We propose a deep learning-based computer-aided detection (CADe) method to detect breast lesions in ultrafast DCE-MRI sequences. This method uses both the 3D spatial information and temporal information obtained from the early-phase of the dynamic acquisition. Methods: The proposed CADe method, based on a modified 3D RetinaNet model, operates on ultrafast T1 weighted sequences, which are preprocessed for motion compensation, temporal normalization, and are cropped before passing into the model. The model is optimized to enable the detection of relatively small breast lesions in a screening setting, focusing on detection of lesions that are harder to differentiate from confounding structures inside the breast. Results: The method was developed based on a dataset consisting of 489 ultrafast MRI studies obtained from 462 patients containing a total of 572 lesions (365 malignant,207 benign) and achieved a detection rate,sensitivity,and detection rate of benign lesions of 0.90 (0.876-0.934), 0.95 (0.934-0.980), and 0.81 (0.751-0.871) at four false positives per normal breast with 10-fold cross-testing, respectively. Conclusions:The deep learning architecture used for the proposed CADe application can efficiently detect benign and malignant lesions on ultrafast DCE-MRI. Furthermore, utilizing the less visible hard-to-detect lesions in training improves the learning process and, subsequently, detection of malignant breast lesions.

No abstract

In this paper, a novel feature extraction method is proposed to handle facial makeup in face recognition. To develop a face recognition method robust to facial makeup, features are extracted from face depth in which facial makeup is not effective. Then, face depth features are added to face texture features to perform feature extraction. Accordingly, a 3D face is reconstructed from only a single 2D frontal image with/without facial expressions. Then, the texture and depth of the face are extracted from the reconstructed model. Afterwards, the DualTree Complex Wavelet Transform (DT-CWT) is applied to both texture and reconstructed depth of the face to extract the feature vectors from both texture and reconstructed depth images. Finally, by combining 2D and 3D feature vectors, the final feature vectors are generated and classified by the Support Vector Machine (SVM). Promising results were achieved for makeup-invariant face recognition on the available image database based on the present method compared to several stateof-the-art methods.

No abstract