Browsing by Subject "Optical microscopy"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Restricted
    Automated Detection of Corneal Edema With Deep Learning-Assisted Second Harmonic Generation Microscopy
    (Institute of Electrical and Electronics Engineers, 2023-11-06) Anton, Stefan; Martínez Ojeda, Rosa M.; Hristu, Radu; Stanciu, George A.; Toma, Antonela; Banica, Cosmin K.; Fernández, Enrique J.; Huttunen, Mikko J.; Bueno, Juan M.; Stanciu, Stefan G.; Stanciu, Stefan G.; Bueno, Juan M.; Física
    Second Harmonic Generation Microscopy (SHG) is widely acknowledged as a valuable non-linear optical imaging tool, its contrast mechanism providing the premises to non-invasively identify, characterize, and monitor changes in the collagen architecture of tissues.However, the interpretation ofSHGdata can pose difficulties even for experts histopathologists, which represents a bottleneck for the translation of SHG-based diagnostic frameworks to clinical settings. The use of artificial intelligence methods for automated SHG analysis is still in an early stage, with only few studies having been reported to date, none addressing ocular tissues yet. In this work we explore the use of three Deep Learning models, the highly popular InceptionV3 and ResNet50, alongside FLIMBA, a custom developed architecture, requiring no pre-training, to automatically detect corneal edema in SHG images of porcine cornea. We observe that Deep Learning models building on different architectures provide complementary results for the classification ofcornea SHG images and demonstrate an AU-ROC=0.98 for their joint use. These results have potential to be extrapolated to other diagnostics scenarios, such as automated extraction of hydration level of cornea, or identification of corneal edema causes, and thus pave the way for novel methods for precision diagnostics of the cornea with Deep-Learning assisted SHG imaging.
  • Thumbnail Image
    Publication
    Open Access
    Comparative value of microscopy, serology and real time PCR in the diagnosis of asymptomatic canine leishmania infantum infection
    (Murcia: Servicio de Publicaciones de la Universidad de Murcia, 2012) Risueño, J.; Bermejo, E.; Muñoz García, C.I.; Chitimia, I.; Del Río Alonso, Laura; García Martínez, Juan Diego; Fisa, R.; Riera, C.; Martínez Ramírez, A.; Meseguer Meseguer, José María; Murcia, L.; Segovia Hernández, Manuel; Berriatua Fernández de Larrea, Eduardo; Goyena Salgado, Elena; Jiménez Montalbán, Pedro Javier; Facultad de Veterinaria; Facultad de Medicina
    The sensitivity (SE) of cytological examination of spleen and lymphnode smears by optical microscopy (OM), antibody-ELISA (enzyme-linked immunosorbent assays) and real-time (rt) PCR (polymerase chain reaction), for diagnosing asymptomatic canine Leishmania infantum infection was investigated in 110 apparently healthy dogs from southeast Spain. The percentage of OM, ELISA and rtPCR positive dogs were 2% (2/110), 27% (26/97) y 67% (39/58), respectively, although the percentage of rtPCR-positive dogs were 35-41% in individual tissues and 9% in blood. The estimated SE (95% confidence interval) of OM relative to the rtPCR and ELISA tests was 5% (0-12) and 8% (0-18), respectively. Results confirm that most apparently healthy dogs from L. infantum endemic areas are infected, that approximately only one third of these infected dogs develop antibodies and that very few have parasite loads that are high enough to allow detection by OM. As a result, the degree of agreement between rtPCR, ELISA and OM for L. infantum diagnosis in subclinnically infected dogs is low.