Browsing by Author "Bagci, Ulas"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Advances for Managing Pancreatic Cystic Lesions: Integrating Imaging and AI Innovations
    (MDPI, 2024-12-22) Seyithanoglu, Deniz; Durak, Gorkem; Keles, Elif; Medetalibeyoglu, Alpay; Hong, Ziliang; Zhang, Zheyuan; Taktak, Yavuz B.; Cebeci, Timurhan; Tiwari, Pallavi; Velichko, Yuri S.; Yazici, Cemal; Tirkes, Temel; Miller, Frank H.; Keswani, Rajesh N.; Spampinato, Concetto; Wallace, Michael B.; Bagci, Ulas; Radiology and Imaging Sciences, School of Medicine
    Pancreatic cystic lesions (PCLs) represent a spectrum of non-neoplasms and neoplasms with varying malignant potential, posing significant challenges in diagnosis and management. While some PCLs are precursors to pancreatic cancer, others remain benign, necessitating accurate differentiation for optimal patient care. Conventional approaches to PCL management rely heavily on radiographic imaging, and endoscopic ultrasound (EUS) guided fine-needle aspiration (FNA), coupled with clinical and biochemical data. However, the observer-dependent nature of image interpretation and the complex morphology of PCLs can lead to diagnostic uncertainty and variability in patient management strategies. This review critically evaluates current PCL diagnosis and surveillance practices, showing features of the different lesions and highlighting the potential limitations of conventional methods. We then explore the potential of artificial intelligence (AI) to transform PCL management. AI-driven strategies, including deep learning algorithms for automated pancreas and lesion segmentation, and radiomics for analyzing heterogeneity, can improve diagnostic accuracy and risk stratification. These advanced techniques can provide more objective and reproducible assessments, aiding clinicians in decision-making regarding follow-up intervals and surgical interventions. Early results suggest that AI-driven methods can significantly improve patient outcomes by enabling earlier detection of high-risk lesions and reducing unnecessary procedures for benign cysts. Finally, this review emphasizes that AI-driven approaches could potentially reshape the landscape of PCL management, ultimately leading to improved pancreatic cancer prevention.
  • Thumbnail Image
    Item
    Design and Rationale for the Use of Magnetic Resonance Imaging Biomarkers to Predict Diabetes After Acute Pancreatitis in the Diabetes RElated to Acute Pancreatitis and Its Mechanisms Study: From the Type 1 Diabetes in Acute Pancreatitis Consortium
    (Wolters Kluwer, 2022) Tirkes, Temel; Chinchilli, Vernon M.; Bagci, Ulas; Parker, Jason G.; Zhao, Xuandong; Dasyam, Anil K.; Feranec, Nicholas; Grajo, Joseph R.; Shah, Zarine K.; Poullos, Peter D.; Spilseth, Benjamin; Zaheer, Atif; Xie, Karen L.; Wachsman, Ashley M.; Campbell-Thompson, Martha; Conwell, Darwin L.; Fogel, Evan L.; Forsmark, Christopher E.; Hart, Phil A.; Pandol, Stephen J.; Park, Walter G.; Pratley, Richard E.; Yazici, Cemal; Laughlin, Maren R.; Andersen, Dana K.; Serrano, Jose; Bellin, Melena D.; Yadav, Dhiraj; Type 1 Diabetes in Acute Pancreatitis Consortium (T1DAPC); Radiology and Imaging Sciences, School of Medicine
    This core component of the Diabetes RElated to Acute pancreatitis and its Mechanisms (DREAM) study will examine the hypothesis that advanced magnetic resonance imaging (MRI) techniques can reflect underlying pathophysiologic changes and provide imaging biomarkers that predict diabetes mellitus (DM) following acute pancreatitis (AP). A subset of participants in the DREAM study will enroll and undergo serial MRI examinations using a specific research protocol. We aim to differentiate at-risk individuals from those who remain euglycemic by identifying parenchymal features following AP. Performing longitudinal MRI will enable us to observe and understand the natural history of post-AP DM. We will compare MRI parameters obtained by interrogating tissue properties in euglycemic, prediabetic and incident diabetes subjects and correlate them with metabolic, genetic, and immunological phenotypes. Differentiating imaging parameters will be combined to develop a quantitative composite risk score. This composite risk score will potentially have the ability to monitor the risk of DM in clinical practice or trials. We will use artificial intelligence, specifically deep learning, algorithms to optimize the predictive ability of MRI. In addition to the research MRI, the DREAM study will also correlate clinical computerized tomography and MRI scans with DM development.
  • Thumbnail Image
    Item
    Quality Assurance of Computer-Aided Detection and Diagnosis in Colonoscopy
    (Elsevier, 2019) Vinsard, Daniela Guerrero; Mori, Yuichi; Misawa, Masashi; Kudo, Shin-ei; Rastogi, Amit; Bagci, Ulas; Rex, Douglas K.; Wallace, Michael B.; Medicine, School of Medicine
    Recent breakthroughs in artificial intelligence (AI), specifically via its emerging sub-field “Deep Learning,” have direct implications for computer-aided detection and diagnosis (CADe/CADx) for colonoscopy. AI is expected to have at least 2 major roles in colonoscopy practice; polyp detection (CADe) and polyp characterization (CADx). CADe has the potential to decrease polyp miss rate, contributing to improving adenoma detection, whereas CADx can improve the accuracy of colorectal polyp optical diagnosis, leading to reduction of unnecessary polypectomy of non-neoplastic lesions, potential implementation of a resect and discard paradigm, and proper application of advanced resection techniques. A growing number of medical-engineering researchers are developing both, CADe and CADx systems, some of which allow real-time recognition of polyps or in vivo identification of adenomas with over 90% accuracy. However, the quality of the developed AI systems as well as that of the study designs vary significantly, hence raising some concerns regarding the generalization of the proposed AI systems. Initial studies were conducted in an exploratory or retrospective fashion using stored images and likely overestimating the results. These drawbacks potentially hinder smooth implementation of this novel technology into colonoscopy practice. The aim of this article is to review both contributions and limitations in recent machine learning based CADe/CADx colonoscopy studies and propose some principles that should underlie system development and clinical testing.
  • Thumbnail Image
    Item
    Radiomics Boosts Deep Learning Model for IPMN Classification
    (Springer, 2023) Yao, Lanhong; Zhang, Zheyuan; Demir, Ugur; Keles, Elif; Vendrami, Camila; Agarunov, Emil; Bolan, Candice; Schoots, Ivo; Bruno, Marc; Keswani, Rajesh; Miller, Frank; Gonda, Tamas; Yazici, Cemal; Tirkes, Temel; Wallace, Michael; Spampinato, Concetto; Bagci, Ulas; Radiology and Imaging Sciences, School of Medicine
    Intraductal Papillary Mucinous Neoplasm (IPMN) cysts are pre-malignant pancreas lesions, and they can progress into pancreatic cancer. Therefore, detecting and stratifying their risk level is of ultimate importance for effective treatment planning and disease control. However, this is a highly challenging task because of the diverse and irregular shape, texture, and size of the IPMN cysts as well as the pancreas. In this study, we propose a novel computer-aided diagnosis pipeline for IPMN risk classification from multi-contrast MRI scans. Our proposed analysis framework includes an efficient volumetric self-adapting segmentation strategy for pancreas delineation, followed by a newly designed deep learning-based classification scheme with a radiomics-based predictive approach. We test our proposed decision-fusion model in multi-center data sets of 246 multi-contrast MRI scans and obtain superior performance to the state of the art (SOTA) in this field. Our ablation studies demonstrate the significance of both radiomics and deep learning modules for achieving the new SOTA performance compared to international guidelines and published studies (81.9% vs 61.3% in accuracy). Our findings have important implications for clinical decision-making. In a series of rigorous experiments on multi-center data sets (246 MRI scans from five centers), we achieved unprecedented performance (81.9% accuracy). The code is available upon publication.