Intelligent Ultrasound Share Discussion Threads

[eeza] 15/11/2023 15:06

If so, should be RNSed.

[gsbmba99] 15/11/2023 14:15

Have a look at Expert 22 BT24 and Expert 20. SonoLystlive appears as a product feature. I think this is new. I believe it was previously a selectable add-on under "Options" in the configuration process (as it currently does for SWIFT BT23).

[bamboo2] 13/11/2023 21:46

Point-of-Care Ultrasound (PoCUS) is now part of Certified Registered Nurse Anesthetist (CRNA) graduation requirements, with the Council on Accreditation (COA) adding PoCUS to the school curriculum in 2022. But CRNA programs are having to adapt with limited structure and resources. We spoke to John Shields, DNP, CRNA; about how PoCUS is changing the landscape of CRNA education and clinical practice.

“it’s an extension of what we use ultrasound for” explained Dr Shields. “CRNAs already use ultrasound for starting IV catheters, arterial lines, and central lines, as well as placing regional anesthesia and blocks, so it’s not like ultrasound is something they’ve never seen before. And with the advent of handhelds, the use of ultrasound in our day-to-day practice is now just a natural extension of what we do.”...more

[bamboo2] 11/11/2023 10:36

40 F, well found! re, "This would seem to indicate that we are very close to a launch of the new Voluson Expert range with Sonolyst Live incorporated as a standard feature"

The pdf doesn't actually seem to specify that SonoLyst Live will become standard, although it does look like it will extend to the Voluson 18. I may not be reading it correctly.

The paperwork outlines...

"..additional AI software features SonoPelvicFloor2.0 (extension of existing Feature SonoPelvicFloor) , SonoAVC2.0 (extension of existing Feature SonoAVC), Fibroid Mapping (as part ofOption SonoGYN) to the system.

Additional the existing features SonoLyst/ Sonolyst Live have been improved

• The proposed Voluson Expert Series 22/20/18 adds additional software features BSI (Blood Speckle Imaging) and Ophthalmic Artery Measurement to the system..."

==========================

I did notice in the results that GEHC don't seem to have made any headway in reducing the waiting list for installation at customers premises. I guess that existing set-ups will be upgraded, which should help IUG income.

[40 fathoms] 11/11/2023 09:36

A bit of an update on the Voluson Expert and sonolyst/sonolyst live.

See the link below to an FDA 510K approval letter taken from the FDA database, note it was only issued on 30th October 2023. For the relevant bits for us look at page 4 & page 10 onwards.



This would seem to indicate that we are very close to a launch of the new Voluson Expert range with Sonolyst Live incorporated as a standard feature.

[bamboo2] 07/11/2023 08:10

Intelligent Ultrasound Group PLC

07 November 2023

Intelligent Ultrasound signs research agreement with University of Dundee to develop AI-based diagnostic tools for liver disease

PRESS RELEASE 07 November 2023: Intelligent Ultrasound Group plc (AIM: IUG), the 'classroom to clinic' ultrasound company, specialising in artificial intelligence (AI) software and simulation, is pleased to announce that it has signed a research agreement with the University of Dundee to initiate the first phase of proof-of-concept work to develop AI-based tools for screening patients with liver disease.

Utilising the comprehensive archive comprising over one million ultrasound images from approximately 50,000 patients from the University of Dundee and NHS Tayside, the Intelligent Ultrasound team intends to create machine-learning models that make it easier to stage liver disease and monitor disease progression.

The agreement, which is mainly royalty-based, will allow Intelligent Ultrasound to develop ultrasound-based AI tools with the potential to support clinicians in the clinical management of metabolic dysfunction-associated steatotic liver disease (MASLD) and its advanced form, metabolic dysfunction-associated steatohepatitis (MASH). MASLD is the leading cause of liver disease and is closely related to obesity, the rates of which are rising. [1] Monitoring MASLD is important as patients in the early stages of the disease may be able to reduce the effects on their liver with dietary and lifestyle changes if caught in time. [2]

Around 30% of the world's population have MASLD, and by 2030 it is expected that healthcare systems will need to accurately stage the disease to allow them to target treatment. [3] As current methods for diagnosis are either invasive, costly, or inaccurate, it is hoped that AI-based ultrasound may prove to be a cost-effective point of care technique that can give clinicians the answers they need.

Nicholas Sleep, COO at Intelligent Ultrasound said:

"We are very pleased to be working with Prof. John Dillon at the University of Dundee on this exciting project. John is a world-renowned hepatologist, having played a major role in introducing Hepatitis C screening in Scotland. His team's clinical experience, combined with the richness of the Dundee dataset, create a strong pairing with Intelligent Ultrasound's expertise in creating healthcare AI solutions. This is a key longer-term step for us as we look to build our fourth AI ultrasound platform and we have high hopes for this proof-of-concept work."

Professor John Dillon, Professor of Hepatology and Gastroenterology, Clinical Professor (Teaching and Research) of Hepatology and Gastroenterology, Molecular and Clinical Medicine at the University of Dundee said:

"One of the largest challenges facing us in medicine today is how to stratify a disease - MASLD - that affects 30% of the global population and find the much smaller group with MASH who are at high risk of complications. I am optimistic that by working with the AI specialists at Intelligent Ultrasound, we may be able to make the widely available ultrasound scanning facilities much more useful by adding the ability to differentiate MASH from MASLD patients."

[40 fathoms] 07/11/2023 07:30

Looks like we are making a start on our 4th AI product ... It has clearly been in the works for a while as they have mentioned liver on a number of occasions over the last couple of years.

Once you move in to diagnosis and disease staging you will also be looking at a much higher value product than the protocol and anatomy highlighting based products we currently have in the market.

With a longer-term view this is very good news indeed.

[eeza] 07/11/2023 07:05

RNS - research agreement

[bamboo2] 05/11/2023 10:24

Regional anaesthesia has traditionally been performed using anatomical landmarks to identify underlying structures, in addition to information gathered from patient symptoms (e.g., paraesthesia), to guide needle placement and injection. The use of electrical stimulation was introduced used to elicit a motor or sensory response, and improve nerve identification.3 Ultrasound image guidance, first described in 1989,4 now forms the basis of practice for most regional anaesthesia.5 Ultrasound-guided regional anaesthesia (UGRA) revolutionised peripheral nerve blockade, with improved success rate, faster onset and reduced rates of complications including vascular injury and local anaesthetic systemic toxicity.5, 6

[bmcollins] 03/11/2023 00:55

@bamboo
Great input, much appreciated. One wonders why the IUG stock has not seen any apparent stakebuilding though, all it seems to see is persistent selling ? Nevertheless even with the selling to me there is a compelling case to hold IUG, if GE do show their hand then that really is the icing on the cake for us holders.

[bamboo2] 02/11/2023 23:13

Q3 2023 GE Healthcare Technologies Inc Earnings Call Transcript



"...We closed the Caption Health acquisition in February, within 6 months, we incorporated this technology into our portfolio, and we're evaluating other ultrasound use cases to drive future growth..."

[bamboo2] 01/11/2023 12:26

eeza, yes they do!

Typically US co's buying UK co's often seem to announce around 1pm GMT

Caption Health was announced on Thursday Feb 9th 2023, 8 trading days after GEHC's Q4 results [Monday Jan 30th 2023]

[eeza] 01/11/2023 10:44

They have an easy candidate under their noses.

[bamboo2] 01/11/2023 10:33

October 31, 2023 at 08:30 am EDT

GE HealthCare Technologies Inc. (NasdaqGS:GEHC) is looking for M&A. Peter Arduini, President and Chief Executive Officer said, "Our strong free cash flow generation in the third quarter positions us to be flexible in our capital allocation priorities. We aim to deliver a dividend while continuing to evaluate organic and inorganic investments and deleveraging opportunities".

[bamboo2] 01/11/2023 10:08

I listened to the GEHC Q3 call yesterday, although some sound quality issues.
Anyone else take a look?

Webcast...
Presentation...
Press Release...



Call...



Call transcription...

[bamboo2] 30/10/2023 15:29

Back to historical support. Added a few more.

GEHC results tomorrow, so we should get a better idea on how the Voluson upgrade is selling.

[40 fathoms] 20/10/2023 23:58

Trade magazine video demonstration of Baby Works

[40 fathoms] 19/10/2023 15:56

I have been following Sonio.ai for a while now. Very good company, in the few areas they overlap they are not really direct competitors and are at least @24 months to 36 months behind IUG and without an OEM deal in the near future they will fall further behind. That said they have a much broader product focus in women's health than we do and that has value. Business wise the off machine model when many/all of the OEMs offer products than can do the same/similar thing I think could be tough.

However, one of the areas where I think IUG Board and management have been very good over the years is to focus on commercial opportunity over what is technologically possible. Looking 12 to 24 months ahead, where I see the really big money is when we move in diagnosis. It is going to take additional cash to validate and to bring to market but we have a clear research advantage in liver disease (both cancer and cirrhosis). Here we may start to see the intersection with at home scanning as a monitoring tool ..... it is all mapped out in the academic research. This and similar will have the potenial for much higher licence fee income per indication than for the anatomy highlighting products. if successful just for liver it could be worth @ US$ 15 million to US$ 20 million per year to IUG, but all of that is for another day and not required to take us to 30p+ per share.

[z1co] 19/10/2023 15:08

bamboo check your messages

[bamboo2] 19/10/2023 15:05

GE HealthCare (Nasdaq: GEHC), a leader in precision care innovation, will announce its third quarter 2023 financial results before the market opens on Tuesday, October 31, 2023. The GE HealthCare management team will also host a conference call and webcast at 8:30 a.m. Eastern Time on that same day, which will be a live webcast and accessible at



The earnings release, accompanying financial information, and webcast replay will also all be posted at the same link on the GE HealthCare Investor Relations website.

[gsbmba99] 19/10/2023 14:38

Ran across another company in the OBGYN ultrasound AI space - sonio.ai based in France. I haven't spent much time looking at it other than to note that it was founded in 2020 and already has an FDA approved product. It looks like they secured €5m seed funding, €10m from EIC accelerator and €13m in Series A. The 510(k) for their FDA approved Sonio Detect product is here ( It's intended to be used concurrently with the exam but doesn't sit on the machine. As it happens, Prof. Magdalena Sanz-Cortes (who tweeted the comment on the AI gestational age presentation) is a member of Sonio.ai's scientific advisory board.

[40 fathoms] 19/10/2023 01:34

I also assume it is Sonolyst live, my suspicion is that we will get an RNS with a formal "GE" launch of the Expert BT24.

Just as a follow on a gestational age product. One would assume based on the patents and the published academic research that this will not only be more accurate but will be faster and automated. No messing around to find the right plane, freezing the the image and then using digital callipers to measure the foetus, then doing all this again in another plane to provide a cross check.

As a general rule we like better, faster and more accurate.

[gsbmba99] 18/10/2023 22:37

Those mean absolute errors are very low and the 95% confidence intervals are very tight (a couple of hours either side of the estimate). I can see why Dr. Sanz (who, incidentally, is a member of the ISUOG Scientific Committee) is very impressed.

I had assumed the "still secret" AI feature was SonoLyst and SonoLystlive. Having the best image selected automatically and also the checklist functionality is now wedded with no longer having to pause and press the image capture button on the machine given the autocapture function. I think I was told that SonoLyst could save up to 30-35% on scan time a few years ago subject to caveats about the baby's position and the skill level of the operator.

[bamboo2] 18/10/2023 21:34

40F, from your post on 7/10/23 I am still waiting for this to materialise...

"a still secret AI feature reducing scanning time by 40%"

[40 fathoms] 18/10/2023 21:14

Gestational age estimation is interesting and has the potential to be very useful. Below is an abstract from a paper from Prof Noble and Prof Papageorghiou published earlier this year.

“ Accurate estimation of gestational age is an essential component of good obstetric care and informs clinical decision-making throughout pregnancy. As the date of the last menstrual period is often unknown or uncertain, ultrasound measurement of fetal size is currently the best method for estimating gestational age. The calculation assumes an average fetal size at each gestational age. The method is accurate in the first trimester, but less so in the second and third trimesters as growth deviates from the average and variation in fetal size increases. Consequently, fetal ultrasound late in pregnancy has a wide margin of error of at least ±2 weeks' gestation. Here, we utilise state-of-the-art machine learning methods to estimate gestational age using only image analysis of standard ultrasound planes, without any measurement information. The machine learning model is based on ultrasound images from two independent datasets: one for training and internal validation, and another for external validation. During validation, the model was blinded to the ground truth of gestational age (based on a reliable last menstrual period date and confirmatory first-trimester fetal crown rump length). We show that this approach compensates for increases in size variation and is even accurate in cases of intrauterine growth restriction. Our best machine-learning based model estimates gestational age with a mean absolute error of 3.0 (95% CI, 2.9-3.2) and 4.3 (95% CI, 4.1-4.5) days in the second and third trimesters, respectively, which outperforms current ultrasound-based clinical biometry at these gestational ages. Our method for dating the pregnancy in the second and third trimesters is, therefore, more accurate than published methods.”