SLIDE 1
Radiomics: bringing radiology into the 21 st century Dr Tim Rosenow - - PowerPoint PPT Presentation
Radiomics: bringing radiology into the 21 st century Dr Tim Rosenow - - PowerPoint PPT Presentation
Radiomics: bringing radiology into the 21 st century Dr Tim Rosenow How radiology operates Sometimes hilariously vague Normal abdomen radiographically with no visualized acute diagnostic abnormalities evident within the abdomen on this
SLIDE 2
SLIDE 3
Sometimes hilariously vague
- Normal abdomen radiographically with no
visualized acute diagnostic abnormalities evident within the abdomen on this examination at the present time
- radiographically. Opinion: Abdomen within
the range of normal
SLIDE 4
Reports are poorly repeatable
- “in patients with pneumonia, the
interpretation of the chest X-ray, especially the smallest of details, depends solely on the reader.” Moncada 2010 Braz J Infect Dis
SLIDE 5
Difficult to compare over time
- Baseline scan:
– “Numerous clusters of small nodules, likely inflammatory in nature.”
- Six months later:
– “Heterogeneously distributed clusters of inflammatory nodules.”
SLIDE 6
Radiomics
- Quantitative data extracted from medical
images
- Small or no involvement by humans
– Unbiased, objective, sensitive – Less labour intensive
SLIDE 7
Simple analytics
SLIDE 8
Example: cardiac disease
SLIDE 9
Example: lung V’ and Q’
SLIDE 10
3D models
SLIDE 11
3D model simulations
http://vasclab.mech.uwa.edu.au
SLIDE 12
4D data analysis
SLIDE 13
Artificial intelligence pipelines
PRAGMA-CF: a case study
SLIDE 14
Early intervention
USCF Data Registry Annual Report 2015
SLIDE 15
AREST CF Early Surveillance Program
Birth 1 year Annually to 5 years Clinical progress Bronchoalveolar lavage Chest CT scan Epithelial samples Lung function (MBW, RVRTC, FOT) Exhaled Breath Condensate QoL/Psychosocial 3 months
SLIDE 16
CT lung disease
SLIDE 17
Morphometric analysis
Legend:
- 1. “Normal” lung
- 2. Bronchiectasis
- 3. Mucous plugging
/ consolidation
- 4. Bronchial wall thickening
- 5. Atelectasis
SLIDE 18
Biologic validation
Neutrophils*
- N. Elastase+
PRAGMA-CF 0.41 (0.025) 0.004 CT score 0.31 (0.096) 0.110
N = 60 scans N = 683 scans
* Spearman’s rho (P-value) + Wilcoxon rank-sum P-value
SLIDE 19
Databank and training
- Requires collaboration
- 300 + 900 patients
- 1000 + 2500 scans
- 35,000 annotated slices
- 3.5 million annotations
Machine learning
SLIDE 20
Validation and application
- Interface, integration
and regulation
– FDA – EMA – TGA
- Reserve dataset
OR
- New dataset
- Testing, tweaking
SLIDE 21
Radiologist workflow
SLIDE 22
Generic pipeline
SLIDE 23