LIDS was represented at the SPIE Medical Imaging 2019 at San Diego, USA. It is one of the most traditional and important conference of the area leading researchers in image processing, computer-aided diagnosis, machine learning, among others.
The Ph.D. student Azael Sousa presented the paper "A computational method to aid the detection and annotation of pleural lesions in CT images of the thorax". The work proposes the use of fast image processing operators based on optimum connectivity to segment both lungs and the trachea, and then highlight all possible lesions on the pleura.
Our Ph.D. candidate Samuel Martins presented the work "Modeling normal brain asymmetry in MR images applied to anomaly detection without segmentation and data annotation". The work combines Encoder-Decoder Neural Networks and One-Class Classifiers to model "normal" brain asymmetries which is then used to detect anomalies (abnormal asymmetries) caused by diseases. The proposed method was evaluated to detect abnormal hippocampal asymmetries in MR-T1 brain images of Epilepsy patients.
Prof. Dr. Alexandre Falcão has also attended to the conference being Session Chair in two sessions of the event.