Browsing by Author "Velichko, Yuri S."

Now showing 1 - 3 of 3
  • 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
    Paradoxical Response to Neoadjuvant Therapy in Undifferentiated Pleomorphic Sarcoma: Increased Tumor Size on MRI Associated with Favorable Pathology
    (MDPI, 2025-02-27) Goreish, Mariam H.; Gennaro, Nicolò; Perronne, Laetitia; Durak, Gorkem; Borhani, Amir A.; Savas, Hatice; Kelahan, Linda; Avery, Ryan; Subedi, Kamal; Trabzonlu, Tugce Agirlar; Bagci, Ulas; Turkbey, Baris; Bakas, Spyridon; Sachdev, Sean; Sumagin, Ronen; Alexiev, Borislav A.; de Viveiros, Pedro Hermida; Pollack, Seth M.; Velichko, Yuri S.; Pathology and Laboratory Medicine, School of Medicine
    Background/Objectives: To correlate size changes in undifferentiated pleomorphic sarcoma (UPS) on magnetic resonance imaging (MRI) after neoadjuvant chemoradiation therapy (nCRT) with pathological response, risk of local recurrence, and therapeutic regimens. Methods: This retrospective study analyzed clinical, pathological, and imaging data from 39 biopsy-proven UPS subjects. Four readers measured the tumor dimensions before and after nCRT, including two perpendicular axial diameters and the longest coronal/sagittal diameter. Three cross-sectional areas and bounding volume were also calculated. Responders (pR) were defined as having ≤10% viable cells and non-responders (pNR) as having more. Inter-reader agreement was evaluated using Kendall's concordance coefficient. Changes in tumor size were compared between pR and pNR using one-way ANOVA and Tukey's HSD test for multiple comparisons of means. Results: pR showed a greater increase in size across all measurements compared to pNR. For the longest axial diameter, the mean increase was 30% ± 35% for pR and 14% ± 31% for pNR, with a mean difference (pR-pNR) of 16% (95% CI: 6-27%, p = 0.003). In tumors treated with radiotherapy alone, pR exhibited larger size increases in all dimensions compared to pNR. In contrast, in the chemoradiation group, pR showed a slight increase, while pNR generally shrank, although these differences did not reach statistical significance. Notably, pNR with local recurrence exhibited a reduction in all tumor dimensions compared to pNR without local recurrence. Conclusions: This exploratory study suggests that tumor size changes may predict pathological response and local recurrence after nCRT in UPS; however, the small sample size limits the generalizability of these findings.
  • Thumbnail Image
    Item
    The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI
    (ArXiv, 2023-06-01) Moawad, Ahmed W.; Janas, Anastasia; Baid, Ujjwal; Ramakrishnan, Divya; Jekel, Leon; Krantchev, Kiril; Moy, Harrison; Saluja, Rachit; Osenberg, Klara; Wilms, Klara; Kaur, Manpreet; Avesta, Arman; Cassinelli Pedersen, Gabriel; Maleki, Nazanin; Salimi, Mahdi; Merkaj, Sarah; von Reppert, Marc; Tillmans, Niklas; Lost, Jan; Bousabarah, Khaled; Holler, Wolfgang; Lin, MingDe; Westerhoff, Malte; Maresca, Ryan; Link, Katherine E.; Tahon, Nourel Hoda; Marcus, Daniel; Sotiras, Aristeidis; LaMontagne, Pamela; Chakrabarty, Strajit; Teytelboym, Oleg; Youssef, Ayda; Nada, Ayaman; Velichko, Yuri S.; Gennaro, Nicolo; Connectome Students; Group of Annotators; Cramer, Justin; Johnson, Derek R.; Kwan, Benjamin Y. M.; Petrovic, Boyan; Patro, Satya N.; Wu, Lei; So, Tiffany; Thompson, Gerry; Kam, Anthony; Guzman Perez-Carrillo, Gloria; Lall, Neil; Group of Approvers; Albrecht, Jake; Anazodo, Udunna; Lingaru, Marius George; Menze, Bjoern H.; Wiestler, Benedikt; Adewole, Maruf; Anwar, Syed Muhammad; Labella, Dominic; Li, Hongwei Bran; Iglesias, Juan Eugenio; Farahani, Keyvan; Eddy, James; Bergquist, Timothy; Chung, Verena; Shinohara, Russel Takeshi; Dako, Farouk; Wiggins, Walter; Reitman, Zachary; Wang, Chunhao; Liu, Xinyang; Jiang, Zhifan; Van Leemput, Koen; Piraud, Marie; Ezhov, Ivan; Johanson, Elaine; Meier, Zeke; Familiar, Ariana; Kazerooni, Anahita Fathi; Kofler, Florian; Calabrese, Evan; Aneja, Sanjay; Chiang, Veronica; Ikuta, Ichiro; Shafique, Umber; Memon, Fatima; Conte, Gian Marco; Bakas, Spyridon; Rudie, Jeffrey; Aboian, Mariam; Radiology and Imaging Sciences, School of Medicine
    Clinical monitoring of metastatic disease to the brain can be a laborious and timeconsuming process, especially in cases involving multiple metastases when the assessment is performed manually. The Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) guideline, which utilizes the unidimensional longest diameter, is commonly used in clinical and research settings to evaluate response to therapy in patients with brain metastases. However, accurate volumetric assessment of the lesion and surrounding peri-lesional edema holds significant importance in clinical decision-making and can greatly enhance outcome prediction. The unique challenge in performing segmentations of brain metastases lies in their common occurrence as small lesions. Detection and segmentation of lesions that are smaller than 10 mm in size has not demonstrated high accuracy in prior publications. The brain metastases challenge sets itself apart from previously conducted MICCAI challenges on glioma segmentation due to the significant variability in lesion size. Unlike gliomas, which tend to be larger on presentation scans, brain metastases exhibit a wide range of sizes and tend to include small lesions. We hope that the BraTS-METS dataset and challenge will advance the field of automated brain metastasis detection and segmentation.