Digital Imaging and Communications in Medicine

Onken, Michael D.; Eichelberg, Marco; Riesmeier, Jörg; Jensch, P.

doi:10.1007/978-3-642-15816-2_17

Cited by 17 publications

(8 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…COVLIAS 1.0 is an AI system that employed two HDL models (VGG-SegNet and ResNet-SegNet), while MedSeg used its own DL model. COVLIAS was designed to work on PNG, JPEG, DICOM, and NIfTI images, while MedSeg can only work on NIfTI [ 68 ] or DICOM [ 71 ] format images. Both COVLIAS and MedSeg processed the binary mask images to compute the lung area during performance evaluation.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

COVLIAS 1.0 vs. MedSeg: Artificial Intelligence-Based Comparative Study for Automated COVID-19 Computed Tomography Lung Segmentation in Italian and Croatian Cohorts

Suri¹,

Agarwal

Carriero

et al. 2021

Diagnostics

View full text Add to dashboard Cite

(1) Background: COVID-19 computed tomography (CT) lung segmentation is critical for COVID lung severity diagnosis. Earlier proposed approaches during 2020–2021 were semiautomated or automated but not accurate, user-friendly, and industry-standard benchmarked. The proposed study compared the COVID Lung Image Analysis System, COVLIAS 1.0 (GBTI, Inc., and AtheroPointTM, Roseville, CA, USA, referred to as COVLIAS), against MedSeg, a web-based Artificial Intelligence (AI) segmentation tool, where COVLIAS uses hybrid deep learning (HDL) models for CT lung segmentation. (2) Materials and Methods: The proposed study used 5000 ITALIAN COVID-19 positive CT lung images collected from 72 patients (experimental data) that confirmed the reverse transcription-polymerase chain reaction (RT-PCR) test. Two hybrid AI models from the COVLIAS system, namely, VGG-SegNet (HDL 1) and ResNet-SegNet (HDL 2), were used to segment the CT lungs. As part of the results, we compared both COVLIAS and MedSeg against two manual delineations (MD 1 and MD 2) using (i) Bland–Altman plots, (ii) Correlation coefficient (CC) plots, (iii) Receiver operating characteristic curve, and (iv) Figure of Merit and (v) visual overlays. A cohort of 500 CROATIA COVID-19 positive CT lung images (validation data) was used. A previously trained COVLIAS model was directly applied to the validation data (as part of Unseen-AI) to segment the CT lungs and compare them against MedSeg. (3) Result: For the experimental data, the four CCs between COVLIAS (HDL 1) vs. MD 1, COVLIAS (HDL 1) vs. MD 2, COVLIAS (HDL 2) vs. MD 1, and COVLIAS (HDL 2) vs. MD 2 were 0.96, 0.96, 0.96, and 0.96, respectively. The mean value of the COVLIAS system for the above four readings was 0.96. CC between MedSeg vs. MD 1 and MedSeg vs. MD 2 was 0.98 and 0.98, respectively. Both had a mean value of 0.98. On the validation data, the CC between COVLIAS (HDL 1) vs. MedSeg and COVLIAS (HDL 2) vs. MedSeg was 0.98 and 0.99, respectively. For the experimental data, the difference between the mean values for COVLIAS and MedSeg showed a difference of <2.5%, meeting the standard of equivalence. The average running times for COVLIAS and MedSeg on a single lung CT slice were ~4 s and ~10 s, respectively. (4) Conclusions: The performances of COVLIAS and MedSeg were similar. However, COVLIAS showed improved computing time over MedSeg.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The basic requirements to run this tool are an up-to-date web browser, keyboard, mouse, and a GPU (for increasing the efficiency of segmentation). This tool accepts data in NIfTI [ 68 ] or DICOM [ 71 ] format. It is an interactive tool where the user can either drag and drop the image or select it from the directory.…”

Section: Discussionmentioning

confidence: 99%

COVLIAS 1.0 vs. MedSeg: Artificial Intelligence-Based Comparative Study for Automated COVID-19 Computed Tomography Lung Segmentation in Italian and Croatian Cohorts

Suri¹,

Agarwal

Carriero

et al. 2021

Diagnostics

View full text Add to dashboard Cite

show abstract

“…The selection of a hanging protocol takes place after a radiologist selected a case in their worklist. It is based on specific keywords in the DICOM header [109], [119]. This formal description includes the imaging modality, e.g., CT, specific parameters of the examination, e.g., the anatomical region that is displayed, and the reason for the examination.…”

Section: B Hanging Protocolsmentioning

confidence: 99%

A Survey of Medical Visualization through the Lens of Metaphors

Preim,

Meuschke,

Weis

2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

We provide an overview of metaphors that were used in medical visualization and related user interfaces. Metaphors are employed to translate concepts from a source domain to a target domain. The survey is grounded in a discussion of metaphor-based design involving the identification and reflection of candidate metaphors. We consider metaphors that have a source domain in one branch of medicine, e.g., the virtual mirror that solves problems in orthopedics and laparoscopy with a mirror that resembles the dentist's mirror. Other metaphors employ the physical world as the source domain, such as crepuscular rays that inspire a solution for access planning in tumor therapy. Aviation is another source of inspiration, leading to metaphors, such as surgical cockpits, surgical control towers, and surgery navigation according to an instrument flight. This paper should raise awareness for metaphors and their potential to focus the design of computer-assisted systems on useful features and a positive user experience. Limitations and potential drawbacks of a metaphor-based user interface design for medical applications are also considered.

show abstract

“…In addition, lower black luminance can provide expression of displayed object in more detail at low luminance range because human visual system is more sensitive to luminance change in dark region. Digital imaging and communications in medicine (DICOM) published by National Electrical Manufacturers Association (NEMA), developed grayscale standard display function based on human contrast sensitivity and Barten's model [8]. Grayscale standard display function is described as a function of just noticeable difference (JND) index and luminance.…”

Section: Figure 2 An Example Of Simultaneous Contrast Effectmentioning

confidence: 99%

P‐13: Picture Quality of In‐Plane Switching Liquid Crystal Displays with Deep Black

Kwon,

Lim,

Park

et al. 2023

Symp Digest of Tech Papers

View full text Add to dashboard Cite

In‐Plane Switching (IPS) liquid crystal display (LCD) is one of leading technologies in display industrials because of its superior picture quality. This paper provides picture quality of high contrast IPS LCD in terms of color contrast, dynamic range, color expression and PQ‐EOTF accuracy in HDR compared to conventional IPS LCD. Furthermore, to evaluate its performance as a gaming display, reaction time between two IPS LCDs have different contrast ratio was tested. Experimental results indicate that observer's reaction time for high contrast IPS LCD was faster than conventional IPS LCD because of superior color contrast and color gamut at low luminance level.

show abstract

Digital Imaging and Communications in Medicine

Cited by 17 publications

References 1 publication

COVLIAS 1.0 vs. MedSeg: Artificial Intelligence-Based Comparative Study for Automated COVID-19 Computed Tomography Lung Segmentation in Italian and Croatian Cohorts

COVLIAS 1.0 vs. MedSeg: Artificial Intelligence-Based Comparative Study for Automated COVID-19 Computed Tomography Lung Segmentation in Italian and Croatian Cohorts

A Survey of Medical Visualization through the Lens of Metaphors

P‐13: Picture Quality of In‐Plane Switching Liquid Crystal Displays with Deep Black

Contact Info

Product

Resources

About