IU Indianapolis ScholarWorks :: Browsing by Author "Gruionu, Gabriel"

Browsing by Author "Gruionu, Gabriel"

Now showing 1 - 10 of 10

Assessment of Deep Learning Methods for Differentiating Autoimmune Disorders in Ultrasound Images
(Medical University Publishing House Craiova, 2021) Vasile, Corina Maria; Udriştoiu, Anca Loredana; Ghenea, Alice Elena; Padureanu, Vlad; Udriştoiu, Ştefan; Gruionu, Lucian Gheorghe; Gruionu, Gabriel; Iacob, Andreea Valentina; Popescu, Mihaela; Medicine, School of Medicine
At present, deep learning becomes an important tool in medical image analysis, with good performance in diagnosing, pattern detection, and segmentation. Ultrasound imaging offers an easy and rapid method to detect and diagnose thyroid disorders. With the help of a computer-aided diagnosis (CAD) system based on deep learning, we have the possibility of real-time and non-invasive diagnosing of thyroidal US images. This paper proposed a study based on deep learning with transfer learning for differentiating the thyroidal ultrasound images using image pixels and diagnosis labels as inputs. We trained, assessed, and compared two pre-trained models (VGG-19 and Inception v3) using a dataset of ultrasound images consisting of 2 types of thyroid ultrasound images: autoimmune and normal. The training dataset consisted of 615 thyroid ultrasound images, from which 415 images were diagnosed as autoimmune, and 200 images as normal. The models were assessed using a dataset of 120 images, from which 80 images were diagnosed as autoimmune, and 40 images diagnosed as normal. The two deep learning models obtained very good results, as follows: the pre-trained VGG-19 model obtained 98.60% for the overall test accuracy with an overall specificity of 98.94% and overall sensitivity of 97.97%, while the Inception v3 model obtained 96.4% for the overall test accuracy with an overall specificity of 95.58% and overall sensitivity of 95.58.
Deep Learning Algorithm for the Confirmation of Mucosal Healing in Crohn’s Disease, Based on Confocal Laser Endomicroscopy Images
(2021) Udristoiu, Anca Loredana; Stefanescu, Daniela; Gruionu, Gabriel; Gruionu, Lucian Gheorghe; Iacob, Andreea Valentina; Karstensen, John Gasdal; Vilman, Peter; Saftoiu, Adrian; Medicine, School of Medicine
Background and Aims: Mucosal healing (MH) is associated with a stable course of Crohn’s disease (CD) which can be assessed by confocal laser endomicroscopy (CLE). To minimize the operator’s errors and automate assessment of CLE images, we used a deep learning (DL) model for image analysis. We hypothesized that DL combined with convolutional neural networks (CNNs) and long short-term memory (LSTM) can distinguish between normal and inflamed colonic mucosa from CLE images. Methods: The study included 54 patients, 32 with known active CD, and 22 control patients (18 CD patients with MH and four normal mucosa patients with no history of inflammatory bowel diseases). We designed and trained a deep convolutional neural network to detect active CD using 6,205 endomicroscopy images classified as active CD inflammation (3,672 images) and control mucosal healing or no inflammation (2,533 images). CLE imaging was performed on four colorectal areas and the terminal ileum. Gold standard was represented by the histopathological evaluation. The dataset was randomly split in two distinct training and testing datasets: 80% data from each patient were used for training and the remaining 20% for testing. The training dataset consists of 2,892 images with inflammation and 2,189 control images. The testing dataset consists of 780 images with inflammation and 344 control images of the colon. We used a CNN-LSTM model with four convolution layers and one LSTM layer for automatic detection of MH and CD diagnosis from CLE images. Results: CLE investigation reveals normal colonic mucosa with round crypts and inflamed mucosa with irregular crypts and tortuous and dilated blood vessels. Our method obtained a 95.3% test accuracy with a specificity of 92.78% and a sensitivity of 94.6%, with an area under each receiver operating characteristic curves of 0.98. Conclusions: Using machine learning algorithms on CLE images can successfully differentiate between inflammation and normal ileocolonic mucosa and can be used as a computer aided diagnosis for CD. Future clinical studies with a larger patient spectrum will validate our results and improve the CNN-SSTM model.
Experimental and theoretical model of microvascular network remodeling and blood flow redistribution following minimally invasive microvessel laser ablation
(Springer Nature, 2024-04-16) Gruionu, Gabriel; Baish, James; McMahon, Sean; Blauvelt, David; Gruionu, Lucian G.; Lenco, Mara Onita; Vakoc, Benjamin J.; Padera, Timothy P.; Munn, Lance L.; Medicine, School of Medicine
Overly dense microvascular networks are treated by selective reduction of vascular elements. Inappropriate manipulation of microvessels could result in loss of host tissue function or a worsening of the clinical problem. Here, experimental, and computational models were developed to induce blood flow changes via selective artery and vein laser ablation and study the compensatory collateral flow redistribution and vessel diameter remodeling. The microvasculature was imaged non-invasively by bright-field and multi-photon laser microscopy, and optical coherence tomography pre-ablation and up to 30 days post-ablation. A theoretical model of network remodeling was developed to compute blood flow and intravascular pressure and identify vessels most susceptible to changes in flow direction. The skin microvascular remodeling patterns were consistent among the five specimens studied. Significant remodeling occurred at various time points, beginning as early as days 1–3 and continuing beyond day 20. The remodeling patterns included collateral development, venous and arterial reopening, and both outward and inward remodeling, with variations in the time frames for each mouse. In a representative specimen, immediately post-ablation, the average artery and vein diameters increased by 14% and 23%, respectively. At day 20 post-ablation, the maximum increases in arterial and venous diameters were 2.5× and 3.3×, respectively. By day 30, the average artery diameter remained 11% increased whereas the vein diameters returned to near pre-ablation values. Some arteries regenerated across the ablation sites via endothelial cell migration, while veins either reconnected or rerouted flow around the ablation site, likely depending on local pressure driving forces. In the intact network, the theoretical model predicts that the vessels that act as collaterals after flow disruption are those most sensitive to distant changes in pressure. The model results correlate with the post-ablation microvascular remodeling patterns.
Experimental and Theoretical Model of Single Vessel Minimally Invasive Micro-Laser Ablation: Inducing Microvascular Network Remodeling and Blood Flow Redistribution Without Compromising Host Tissue Function
(Research Square, 2023-12-18) Gruionu, Gabriel; Baish, James; McMahon, Sean; Blauvelt, David; Gruionu, Lucian G.; Lenco, Mara Onita; Vakoc, Benjamin J.; Padera, Timothy P.; Munn, Lance L.; Medicine, School of Medicine
Overly dense microvascular networks are treated by selective reduction of vascular elements. Inappropriate manipulation of microvessels could result in loss of host tissue function or a worsening of the clinical problem. Here, experimental, and computational models were developed to induce blood flow changes via selective artery and vein laser ablation and study the compensatory collateral flow redistribution and vessel diameter remodeling. The microvasculature was imaged non-invasively by bright-field and multi-photon laser microscopy, and Optical Coherence Tomography pre-ablation and up to 30 days post-ablation. A theoretical model of network remodeling was developed to compute blood flow and intravascular pressure and identify vessels most susceptible to changes in flow direction. The skin microvascular remodeling patterns were consistent among the five specimens studied. Significant remodeling occurred at various time points, beginning as early as days 1-3 and continuing beyond day 20. The remodeling patterns included collateral development, venous and arterial reopening, and both outward and inward remodeling, with variations in the time frames for each mouse. In a representative specimen, immediately post-ablation, the average artery and vein diameters increased by 14% and 23%, respectively. At day 20 post-ablation, the maximum increases in arterial and venous diameters were 2.5x and 3.3x, respectively. By day 30, the average artery diameter remained 11% increased whereas the vein diameters returned to near pre-ablation values. Some arteries regenerated across the ablation sites via endothelial cell migration, while veins either reconnected or rerouted flow around the ablation site, likely depending on local pressure driving forces. In the intact network, the theoretical model predicts that the vessels that act as collaterals after flow disruption are those most sensitive to distant changes in pressure. The model results match the post-ablation microvascular remodeling patterns.
Feasibility of a lung airway navigation system using fiber-Bragg shape sensing and artificial intelligence for early diagnosis of lung cancer
(Public Library of Science, 2022-12-07) Gruionu, Lucian Gheorghe; Udriștoiu, Anca Loredana; Iacob , Andreea Valentina; Constantinescu, Cătălin; Stan, Răzvan; Gruionu, Gabriel; Medicine, School of Medicine
Currently early diagnosis of malignant lesions at the periphery of lung parenchyma requires guidance of the biopsy needle catheter from the bronchoscope into the smaller peripheral airways via harmful X-ray radiation. Previously, we developed an image-guided system, iMTECH which uses electromagnetic tracking and although it increases the precision of biopsy collection and minimizes the use of harmful X-ray radiation during the interventional procedures, it only traces the tip of the biopsy catheter leaving the remaining catheter untraceable in real time and therefore increasing image registration error. To address this issue, we developed a shape sensing guidance system containing a fiber-Bragg grating (FBG) catheter and an artificial intelligence (AI) software, AIrShape to track and guide the entire biopsy instrument inside the lung airways, without radiation or electromagnetic navigation. We used a FBG fiber with one central and three peripheral cores positioned at 120° from each other, an array of 25 draw tower gratings with 1cm/3nm spacing, 2 mm grating length, Ormocer-T coating, and a total outer diameter of 0.2 mm. The FBG fiber was placed in the working channel of a custom made three-lumen catheter with a tip bending mechanism (FBG catheter). The AIrShape software determines the position of the FBG catheter by superimposing its position to the lung airway center lines using an AI algorithm. The feasibility of the FBG system was tested in an anatomically accurate lung airway model and validated visually and with the iMTECH platform. The results prove a viable shape-sensing hardware and software navigation solution for flexible medical instruments to reach the peripheral airways. During future studies, the feasibility of FBG catheter will be tested in pre-clinical animal models.
Finite Element Analysis of a Novel Aortic Valve Stent
(Medical University Publishing House Craiova, 2020-09-30) Castravete, Ştefan; Mazilu, Dumitru; Gruionu, Lucian Gheorghe; Militaru, Cristian; Militaru, Sebastian; UdriŞtoiu, Anca-Loredana; Iacob, Andreea Valentina; Gruionu, Gabriel; Medicine, School of Medicine
Worldwide, one of the leading causes of death for patients with cardiovascular disease is aortic valve failure or insufficiency as a result of calcification and cardiovascular disease. The surgical treatment consists of repair or total replacement of the aortic valve. Artificial aortic valve implantation via a percutaneous or endovascular procedure is the minimally invasive alternative to open chest surgery, and the only option for high-risk or older patients. Due to the complex anatomical location between the left ventricle and the aorta, there are still engineering design optimization challenges which influence the long-term durability of the valve. In this study we developed a computer model and performed a numerical analysis of an original self-expanding stent for transcatheter aortic valve in order to optimize its design and materials. The study demonstrates the current valve design could be a good alternative to the existing commercially available valve devices.
Heart Rate Variability Parameters Indicate Altered Autonomic Tone in Patients with COVID‐19
(Wiley, 2022) Gruionu, Gabriel; Gupta, Anita; Rattin, Megan; Nowak, Thomas V.; Ward, Matthew; Everett, Thomas H.; Medicine, School of Medicine
The COVID‐19 disease induces long term heart health complications and may induce autonomic nervous system dysfunction. Heart Rate Variability (HRV) is a measure of sympathetic (SNS) and parasympathetic (PNS) control of heart function. Recently, studies have shown that HRV analysis may be used as a predictor of COVID‐19 symptoms and correlates with progression of the disease. We aimed to uncover the interplay between SNS and PNS in hospitalized COVID‐19 patients at the time of admission and compare it with similar measurements in healthy patients (no comorbidities) and patients with cardiovascular disease. We hypothesized that COVID‐19 would induce autonomic dysfunction similar to patients with cardiovascular disease (CVD). ECG telemetry recordings of 30‐60 minutes in duration were acquired from patients that were admitted to Indiana University Health system hospitals for either COVID‐19 complications or for complications associated with cardiovascular disease (CVD) states (arrhythmia, heart failure, coronary artery disease). In addition, 20‐minute ECG Lead I recordings were obtained from healthy volunteers with no associated comorbidities. HRV parameters were calculated during sinus rhythm in the time, frequency, and nonlinear domains from the ECG telemetry recordings. The patient population was composed of 50 COVID‐19 patients (average age 63, range 26‐94), 32 healthy (average age 32.7, range 17‐69) and 49 patients with cardiovascular disease (average age 65.4, range 30‐88) as control groups. The COVID‐19 group had a higher percentage of patients with BMI>30 (obese) than the control groups (55% vs 36%). Also, the COVID‐19 and CVD patients had significantly higher heart rate and time‐domain HRV parameters (including SDRR, RMSSD, SDSD) and SD1 in the non‐linear domain when compared to healthy patients (88.8±53.0 and 87.9±55.2 vs 49.5±31.3, p<0.01). In the frequency domain, the LF/HF ratio was significantly lower in the COVID and CVD groups compared to healthy controls (0.5±0.76 and 0.55±0.50 vs 1.05±0.96, p<0.01). COVID‐19 patients have significant HRV alterations which suggest increased vagal tone than in healthy volunteers but similar to patients with severe cardiovascular disease comorbidities. Even though the COVID patients had an increased heart rate, the results of the HRV analysis indicate increased vagal tone which would support autonomic nervous system dysfunction in these patients.
Image Fusion Involving Real-Time Transabdominal or Endoscopic Ultrasound for Gastrointestinal Malignancies: Review of Current and Future Applications
(MDPI, 2022-12-19) Singh, Ben S.; Cazacu, Irina M.; Deza, Carlos A.; Rigaud, Bastien S.; Saftoiu, Adrian; Gruionu, Gabriel; Guionu, Lucian; Brock, Kristy K.; Koay, Eugene J.; Herman, Joseph M.; Bhutani, Manoop S.; Medicine, School of Medicine
Image fusion of CT, MRI, and PET with endoscopic ultrasound and transabdominal ultrasound can be promising for GI malignancies as it has the potential to allow for a more precise lesion characterization with higher accuracy in tumor detection, staging, and interventional/image guidance. We conducted a literature review to identify the current possibilities of real-time image fusion involving US with a focus on clinical applications in the management of GI malignancies. Liver applications have been the most extensively investigated, either in experimental or commercially available systems. Real-time US fusion imaging of the liver is gaining more acceptance as it enables further diagnosis and interventional therapy of focal liver lesions that are difficult to visualize using conventional B-mode ultrasound. Clinical studies on EUS guided image fusion, to date, are limited. EUS-CT image fusion allowed for easier navigation and profiling of the target tumor and/or surrounding anatomical structure. Image fusion techniques encompassing multiple imaging modalities appear to be feasible and have been observed to increase visualization accuracy during interventional and diagnostic applications.
Intelligent Diagnosis of Thyroid Ultrasound Imaging Using an Ensemble of Deep Learning Methods
(MDPI, 2021-04-19) Vasile, Corina Maria; Udriștoiu, Anca Loredana; Ghenea, Alice Elena; Popescu, Mihaela; Gheonea, Cristian; Niculescu, Carmen Elena; Ungureanu, Anca Marilena; Udriștoiu, Ștefan; Drocaş, Andrei Ioan; Gruionu, Lucian Gheorghe; Gruionu, Gabriel; Iacob, Andreea Valentina; Alexandru, Dragoş Ovidiu; Medicine, School of Medicine
Background and Objectives: At present, thyroid disorders have a great incidence in the worldwide population, so the development of alternative methods for improving the diagnosis process is necessary. Materials and Methods: For this purpose, we developed an ensemble method that fused two deep learning models, one based on convolutional neural network and the other based on transfer learning. For the first model, called 5-CNN, we developed an efficient end-to-end trained model with five convolutional layers, while for the second model, the pre-trained VGG-19 architecture was repurposed, optimized and trained. We trained and validated our models using a dataset of ultrasound images consisting of four types of thyroidal images: autoimmune, nodular, micro-nodular, and normal. Results: Excellent results were obtained by the ensemble CNN-VGG method, which outperformed the 5-CNN and VGG-19 models: 97.35% for the overall test accuracy with an overall specificity of 98.43%, sensitivity of 95.75%, positive and negative predictive value of 95.41%, and 98.05%. The micro average areas under each receiver operating characteristic curves was 0.96. The results were also validated by two physicians: an endocrinologist and a pediatrician. Conclusions: We proposed a new deep learning study for classifying ultrasound thyroidal images to assist physicians in the diagnosis process.
Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model
(PLOS, 2021-06-28) Udriştoiu, Anca Loredana; Cazacu, Irina Mihaela; Gruionu, Lucian Gheorghe; Gruionu, Gabriel; Iacob, Andreea Valentina; Burtea, Daniela Elena; Ungureanu, Bogdan Silviu; Costache, Mădălin Ionuţ; Constantin, Alina; Popescu, Carmen Florina; Udriştoiu, Ştefan; Săftoiu, Adrian; Medicine, School of Medicine
Differential diagnosis of focal pancreatic masses is based on endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA/FNB). Several imaging techniques (i.e. gray-scale, color Doppler, contrast-enhancement and elastography) are used for differential diagnosis. However, diagnosis remains highly operator dependent. To address this problem, machine learning algorithms (MLA) can generate an automatic computer-aided diagnosis (CAD) by analyzing a large number of clinical images in real-time. We aimed to develop a MLA to characterize focal pancreatic masses during the EUS procedure. The study included 65 patients with focal pancreatic masses, with 20 EUS images selected from each patient (grayscale, color Doppler, arterial and venous phase contrast-enhancement and elastography). Images were classified based on cytopathology exam as: chronic pseudotumoral pancreatitis (CPP), neuroendocrine tumor (PNET) and ductal adenocarcinoma (PDAC). The MLA is based on a deep learning method which combines convolutional (CNN) and long short-term memory (LSTM) neural networks. 2688 images were used for training and 672 images for testing the deep learning models. The CNN was developed to identify the discriminative features of images, while a LSTM neural network was used to extract the dependencies between images. The model predicted the clinical diagnosis with an area under curve index of 0.98 and an overall accuracy of 98.26%. The negative (NPV) and positive (PPV) predictive values and the corresponding 95% confidential intervals (CI) are 96.7%, [94.5, 98.9] and 98.1%, [96.81, 99.4] for PDAC, 96.5%, [94.1, 98.8], and 99.7%, [99.3, 100] for CPP, and 98.9%, [97.5, 100] and 98.3%, [97.1, 99.4] for PNET. Following further validation on a independent test cohort, this method could become an efficient CAD tool to differentiate focal pancreatic masses in real-time.

Browsing by Author "Gruionu, Gabriel"

Results Per Page

Sort Options