We will stick to low frequency probes here (i.e. curvilinear and phased array - linear has its own purpose for detailed pleural assessment)
Which preset do you prefer for B line assessment?
2/
A tweetorial on optimal machine settings for B line image acquisition, with a focus on: focal position at pleura, harmonics off, and increased far gain.
Inspired/based on the recent article - https://t.co/vv2xBSZm6N
@cameron_baston @IsaacMatthiasM1
#POCUS #IMPOCUS
1/18
We will stick to low frequency probes here (i.e. curvilinear and phased array - linear has its own purpose for detailed pleural assessment)
Which preset do you prefer for B line assessment?
2/
4/
We won't discuss much about preset or probe type. But we will discuss machine settings to optimize B line quality, based on
1) Theory based on physical basis of B lines
2) In vitro study
3) Study in patients
5/
B lines are
1) reverberation artifacts
2) formed from the pleural interface when the interstitium is thickened
3) span the full depth of the field
See explanation in tweetorial on ABCs of lung ultrasound here
https://t.co/6GPdnK9gUP
6/
When the interstitium thickens, B lines form. The mechanism is not entirely understood. Either
— IM POCUS Focus (@IMPOCUSFocus) September 27, 2019
1) Tetrahedral structure created at the pleural surface continuously reflects
2) Some waves are able to pass through the lung
11/ pic.twitter.com/rrWEI2ICfX
Tissue harmonic imaging is a technology designed to minimize artifact. In theory, harmonics being "on" may reduce B line quantity. The same idea applies for cardiac presets, which tend to minimize artifact.
(Notably, there is conflicting literature here)
7/
Thus it would make sense to put the focus at the pleural line. The focal position is the depth at which lateral resolution is highest, so interstitial thickening is more likely to be detected w pleural at focal position.
Here, focus at 10 cm
8/
9/
Often the brightness of B lines fades deeper into the image due to loss of energy with subsequent reverberations. Increasing the far gain can theoretically improve ease of visualizing B lines in the far field (as shown here).
10/
-focus at pleura
-more far-gain
-lung preset (vs abd)
Did not acheive significance for "harmonics off"
Limitations: one machine (Sparq), needs further study in pts.
https://t.co/jzJmSr0ZRZ
11/
This study sought to test if adjusted settings (developed based on in-vitro experiments) were associated change in perceived quality (and quantity) of B lines.
12/
In a retrospective study, most exams resembled the typical settings (and cardiac was most common preset).
13/
Adj settings were reported to have better quality in ~97% of cases
14/
Though more data is needed, it seems reasonable that for B line assessment:
1) focus set at pleural line
2) harmonics off
3) increased fair gain
Limitations: these were studied as a bundle (not individual). Study not designed to compare probes or presets.
15/
1) Consistency is important, in both clinical practice and in research.
2) The utility of B lines lies in their high sensitivity for interstitial edema. If settings are suboptimum and limit sensitivity, that reduces the power of the B line assessment.
16/
-remember to find the most perpendicular angle to the pleural line. Otherwise you may end up with a non-A non-B pattern, which is non-diagnostic.
-if ribs are obscuring view, can turn probe to remove ribs from view.
17/
18/
Tagging a few #POCUS friends @kyliebaker888 @iceman_ex @msenussiMD @cameron_baston @Manoj_Wickram @DRsonosRD @NephroP @ArgaizR @ria_dancel @hraza222 @ThinkingCC @Wilkinsonjonny @katiewiskar
More from Machine learning
This is a Twitter series on #FoundationsOfML.
❓ Today, I want to start discussing the different types of Machine Learning flavors we can find.
This is a very high-level overview. In later threads, we'll dive deeper into each paradigm... 👇🧵
Last time we talked about how Machine Learning works.
Basically, it's about having some source of experience E for solving a given task T, that allows us to find a program P which is (hopefully) optimal w.r.t. some metric
According to the nature of that experience, we can define different formulations, or flavors, of the learning process.
A useful distinction is whether we have an explicit goal or desired output, which gives rise to the definitions of 1️⃣ Supervised and 2️⃣ Unsupervised Learning 👇
1️⃣ Supervised Learning
In this formulation, the experience E is a collection of input/output pairs, and the task T is defined as a function that produces the right output for any given input.
👉 The underlying assumption is that there is some correlation (or, in general, a computable relation) between the structure of an input and its corresponding output and that it is possible to infer that function or mapping from a sufficiently large number of examples.
❓ Today, I want to start discussing the different types of Machine Learning flavors we can find.
This is a very high-level overview. In later threads, we'll dive deeper into each paradigm... 👇🧵
Last time we talked about how Machine Learning works.
Basically, it's about having some source of experience E for solving a given task T, that allows us to find a program P which is (hopefully) optimal w.r.t. some metric
I'm starting a Twitter series on #FoundationsOfML. Today, I want to answer this simple question.
— Alejandro Piad Morffis (@AlejandroPiad) January 12, 2021
\u2753 What is Machine Learning?
This is my preferred way of explaining it... \U0001f447\U0001f9f5
According to the nature of that experience, we can define different formulations, or flavors, of the learning process.
A useful distinction is whether we have an explicit goal or desired output, which gives rise to the definitions of 1️⃣ Supervised and 2️⃣ Unsupervised Learning 👇
1️⃣ Supervised Learning
In this formulation, the experience E is a collection of input/output pairs, and the task T is defined as a function that produces the right output for any given input.
👉 The underlying assumption is that there is some correlation (or, in general, a computable relation) between the structure of an input and its corresponding output and that it is possible to infer that function or mapping from a sufficiently large number of examples.
Do you want to learn the maths for machine learning but don't know where to start?
This thread is for you.
🧵👇
The guide that you will see below is based on resources that I came across, and some of my experiences over the past 2 years or so.
I use these resources and they will (hopefully) help you in understanding the theoretical aspects of machine learning very well.
Before diving into maths, I suggest first having solid programming skills in Python.
Read this thread for more
These are topics of math you'll have to focus on for machine learning👇
- Trigonometry & Algebra
These are the main pre-requisites for other topics on this list.
(There are other pre-requites but these are the most common)
- Linear Algebra
To manipulate and represent data.
- Calculus
To train and optimize your machine learning model, this is very important.
This thread is for you.
🧵👇
The guide that you will see below is based on resources that I came across, and some of my experiences over the past 2 years or so.
I use these resources and they will (hopefully) help you in understanding the theoretical aspects of machine learning very well.
Before diving into maths, I suggest first having solid programming skills in Python.
Read this thread for more
Are you planning to learn Python for machine learning this year?
— Pratham Prasoon (@PrasoonPratham) February 13, 2021
Here's everything you need to get started.
\U0001f9f5\U0001f447
These are topics of math you'll have to focus on for machine learning👇
- Trigonometry & Algebra
These are the main pre-requisites for other topics on this list.
(There are other pre-requites but these are the most common)
- Linear Algebra
To manipulate and represent data.
- Calculus
To train and optimize your machine learning model, this is very important.
You May Also Like
Following @BAUDEGS I have experienced hateful and propagandist tweets time after time. I have been shocked that an academic community would be so reckless with their publications. So I did some research.
The question is:
Is this an official account for Bahcesehir Uni (Bau)?
Bahcesehir Uni, BAU has an official website https://t.co/ztzX6uj34V which links to their social media, leading to their Twitter account @Bahcesehir
BAU’s official Twitter account
BAU has many departments, which all have separate accounts. Nowhere among them did I find @BAUDEGS
@BAUOrganization @ApplyBAU @adayBAU @BAUAlumniCenter @bahcesehirfbe @baufens @CyprusBau @bauiisbf @bauglobal @bahcesehirebe @BAUintBatumi @BAUiletisim @BAUSaglik @bauebf @TIPBAU
Nowhere among them was @BAUDEGS to find
The question is:
Is this an official account for Bahcesehir Uni (Bau)?
Bahcesehir Uni, BAU has an official website https://t.co/ztzX6uj34V which links to their social media, leading to their Twitter account @Bahcesehir
BAU’s official Twitter account
BAU has many departments, which all have separate accounts. Nowhere among them did I find @BAUDEGS
@BAUOrganization @ApplyBAU @adayBAU @BAUAlumniCenter @bahcesehirfbe @baufens @CyprusBau @bauiisbf @bauglobal @bahcesehirebe @BAUintBatumi @BAUiletisim @BAUSaglik @bauebf @TIPBAU
Nowhere among them was @BAUDEGS to find
