Histopathology image analysis plays a pivotal role in disease diagnosis and treatment planning, relying heavily on accurate nuclei segmentation for extracting vital cellular information. In recent years, artificial intelligence (AI) and in particular deep learning models have been applied successfully in solving computational pathology image analysis tasks. The You Only Look Once (YOLO) object detection framework, which is based on a convolutional neural network (CNN) architecture has gained traction across various domains for its real-time processing capabilities. This systematic review aims to comprehensively explore and evaluate the advancements, challenges, and applications of YOLO-based methodologies in nuclei segmentation within the domain of histopathological images. The review encompasses a structured analysis of recent literature, focusing on the utilization of YOLO variants for nuclei segmentation. Key methodologies, training strategies, dataset specifics, and performance metrics are evaluated to elucidate the strengths and limitations of YOLO in this context. Additionally, the review highlights the unique characteristics of YOLO that enable efficient object detection and delineation of nuclei structures, offering a comparative analysis against traditional segmentation approaches. This systematic review underscores the promising outcomes achieved through YOLO-based architectures, emphasizing their potential for accurate and rapid nuclei segmentation. Furthermore, it identifies persistent challenges such as handling variances in nuclei appearances, optimizing model architectures for histopathological images, and improving generalization across diverse datasets. Insights derived from this review can provide a foundation for future research directions and enhancements in nuclei segmentation methodologies using YOLO within histopathology, fostering advancements in disease diagnosis and biomedical research.
This capstone report presents E.D.E.N. (Every Day, Every Night) — an original continuous improvement framework designed for nonstop, high-dependency operations in industries such as logistics, aviation, digital infrastructure, and healthcare. Drawing on principles from Lean, Six Sigma, high-reliability organizations (HROs), and data-driven decision science, the paper introduces four interlocking pillars: Engaged & Empowered Teams, Data-Driven Continuous Feedback, End-to-End Alignment, and Nonstop Adaptive Resilience. Through detailed analysis of recent global disruptions — including the 2025 CrowdStrike outage, Boeing’s manufacturing failures, the Red Sea shipping crisis, and Taiwan’s semiconductor challenges — the work demonstrates how organizations can embed real-time adaptability, resilience, and continuous improvement directly into their operations. The E.D.E.N. framework is proposed as a new model for achieving operational excellence and resilience in an era where downtime is no longer an option.
This data set contains ultrasound image, tissue ablation. and temperature data measured in the study reported in the article:
Real-time control of radiofrequency ablation using three-dimensional ultrasound echo decorrelation imaging in normal and diseased ex vivo human liver
Elmira Ghahramani, Peter D Grimm, Benjamin E Weiss, Nicholas S Schoenleb, Alexander J Knapp, Jiang Wang, Syed A Ahmad, Shimul A Shah, Ralph C Quillin III, Sameer H Patel
Physics in Medicine and Biology, 2025
https://iopscience.iop.org/article/10.1088/1361-6560/adaacb
To best understand and use this data set, please refer to this article.
Files in the data set include:
Annotated Excel spreadsheet containing summary data for all 109 trials in this study (12 preliminary trials, followed by 97 primary trials; see spreadsheet for variable listing):
ExVivoHumanLiver_RFA_Decorrelation_SummaryData.xlsx
CSV spreadsheet containing the same summary data without annotations:
ExVivoHumanLiver_RFA_Decorrelation_SummaryData.csv
MATLAB data file (version 7) containing the same summary data, within the structure variable 'summary':
ExVivoHumanLiver_RFA_Decorrelation_SummaryData.mat
Example MATLAB script demonstrating reading and some analysis of results from all trials, with PDF of code and its output:
ExVivoHumanLiver_RFA_Decorrelation_ExampleScript.m
ExVivoHumanLiver_RFA_Decorrelation_ExampleScript.pdf
MATLAB data files (version 7) containing results from each trial:
ExVivoHumanLiver_RFA_Decorrelation_RawData_Trial1.mat through ExVivoHumanLiver_RFA_Decorrelation_RawData_Trial109.mat.
Each of these files contains the structure variable "rawdata", containing the following fields for each trial:
segmented_ablation_zone:
60x60x60 logical array (step size 1 mm) of segmented liver tissue map (1=ablated, 0=unablated). Dimensions are (z,y,x) as defined in Ghahramani et al. (2025), with z being range from the transducer surface (horizontal in room coordinates), y the azimuthal array direction (horizontal in room coordinates), and x the elevational array direction (vertical in room coordinates). The RFA probe was placed with its tip approximately at the center of this volume, with its needle parallel to the x axis.
IQ_echo_data:
60x60x60x2xN complex array containing beamformed, demodulated IQ (in-phase/quadrature) echo data interpolated onto the same grid. The array of echo volumes comprises N pairs (one pair acquired every 22 s), with the two volumes from each pair separated by the inter-frame time of 50 ms.
instantaneous_decorrelation:
60x60x60xN real array containing echo decorrelation per ms (linear scale) computed for each frame pair, using the equation and methods from section 2.3 in Ghahramani et al. (2025).
thermocouple_locations:
4x3 real array (same for each trial), with each row comprising the (z,y,x) coordinates (voxel indices within the 60x60x60 grid) of a corresponding thermocouple integrated into the RFA probe.
thermocouple_temperatures:
4xM real array, with each row comprising the measured temperatures (degrees C) measured during ablation, synchronous with the last M ultrasound IQ and decorrelation frames of each trial (not available for trials 30, 78, 91, and 102-109).
decorrelation_at_thermocouples:
4xM real array, with each row comprising the measured decorrelation per ms (linear scale) at each thermocouple location, synchronous with the last M ultrasound IQ and decorrelation frames of each trial.
Replication Package of "Exploiting Vision-Language Models in GUI Reuse", a paper published in the 22nd International Conference on Systems and Software Reuse (ICSR), Ottawa, Canada, April 27 2025.
The authors are: Victoria Niu, Walaa Alshammari, Naga Mamata Iluru, Padmaja Vaishnavi Teeleti, Nan Niu, Tanmay Bhowmik, and Jianzhang Zhang.
Artifacts of the paper entitled:
A Study of Natural-Language and Vision-Language GUI Retrieval
Authors: Walaa Alshammari, Yitong Yang, Yinglin Wang, Nan Niu, Tanmay Bhowmik, Padmaja Vaishnavi Teeleti, and Naga Mamata Iluru
The content is:
A-relevance-judging-results.xlsx has five sheets recording the four judges' assessment and their inter-rater agreement levels;
B-GUI-retrieval-answer-set.xlsx specifies the relevance relations between 40 GUI images and 27 NL queries;
C-retrieval-results.xlsx contains top-10 NL-based results in one sheet, and top-5 NL-based and VL-based results in the other four sheets; and
D-human-subject-study-material.pdf documents the five GUI reuse tasks approved by an institutional review board.
D-
This is a poster detailing the scope, design, process safety, and economics for a chemical engineering capstone by project group 5046-2403. The project is centered around capturing carbon dioxide emissions from indoor testing cells at the General Electric Aerospace site in Peebles, Ohio. The process captures carbon dioxide from jet engine exhaust through a series of adsorption towers with activated carbon sorbent. The adsorbate goes through a desorption cycle to release purified gaseous carbon dioxide from the surface of the activated carbon. The gas is compressed for storage and off-site transport.
Replication Package of Environmental Variations of Software Features: A Logical Test Cases' Perspective authored by Md Rayhan Amin,Tanmay Bhowmik, Nan Niu, and Juha Savolainen
Artifacts of the paper entitled:
Prompting Creative Requirements via Traceable and Adversarial Examples in Deep Learning
Authors: Hemanth Gudaparthi, Nan Niu, Boyang Wang, Tanmay Bhowmik, Hui Liu, Jianzhang Zhang, Juha Savolainen, Glen Horton, Sean Crowe, Thomas Scherz and Lisa Haitz
To appear in the Proceedings of the 31st IEEE International Requirements Engineering Conference (RE 2023 https://conf.researchr.org/home/RE-2023)
