Apollo: University of Cambridge repository

Clink, Kellian

doi:10.1108/rr-11-2017-0220

Cited by 4 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used these annotations to generate the ground truth breast mask for a total of 200 images. • Mini-MIAS (public): The Mini-MIAS database [22], created by the Mammographic Image Analysis Society (MIAS), is a resource that has been extensively used in prior research. It contains 322 digitized mammographic films in MLO view.…”

Section: Datasetsmentioning

confidence: 99%

Breast Delineation in Full-Field Digital Mammography Using the Segment Anything Model

Larroza,

Pérez-Benito,

Tendero

et al. 2024

Diagnostics

View full text Add to dashboard Cite

Breast cancer is a major health concern worldwide. Mammography, a cost-effective and accurate tool, is crucial in combating this issue. However, low contrast, noise, and artifacts can limit the diagnostic capabilities of radiologists. Computer-Aided Diagnosis (CAD) systems have been developed to overcome these challenges, with the accurate outlining of the breast being a critical step for further analysis. This study introduces the SAM-breast model, an adaptation of the Segment Anything Model (SAM) for segmenting the breast region in mammograms. This method enhances the delineation of the breast and the exclusion of the pectoral muscle in both medio lateral-oblique (MLO) and cranio-caudal (CC) views. We trained the models using a large, multi-center proprietary dataset of 2492 mammograms. The proposed SAM-breast model achieved the highest overall Dice Similarity Coefficient (DSC) of 99.22% ± 1.13 and Intersection over Union (IoU) 98.48% ± 2.10 over independent test images from five different datasets (two proprietary and three publicly available). The results are consistent across the different datasets, regardless of the vendor or image resolution. Compared with other baseline and deep learning-based methods, the proposed method exhibits enhanced performance. The SAM-breast model demonstrates the power of the SAM to adapt when it is tailored to specific tasks, in this case, the delineation of the breast in mammograms. Comprehensive evaluations across diverse datasets—both private and public—attest to the method’s robustness, flexibility, and generalization capabilities.

show abstract

Section: Datasetsmentioning

confidence: 99%

Breast Delineation in Full-Field Digital Mammography Using the Segment Anything Model

Larroza,

Pérez-Benito,

Tendero

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…The real-time digital representation of the infrastructure, where data is usually gathered on-site using sensors that continuously monitor changes and consequently update the building information modeling (BIM) model. Center of Digital Built Britain (33) The realistic digital representation of assets, processes, or systems in the built environment. A Digital Twin can be distinguished from other replicas or models by its connection with the physical assets.…”

Section: European Construction Sector Observatory (32)mentioning

confidence: 99%

Departments of Transportation Efforts to Digitize Ancillary Transportation Asset Data: A Step Toward Digital Twins

Ammar

Maier²,

Catchings

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

The mission of state Departments of Transportation (DOTs) has evolved, and their perception has shifted from focusing on constructing new assets to managing and maintaining existing transportation assets and optimizing asset performance. In response to this change, state DOTs began adopting a “transportation asset management” approach, an intensive data-driven decision-making process to maintain and extend the serviceability of transportation assets throughout their lifecycle. However, state DOTs continue to face challenges in conducting cross-asset system analysis and integrating data across systems throughout the asset lifecycle. Conversely, emerging technologies, namely Digital Twins, have the potential to leverage the value of asset data and transform data into valuable insights to inform decision-making. The definition of Digital Twins in the infrastructure industry is inconsistent, and the transition toward a digitized built environment—a preliminary step required for a successful implementation of Digital Twins—has not been investigated. Thus, this paper presents the burning platform for the need for Digital Twins and defines the concept. Additionally, this study investigates the current practices of state DOTs toward the digital transition of their transportation asset data and contextualizes the DOTs’ maturity in the advancement of digital processes. This paper focuses on ancillary asset systems, particularly Roadside, Electronic, and Drainage Asset systems. A web-based survey was developed and distributed to state DOTs for data collection. For each asset, the perceived timeline for digitization was investigated, and three variables related to data digitization were explored: data format, data level of detail, and data collection technique.

show abstract

Ontological Modeling of POHUA: An Institutional Knowledge Repository

Castillo

Villagómez

Nieto

et al. 2019

CyS

View full text Add to dashboard Cite

Apollo: University of Cambridge repository

Abstract: Have you ever been curious about libraries? Have you ever wondered when the first public

Cited by 4 publications

References 1 publication

Breast Delineation in Full-Field Digital Mammography Using the Segment Anything Model

Breast Delineation in Full-Field Digital Mammography Using the Segment Anything Model

Departments of Transportation Efforts to Digitize Ancillary Transportation Asset Data: A Step Toward Digital Twins

Ontological Modeling of POHUA: An Institutional Knowledge Repository

Contact Info

Product

Resources

About