RESUMEN
We present the VIS30K dataset, a collection of 29,689 images that represents 30 years of figures and tables from each track of the IEEE Visualization conference series (Vis, SciVis, InfoVis, VAST). VIS30K's comprehensive coverage of the scientific literature in visualization not only reflects the progress of the field but also enables researchers to study the evolution of the state-of-the-art and to find relevant work based on graphical content. We describe the dataset and our semi-automatic collection process, which couples convolutional neural networks (CNN) with curation. Extracting figures and tables semi-automatically allows us to verify that no images are overlooked or extracted erroneously. To improve quality further, we engaged in a peer-search process for high-quality figures from early IEEE Visualization papers. With the resulting data, we also contribute VISImageNavigator (VIN, visimagenavigator.github.io), a web-based tool that facilitates searching and exploring VIS30K by author names, paper keywords, title and abstract, and years.
RESUMEN
OBJECTIVES: The study aims were to evaluate: (1) whether a short-protocol (SP) MRI for the surveillance of pancreatic cystic neoplasms (PCN) provides equivalent clinical information as a comprehensive-protocol (CP), and (2) the cost reduction from substituting CP with SP for patient surveillance. METHODS: This retrospective study included 154 consecutive patients (median age: 66, 52 % men) with working-diagnosis of PCN and available contrast-enhanced MRI/MRCP. Three radiologists evaluated independently two imaging sets (SP/CP) per patient. The CP included: T2-weighted (HASTE/MRCP), DWI and T1-weighted (chemical-shift/pre-/post-contrast) images [acquisition time (AT) ≈ 35 min], whereas the SP included: T2-weighted HASTE and T1-weighted pre-contrast images (AT ≈ 8 min). Mean values of largest cyst/main pancreatic duct diameter (DC/DMPD) were compared. Agreement regarding presence/absence of cystic/MPD mural nodules (MNC/MNMPD), inter-observer agreement and cost differences between SP/CP were calculated. RESULTS: For DC and DMPD, mean values with SP/CP were 21.4/21.7 mm and 3.52/3.58 mm, while mean differences SP-CP were 0.3 mm (p = 0.02) and 0.06 mm (p = 0.12), respectively. For presence/absence of MNC and MNMPD, SP/CP coincided in 93 % and 98 % of cases, respectively. Inter-observer agreement was strong for SP/CP. SP-cost was 25 % of CP-cost. CONCLUSIONS: For the surveillance of PCN, short-protocol MRI provides information equivalent to the more time-consuming and costly comprehensive-protocol. KEY POINTS: ⢠Pancreatic cystic neoplasms (PCN) are increasingly diagnosed in the general population. ⢠Multiple imaging controls are recommended for the surveillance of patients with PCN. ⢠Short and comprehensive MRI-protocols are equivalent for decision-making in PCN under surveillance. ⢠Evaluation of imaging risk factors in PCNs is comparable with both MRI-protocols. ⢠Use of the short MRI-protocol may rationalise healthcare resources.