Date: Thu, 28 Mar 2024 20:43:44 -0500 (CDT)
Message-ID: <325262078.42702.1711676624567@tcia-wiki-rh-1.ad.uams.edu>
Subject: Exported From Confluence
MIME-Version: 1.0
Content-Type: multipart/related;
boundary="----=_Part_42701_1208463223.1711676624563"
------=_Part_42701_1208463223.1711676624563
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Content-Location: file:///C:/exported.html
TCIA Sessions at RSNA 2019
TCIA Sessions at RSNA 2019
TCIA-Initiated
- All Day | AI050 | AI Community, Learning Center<=
br class=3D"_mce_tagged_br">
- Crowds Cure Cancer: Help Annotate Data from the Cancer Imaging =
Archive
- Attendees at this year's RSNA meeting are encouraged to participate in =
an exciting new activity that will provide valuable data to cancer research=
ers working in deep learning, radiomics and radiogenomics. This kiosk offer=
s radiologist attendees an opportunity to participate in a 'crowd-sourcing'=
experiment to accelerate quantitative imaging research. Images are provide=
d by The National Cancer Institute's Cancer Imaging Archive (http://www.cancerimagingarchive.net/), which is a massive public-acces=
s resource of cancer radiology images linked to genetic/proteomic, patholog=
y images and clinical data. Many of these cases lack the tumor-location lab=
els needed by computer scientists to jump-start their work on machine learn=
ing and quantitative imaging radiomics. Participants will be asked to spend=
a few minutes anonymously reviewing cases and visually marking their tumor=
locations. Upon completion, they will receive a ribbon to add to their RSN=
A badge acknowledging their participation. The data resulting from this pro=
cess will be openly shared on TCIA with the radiology and computer science =
communities to accelerate cancer research.
- Sunday 4:00-5:30 PM | RCC13 |&nb=
sp;Room:
C=
reating publicly-accessible radiology imaging resources for Machine Learnin=
g and AI
- Learn from leaders in the fields of radiology and AI about their experi=
ences developing and leveraging publicly-accessible data resources for AI.<=
/li>
- Monday 8:30-10:00 AM | RCA21 | Room: =
=20
An Introduction to =
Using the NIH/NCI's Cancer Imaging Archive (TCIA) (Hands-on)
- Access to large, high quality dat=
a is essential for researchers to understand disease and precision medicine=
pathways, especially in cancer. However HIPAA constraints make sharing med=
ical images outside an individual institution a complex process. The NCI's =
Cancer Imaging Archive (TCIA) addresses this challenge by providing hosting=
and de-identification services which take the burden of data sharing off r=
esearchers. TCIA now contains over 100 unique data collections of more than=
30 million images. Recognizing that images alone are not enough to conduct=
meaningful research, most collections are linked to rich supporting data i=
ncluding patient outcomes, treatment information, genomic / proteomic analy=
ses, and expert image analyses (segmentations, annotations, and radiomic / =
radiogenomic features). This hands-on session will teach the skills needed =
to fully access our existing data as well as learn how to submit new data f=
or potential inclusion in TCIA.
- Monday 10:30-12:00 PM | RCC22 | Room:&n=
bsp;
Novel Discoveries U=
sing the NCI's Cancer Imaging Archive (TCIA) Public Data Sets
- This didactic session will highli=
ght popular data sets and major projects utilizing TCIA with presentations =
from leading researchers and data contributors. Attendees will also learn a=
bout a number of new, major NIH data collection initiatives that are ongoin=
g or coming in the near future which they can leverage in their own researc=
h.
- Wednesday 4:30-6:00 PM | RCC45 | Room:<=
br>
Imaging in Proteogenomics Research<=
/h4>
- Highlight research trends and major NIH new data programs in proteogeno=
mics, and the potential contribution of imaging
- Thursday 8:30-10:00 AM | RC625 | Room: =
Radiomics: Informatics Tools and Databases
- 1) Understand the role of challen=
ges in facilitating reproducible radiomics research. 2) Learn about past ch=
allenges and lessons learned. 3) Learn about best practices based on experi=
ences from multisite challenges. 4) Review the meaning and importance of in=
teroperability for quantitative image analysis tools. 5) Review specific us=
e cases motivating interoperable communication of the analysis results. 6) =
Learn about the tools that support interoperable communication of the analy=
sis results using the DICOM standard. 7) Understand the importance of open =
science methods to facilitate reproducible radiomics research. 8) Become fa=
miliar with publicly available sites where you can download existing radiom=
ic data sets, request to upload new radiomic/radiogenomic data sets, and ma=
nage your research projects, and learn about data citations and new data-ce=
ntric journals which help enable researchers to receive academic credit for=
releasing well-annotated data sets to the public.
- Thursday 4:30-6:00 PM | RCC55 | Room:&n=
bsp;=20
Deep Learning-An Imaging Roadmap
- Deep Learning,' an independent se=
lf-learning computational environment that uses multilayered computational =
neural nets, has generated considerable excitement (as well as concerns and=
misperceptions) in medical imaging. Deep learning computational techniques=
, such as convolutional neural networks (CNNs) generate multiple layer feat=
ure classifiers that extract disease relevant features from entire regions =
of medical images without the need for localization or pre-segmentation of =
lesions. Although CNNs require training on very large image datasets that e=
ncompass particular disease expressions, they can be diagnostically effecti=
ve since no human input of segmentation features such as size, shape, margi=
n sharpness, texture, and kinetics are required. But their immediate and fu=
ture applicability as tools for unsupervised medical decision-making are, a=
s yet, not well understood by most clinical radiologists. This overview ses=
sion of Deep Learning will provide a clearer picture by presenters who are =
active in that field and who can clarify how the unique characteristics of =
Deep Learning could impact clinical radiology. It will address how radiolog=
ists can contribute to, and benefit from, this new technology. Topics of th=
is multi-speaker session will cover: 1) the general principles of deep lear=
ning computational schemas and their mechanisms of handling image inputs an=
d outputs. 2) new technology including hardware shifts in microprocessors f=
rom CPU's to GPU devices that offer significant computational advantages 3)=
how to ensure that Deep Learning results are consistently clinically relev=
ant and meaningful including nodal element tuning and provability so as to =
assure medical care consistency and reproducibility. 4) how to develop and =
leverage datasets for deep learning on archives such as the NIH The Cancer =
Imaging Archive (TCIA) including requirements for input image dataset magni=
tude and completeness of disease spectrum representation. 5) how to embed e=
ssential non-imaging data needed as inputs, (e.g. EHR, outcome, cross-disci=
plinary metadata, and the data pre-processing required to make DICOM ready =
for Deep Learning. The presentations will be at a level understandable and =
relevant to the RSNA radiologist audience.
Do you have a TCIA-related presentation at RSNA that's not listed below?=
Contact the helpdesk to request it be added!
<=
/p>
- Sunday 10:55-11:05 AM | SSA12-02 | Roo=
m:
- FalcoNet-GMC: A 3D Convolutional Neural Network Module for Inst=
ance Segmentation and Quantification of Distant Recurrence from Gynecologic=
al Cancers
- A multifunctional web-based auxil=
iary system for distant recurrence from gynecologic cancer will enhance the=
early detection for salvage treatment, with better segmentation by compart=
ment weight maps.
- Sunday 1:00-1:30 PM | IN006-EB-SUB | Room:
Reproducibility of Quantitat=
ive Features in Prostate mpMRI
- Multiparametric magnetic resonanc=
e imaging (mpMRI) has emerged as a non-invasive modality to diagnose and mo=
nitor prostate cancer. Quantitative metrics on the regions of abnormality i=
n prostate mpMRI has shown to be predictive of clinically significant cance=
r defined by Gleason grade groups. In this study we evaluate the reproducib=
ility of quantitative imaging features using repeated mpMRI on the same pat=
ients. We have shown that some quantitative imaging features are repro=
ducible across sequential prostate mpMRI acquisition at a preset level of f=
ilters. A validated set of reproducible image features in mpMRI will allow =
us to develop a clinically reliable malignance risk stratification score. T=
his will enable the possibility of using imaging as a surrogate to invasive=
biopsies
- Monday 10:30-10:40 AM&nbs=
p;| SSC03-01&nb=
sp;| Room:
- Impact of Interobserver V=
ariability in Manual Segmentation of Non-small Cell Lung Cancer (NSCLC) on =
Computed Tomography
- Discovery of predictive and progn=
ostic radiomic features in cancer is currently of great interest to the rad=
iologic community. Since there is no reliable automated means of segmenting=
lung cancer, tumor labeling is typically performed by imaging analysts, ph=
ysician trainees and attending physicians. Here we examine the impact of le=
vel of specialty training on interobserver variability in manual segmentati=
on of non-small cell lung cancer (NSCLC).
- Monday 10:50-11:00 AM | SSC03-03 | Room:
Co=
rrelation-Incorporated Hierarchical Clustering of High-Dimensional Radiomic=
Features for Prognostic Phenotype Identification of EGFR-mutated Non-Small=
Cell Lung Cancer
- We propose a correlation-incorpor=
ated unsupervised hierarchical clustering algorithm and evaluate it in iden=
tifying computed tomography (CT) radiomic phenotypes of EGFR-mutated non-sm=
all cell lung cancer (NSCLC) in association with patient overall survival.&=
nbsp;CHCA effectively reduces the high dimensionality of radiomic features =
while allowing for robust identification of CT-based phenotypes of EGFR-mut=
ated NSCLC that are associated with patient survival.
- Tuesday 9:20-9:30 AM =
;|RC305-04 | Roo=
m:
- A Radiomics Nomogram Base=
d on Multiregional Features Might Predict MGMT Promoter Methylation of Glio=
blastoma Patients
- To investigate multiregional feat=
ures from multimodal MRI in reflecting O6-methylguanine methyltransferase (=
MGMT) promoter methylation status, and to establish visualized nomogram for=
MGMT methylation prediction of glioblastomas (GBM) patients. The radi=
omics nomogram based on multiregional features from multimodal MRI was prop=
osed in our study, and could individually and visually predict MGMT status =
of GBM patients. In addition, the rEA and rNec areas of GBM play an importa=
nt role in the prediction of MGMT methylation.
- Wednesday 12:45-1:15=
PM | NR386-SD-WEB2 | Room: N/A
Radiogenomic Analysis of Glioblastoma on=
Pre-treatment Gd-T1w MRI Reveals Gender-specific Imaging Features and Sign=
aling Pathways
- Recent epidemiological studies su=
ggest that gender differences in Glioblastoma (GBM) influence the prognosti=
c outcome of patients, and thus should be considered for targeted treatment=
. We hypothesize that (1) radiomic features from GBM sub-compartments (peri=
-tumoral edema, enhancing tumor, non-enhancing and necrotic core) on pre-tr=
eatment Gadolinium(Gd)-T1w MRI will have distinct imaging attributes that a=
re prognostic of gender-specific survival, and (2) corresponding transcript=
omic data can reveal signaling pathways that drive gender-specific tumor bi=
ology and treatment response.
- Thursday 11:30-11:40=
AM | SSQ15-07 | =
Room: N/A
Classification of=
IDH Mutation Status in Brain Tumors using Deep Learning
- Isocitrate dehydrogenase (IDH) mu=
tation status is a widely recognized biomarker in diagnosing and treating p=
rimary brain tumors. Currently, it is determined using immunohistochemistry=
or gene sequencing on tissue specimens, acquired through biopsy or surgery=
. In this work, we developed a fully automated deep-learning network for no=
n-invasive prediction of IDH mutation status using MRI.
- Friday 8:30-10:00 AM | RC825 | Ro=
om:
Radiomics: From Image to Radiomics
- 1) Learn about the role of image =
annotations in radiology and their relevance to enabling interoperability a=
nd for communicating results and value for machine learning and decision su=
pport. 2) Become acquainted with important standards and tools that support=
the creation, management, and use of image annotations. 3) See case exampl=
es of image annotations in practice to enable developing applications that =
help the practice of radiology. 4) Understand the categories of, and the sp=
ecific radiomic image features that can be computed from images. 5) Underst=
and the effect and implications of image acquisition and reconstruction on =
radiomic image features. 6) Learn about workflows that drive the creation o=
f predictive models from radiomic image features. 7) Understand the methods=
for and the potential value of correlating radiological images with genomi=
c data for research and clinical care. 8) Learn how to access genomic and i=
maging data from databases such as The Cancer Genome Atlas (TCGA) and The C=
ancer Imaging Archive (TCIA) databases, respectively. 9) Learn about method=
s and tools for annotating regions within images and link them with semanti=
c and computational features.10) Learn about methods and tools for analyzin=
g molecular data, generating molecular features and associating them with i=
maging features. 11) Learn how deep learning can revolutionize interpretati=
on of medical images.
------=_Part_42701_1208463223.1711676624563--