses belong to the medium level, which can be classified into a quadrant by examining both their attractiveness score and progress score. The results can be used to allocate community resources to improve the operational directions and develop incentives for halfway houses with attractive and progressive values, which can reduce the institutionalization and waste of medical resources caused by the long-term hospitalization of patients with mental illnesses. Our proposed approach can also provide references for operators and policy makers to improve the management, accreditation, and resource allocation of institutions.