المؤلفون: Ziogas, Ioannis, Alfalahi, Hessa, Khandoker, Ahsan H., Hadjileontiadis, Leontios J.

مصطلحات موضوعية: Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Signal Processing, Statistics - Machine Learning

الوصف: Self-supervised learning (SSL) for automated speech recognition in terms of its emotional content, can be heavily degraded by the presence noise, affecting the efficiency of modeling the intricate temporal and spectral informative structures of speech. Recently, SSL on large speech datasets, as well as new audio-specific SSL proxy tasks, such as, temporal and frequency masking, have emerged, yielding superior performance compared to classic approaches drawn from the image augmentation domain. Our proposed contribution builds upon this successful paradigm by introducing CochCeps-Augment, a novel bio-inspired masking augmentation task for self-supervised contrastive learning of speech representations. Specifically, we utilize the newly introduced bio-inspired cochlear cepstrogram (CCGRAM) to derive noise robust representations of input speech, that are then further refined through a self-supervised learning scheme. The latter employs SimCLR to generate contrastive views of a CCGRAM through masking of its angle and quefrency dimensions. Our experimental approach and validations on the emotion recognition K-EmoCon benchmark dataset, for the first time via a speaker-independent approach, features unsupervised pre-training, linear probing and fine-tuning. Our results potentiate CochCeps-Augment to serve as a standard tool in speech emotion recognition analysis, showing the added value of incorporating bio-inspired masking as an informative augmentation task for self-supervision. Our code for implementing CochCeps-Augment will be made available at: https://github.com/GiannisZgs/CochCepsAugmentTest.
Comment: 5 pages, 1 figure Accepted in IEEE ICASSP 2024 Workshops - Self-Supervision in Audio, Speech, and Beyond

الوصول الحر: http://arxiv.org/abs/2402.06923Test

المؤلفون: Wu, Wei, Ukita, Rei, Patel, Yatrik, Cortelli, Michael, Trinh, Vincent, Ziogas, Ioannis, Francois, Sean, Mentz, Meredith, Cardwell, Nancy, Talackine, Jennifer, Grogan, William, Stokes, John, Lee, Youngmin, Kim, Jinho, Alexopoulos, Sophoclis, Bacchetta, Matthew

المصدر: Hepatology. 78(3)

مصطلحات موضوعية: Humans, Swine, Animals, Liver, Liver Transplantation, Bile, Perfusion, Organ Preservation

الوصف: BACKGROUND AND AIMS: The scarcity of suitable donor livers highlights a continuing need for innovation to recover organs with reversible injuries in liver transplantation. APPROACH AND RESULTS: Explanted human donor livers (n = 5) declined for transplantation were supported using xenogeneic cross-circulation of whole blood between livers and xeno-support swine. Livers and swine were assessed over 24 hours of xeno-support. Livers maintained normal global appearance, uniform perfusion, and preservation of histologic and subcellular architecture. Oxygen consumption increased by 75% ( p = 0.16). Lactate clearance increased from -0.4 ± 15.5% to 31.4 ± 19.0% ( p = 0.02). Blinded histopathologic assessment demonstrated improved injury scores at 24 hours compared with 12 hours. Vascular integrity and vasoconstrictive function were preserved. Bile volume and cholangiocellular viability markers improved for all livers. Biliary structural integrity was maintained. CONCLUSIONS: Xenogeneic cross-circulation provided multisystem physiological regulation of ex vivo human livers that enabled functional rehabilitation, histopathologic recovery, and improvement of viability markers. We envision xenogeneic cross-circulation as a complementary technique to other organ-preservation technologies in the recovery of marginal donor livers or as a research tool in the development of advanced bioengineering and pharmacologic strategies for organ recovery and rehabilitation.

وصف الملف: application/pdf

الوصول الحر: https://escholarship.org/uc/item/2qc2c8trTest

المؤلفون: Pullar-Strecker, Zac, Chang, Xinglong, Brydon, Liam, Ziogas, Ioannis, Dost, Katharina, Wicker, Jörg

مصطلحات موضوعية: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

الوصف: Running complex sets of machine learning experiments is challenging and time-consuming due to the lack of a unified framework. This leaves researchers forced to spend time implementing necessary features such as parallelization, caching, and checkpointing themselves instead of focussing on their project. To simplify the process, in this paper, we introduce Memento, a Python package that is designed to aid researchers and data scientists in the efficient management and execution of computationally intensive experiments. Memento has the capacity to streamline any experimental pipeline by providing a straightforward configuration matrix and the ability to concurrently run experiments across multiple threads. A demonstration of Memento is available at: https://wickerlab.org/publication/mementoTest.

الوصول الحر: http://arxiv.org/abs/2304.09175Test

المؤلفون: Rauf, Muhammad, Ziogas, Ioannis, Sealock, Julia, Davis, Lea, Izzy, Manhal, Alexopoulos, Sophoclis, Matsuoka, Lea

مصطلحات موضوعية: Liver transplantation (LT), case series, immunosuppression, malignancy, pancreatic adenocarcinoma

الوصف: BACKGROUND: Malignancy is one of the known leading causes of death among long-term liver transplantation (LT) survivors. Pancreatic cancer has an incidence of 7.6/100,000 in North America and constitutes a diagnostic challenge post-LT. METHODS: This is a single-center, retrospective review of the electronic health records (EHRs) of LT recipients with pancreatic adenocarcinoma (1990-2019). The prevalence of pancreatic adenocarcinoma in our institutional non-LT population was assessed using an institutional de-identified database (Synthetic Derivative). RESULTS: Six out of 2,232 (0.27%) LT recipients were diagnosed with pancreatic adenocarcinoma. Median age at diagnosis was 66.0 years (IQR, 57.8-71.8 years). Median time from LT to pancreatic adenocarcinoma diagnosis was 8.9 years (IQR, 4.7-16.2 years), the median size on imaging was 3.2 cm (IQR, 3.1-4.7 cm), and all tumors were located on the head of the pancreas. Three patients underwent surgical resection (one with adjuvant chemotherapy), two underwent palliative care, and one palliative chemotherapy with gemcitabine and abraxane. Over a median follow-up of 220.5 days (IQR, 144.8-399.5 days), all six patients died due to disease progression (100%). Pancreatic adenocarcinoma was diagnosed in 5,033 out of 2,484,772 (0.20%) individuals in the Synthetic Derivative. CONCLUSIONS: Our findings identified an increased incidence of pancreatic adenocarcinoma following LT compared to the general population.

وصف الملف: application/pdf

الوصول الحر: https://escholarship.org/uc/item/09x8v7b2Test

المؤلفون: Kakos, Christos, Ziogas, Ioannis, Tsoulfas, Georgios, Alexopoulos, Sophoclis

المصدر: World Journal of Transplantation. 11(9)

مصطلحات موضوعية: Biliary atresia, Kasai procedure, Liver transplantation, Native liver survival, Portoenterostomy

الوصف: Kasai procedure (KP) and liver transplantation (LT) represent the only therapeutic options for patients with biliary atresia (BA), the most common indication for LT in the pediatric population. However, KP represents by no means a radical option but rather a bridging one, as nearly all patients will finally require a liver graft. More and more experts in the field of transplant surgery propose that maybe it is time for a paradigm change in BA treatment and abandon KP as transplantation seems inevitable. Inadequacy of organs yet makes this option currently not feasible, so it seems useful to find ways to maximize the efficacy of KP. In previous decades, multiple studies tried to identify these factors which opt for better results, but in general, outcomes of KP have not improved to the level that was anticipated. This review provides the framework of conditions which favor native liver survival after KP and the ones which optimize a positive LT outcome. Strategies of transition of care at the right time are also presented, as transplantation plays a key role in the surgical treatment of BA. Future studies and further organization in the transplant field will allow for greater organ availability and better outcomes to be achieved for BA patients.

وصف الملف: application/pdf

الوصول الحر: https://escholarship.org/uc/item/20k7p9z0Test

المؤلفون: Ziogas, Ioannis, author

الإتاحة: https://doi.org/10.1093/oso/9780198845140.001.0001Test

المؤلفون: Ziogas, Ioannis, Lamprou, Charalampos, Hadjileontiadis, Leontios J.

المساهمون: Khalifa University of Science and Technology, European Union’s HORIZON-RIA Program ‘‘AI-PROGNOSIS’’

المصدر: IEEE Access ; volume 11, page 114459-114474 ; ISSN 2169-3536

مصطلحات موضوعية: General Engineering, General Materials Science, General Computer Science, Electrical and Electronic Engineering

الإتاحة: https://doi.org/10.1109/access.2023.3324987Test
http://xplorestaging.ieee.org/ielx7/6287639/10005208/10286508.pdf?arnumber=10286508Test

المؤلفون: Papadakis, Harris, Panagiotakis, Costas, Fragopoulou, Paraskevi, Chalkiadakis, Georgios, Streviniotis, Errikos, Ziogas, Ioannis-Panagiotis, Koutsmanis, Michail, Bariamis, Panagiotis

المصدر: Computer Science & Information Systems; Jun2024, Vol. 21 Issue 3, p923-946, 24p

مستخلص: The paper presents Visit Planner (ViP), a mobile application prototype that provides a solution to the challenging tourist trip design problem. ViP follows a holistic approach offering personalized recommendations for Points of Interest (POIs) based on preferences either explicitly collected by the application, or inferred by the users' ongoing interaction with the system. ViP proposes to the final user, a trajectory of POIs calculated using an Expectation Maximization method that maximizes user satisfaction taking into consideration a variety of time and spatial constraints for both users and POIs. Additionally, POIs are divided into categories, so that a certain number of POIs from each category to be included in the final itinerary. The application is implemented as a user-interactive system that allows the flexibility for easy content adaptation and facilitates management of content and services by the user. The prototype has been implemented for Android-based smartphones, on an open application environment, using standard communication protocols and open database technology. Currently, it is applied to the city of Agios Nikolaos in Crete, and is available for download from Google play. [ABSTRACT FROM AUTHOR]

: Copyright of Computer Science & Information Systems is the property of ComSIS Consortium and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

المؤلفون: Kokkinakis, Stamatios¹ (AUTHOR) stamatioskokkinakis@gmail.com, Ziogas, Ioannis A.² (AUTHOR) ioannis.ziogas@cuanschutz.edu, Llaque Salazar, Jose D.² (AUTHOR) jose.llaquesalazar@cuanschutz.edu, Moris, Dimitrios P.³ (AUTHOR) dimitrios.moris@duke.edu, Tsoulfas, Georgios⁴ (AUTHOR) tsoulfasg@auth.gr

المصدر: Cancers. May2024, Vol. 16 Issue 9, p1645. 27p.

مصطلحات موضوعية: *LIVER tumors, *RISK assessment, *PREDICTION models, *ARTIFICIAL intelligence, *COLORECTAL cancer, *METASTASIS, *SURGICAL complications, *PROGRESSION-free survival, *DISEASE relapse, *MACHINE learning, *OVERALL survival

مستخلص: Simple Summary: Interest in stratification of prognosis for patients with colorectal liver metastases is growing. Numerous clinical prediction models have been developed for this purpose in recent years, either with the aid of traditional statistical methods or by using the aid of artificial intelligence techniques. We herein provide an overview of relevant studies discussing the different types of predictors proven to be of importance and critically assess the variable model development and validation techniques as well as the performance of the reported models. Colorectal liver metastasis (CRLM) is a disease entity that warrants special attention due to its high frequency and potential curability. Identification of "high-risk" patients is increasingly popular for risk stratification and personalization of the management pathway. Traditional regression-based methods have been used to derive prediction models for these patients, and lately, focus has shifted to artificial intelligence-based models, with employment of variable supervised and unsupervised techniques. Multiple endpoints, like overall survival (OS), disease-free survival (DFS) and development or recurrence of postoperative complications have all been used as outcomes in these studies. This review provides an extensive overview of available clinical prediction models focusing on the prognosis of CRLM and highlights the different predictor types incorporated in each model. An overview of the modelling strategies and the outcomes chosen is provided. Specific patient and treatment characteristics included in the models are discussed in detail. Model development and validation methods are presented and critically appraised, and model performance is assessed within a proposed framework. [ABSTRACT FROM AUTHOR]

المؤلفون: Ziogas, Ioannis A, Hills-Dunlap, Jonathan L, Corkum, Kristine S, Cost, Nicholas G, Gosain, Ankush, Roach, Jonathan P

المصدر: J Surg Res ; ISSN:1095-8673 ; Volume:301

مصطلحات موضوعية: Adrenalectomy, Adrenocortical carcinoma, National Cancer Database, Pediatric adrenal tumors, Pediatric cancer

الوصف: Adrenocortical carcinoma (ACC) is a rare but aggressive pediatric endocrine tumor. However, there is no recent US national report on the management or outcomes of pediatric ACC. We aimed to examine the clinical characteristics, current management strategies, and outcomes of pediatric ACC.

العلاقة: https://doi.org/10.1016/j.jss.2024.04.086Test; https://pubmed.ncbi.nlm.nih.gov/38925097Test

الإتاحة: https://doi.org/10.1016/j.jss.2024.04.086Test
https://pubmed.ncbi.nlm.nih.gov/38925097Test