Background: Recent developments to segment and characterize the regions of interest (ROI) within medical images have led to promising shape analysis studies. However, the procedures to analyze the ROI are arbitrary and vary by study. A tool to translate the ROI to analyzable shape representations and features is greatly needed.

Results: We developed SAFARI (shape analysis for AI-segmented images), an open-source R package with a user-friendly online tool kit for ROI labelling and shape feature extraction of segmented maps, provided by AI-algorithms or manual segmentation. We demonstrated that half of the shape features extracted by SAFARI were significantly associated with survival outcomes in a case study on 143 consecutive patients with stage I-IV lung cancer and another case study on 61 glioblastoma patients.

Conclusions: SAFARI is an efficient and easy-to-use toolkit for segmenting and analyzing ROI in medical images. It can be downloaded from the comprehensive R archive network (CRAN) and accessed at https://lce.biohpc.swmed.edu/safari/ .

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9308199PMC
http://dx.doi.org/10.1186/s12880-022-00849-8DOI Listing

Publication Analysis

Top Keywords

shape analysis
12
safari shape
8
analysis ai-segmented
8
ai-segmented images
8
roi medical
8
medical images
8
case study
8
roi
5
shape
5
safari
4

Similar Publications

The great diversity of specialist plant-feeding insects suggests that host plant shifts may initiate speciation, even without geographic barriers. Pheromones and kairomones mediate sexual communication and host choice, and the response to these behaviour-modifying chemicals is under sexual and natural selection, respectively. The concept that the interaction of mate signals and habitat cues facilitates reproductive isolation and ecological speciation is well established, while the traits and the underlying sensory mechanisms remain unknown.

View Article and Find Full Text PDF

Super-Resolved Mapping of Electrochemical Reactivity in Single 3D Catalysts.

Nano Lett

January 2025

Institute of Nanochemistry and Nanobiology, School of Environmental and Chemical Engineering, Shanghai University, Shanghai 200444, P.R. China.

Crystals with three-dimensional (3D) stereoscopic structures, characterized by diverse shapes, crystallographic planes, and morphologies, represent a significant advancement in catalysis. Differentiating and quantifying the catalytic activity of specific surface facets and sites at the single-particle level is essential for understanding and predicting catalytic performance. This study employs super-resolution radial fluctuations electrogenerated chemiluminescence microscopy (SRRF-ECLM) to achieve high-resolution mapping of electrocatalytic activity on individual 3D CuO crystals, including cubic, octahedral, and truncated octahedral structures.

View Article and Find Full Text PDF

Drug use among men is a significant public health concern in China, with compulsory drug treatment centers being the primary approach. Police officers in these centers play a crucial role in shaping the interactions and experiences of men who use drugs (MWUD). However, little research exists on the attitudes of police officers toward MWUD in China.

View Article and Find Full Text PDF

Decision Trees for the Recognition of Metal-Centered Chirality in Coordination Complexes.

J Comput Chem

January 2025

Departamento de Química Fundamental, Universidade Federal de Pernambuco, Recife, Pernambuco, Brazil.

While established guidelines exist for chirality in tetrahedral molecules, there is a notable absence of clear rules for recognizing metal-centered chirality in higher-coordination complexes. We develop decision trees to assess the likelihood of chirality-at-metal in coordination complexes with coordination numbers 4-9 with mono and bidentate ligands. Using binary decision rules based on shape, ligand type, and quantity, the trees classify complexes as chiral or achiral.

View Article and Find Full Text PDF

Human activities such as agriculture and urban development are linked to water quality degradation. Canada represents a large and heterogeneous landscape of freshwater lakes, where variations in climate, geography and geology interact with land cover alteration to influence water quality differently across regions. In this study, we investigated the influence of water quality and land use on bacterial communities across 12 ecozones.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!