0000000000147521
AUTHOR
Sergi Ganau
Automatic Seed Placement for Breast Lesion Segmentation on US Images
Breast lesion boundaries have been mostly extracted by using conventional approaches as a previous step in the development of computer-aided diagnosis systems. Among these, region growing is a frequently used segmentation method. To make the segmentation completely automatic, most of the region growing methods incorporate automatic selection of the seed points. This paper proposes a new automatic seed placement algorithm for breast lesion segmentation on ultrasound images by means of assigning the probability of belonging to a lesion for every pixel depending on intensity, texture and geometrical constraints. The proposal has been evaluated using a set of sonographic breast images with acco…
Abstract OT-13-06: Solti-1503 PROMETEO: Talimogene laherparepvec (T-VEC) + atezolizumab combination in early breast cancer
Abstract Background Residual disease (RD) after standard neoadjuvant chemotherapy (NAC) is composed of drug resistant cells and associates with increased risk of relapse, especially in triple negative, HER2-positive, and highly proliferative Luminal tumors. Immunotherapy combinations can induce of specific anti-tumor immune responses, such as those mediated by T-cells, and which might represent an additional strategy for the control or elimination of residual tumor cells. Preliminary results in melanoma showed that the combination of T-VEC with an anti PD-L1 or anti CTLA4 has greater efficacy than either therapy alone, without additional safety concerns beyond those expected for each agent.…
SIFT Texture Description for Understanding Breast Ultrasound Images
Texture is a powerful cue for describing structures that show a high degree of similarity in their image intensity patterns. This paper describes the use of Self-Invariant Feature Transform (SIFT), both as low-level and high-level descriptors, applied to differentiate the tissues present in breast US images. For the low-level texture descriptors case, SIFT descriptors are extracted from a regular grid. The high-level texture descriptor is build as a Bag-of-Features (BoF) of SIFT descriptors. Experimental results are provided showing the validity of the proposed approach for describing the tissues in breast US images.
SOLTI-1503 PROMETEO TRIAL: combination of talimogene laherparepvec with atezolizumab in early breast cancer
New treatment strategies such as immune checkpoint inhibitors and oncolytic viruses are opening new possibilities in cancer therapy. Preliminary results in melanoma and other tumors showed that the combination of talimogene laherparepvec with an anti-PD-1/PD-L1 or anti-CTLA4 has greater efficacy than either therapy alone, without additional safety concerns beyond those expected for each agent. The presence of residual cancer after neoadjuvant chemotherapy in early breast cancer patients is an unmet medical need. SOLTI-1503 PROMETEO is a window of opportunity trial, which evaluates the combination of talimogene laherparepvec in combination with atezolizumab in women with operable HER2-negati…