abstract: Rapid intraoperative diagnosis of brain tumors is of great importance for planning treatment and guiding the surgeon about the extent of resection. Currently, the standard for the preliminary intraoperative tissue analysis is frozen section biopsy that has major limitations such as tissue freezing and cutting artifacts, sampling errors, lack of immediate interaction between the pathologist and the surgeon, and time consuming. Handheld, portable confocal laser endomicroscopy (CLE) is being explored in neurosurgery for its ability to image histopathological features of tissue at cellular resolution in real time during brain tumor surgery. Over the course of examination of the surgical tumor resection, hundreds to thousands of images may be collected. The high number of images requires significant time and storage load for subsequent reviewing, which motivated several research groups to employ deep convolutional neural networks (DCNNs) to improve its utility during surgery. DCNNs have proven to be useful in natural and medical image analysis tasks such as classification, object detection, and image segmentation. This thesis proposes using DCNNs for analyzing CLE images of brain tumors. Particularly, it explores the practicality of DCNNs in three main tasks. First, off-the shelf DCNNs were used to classify images into diagnostic and non-diagnostic. Further experiments showed that both ensemble modeling and transfer learning improved the classifier’s accuracy in evaluating the diagnostic quality of new images at test stage. Second, a weakly-supervised learning pipeline was developed for localizing key features of diagnostic CLE images from gliomas. Third, image style transfer was used to improve the diagnostic quality of CLE images from glioma tumors by transforming the histology patterns in CLE images of fluorescein sodium-stained tissue into the ones in conventional hematoxylin and eosin-stained tissue slides. These studies suggest that DCNNs are opted for analysis of CLE images. They may assist surgeons in sorting out the non-diagnostic images, highlighting the key regions and enhancing their appearance through pattern transformation in real time. With recent advances in deep learning such as generative adversarial networks and semi-supervised learning, new research directions need to be followed to discover more promises of DCNNs in CLE image analysis. / Dissertation/Thesis / Doctoral Dissertation Neuroscience 2019

Esophagectomy often presents anastomotic leaks (AL), due to tenuous perfusion of gastric conduit fundus (GCF). Hybrid (endovascular/surgical) ischemic gastric preconditioning (IGP), might improve GCF perfusion. Sixteen pigs undergoing IGP were randomized: (1) Max-IGP (n = 6): embolization of left gastric artery (LGA), right gastric artery (RGA), left gastroepiploic artery (LGEA), and laparoscopic division (LapD) of short gastric arteries (SGA); (2) Min-IGP (n = 5): LGA-embolization, SGA-LapD; (3) Sham (n = 5): angiography, laparoscopy. At day 21 gastric tubulation occurred and GCF perfusion was assessed as: (A) Serosal-tissue-oxygenation (StO2) by hyperspectral-imaging; (B) Serosal time-to-peak (TTP) by fluorescence-imaging; (C) Mucosal functional-capillary-density-area (FCD-A) index by confocal-laser-endomicroscopy. Local capillary lactates (LCL) were sampled. Neovascularization was assessed (histology/immunohistochemistry). Sham presented lower StO2 and FCD-A index (41 ± 10.6%; 0.03 ± 0.03 respectively) than min-IGP (66.2 ± 10.2%, p-value = 0.004; 0.22 ± 0.02, p-value < 0.0001 respectively) and max-IGP (63.8 ± 9.4%, p-value = 0.006; 0.2 ± 0.02, p-value < 0.0001 respectively). Sham had higher LCL (9.6 ± 4.8 mL/mol) than min-IGP (4 ± 3.1, p-value = 0.04) and max-IGP (3.4 ± 1.5, p-value = 0.02). For StO2, FCD-A, LCL, max- and min-IGP did not differ. Sham had higher TTP (24.4 ± 4.9 s) than max-IGP (10 ± 1.5 s, p-value = 0.0008) and min-IGP (14 ± 1.7 s, non-significant). Max- and min-IGP did not differ. Neovascularization was confirmed in both IGP groups. Hybrid IGP improves GCF perfusion, potentially reducing post-esophagectomy AL.