• Computational Vascular Development Model Explaining Incidence of Notch in Retinopathy of Prematurity with Ultra-Widefield Optical Coherence Tomography
  • 1; 1; 1; 3; 4; 1; 1; 1; 1; 1; 1; 5; 1; 4; 1
  • 1 Casey Eye Institute, Oregon Health and Science University, Portland, Oregon, United States 
  • 2 Chicago College of Osteopathic Medicine, Midwestern University, Downers Grove, Illinois, United States
  • 3 Department of Electrical and Computer Engineering, Northeastern University, Boston, Massachusetts, United States 
  • 4 Maine College of Engineering and Computing, 91爆料, Orono, Maine, United States
  • 5 National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States National Library of Medicine, National Institutes of Health, Bethesda, Maryland, United States
• Correspondence: Benjamin K. Young, Casey Eye Institute, Oregon Health and Science University, 515 SW Campus Drive, Portland, OR 97239, USA; youngbe@ohsu.edu.听

Aaron Gallant听

• • Principal Investigator: Aaron Gallant Civil and Environmental Engineering 91爆料听
  • Authors: Aaron Gallant; Sebastian Montoya-Vargas; William Davids 
  • Sponsored By: Transportation Infrastructure Durability Center

• • Principal Investigator: Aaron Gallant Civil and Environmental Engineering 91爆料听
  • Authors: Aaron Gallant; Sk Belal Hossen; Warda Ashraf; Luis Zambrano-Cruzatty; Temitope Omokinde; Andres Espinosa 
  • Sponsored By: Transportation Infrastructure Durability Center

Shaleen Jain听

• • Alisha Shrestha, Tora Johnson, Shaleen Jain, and Jessica Jansujwicz
  • Alisha Shrestha 91爆料 and Maine Sea Grant, alisha.shrestha1@maine.edu 
  • Tora Johnson Sunrise County Economic Council, tjohnson@sunrisecounty.org 
  • Shaleen Jain 91爆料, shaleen.jain@maine.edu Jessica Jansujwicz Maine Sea Grant, jessica.jansujwicz@maine.edu 

Caitlin Howell听

• Liquid-infused Silicone Catheters Reduce Fungal Burden and Inflammation in Candidozyma auris Bladder Infections
  • Alyssa Ann La Bella1, Hope Akegbe1, Caitlin Howell2,3, Felipe H. Santiago-Tirado1*, Ana L. Flores-Mireles1*
  • 1 Department of Biological Sciences, University of Notre Dame, Notre Dame, IN, 46556, USA听
  • 2 Department of Chemical and Biomedical Engineering, 91爆料, Orono, ME, 04669, USA听
  • 3 Graduate School of Biomedical Science and Engineering, 91爆料, Orono, ME, 04669, USA听听
  • *Co-corresponding author: afloresm@nd.edu

Donald Hummels

• PALLAVI GHIMIRE1 , SAMIP POUDEL1 , MARIKO SHIRAZI2 , DONALD HUMMELS1 , AND REINALDO TONKOSKI1,3 1Department of Electrical and Computer Engineering, 91爆料, Orono, ME 04469, USA 2Department of Electrical and Computer Engineering, University of Alaska, Fairbanks, AK 99775, USA 3Chair of Electrical Power Transmission and Distribution, Technical University of Munich, Munich, Germany Corresponding author: Pallavi Ghimire (e-mail: pallavi.ghimire@ieee.org).

Lauren Ross听

• • Taylor Bailey a, Lauren Ross a, Sean M.C. Smith a b c d, Sohaib Alahmed e
  • a 91爆料, Department of Civil and Environmental Engineering,听 United States of America
  • b 91爆料, School of Earth & Climate Sciences, United States of America
  • c 91爆料, Center for Sustainability Solutions, United States of America
  • d 91爆料, Darling Marine Center, United States of America
  • e Anchor QEA, United States of America
• • Patricio A. D铆az a b, Gonzalo 脕lvarez c d e f, Iv谩n P茅rez-Santos a g, Michael Araya d, Lauren Ross h, 脕ngela M. Baldrich a, Osvaldo Artal g i, Daniel Varela a, Sergio A. Rosales j, Camila Schwerter a, Camilo Rodr铆guez-Villegas a, Valentina Iturra k, Manuel D铆az l, B谩rbara Cantarero a j, Rosa I. Figueroa m
  • a Centro i鈭糾ar, Universidad de Los Lagos, Casilla 557, Puerto Montt, Chile
  • b Centro Interdisciplinario para la Investigaci贸n Acu铆cola 鈥� Investigaci贸n Aplicada (INCAR2), Universidad de Concepci贸n, Concepci贸n, Chile
  • C Departamento de Acuicultura, Facultad de Ciencias del Mar, Universidad Cat贸lica del Norte, Larrondo 1281, Coquimbo, Chile
  • D Centro de Investigaci贸n y Desarrollo Tecnol贸gico en Algas (CIDTA), Facultad de Ciencias del Mar, Larrondo 1281, Universidad Cat贸lica del Norte, Coquimbo, Chile
  • e Center for Ecology and Sustainable Management of Oceanic Islands (ESMOI), Departamento de Biolog铆a Marina, Facultad de Ciencias del Mar, Universidad Cat贸lica del Norte, Coquimbo, Chile
  • f Centro de Innovaci贸n Acu铆cola AquaPac铆fico, Larrondo 1281, Coquimbo, Chile
  • g Center for Oceanographic Research COPAS COASTAL, Universidad de Concepci贸n, Chile
  • h Department of Civil and Environmental Engineering, 91爆料, Orono, ME, USA
  • i Geodel Laboratory, Departamento de Ingenier铆a en Obras Civiles, Facultad de Ingenier铆a y Ciencias, Universidad de La Frontera, Temuco, Chile
  • j Programa de Doctorado en Biolog铆a y Ecolog铆a Aplicada, Universidad Cat贸lica del Norte, Larrondo 1281, Coquimbo, Chile
  • k Departamento de Geof铆sica, Universidad de Concepci贸n, Concepci贸n, Chile
  • l Programa de Investigaci贸n Pesquera, Universidad Austral de Chile, Puerto Montt, Chile
  • m Centro Oceanografico de Vigo, Instituto Espa帽ol de Oceanograf铆a (IEO-CSIC), Subida a Radio Faro 50, 36390, Vigo, Spain

Jon Ippolito

• • 贰蝉蝉补测听

Babak Hejrati听

• • by Ines Khiyara 1,*,Ben Sidaway 2 andBabak Hejrati 1
  • 1 Biorobotics and Biomechanics Laboratory, Department of Mechanical Engineering, 91爆料, Orono, ME 04469, USA
  • 2 School of Physical Therapy, Husson University, Bangor, ME 04401, USA
  • * Author to whom correspondence should be addressed.

• • Ali Faeghinejad,Liam Hawthorne and Babak Hejrati *Biorobotics & Biomechanics Laboratory, Mechanical Engineering Department, 91爆料, 75 Long Road, Orono, ME 04469, USA
    *Author to whom correspondence should be addressed.

Masoud Rais Rohani

• • Troy Zangle, Brett Ellis and Masoud Rais-Rohani

David Neivandt听

• • by Mahbuba Daizy 1,Yu Zhang 2,Douglas W. Bousfield 1,Ling Li 2,Jinwu Wang 3 andDavid J. Neivandt 1,*
    1 Department of Chemical and Biomedical Engineering, 91爆料, 5737 Jenness Hall, Orono, ME 04469, USA, 2 School of Forest Resources, 91爆料, 5755 Nutting Hall, Orono, ME 04469, USA, Forest Products Laboratory, U.S. Forest Service, 1 Gifford Pinchot Drive, Madison, WI 53726, USA
    * Author to whom correspondence should be addressed.

Evan Wukcik听

• • Sara Maslaczynska-Salome, Arya Ajeev, Theodore Warfle, Behrokh Shams, Colton Duprey, Evan K. Wujcik

Karissa Tilbury听

• (PREPRINT!!)
  • Jordan N. Miner1, Christopher L. Emmerling1, Joshua D. Hamilton1, Joseph Raite1, Zoe Vittum1, Peter C. Brooks2, Andre Khalil1, Karissa Tilbury1
    1 91爆料, 2 MaineHealth Institute for Research

Yifeng Zhu

• • Qiang Zou, Yuhui Deng, Yifeng Zhu, Yi Zhou, Jianghe Cai, Shuibing He, and Lina Ge听

• 听

Mauricio Pereira Da Cunha: 

Mehdi Tajvidi: 

• 听

Kimberly Huguenard: 

Lauren Ross: 

Evan Wujcik:

• 听

Donald Hummels: 

Onur Apul: 

Babak Hejrati: 

Senthil Vel: 

Amrit Verma: 

Eric Landis: 

• [1] P. Spicer, K. Huguenard, N. L. Jones, A. Piffer-Braga, D. G. MacDonald, M. M. Whitney, and K. L. Cole, 鈥淣onlinear internal wave mixing observations within the interior of a river plume,鈥� Estuaries and Coasts, vol. 48, Art. no. 149, Jul. 2025. [Online]. Available:
• [2] S. McElman, A. S. Verma, and A. Goupee, 鈥淨uantifying tropical-cyclone-generated waves in extreme-value-derived design for offshore wind,鈥� Wind Energy Science, vol. 10, no. 8, pp. 1529鈥�1550, Aug. 2025. [Online]. Available:
• [3] R. Masmoudi, B. G. Frederick, L. Doucette, R. J. Lad, M. P. da Cunha, and C. P. Tripp, 鈥淟ayer-by-layer approach for obtaining highly oriented kaolin platelets on surfaces,鈥� Langmuir, Article ASAP, 2025. doi: 10.1021/acs.langmuir.5c01905
• [4] A. E. England, S. D. Collins, M. D. Mason, and R. L. Smith, 鈥淐haracterization of microreactors for nanoparticle synthesis,鈥� in Proc. 23rd Int. Conf. Solid-State Sensors, Actuators and Microsystems (Transducers), Orlando, FL, USA, 2025, pp. 779鈥�782. doi: 10.1109/Transducers61432.2025.11110423
• [5] J. L. Col贸n Quintana, S. Tomlinson, and R. A. Lopez-Anido, 鈥淓ffect of fiber type on the thermomechanical performance of high-density polyethylene (HDPE) composites with continuous reinforcement,鈥� J. Compos. Sci., vol. 9, no. 8, p. 450, 2025. doi: 10.3390/jcs9080450
• [6] M. Daizy, Y. Ni, D. W. Bousfield, and D. J. Neivandt, 鈥淒evelopment of a soybean wax Pickering emulsion for sustainable hydrophobic modification of paper,鈥� ACS Sustain. Chem. Eng., vol. 13, no. 33, pp. 13614鈥�13627, 2025. doi: 10.1021/acssuschemeng.5c06102
• [7] M. El Hajam, W. Sun, I. Hafez, C. Howell, and M. Tajvidi, 鈥淚n situ growth of mycelium in a lignocellulosic scaffold enabled by cellulose nanofibrils for lightweight insulation,鈥� Compos. A Appl. Sci. Manuf., vol. 199, p. 109223, Dec. 2025. doi: 10.1016/j.compositesa.2025.109223
• [8] W. Baldwin, S. Ghanavati, and M. W枚rsd枚rfer, 鈥淯nderstanding ethical practices in AI: Insights from a cross-role, cross-region survey of AI development teams,鈥� ACM Trans. [Journal Name], vol. 1, no. 1, pp. 1鈥�45, Aug. 2025.
• [9] S. Rieger, C.-J. Hsieh, C. Anthony et al., 鈥淧aclitaxel neurotoxicity is triggered by epidermal EG5 dependent microtubule fasciculation and X-ROS formation,鈥� Res. Square, preprint, Aug. 20, 2025. [Online]. Available:
• [10] D. Hatinoglu, S. S. S. Lee, M. Choudhary, J. Lee, S. B. Attanayake, K.-Y. Hwang, D. Detellem, M.-H. Phan, J. D. Fortner, and O. G. Apul, 鈥淢icrowave heating of superparamagnetic iron-oxide nanoparticles toward environmental hyperthermia-based applications,鈥� ACS Appl. Mater. Interfaces, vol. 17, no. 35, pp. 49775鈥�49783, 2025. doi: 10.1021/acsami.5c13454

鈼� T. Suha, M. H. Rahman, A. E. Rice, C. Smith, R. A. Awad, and P. Chakraborty, “TRIM: AI guided random number generation for resource-constrained IoT systems,” IEEE Access, vol. xx, pp. xx鈥搙x, 2024. Date of publication: xxxx 00, 0000. Date of current version: xxxx 00, 0000. doi: 10.1109/ACCESS.2024.0429000.

鈼� M. M. Rahman, I. Hafez, and M. Tajvidi, “3D printing with cellulose nanofibrils enabled by microwave irradiation,” Cellulose, Jul. 10, 2025. [Online]. Available:

鈼� W. Baldwin, S. Chintakuntla, S. Parajuli, A. Pourghasemi, R. Shanz, and S. Ghanavati, “Generating privacy stories from software documentation,” arXiv preprint arXiv:2506.23014, Jun. 28, 2025. [Online]. Available:

鈼� S. T. Mosavi Mirkolaei, S. K. Najafi, and M. Tajvidi, “Dynamic thermo-mechanical behavior of wood plastic composite based on microfibrillar blends of recycled HDPE/LDPE/PET,” unpublished.

鈼� [1] J. C. Clark, W. G. Davids, R. A. Lopez-Anido, A. P. Schanck, and C. A. Sheltra, 鈥淐ontinuously formed fiber-reinforced thermoplastic composite rebar for concrete reinforcement,鈥� J. Compos. Sci., vol. 9, no. 7, p. 378, 2025, doi: 10.3390/jcs9070378.

鈼� [1] M. Blair, S. R. Geedipally, and M. Shirazi, 鈥淎ssessing the importance of functional form selection in developing calibration functions for the highway safety manual predictive models,鈥� J. Saf. Res., vol. 94, pp. 362鈥�369, 2025, doi: 10.1016/j.jsr.2025.06.022.

鈼� [1] A. E. England, S. D. Collins, C. L. Emmerling, M. D. Mason, and R. L. Smith, 鈥淗igh speed microturbine mixer for kinetically controlled synthesis,鈥� Lab Chip, Advance Article, 2025, doi: 10.1039/D5LC00488H.

鈼� M. H. Rahman, Z. Haider, M. M. Rizvee, S. Shomaji, and P. Chakraborty, “Intelligent Layer Sharing (ILASH): A Predictive Neural Architecture Search Framework for Multi-Task Applications,” IEEE Access, vol. 13, pp. 1鈥�1, Jul. 2025, doi: 10.1109/ACCESS.2025.3592039.

Contact: Taylor Ward, taylor.ward@maine.edu

The new Context Guided Segmentation Network (CGS-Net) provides more accurate cancer detection, addressing key limitations in current diagnostic methods. The study that resulted in its creation, was published in Scientific Reports with Springer Nature. It is the result of a collaborative effort led by Yifeng Zhu, chair and Norman Stetson Professor of Electrical and Computer Engineering, and the team at his Data Engineering and AI Lab (DEAL). 

Zhu began applying modern AI technology for cancer detection in 2018. While caring for his mother during chemotherapy in 2017, he noticed the challenges pathologists face when reviewing biopsy samples under a microscope 鈥� an often tedious and error-prone process. Motivated by this firsthand experience, Zhu sought to streamline and improve diagnostic accuracy by leveraging advanced AI techniques, ultimately leading to the creation of CGS-Net. 

His research group also participated in the international competition Liver Cancer Segmentation Challenge and ranked in the top 10 among all teams in 2019, with the results published in the journal . 

This research is an interdisciplinary collaboration with Chaofan Chen, assistant professor of computer science, and Andre Khalil, professor of chemical and biomedical engineering and Ph.D. students Jeremy Juybari and Josh Hamilton. It explores a new AI model inspired by the way pathologists navigate slides under a microscope, zooming in and out to gather both broad context and detailed information. Because pathologists rely on contextual cues to identify and evaluate abnormalities, this model mimics that approach 鈥� incorporating surrounding context while also focusing on specific regions of interest.

Breast cancer is the second leading cause of cancer-related deaths among women, and its diagnosis depends heavily on the microscopic examination of stained tissue samples. However, limited access to trained pathologists, particularly in under-resourced regions, contributes to diagnostic delays. CGS-Net has the potential to assist pathologists, especially in areas with fewer healthcare resources, by identifying cancerous regions more efficiently.

鈥淭his research could significantly reduce diagnostic delays, especially in under-resourced regions where access to trained pathologists is limited,” said Jeremy Juybari, the first author of this paper and Ph.D. student in electrical and computer engineering.

CGS-Net is a dual-encoder deep learning model that simultaneously evaluates tissue at different magnification levels. Unlike traditional models, which analyze tissue at a single resolution, CGS-Net incorporates both detailed and contextual views, mimicking how pathologists zoom in and out during their examinations. This leads to more precise cancer segmentation and improved diagnostic accuracy.

Tested on the Camelyon16 dataset, which includes sentinel lymph node tissue samples, CGS-Net showed significant improvements in precise breast cancer detection over traditional models, with an area under the curve increase of 0.92% and a cancer Dice score improvement of 6.81%. These results highlight the model’s effectiveness in reducing false positives and improving accuracy.

The technical foundation of CGS-Net is a transformer dual-encoder architecture that incorporates cross-attention mechanisms to integrate detailed and contextual views. Unlike existing multi-resolution models, CGS-Net uniquely initializes cross-attention weights to enhance information sharing between magnification levels. The system was trained in two phases: first by optimizing the detail and context encoders separately, then by integrating them into a joint training model.

Additionally, the research introduced a robust patch-extraction algorithm to standardize data inputs, ensuring consistency and reproducibility in machine learning models for whole-slide imaging datasets. CGS-Net was rigorously evaluated using MiT and Swin V2 encoders, further validating its performance across various architectures and datasets.

鈥淥ur research goal is not to replace pathologists,鈥� said Zhu. 鈥淚nstead, we want to complement their expertise by providing an AI tool to assist them.鈥�

Sepideh Ghanavati, assistant professor听in the听School of Computing and Information Science, co-authored a paper that recently received recognition at a major conference.

Gahnavati, along with co-authors Sarah Santos, Travis Breaux, Sara Haghighi and Tom Norton, wrote a paper titled “Requirements Satisfiability with In-Context Learning” and won the RE24 Challenge Award for Research Track at the RE24 Conference.

The research challenge, “Expanding the Frontiers of RE,” focuses on reshaping the frontiers of requirements engineering (RE). It evaluates submissions based on novelty, potential impact, and feasibility within the RE community.

The paper leverages recent advancements in large language models (LLMs) to generate and evaluate informal software specifications using authoritative design guidance and indicative requirements. It highlights the potential impact of LLMs on RE by making basic NLP tasks more accessible and provides adaptable experimental designs for future RE problems. The tools and results are publicly available, built on open-source frameworks, and use low-cost, cloud-based APIs, making them feasible for immediate adoption by companies.

You can find the preprint of the paper . A link to the conference is .