Systems and Methods for Image Processing to Identify Patients with Pulmonary Embolism
A method for processing images of lungs including defining lung segmentation of the lungs, performing deformable image registration on the segmented lungs, performing ventilation estimation operations to determine a ventilation estimation, performing perfusion estimation operations to determine a perfusion estimation, comparing the ventilation estimation to the perfusion estimation, and determining a pulmonary embolism risk score based on the comparison of the ventilation estimation to the perfusion estimation.
1 . A method for processing images of lungs, the method comprising:
defining, via data processing hardware, lung segmentation of the lungs;
performing, via the data processing hardware, deformable image registration on the segmented lungs;
performing, via the data processing hardware, ventilation estimation operations to determine a ventilation estimation;
performing, via the data processing hardware, perfusion estimation operations to determine a perfusion estimation;
comparing, via the data processing hardware, the ventilation estimation to the perfusion estimation; and
determining, via the data processing hardware, a pulmonary embolism risk score based on the comparison of the ventilation estimation to the perfusion estimation.
2 . The method of claim 1 , wherein the images of the lungs are obtained using non-contrast 4-dimensional computed tomography.
3 . The method of claim 1 , further comprising receiving, via the data processing hardware, the images of the lungs.
4 . The method of claim 1 , wherein the lungs are segmented into five regions.
5 . The method of claim 4 , wherein the pulmonary embolism risk score is on a scale from 0 to 5 based on the number of lung regions that have ventilation/perfusion mismatch.
6 . The method of claim 5 , wherein ventilation/perfusion mismatch is defined by:
B
(
Ω
i
;
p
i
,
v
i
)
=
{
0
,
Perf
(
Ω
i
)
<
p
i
and
Vent
(
Ω
i
)
<
v
i
(
Matched
Function
)
0
,
Perf
(
Ω
i
)
≥
p
i
and
Vent
(
Ω
i
)
≥
v
i
(
Matched
Function
)
1
,
Perf
(
Ω
i
)
<
p
i
and
Vent
(
Ω
i
)
≥
v
i
(
Mismatched
Function
)
1
,
Perf
(
Ω
i
)
≥
p
i
and
Vent
(
Ω
i
)
<
v
i
(
Mismatched
Function
)
.
7 . The method of claim 1 , wherein optimal threshold values are determined by:
max
p
,
v
1
❘
"\[LeftBracketingBar]"
I
pos
❘
"\[RightBracketingBar]"
∑
j
∈
I
pos
F
(
s
j
(
p
,
v
)
)
+
1
❘
"\[LeftBracketingBar]"
I
neg
❘
"\[RightBracketingBar]"
∑
j
∈
I
neg
G
(
s
j
(
p
,
v
)
)
.
8 . The method of claim 7 , wherein the optimal solution obtained from the equation in claim 7 is:
v
*
=
[
0.12
0.15
0.15
0.11
0.12
]
,
p
*
=
[
0.03
0.1
0.07
0.01
0.13
]
.
9 . The method of claim 1 , wherein the pulmonary embolism risk score is determined using one or more of artificial intelligence, machine learning, and a neural network.
10 . The method of claim 1 , wherein the pulmonary embolism risk score is determined by:
s
(
p
,
v
)
=
∑
i
=
1
5
B
(
Ω
i
;
p
i
,
v
i
)
.
11 . A system comprising:
data processing hardware; and
memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
defining lung segmentation of the lungs;
performing deformable image registration on the segmented lungs;
performing ventilation estimation operations to determine a ventilation estimation;
performing perfusion estimation operations to determine a perfusion estimation;
comparing the ventilation estimation to the perfusion estimation; and
determining a pulmonary embolism risk score based on the comparison of the ventilation estimation to the perfusion estimation.
12 . The system of claim 11 , wherein the images of the lungs are obtained using non-contrast 4-dimensional computed tomography.
13 . The system of claim 11 , wherein the operations include receiving the images of the lungs.
14 . The system of claim 11 , wherein the lungs are segmented into five regions.
15 . The system of claim 14 , wherein the pulmonary embolism risk score is on a scale from 0 to 5 based on the number of lung regions that have ventilation/perfusion mismatch.
16 . The system of claim 15 , wherein ventilation/perfusion mismatch is defined by:
B
(
Ω
i
;
p
i
,
v
i
)
=
{
0
,
Perf
(
Ω
i
)
<
p
i
and
Vent
(
Ω
i
)
<
v
i
(
Matched
Function
)
0
,
Perf
(
Ω
i
)
≥
p
i
and
Vent
(
Ω
i
)
≥
v
i
(
Matched
Function
)
1
,
Perf
(
Ω
i
)
<
p
i
and
Vent
(
Ω
i
)
≥
v
i
(
Mismatched
Function
)
1
,
Perf
(
Ω
i
)
≥
p
i
and
Vent
(
Ω
i
)
<
v
i
(
Mismatched
Function
)
.
17 . The system of claim 11 , wherein optimal threshold values are determined by:
max
p
,
v
1
❘
"\[LeftBracketingBar]"
I
pos
❘
"\[RightBracketingBar]"
∑
j
∈
I
pos
F
(
s
j
(
p
,
v
)
)
+
1
❘
"\[LeftBracketingBar]"
I
neg
❘
"\[RightBracketingBar]"
∑
j
∈
I
neg
G
(
s
j
(
p
,
v
)
)
.
18 . The system of claim 17 , wherein the optimal solution obtained from the equation in claim 17 is:
v
*
=
[
0.12
0.15
0.15
0.11
0.12
]
,
p
*
=
[
0.03
0.1
0.07
0.01
0.13
]
.
19 . The system of claim 11 , wherein the pulmonary embolism risk score is determined using one or more of artificial intelligence, machine learning, and a neural network.
20 . The system of claim 11 , wherein the pulmonary embolism risk score is determined by:
s
(
p
,
v
)
=
∑
i
=
1
5
B
(
Ω
i
;
p
i
,
v
i
)
.