Screen Australia

Previous research has revealed that Vietnamese radiologists had lower diagnostic efficacy in interpreting mammograms than radiologists from Western countries. This study investigated the improvement in diagnostic performances of Vietnamese doctors in breast cancer detection via VIETRAD (VIEtnam: Transformation of Radiological Detection) program. Data of 33 participants who completed three training sessions containing normal and cancer mammographic cases from Australia and Vietnam were assessed in sensitivity, specificity, ROC and JAFROC. Results show that Vietnamese doctors have improved their diagnostic accuracy in identifying normal and cancer cases on mammograms across different levels of breast density.

Constrained combinatorial clustering (CCC) is a new approach for grouping multiple features where the clustering metric depends on an unknown communication channel assignment. Features assigned to the same channel cannot be from the same source and, conversely, channels assigned to the same source must be distinct. While the number of sources and their states are unknown, the channels are assumed to be known except for additive noise. Potential clustering assignments are checked for compatibility with the constraints in a structured way that results in significant computational savings with respect to exhaustive enumeration, especially when combined with a $K$-best channel assignment algorithm that has polynomial complexity. By combining two channel assignment methods (exhaustive and $K$ -best) with two clustering techniques (CCC and greedy), four new algorithms are presented to solve this novel problem, along with detailed computational complexity analyses. The main algorithm (CCC) is a top-down clustering strategy based on assignment aggregation in a channel constrained environment. The approaches are compared on a one-dimensional simulation. Significant performance differences in source estimation accuracy and estimated number of sources are observed at low signal-to-noise ratios (SNRs) and for low values of $K$. Some novel permutation symmetry properties arising from the study, which lead to a new type of self-affine set or discrete fractal, are also presented.