VAPOR: Visual Analytics for the Exploration of Pelvic Organ Variability in Radiotherapy

Furmanová, Katarína; Großmann, Nicolas; Muren, L.P.; Casares-Magaz, Oscar; Moiseenko, Vitali; Einck, John; Gröller, M. Eduard; Raidou, Renata Georgia

doi:10.1016/j.cag.2020.07.001

Cited by 13 publications

(3 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Focusing on cohorts of RT data, BladderRunner [RCMA * 18] visualized cohorts of prostate cancer patients which used a mixture of T‐SNE and Gaussian mean‐shift clustering to group patients based on bladder shape. VAPOR [FGM * 20] extended their work to consider RT‐induced treatment toxicity. Other work has extended these results to explore uncertainty in RT data for visual analysis [GCMM * 19, RPHL14] and predictive models [FMCM * 21].…”

Section: Related Workmentioning

confidence: 99%

DASS Good: Explainable Data Mining of Spatial Cohort Data

Wentzel

Floricel

Canahuate

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Developing applicable clinical machine learning models is a difficult task when the data includes spatial information, for example, radiation dose distributions across adjacent organs at risk. We describe the co‐design of a modeling system, DASS, to support the hybrid human‐machine development and validation of predictive models for estimating long‐term toxicities related to radiotherapy doses in head and neck cancer patients. Developed in collaboration with domain experts in oncology and data mining, DASS incorporates human‐in‐the‐loop visual steering, spatial data, and explainable AI to augment domain knowledge with automatic data mining. We demonstrate DASS with the development of two practical clinical stratification models and report feedback from domain experts. Finally, we describe the design lessons learned from this collaborative experience.

show abstract

Section: Related Workmentioning

confidence: 99%

DASS Good: Explainable Data Mining of Spatial Cohort Data

Wentzel

Floricel

Canahuate

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Angelelli et al [5] proposed an interactive system for hypothesis generation with retrospective cohort study data using a data-cube-based model that used linked views for spatial and nonspatial data. Other applications have integrated interactive interfaces with application-specific visual encodings with linked views [32,96,98] to support active collaboration between data analysts and domain experts. However, none of these approaches consider temporal changes in outcome data or nuanced quality of life outcomes, and do not account for missing data.…”

Section: Related Workmentioning

confidence: 99%

THALIS: Human-Machine Analysis of Longitudinal Symptoms in Cancer Therapy

Floricel¹,

Nipu²,

Biggs³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fig. 1. THALIS analysis of longitudinal symptom data. A) Association Rule Diagram panel, showing here association-rule-mining (ARM) relationships among the most frequent late-stage symptoms; rules are represented using bubbles, with size and color encoding the support and lift metrics. B) Symptom trajectory panel-filament plots encode here mean rating values per therapeutic combination, with more frequent observations in the acute stage (left-end) than in the late stage (right-end). C) Sketch of areas affected by the selected symptoms (dry mouth and taste). D) Cohort symptom panel showing via summarization with shade and height the percentile rating distribution. E) Correlation matrix showing associations with the selected symptom. Image cropped and edited for in-print legibility.

show abstract

“…Consequently, we accepted the six papers that are now collected in this special section. The section includes a survey on medical animation, covering applications in medical education, diagnosis, treatment planning and forensics [1] , one paper that proposes a novel approach for the visual exploration of large normal mode spaces to study protein flexibility [2] , one paper presenting a complete system for the data extraction and visual exploration of colon contents and morphological data [3] , and three visual analytics papers, addressing the exploration and analysis of pelvic organ variability in cohorts of patients undergoing radiotherapy [4] , the interactive exploration of metabolite signatures in MR spectroscopy studies [5] , and explainability in clinical decision support, inspired by decision making within clinical routine [6] .…”

Section: Computers and Graphicsmentioning

confidence: 99%