Laura Tiusaba
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Laura Tiusaba has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Marc Aaron Levitt
Division of Colorectal and Pelvic Reconstruction, Children’s National Hospital, Washington, DC 20010, USA
3 shared publications - Shimon Eric Jacobs
Division of Colorectal and Pelvic Reconstruction, Children's National Medical Center, Washington, District of Columbia, United States
3 shared publications - Christina Feng
Children’s National Hospital
2 shared publications - Teresa Lynn Russell
Department of Preventive Medicine and Biostatistics, Uniformed Services University of the Health Sciences, Bethesda, Maryland, USA
2 shared publications - Allison C. Mayhew
Division of Colorectal and Pelvic Reconstruction, Children’s National Hospital, Washington, DC 20010, USA
1 shared publication - Andrea Badillo
Department of Surgery, Children's National Hospital, George Washington University, Washington, DC, USA
1 shared publication
Latest Publications
- Open Access
- 1 November 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 9 (06) , 064502-18
Unsupervised and quantitative intestinal ischemia detection using conditional adversarial network in multimodal optical imaging
PurposeIntraoperative evaluation of bowel perfusion is currently dependent upon subjective assessment. Thus, quantitative and objective methods of bowel viability in intestinal anastomosis are scarce. To address this clinical need, a conditional adversarial network is used to analyze the data from laser speckle contrast imaging (LSCI) paired with a visible-light camera to identify abnormal tissue perfusion regions.ApproachOur vision platform was based on a dual-modality bench-top imaging system with red-green-blue (RGB) and dye-free LSCI channels. Swine model studies were conducted to collect data on bowel mesenteric vascular structures with normal/abnormal microvascular perfusion to construct the control or experimental group. Subsequently, a deep-learning model based on a conditional generative adversarial network (cGAN) was utilized to perform dual-modality image alignment and learn the distribution of normal datasets for training. Thereafter, abnormal datasets were fed into the predictive model for testing. Ischemic bowel regions could be detected by monitoring the erroneous reconstruction from the latent space. The main advantage is that it is unsupervised and does not require subjective manual annotations. Compared with the conventional qualitative LSCI technique, it provides well-defined segmentation results for different levels of ischemia.ResultsWe demonstrated that our model could accurately segment the ischemic intestine images, with a Dice coefficient and accuracy of 90.77% and 93.06%, respectively, in 2560 RGB/LSCI image pairs. The ground truth was labeled by multiple and independent estimations, combining the surgeons’ annotations with fastest gradient descent in suspicious areas of vascular images. The total processing time was 0.05 s for an image size of 256 × 256.ConclusionsThe proposed cGAN can provide pixel-wise and dye-free quantitative analysis of intestinal perfusion, which is an ideal supplement to the traditional LSCI technique. It has potential to help surgeons increase the accuracy of intraoperative diagnosis and improve clinical outcomes of mesenteric ischemia and other gastrointestinal surgeries.
- 1 November 2022
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 9 (06) , 064502-18
Open AccessUnsupervised and quantitative intestinal ischemia detection using conditional adversarial network in multimodal optical imaging
PurposeIntraoperative evaluation of bowel perfusion is currently dependent upon subjective assessment. Thus, quantitative and objective methods of bowel viability in intestinal anastomosis are scarce. To address this clinical need, a conditional adversarial network is used to analyze the data from laser speckle contrast imaging (LSCI) paired with a visible-light camera to identify abnormal tissue perfusion regions.ApproachOur vision platform was based on a dual-modality bench-top imaging system with red-green-blue (RGB) and dye-free LSCI channels. Swine model studies were conducted to collect data on bowel mesenteric vascular structures with normal/abnormal microvascular perfusion to construct the control or experimental group. Subsequently, a deep-learning model based on a conditional generative adversarial network (cGAN) was utilized to perform dual-modality image alignment and learn the distribution of normal datasets for training. Thereafter, abnormal datasets were fed into the predictive model for testing. Ischemic bowel regions could be detected by monitoring the erroneous reconstruction from the latent space. The main advantage is that it is unsupervised and does not require subjective manual annotations. Compared with the conventional qualitative LSCI technique, it provides well-defined segmentation results for different levels of ischemia.ResultsWe demonstrated that our model could accurately segment the ischemic intestine images, with a Dice coefficient and accuracy of 90.77% and 93.06%, respectively, in 2560 RGB/LSCI image pairs. The ground truth was labeled by multiple and independent estimations, combining the surgeons’ annotations with fastest gradient descent in suspicious areas of vascular images. The total processing time was 0.05 s for an image size of 256 × 256.ConclusionsThe proposed cGAN can provide pixel-wise and dye-free quantitative analysis of intestinal perfusion, which is an ideal supplement to the traditional LSCI technique. It has potential to help surgeons increase the accuracy of intraoperative diagnosis and improve clinical outcomes of mesenteric ischemia and other gastrointestinal surgeries.
- 29 September 2022
- Published by Springer Nature
- p. 399-420
Anorectal Anomalies
- Open Access
Fetal and Newborn Management of Cloacal Malformations
Cloaca is a rare, complex malformation encompassing the genitourinary and anorectal tract of the female in which these tracts fail to separate in utero, resulting in a single perineal orifice. Prenatal sonography detects a few cases with findings such as renal and urinary tract malformations, intraluminal calcifications, dilated bowel, ambiguous genitalia, a cystic pelvic mass, or identification of other associated anomalies prompting further imaging. Multi-disciplinary collaboration between neonatology, pediatric surgery, urology, and gynecology is paramount to achieving safe outcomes. Perinatal evaluation and management may include treatment of cardiopulmonary and renal anomalies, administration of prophylactic antibiotics, ensuring egress of urine and evaluation of hydronephrosis, drainage of a hydrocolpos, and creation of a colostomy for stool diversion. Additional imaging of the spinal cord and sacrum are obtained to plan possible neurosurgical intervention as well as prognostication of future bladder and bowel control. Endoscopic evaluation and cloacagram, followed by primary reconstruction, are performed by a multidisciplinary team outside of the neonatal period. Long-term multidisciplinary follow-up is essential given the increased rates of renal disease, neuropathic bladder, tethered cord syndrome, and stooling issues. Patients and families will also require support through the functional and psychosocial changes in puberty, adolescence, and young adulthood.
Open AccessFetal and Newborn Management of Cloacal Malformations
Cloaca is a rare, complex malformation encompassing the genitourinary and anorectal tract of the female in which these tracts fail to separate in utero, resulting in a single perineal orifice. Prenatal sonography detects a few cases with findings such as renal and urinary tract malformations, intraluminal calcifications, dilated bowel, ambiguous genitalia, a cystic pelvic mass, or identification of other associated anomalies prompting further imaging. Multi-disciplinary collaboration between neonatology, pediatric surgery, urology, and gynecology is paramount to achieving safe outcomes. Perinatal evaluation and management may include treatment of cardiopulmonary and renal anomalies, administration of prophylactic antibiotics, ensuring egress of urine and evaluation of hydronephrosis, drainage of a hydrocolpos, and creation of a colostomy for stool diversion. Additional imaging of the spinal cord and sacrum are obtained to plan possible neurosurgical intervention as well as prognostication of future bladder and bowel control. Endoscopic evaluation and cloacagram, followed by primary reconstruction, are performed by a multidisciplinary team outside of the neonatal period. Long-term multidisciplinary follow-up is essential given the increased rates of renal disease, neuropathic bladder, tethered cord syndrome, and stooling issues. Patients and families will also require support through the functional and psychosocial changes in puberty, adolescence, and young adulthood.