In this work, we propose a workflow for face recognition under occlusion using the entropy projection from the curved Gabor filter, and create a representative and compact features vector that describes a face. Despite the reduced vector obtained by the entropy projection, it still presents opportunity for further dimensionality reduction. Therefore, we use a Random Forest classifier as an attribute selector, providing a 97% reduction of the original vector while keeping suitable accuracy. A set of experiments using three public image databases: AR Face, Extended Yale B with occlusion and FERET illustrates the proposed methodology, evaluated using the SVM classifier. The results obtained in the experiments show promising results when compared to the available approaches in the literature, obtaining 98.05% accuracy for the complete AR Face, 97.26% for FERET and 81.66% with Yale with 50% occlusion.

Diffuse-type tenosynovial giant cell tumors' (D-TGCTs) intra- and extra-articular expansion about the knee often necessitates an anterior and posterior surgical approach to facilitate an extensive synovectomy. There is no consensus on whether two-sided synovectomies should be performed in one or two stages. This retrospective study included 191 D-TGCT patients from nine sarcoma centers worldwide to compare the postoperative short-term outcomes between both treatments. Secondary outcomes were rates of radiological progression and subsequent treatments. Between 2000 and 2020, 117 patients underwent one-stage and 74 patients underwent two-stage synovectomies. The maximum range of motion achieved within one year postoperatively was similar (flexion 123-120°, p = 0.109; extension 0°, p = 0.093). Patients undergoing two-stage synovectomies stayed longer in the hospital (6 vs. 4 days, p < 0.0001). Complications occurred more often after two-stage synovectomies, although this was not statistically different (36% vs. 24%, p = 0.095). Patients treated with two-stage synovectomies exhibited more radiological progression and required subsequent treatments more often than patients treated with one-stage synovectomies (52% vs. 37%, p = 0.036) (54% vs. 34%, p = 0.007). In conclusion, D-TGCT of the knee requiring two-side synovectomies should be treated by one-stage synovectomies if feasible, since patients achieve a similar range of motion, do not have more complications, but stay for a shorter time in the hospital.