SLIDE 1
Michael Gielda Antmicro
Business Development Manager
23374: Real-Time Scanning with Jetson TX For Skin Cancer Detection
Jeremy Massey Iko
Director
23374: Real-Time Scanning with Jetson TX For Skin Cancer Detection - - PowerPoint PPT Presentation
23374: Real-Time Scanning with Jetson TX For Skin Cancer Detection - - PowerPoint PPT Presentation
23374: Real-Time Scanning with Jetson TX For Skin Cancer Detection Michael Gielda Jeremy Massey Antmicro Iko Business Development Manager Director 1 Skin Cancer Most common form of cancer. ! Skin Cancer Rates Types of skin cancer
SLIDE 2
SLIDE 3
Most common form
- f cancer.
SLIDE 4
Skin Cancer Rates
!
SLIDE 5
Types of skin cancer include:
- Basal Cell Carcinoma (BCC)
- Squamous Cell Carcinoma (SCC)
- Malignant Melanoma (MM)
SLIDE 6
Malignant Melanoma
Comparatively rare form. Highest mortality rate.
SLIDE 7
SLIDE 8
SLIDE 9
Detect it early!
Early surgical intervention is cheap and almost 100% effective.
SLIDE 10
Current Methods
2
SLIDE 11
A
Asymmetry
B
Border
C
Colour
D
Diameter
E
Evolution
Analysis
SLIDE 12
Dermoscopy
SLIDE 13
Photography
SLIDE 14
Digital Dermoscopy Hardware & Software
SLIDE 15
Mapping Software
SLIDE 16
Limitations of Current Methods
3
SLIDE 17
SLIDE 18
Primary: 7.2mm Secondary: 5.9mm
SLIDE 19
Primary: 6.6mm Secondary: 5.1mm
SLIDE 20
Accuracy
Primary: 91.6% Secondary: 86.4%
SLIDE 21
Accurate Affordable
SLIDE 22
Depth Imaging
SLIDE 23
Our patent-pending method of measuring surface features.
SLIDE 24
Figure 1 Figure 2 Figure 3
SLIDE 25
SLIDE 26
Figure 4 Figure 5 Figure 6
SLIDE 27
Figure 7 Figure 8 Figure 9
SLIDE 28
Length: 4.83mm
SLIDE 29
Length: 4.83mm
SLIDE 30
Length: 1.43mm
SLIDE 31
Length: 1.42mm
SLIDE 32
Length: 4.51mm
SLIDE 33
Length: 4.53mm
SLIDE 34
Accuracy > 99%
SLIDE 35
Accurate Affordable
SLIDE 36
SLIDE 37
Device Requirements
- Real-time 3D point cloud registration.
- Real-time 2D de-mosaicing.
- Real-time 3D mesh generation.
SLIDE 38
SLIDE 39
CUDA & Jetson TX
Requirements are well suited to parallel processing and the NVIDIA Jetson TX is perfectly suited for the task.
SLIDE 40
Features
- Depth and colour camera
connected to NVIDIA Jetson TX1/2 module.
- SD card for storage.
- 5” LCD with capacitive touch
screen for UI.
- WiFi Connectivity
- Wired Ethernet
- Debugging via USB UART, OTG
Data acquisition, display & storage: Communication:
SLIDE 41
Getting the Vision / 3D Data
- PixeLink camera for colour data.
(Liquid lens!)
- RealSense SR300 for depth data.
SLIDE 42
SLIDE 43
Challenges for Developing the Hardware
- Compactness
- Easy Handling
- Camera Integration
- Heat Dissipation
SLIDE 44
Compactness
- Dealing with spatial
arrangement between cameras and lighting.
- Battery placement -> serving
as a hand grip.
- Placement of the display.
Making the device portable and reducing overall weight.
SLIDE 45
Easy Handling
- Fully usable in field testing
while fastened.
- Particular sections of PCB
accessible for debugging.
- Convenient dismantling for
hardware maintenance. Plexiglass construction makes (dis)assembling the prototype easy.
SLIDE 46
Camera Integration
USB-FFC adapter board for more robust work with USB 3.0 connectors.
SLIDE 47
Heat Dissipation
Lots of heat sources – heat dissipating aluminum frame.
SLIDE 48
Accurate Affordable
SLIDE 49
Current methods of analysing and monitoring moles are labour intensive making them expensive.
SLIDE 50
Acquisition process has been reduced from potentially hours to a few minutes.
SLIDE 51
System designed with relatively low cost hardware.
SLIDE 52
Accurate Affordable
SLIDE 53
Future
4
SLIDE 54
Automated Analysis
SLIDE 55
Original Corrected Sharpened
SLIDE 56
A
Asymmetry
B
Border
C
Colour
D
Diameter
E
Evolution
SLIDE 57
Thank you!
Jeremy Massey: jeremy@ikocorp.com Michael Gielda: mgielda@antmicro.com
Reach us at: