scholarly journals Deep learning-based fetoscopic mosaicking for field-of-view expansion

2020 ◽  
Vol 15 (11) ◽  
pp. 1807-1816 ◽  
Author(s):  
Sophia Bano ◽  
Francisco Vasconcelos ◽  
Marcel Tella-Amo ◽  
George Dwyer ◽  
Caspar Gruijthuijsen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ex Vivo ◽  
Video Data ◽  
Field Of View ◽  
Small Subset ◽  
Data Generation ◽  
Minimally Invasive Surgical Procedure ◽  
Minimally Invasive Surgical ◽  
Deep Image

Abstract Purpose Fetoscopic laser photocoagulation is a minimally invasive surgical procedure used to treat twin-to-twin transfusion syndrome (TTTS), which involves localization and ablation of abnormal vascular connections on the placenta to regulate the blood flow in both fetuses. This procedure is particularly challenging due to the limited field of view, poor visibility, occasional bleeding, and poor image quality. Fetoscopic mosaicking can help in creating an image with the expanded field of view which could facilitate the clinicians during the TTTS procedure. Methods We propose a deep learning-based mosaicking framework for diverse fetoscopic videos captured from different settings such as simulation, phantoms, ex vivo, and in vivo environments. The proposed mosaicking framework extends an existing deep image homography model to handle video data by introducing the controlled data generation and consistent homography estimation modules. Training is performed on a small subset of fetoscopic images which are independent of the testing videos. Results We perform both quantitative and qualitative evaluations on 5 diverse fetoscopic videos (2400 frames) that captured different environments. To demonstrate the robustness of the proposed framework, a comparison is performed with the existing feature-based and deep image homography methods. Conclusion The proposed mosaicking framework outperformed existing methods and generated meaningful mosaic, while reducing the accumulated drift, even in the presence of visual challenges such as specular highlights, reflection, texture paucity, and low video resolution.

scholarly journals Rectal Cancer Treatment Management: Deep-Learning Neural Network Based on Photoacoustic Microscopy Image Outperforms Histogram-Feature-Based Classification

2021 ◽  
Vol 11 ◽  
Author(s):  
Xiandong Leng ◽  
Eghbal Amidi ◽  
Sitai Kou ◽  
Hassam Cheema ◽  
Ebunoluwa Otegbeye ◽  
...  
Keyword(s):  
Neural Network ◽  
Rectal Cancer ◽  
Deep Learning ◽  
Linear Models ◽  
Ex Vivo ◽  
Residual Tumor ◽  
Photoacoustic Microscopy ◽  
Feature Based ◽  
Histogram Feature

We have developed a novel photoacoustic microscopy/ultrasound (PAM/US) endoscope to image post-treatment rectal cancer for surgical management of residual tumor after radiation and chemotherapy. Paired with a deep-learning convolutional neural network (CNN), the PAM images accurately differentiated pathological complete responders (pCR) from incomplete responders. However, the role of CNNs compared with traditional histogram-feature based classifiers needs further exploration. In this work, we compare the performance of the CNN models to generalized linear models (GLM) across 24 ex vivo specimens and 10 in vivo patient examinations. First order statistical features were extracted from histograms of PAM and US images to train, validate and test GLM models, while PAM and US images were directly used to train, validate, and test CNN models. The PAM-CNN model performed superiorly with an AUC of 0.96 (95% CI: 0.95-0.98) compared to the best PAM-GLM model using kurtosis with an AUC of 0.82 (95% CI: 0.82-0.83). We also found that both CNN and GLMs derived from photoacoustic data outperformed those utilizing ultrasound alone. We conclude that deep-learning neural networks paired with photoacoustic images is the optimal analysis framework for determining presence of residual cancer in the treated human rectum.

scholarly journals Neurochemical Characterization of Brainstem Pro-Opiomelanocortin Cells

Endocrinology ◽  
2020 ◽  
Vol 161 (4) ◽  
Author(s):  
Teodora Georgescu ◽  
David Lyons ◽  
Barbora Doslikova ◽  
Ana Paula Garcia ◽  
Oliver Marston ◽  
...  
Keyword(s):  
Fluorescent Protein ◽  
Ex Vivo ◽  
Genetic Research ◽  
Cell Activity ◽  
Small Subset ◽  
Solitary Tract ◽  
Energy Status ◽  
Pomc Mrna

Abstract Genetic research has revealed pro-opiomelanocortin (POMC) to be a fundamental regulator of energy balance and body weight in mammals. Within the brain, POMC is primarily expressed in the arcuate nucleus of the hypothalamus (ARC), while a smaller population exists in the brainstem nucleus of the solitary tract (POMCNTS). We performed a neurochemical characterization of this understudied population of POMC cells using transgenic mice expressing green fluorescent protein (eGFP) under the control of a POMC promoter/enhancer (PomceGFP). Expression of endogenous Pomc mRNA in the nucleus of the solitary tract (NTS) PomceGFP cells was confirmed using fluorescence-activating cell sorting (FACS) followed by quantitative PCR. In situ hybridization histochemistry of endogenous Pomc mRNA and immunohistochemical analysis of eGFP revealed that POMC is primarily localized within the caudal NTS. Neurochemical analysis indicated that POMCNTS is not co-expressed with tyrosine hydroxylase (TH), glucagon-like peptide 1 (GLP-1), cholecystokinin (CCK), brain-derived neurotrophic factor (BDNF), nesfatin, nitric oxide synthase 1 (nNOS), seipin, or choline acetyltransferase (ChAT) cells, whereas 100% of POMCNTS is co-expressed with transcription factor paired-like homeobox2b (Phox2b). We observed that 20% of POMCNTS cells express receptors for adipocyte hormone leptin (LepRbs) using a PomceGFP:LepRbCre:tdTOM double-reporter line. Elevations in endogenous or exogenous leptin levels increased the in vivo activity (c-FOS) of a small subset of POMCNTS cells. Using ex vivo slice electrophysiology, we observed that this effect of leptin on POMCNTS cell activity is postsynaptic. These findings reveal that a subset of POMCNTS cells are responsive to both changes in energy status and the adipocyte hormone leptin, findings of relevance to the neurobiology of obesity.

Investigating the needle dynamic response during insertion into soft tissue

2009 ◽  
Vol 224 (4) ◽  
pp. 531-540 ◽  
Author(s):  
T Alja'afreh
Keyword(s):  
Soft Tissue ◽  
Ex Vivo ◽  
Surgical Techniques ◽  
Needle Insertion ◽  
Limiting Factor ◽  
Minimally Invasive Surgical ◽  
Soft Tissue Motion ◽  
Insertion Process ◽  
Tissue Motion

This paper investigates the effect of the needle velocity on soft-tissue motion ex vivo and in vivo. In many needle-based intervention procedures, which are common minimally invasive surgical techniques, the needle can be assumed to be rigid and the tissue deforms and displaces considerably as the needle moves forwards to its target. This paper presents an energy-based fracture mechanics approach to show that the increasing needle velocity can reduce tissue motion during the insertion process. The main feature of this paper is that it extends the proposed approach to model the insertion dynamics, whereas most of the literature treats needle insertion as a quasi-static process. Ex-vivo test results on lamb heart samples show that the force required to initiate penetration decreases with increasing needle velocity up to a critical velocity, above which the rate-independent penetration force of the underlying tissue becomes the limiting factor. In-vivo tests show that increased needle velocity results in reduced force and displacement for needle insertion into the heart. Results indicate that automated insertion could substantially improve performance in some applications.

scholarly journals Investigating and Assessing the Dermoepidermal Junction with Multiphoton Microscopy and Deep Learning

2019 ◽  
Author(s):  
Mikko J. Huttunen ◽  
Radu Hristu ◽  
Adrian Dumitru ◽  
Mariana Costache ◽  
Stefan G. Stanciu
Keyword(s):  
Deep Learning ◽  
Human Error ◽  
Ex Vivo ◽  
Multiphoton Microscopy ◽  
Skin Cancer Screening ◽  
Dermoepidermal Junction ◽  
Optical Signals ◽  
Skin Cancers ◽  
Histopathological Image

AbstractHistopathological image analysis performed by a trained expert is currently regarded as the gold-standard in the case of many pathologies, including cancers. However, such approaches are laborious, time consuming and contain a risk for bias or human error. There is thus a clear need for faster, less intrusive and more accurate diagnostic solutions, requiring also minimal human intervention. Multiphoton Microscopy (MPM) can alleviate some of the drawbacks specific to traditional histopathology by exploiting various endogenous optical signals to provide virtual biopsies that reflect the architecture and composition of tissues, both in-vivo or ex-vivo. Here we show that MPM imaging of the dermoepidermal junction (DEJ) in unstained tissues provides useful cues for a histopathologist to identify the onset of non-melanoma skin cancers. Furthermore, we show that MPM images collected on the DEJ, besides being easy to interpret by a trained specialist, can be automatically classified into healthy and dysplastic classes with high precision using a Deep Learning method and existing pre-trained Convolutional Neural Networks. Our results suggest that Deep Learning enhanced MPM for in-vivo skin cancer screening could facilitate timely diagnosis and intervention, enabling thus more optimal therapeutic approaches.

scholarly journals Biopsy-free in vivo virtual histology of skin using deep learning

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Jingxi Li ◽  
Jason Garfinkel ◽  
Xiaoran Zhang ◽  
Di Wu ◽  
Yijie Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Ex Vivo ◽  
Normal Skin ◽  
Ground Truth ◽  
Skin Neoplasms ◽  
Cellular Level ◽  
Label Free ◽  
Virtual Histology

AbstractAn invasive biopsy followed by histological staining is the benchmark for pathological diagnosis of skin tumors. The process is cumbersome and time-consuming, often leading to unnecessary biopsies and scars. Emerging noninvasive optical technologies such as reflectance confocal microscopy (RCM) can provide label-free, cellular-level resolution, in vivo images of skin without performing a biopsy. Although RCM is a useful diagnostic tool, it requires specialized training because the acquired images are grayscale, lack nuclear features, and are difficult to correlate with tissue pathology. Here, we present a deep learning-based framework that uses a convolutional neural network to rapidly transform in vivo RCM images of unstained skin into virtually-stained hematoxylin and eosin-like images with microscopic resolution, enabling visualization of the epidermis, dermal-epidermal junction, and superficial dermis layers. The network was trained under an adversarial learning scheme, which takes ex vivo RCM images of excised unstained/label-free tissue as inputs and uses the microscopic images of the same tissue labeled with acetic acid nuclear contrast staining as the ground truth. We show that this trained neural network can be used to rapidly perform virtual histology of in vivo, label-free RCM images of normal skin structure, basal cell carcinoma, and melanocytic nevi with pigmented melanocytes, demonstrating similar histological features to traditional histology from the same excised tissue. This application of deep learning-based virtual staining to noninvasive imaging technologies may permit more rapid diagnoses of malignant skin neoplasms and reduce invasive skin biopsies.

Synergistic efficacy of dual PI3K-d/g inhibitor Duvelisib with Bcl2 inhibitor Venetoclax in Richter's Syndrome PDX models

Blood ◽  
2021 ◽  
Author(s):  
Andrea Iannello ◽  
Nicoletta Vitale ◽  
Silvia Coma ◽  
Francesca Arruga ◽  
Amy Chadburn ◽  
...  
Keyword(s):  
Ex Vivo ◽  
B Cell Lymphoma ◽  
Lymphocytic Leukemia ◽  
Tumor Growth Inhibition ◽  
Small Subset ◽  
Apoptotic Pathways ◽  
Novel Therapeutic Strategies ◽  
Pdx Models ◽  
Richter’S Syndrome

A small subset of cases of chronic lymphocytic leukemia undergoes transformation to diffuse large B-cell lymphoma, Richter's Syndrome (RS), which is associated with a poor prognosis. Conventional chemotherapy results in limited responses, underlining the need for novel therapeutic strategies. Here, we investigate the ex-vivo and in vivo efficacy of the dual PI3K-d/g inhibitor Duvelisib (Duv) and the Bcl-2 inhibitor Venetoclax (Ven) using four different RS-patient-derived xenograft (PDX) models. Ex-vivo exposure of RS cells to Duv, Ven or their combination results in variable apoptotic responses, in line with the expression levels of target proteins. While RS1316, IP867/17 and RS9737 cells express PI3K-d, PI3K-g and Bcl-2 and respond to the drugs, RS1050 cells, expressing very low levels of PI3K-g and lacking Bcl-2, are fully resistant. Moreover, the combination of these drugs is more effective than each agent alone. When tested in vivo, RS1316 and IP867/17 show the best tumor growth inhibition responses, with Duv/Ven combination leading to complete remission at the end of treatment. The synergistic effect of Duv and Ven relies on the crosstalk between PI3K and apoptotic pathways occurring at the GSK3β level. Indeed, inhibition of PI3K signaling by Duv results in GSK3β activation, leading to ubiquitination and subsequent degradation of both c-Myc and Mcl-1, making RS cells more sensitive to Bcl-2 inhibition by Ven. This work provides, for the first time, a proof-of-concept of the efficacy of dual targeting of PI3K-d/g and Bcl-2 in RS, opening for a Duv/Ven combination for these patients. Clinical studies in aggressive lymphomas, including RS, are underway (NCT03892044).

scholarly journals High-resolution wide-field human brain tumor margin detection and in vivo murine neuroimaging

2018 ◽  
Author(s):  
Derek Yecies ◽  
Orly Liba ◽  
Elliott SoRelle ◽  
Rebecca Dutta ◽  
Edwin Yuan ◽  
...  
Keyword(s):  
Brain Tumor ◽  
White Matter ◽  
Ex Vivo ◽  
Field Of View ◽  
Low Grade ◽  
Wide Field ◽  
Tumor Margin ◽  
Wide Field Of View ◽  
Margin Detection

AbstractCurrent in vivo neuroimaging techniques provide limited field of view or spatial resolution and often require exogenous contrast. These limitations prohibit detailed structural imaging across wide fields of view and hinder intraoperative tumor margin detection. Here we present a novel neuroimaging technique, speckle-modulating optical coherence tomography (SM-OCT), which allows us to image the brains of live mice and ex vivo human samples with unprecedented resolution and wide field of view using only endogenous contrast. The increased effective resolution provided by speckle elimination reveals white matter fascicles and cortical layer architecture in the brains of live mice. To our knowledge, the data reported herein represents the highest resolution imaging of murine white matter structure achieved in vivo across a wide field of view of several millimeters. When applied to an orthotopic murine glioblastoma xenograft model, SM-OCT readily identifies brain tumor margins with near single-cell resolution. SM-OCT of ex vivo human temporal lobe tissue reveals fine structures including cortical layers and myelinated axons. Finally, when applied to an ex vivo sample of a low-grade glioma resection margin, SM-OCT is able to resolve the brain tumor margin. Based on these findings, SM-OCT represents a novel approach for intraoperative tumor margin detection and in vivo neuroimaging.

The Role of Polyphenols in the Modulation of Plasma Non-Enzymatic Antioxidant Capacity (NEAC)

2012 ◽  
Vol 82 (3) ◽  
pp. 228-232 ◽  
Author(s):  
Mauro Serafini ◽  
Giuseppa Morabito
Keyword(s):  
Antioxidant Capacity ◽  
Dietary Intervention ◽  
Ex Vivo ◽  
The Body ◽  
Dietary Polyphenols ◽  
Enzymatic Antioxidant ◽  
Endogenous Antioxidant

Dietary polyphenols have been shown to scavenge free radicals, modulating cellular redox transcription factors in different in vitro and ex vivo models. Dietary intervention studies have shown that consumption of plant foods modulates plasma Non-Enzymatic Antioxidant Capacity (NEAC), a biomarker of the endogenous antioxidant network, in human subjects. However, the identification of the molecules responsible for this effect are yet to be obtained and evidences of an antioxidant in vivo action of polyphenols are conflicting. There is a clear discrepancy between polyphenols (PP) concentration in body fluids and the extent of increase of plasma NEAC. The low degree of absorption and the extensive metabolism of PP within the body have raised questions about their contribution to the endogenous antioxidant network. This work will discuss the role of polyphenols from galenic preparation, food extracts, and selected dietary sources as modulators of plasma NEAC in humans.

Antithrombotic Effects and Bleeding Time Prolongation with Synthetic Platelet GPIIb/llla Inhibitors in Animal Models of Platelet-Mediated Thrombosis

1994 ◽  
Vol 71 (01) ◽  
pp. 095-102 ◽  
Author(s):  
Désiré Collen ◽  
Hua Rong Lu ◽  
Jean-Marie Stassen ◽  
Ingrid Vreys ◽  
Tsunehiro Yasuda ◽  
...  
Keyword(s):  
Platelet Aggregation ◽  
Bleeding Time ◽  
Bolus Injection ◽  
Cell Injury ◽  
Ex Vivo ◽  
Thrombus Formation ◽  
Femoral Vein ◽  
Thrombotic Occlusion ◽  
Antithrombotic Effects

SummaryCyclic Arg-Gly-Asp (RGD) containing synthetic peptides such as L-cysteine, N-(mercaptoacetyl)-D-tyrosyl-L-arginylglycyl-L-a-aspartyl-cyclic (1→5)-sulfide, 5-oxide (G4120) and acetyl-L-cysteinyl-L-asparaginyl-L-prolyl-L-arginyl-glycyl-L-α-aspartyl-[0-methyltyrosyl]-L-arginyl-L-cysteinamide, cyclic 1→9-sulfide (TP9201) bind with high affinity to the platelet GPIIb/IIIa receptor.The relationship between antithrombotic effect, ex vivo platelet aggregation and bleeding time prolongation with both agents was studied in hamsters with a standardized femoral vein endothelial cell injury predisposing to platelet-rich mural thrombosis, and in dogs with a carotid arterial eversion graft inserted in the femoral artery. Intravenous administration of G4120 in hamsters inhibited in vivo thrombus formation with a 50% inhibitory bolus dose (ID50) of approximately 20 μg/kg, ex vivo ADP-induccd platelet aggregation with ID50 of 10 μg/kg, and bolus injection of 1 mg/kg prolonged the bleeding time from 38 ± 9 to 1,100 ± 330 s. Administration of TP9201 in hamsters inhibited in vivo thrombus formation with ID50 of 30 μg/kg, ex vivo platelet aggregation with an ID50 of 50 μg/kg and bolus injection of 1 mg/kg did not prolong the template bleeding time. In the dog eversion graft model, infusion of 100 μg/kg of G4120 over 60 min did not fully inhibit platelet-mediated thrombotic occlusion but was associated with inhibition of ADP-induccd ex vivo platelet aggregation and with prolongation of the template bleeding time from 1.3 ± 0.4 to 12 ± 2 min. Infusion of 300 μg/kg of TP9201 over 60 min completely prevented thrombotic occlusion, inhibited ex vivo platelet aggregation, but was not associated with prolongation of the template bleeding time.TP9201, unlike G4120, inhibits in vivo platelet-mediated thrombus formation without associated prolongation of the template bleeding time.

Sign in / Sign up

Export Citation Format

Share Document