JWJake T. Weeks

Jake T. Weeks

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jake T. Weeks has a total of 25 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Response to “Considerations in Imaging-Based Assessment of Steatotic Liver Disease to Enhance Harmonization, Longitudinal Interpretation, and Clinical Implementation”

    by Shin Mei Chan, Vitor F. Martins, Kathleen Marsh, Kang Wang, Jake T. Weeks, Aiguo Han, Meng Yin, Kathryn J. Fowler, Claude B. Sirlin, Cheng William Hong

    Chan SM, et al. Korean J Radiol. 2026 ;27:e41. https://doi.org/10.3348/kjr.2026.0358

  • Open Access

    Imaging Evaluation for Steatotic Liver Disease

    by Shin Mei Chan, Vitor F Martins, Kathleen Marsh, Kang Wang, Jake T Weeks, Aiguo Han, Meng Yin, Kathryn J. Fowler, Claude B. Sirlin, Cheng William Hong

    Chan SM, et al. Korean J Radiol. 2026 Jan;27:e2. https://doi.org/10.3348/kjr.2025.0966


  • Open Access

    Receptor-Mediated SPION Labeling of CD4+ T Cells for Longitudinal MRI Tracking of Distribution Following Systemic Injection in Mouse

    by Yu Ping, Songyue Han, Brock Howerton, Francesc Marti, Jake Weeks, Roberto Gedaly, Reuben Adatorwovor, Fanny Chapelin

    Tracking T cells in vivo using MRI is a major challenge due to the difficulty of labeling these non-phagocytic cells with a sufficient contrast agent to generate a detectable signal change. In this study, we explored CD4-Superparamagnetic iron oxide nanoparticles (SPION), which is commonly used in magnetic cell sorting, as a potential receptor-mediated, specific CD4+ T cell MRI labeling agent. We optimized the labeling protocol for maximal CD4+ cell labeling and viability. Cell health was confirmed with trypan blue assay, and labeling efficacy was confirmed with Prussian blue staining, transmission electron microscopy, and MRI of labeled cell pellets. Key cell functionality was assessed by flow cytometry. Next, CD4-SPION-labeled T cells or unlabeled T cells were delivered via intravenous injection in naïve mice. Liver MRIs pre-, 24 h, and 72 h post-T cell injection were performed to determine in vivo tracking ability. Our results show that CD4-SPION induces significant attenuation of T2 signals in a concentration-dependent manner, confirming their potential as an effective MRI contrast agent. In vitro, analyses showed that CD4+ T cells were able to uptake CD4-SPION without affecting cellular activity and key functions, as evidenced by Prussian blue staining and flow cytometric analysis of IL-2 receptor and the IL-7 receptor α-chains, CD69 upregulation, and IFN-γ secretion. In vivo, systemically distributed CD4-SPION-labeled T cells could be tracked in the liver at 24 and 72 h after injection, contrary to controls. Histological staining of tissue sections validated the findings. Our results showed that SPION CD4+ T cell sorting coupled with longitudinal MR imaging is a valid method to track CD4+ T cells in vivo. This safe, specific, and sensitive approach will facilitate the use of SPION as an MRI contrast agent in clinical practice, allowing for non-invasive tracking of adoptive cell therapies in multiple disease conditions.


  • Open Access

    Adaptive Evolutionary Optimization of Deep Learning Architectures for Focused Liver Ultrasound Image Segmentation

    by Ali Zifan, Katelyn Zhao, Madilyn Lee, Zihan Peng, Laura J. Roney, Sarayu Pai, Jake T. Weeks, Michael S. Middleton, Ahmed El Kaffas, Jeffrey B. Schwimmer, et al.

    Background: Liver ultrasound segmentation is challenging due to low image quality and variability. While deep learning (DL) models have been widely applied for medical segmentation, generic pre-configured models may not meet the specific requirements for targeted areas in liver ultrasound. Quantitative ultrasound (QUS) is emerging as a promising tool for liver fat measurement; however, accurately segmenting regions of interest within liver ultrasound images remains a challenge. Methods: We introduce a generalizable framework using an adaptive evolutionary genetic algorithm to optimize deep learning models, specifically U-Net, for focused liver segmentation. The algorithm simultaneously adjusts the depth (number of layers) and width (neurons per layer) of the network, dropout, and skip connections. Various architecture configurations are evaluated based on segmentation performance to find the optimal model for liver ultrasound images. Results: The model with a depth of 4 and filter sizes of [16, 64, 128, 256] achieved the highest mean adjusted Dice score of 0.921, outperforming the other configurations, using three-fold cross-validation with early stoppage. Conclusions: Adaptive evolutionary optimization enhances the deep learning architecture for liver ultrasound segmentation. Future work may extend this optimization to other imaging modalities and deep learning architectures.