A5059918946- AI in cancer detection
- Digital Imaging for Blood Diseases
- Testicular diseases and treatments
- Urologic and reproductive health conditions
- Prostate Cancer Diagnosis and Treatment
- Medical Image Segmentation Techniques
- Cancer therapeutics and mechanisms
- Image Retrieval and Classification Techniques
- Spectroscopy Techniques in Biomedical and Chemical Research
- Cancer Diagnosis and Treatment
- Prostate Cancer Treatment and Research
- Generative Adversarial Networks and Image Synthesis
- Sarcoma Diagnosis and Treatment
- Neuroendocrine Tumor Research Advances
- Medical Imaging and Analysis
- Renal and related cancers
- Neural Networks and Applications
- Lung Cancer Treatments and Mutations
- Radiomics and Machine Learning in Medical Imaging
- Pituitary Gland Disorders and Treatments
- Advanced Image Processing Techniques
- Adrenal and Paraganglionic Tumors
- Kawasaki Disease and Coronary Complications
- Pancreatitis Pathology and Treatment
- Acute Lymphoblastic Leukemia research
Hospital Clínico Universitario de Valencia
2015-2024
INCLIVA Health Research Institute
2024
Hospital Arnau de Vilanova
2009
Generalitat Valenciana
2003
Universitat Politècnica de Catalunya
1992
Color variations in digital histopathology severely impact the performance of computer-aided diagnosis systems. They are due to differences staining process and acquisition system, among other reasons. Blind color deconvolution techniques separate multi-stained images into single stained bands which, once normalized, can be used eliminate these negative improve machine learning tasks.In this work, we decompose observed RGB image its hematoxylin eosin components. We apply Bayesian modeling...
Prostate cancer is one of the most common diseases affecting men. The main diagnostic and prognostic reference tool Gleason scoring system. An expert pathologist assigns a grade to sample prostate tissue. As this process very time-consuming, some artificial intelligence applications were developed automatize it. training often confronted with insufficient unbalanced databases which affect generalisability models. Therefore, aim work develop generative deep learning model capable synthesising...
Multiple instance learning (MIL) deals with data grouped into bags of instances, which only the global information is known. In recent years, this weakly supervised paradigm has become very popular in histological image analysis because it alleviates burden labeling all cancerous regions large Whole Slide Images (WSIs) detail. However, these methods require datasets to perform properly, and many approaches focus on simple binary classification. This often does not match real-world problems...
Prostate cancer is a common disease that affects men, and its diagnosis prognosis rely on the Gleason scoring system. To automate this process, generative deep learning models can be used to synthesize histopathological tissue patches of non-cancerous malignant patterns. This work proposes conditional Progressive Growing GAN generate synthetic samples by selecting desired pattern. The model trained using information about pattern, minibatch standard deviation pixel normalization are improve...
A case of granulocytic sarcoma (chloroma) hepatic localization is presented. It a extramedullary strange tumour, composed immature precursors myeloid cells. Clinically it can show, before, during or after acute leukemia, chronic myeloproliferative disorders myelodysplastic syndromes. Our patient, 81 year-old male, presented process important jaundice, with negative image technics, what indicated us the intrahepatic origin, tumorals markers, serology and biopsy (the piece greenish coloration...
Prostate cancer is one of the types with highest incidence in humans. In particular, prostate main cause death from men over 70 years age. The automatic analysis histological images nowadays a key factor for helping doctors diagnosis task. this paper, we present granulometries as novel image descriptor to identify abnormal patterns prostatic tissue. morphological alteration suffered by structures pathological glands are registered proposed and achieved feature vector. A committee SVM...
Abstract Introduction In this study we used nuclear magnetic resonance spectroscopy in prostate tissue to provide new data on potential biomarkers of cancer patients eligible for biopsy. Material and Methods Core needle samples were obtained. After acquiring all the spectra using a Bruker Avance III DRX 600 spectrometer, subjected routine histology confirm presence or absence cancer. Univariate multivariate analyses with metabolic clinical variables performed predict occurrence Results A...
FIBROSARCOMA PARATESTICULAR: UNA NEOPLASIA MALIGNA MUY INFRECUENTE Presentamos los hallazgos clínicos y patológicos de un sarcoma paratesticular cordón espermático muy infrecuente.El tumor fue fibrosarcoma en varón 55 años edad que debutó forma atípica con crecimiento rápido.Se practicó orquiectomía radical ligadura inguinal pedículo sin terapia postoperatoria.Tras 5 seguimiento no hay signos ni radiológicos recidiva locorregional a distancia.Concluimos la cirugía es única alternativa terapéutica,