Singapore Agency for Science, Technology and Research Act (Singapore, SG)
What is a Software Medical Device for Segmenting infarct in diffusion-weighted imaging volume
Is Your Software a Medical Device for Segmenting infarct in diffusion-weighted imaging volume
Cerebral stroke is the most common cause of morbidity and mortality in many countries. People suffering from stroke require prompt treatment and assessment. This helps them to recover some of their neurological functions that were lost in the acutephase. Acute stroke patients can be assessed using two other modalities Perfusion imaging (PI) as well as diffusion-weighted (DWI) in addition to the traditional magnetic resonance imaging (MRI).
Perfusion imaging (PI) is a hemodynamically weighted MR sequences that are built on the movement of magnetic resonance (MR) contrast through the brain’s tissues. The measures of brain perfusion comprise the time of vascular transit, cerebral blood volume, and cerebral blood flow. The continuous analysis of arterial input is used to measure the absolute cerebral blood flow. It involves the measurement of relative blood flow, by comparing the two hemispheres of the brain for differences in regional regions.
Diffusion-weighted images are those that reflect microscopic random motion of water molecules. Images that reflect the microscopic random motion of water molecules are called diffusion-weighted imaging. Water molecules are always in motion and the rate of diffusion is dependent on their energy that is temperature-dependent. Cell membranes and vascular structures, for instance, restrict the diffusion. DWI abnormalities, which are frequently seen in acute strokes, can be a sign of critical Ischemia.
The pulse sequence can be completed by adding two strong gradient pulses to it. This gives diffusion-weighted images. The first pulse de-phases the spins, while the second pulse re-phases the spins if no net movement occurs. If the spins’ net movement occursbetween the gradient pulses, signals are attenuated. The degree of attenuation depends on the magnitude of molecular motion and diffusion weighting. The weighting of diffusion is determined by the strength of diffusion gradients, the duration of the gradients and the time interval between pulses of the gradient.
Automated or semi-automatic tools for evaluating and segmenting acute stroke regions have been suggested. Rapid and precise segmentation of acute infarcts is crucial for evaluation and treatment of stroke patients.
Martel A L, Allder S J Delay G S, Morgan P S and Moody A R, “Measurement of infarct volume in stroke patients by adaptive segmentation of diffusion weighted MR images.” MICCAI, 1679, 22-31, 1998, presents a semi-automatic technique to determine the volume of infarcts using diffusion tensor-MRI. To segment images the adaptive threshold algorithm utilizes a spatial restriction.
Wu Li, Jie Tan, Enzhong Li and Jianping Dai “Robust unsupervised segmentation of the infarct lesion from diffusion Tensor MR images using multiscale statistical classification as well as partial volume voxel reclassification,” Neuroimage, 23, 1507-1518,2004, have proposed an unsupervised method of segmentation using multiscale statistical classification as well as partial volume voxel classification in the case of diffusion tensor MR images. They seek to determine the infarct areas and solve the problem of overlap in intensity due to diffusion anisotropy. This method is claimed to be able to withstand interference and RF inhomogeneities. The method employs DTI volumes to separate and eliminate the artifacts. It’s complex computationally.
Analyzing DWI/PI information is carried out in clinical practice by using manual segmentation and image editing techniques that are available through commercial software. A complete study takes from 15 to 20 minutes for interaction with the user See BarderaA, Boada I, Feixas M, Pedraza S and Rodriguez J, “A Framework to Assist with the diagnosis of acute stroke,” Vision, Modeling, and Visualization (VMV 2005)–Article No. 666, Erlangen, Germany, Nov. 16-18, 2005.
There is a clear need exists for an algorithm for segmentation that is costly computationally and more efficient (capable of completing within less than a minute).
According to one aspect of the invention, there is a method for creating an infarct segment in the diffusion-weighted image (DWI) volume. The DWI volume is comprised of slices, each slice comprising pixels forming an original image. Themethod comprises the steps of: selecting a Region of Interest (ROI) in at least one slice of the DWI volume containing an infarct within the original image with the ROI comprising at a minimum a portion of the slice; choosing an appropriate threshold for the size of the infarct region that specifies an amount of pixels; convolving an energy mask using the selected slice and then normalizing the resulting image to fit within a specified gray scale, and then selecting the ROI of the energy image convolved; determining a threshold for eliminating the background; setting an initial threshold using an image of the ROI of the cut that is not any background area and then creating an initial segmentation of the slice by using the initial threshold; labelingindividual elements of the segmentation that was initially performed and determining a final threshold using histograms of the labeled parts of the initial segmentation. Finally, creating a final segmentation of the slice based on the threshold that is determined at the end.
A method for segmenting an infarct in a volume of diffusion weighted imagery (DWI), is provided in accordance with a different feature. The DWI volume comprises slices, each of which has pixels, which form an original image.The apparatus includes: a module for selecting a Region of Interest (ROI) in at least one slice of the DWI volume that has an infarct from the original image the ROI comprising at least a portion of the slice and a module to select an appropriate threshold for the size of an infarct region with the threshold indicating an amount of pixels that must be incorporated into an energy mask using the selected slice, and normalizing the resulting energy image to occupy a predefined gray scale and a module to select the ROI in the convolved image; a module for eliminating the background as well as a module for determining an appropriate threshold to eliminate the background; a module for determining an initial threshold by using a histogram of the ROI of the slice without abackground region, and performing an initial segmentation of the slice based on the threshold used to determine the initial segmentation as well as a module to label specific components in the segmentation process and a module to determine an appropriate threshold using histograms oflabeled parts of the segmentation that was initially segmented, and performing final segmentation of the slice based on the final threshold.
According to a different aspect of the invention, there is provided a computer-programme product comprising a computer-readable medium that has recorded the computer program used to segment an infarct inside an image that is a diffusion-weighted (DWI)volume. The DWI volume is composed of slices, with each slice comprising pixels that form an original image. The computer program program product comprises: a computer program code module to choose the Region of Interest (ROI) in at least one slice of the DWI volume that contains an infarct within the original image, with the ROI comprising at least one slice; a computer program code module for selecting an appropriate threshold for the size of an infarct, the threshold specifying the minimum amount of pixels; a computer program code module to convolve an energy mask with the selected slice and then normalizing the resulting image to fit within a specified gray scale. A computer program code module that determines the ROI in the convolved energy image and a computer program code module to determine a threshold for eliminating the background; and a computer program code module for determining the threshold that is initialized using a histogram of the ROI of the slice, without a background region and then performing an initial segmentation of the slice by using the initial threshold as well as a computer code module for labeling individual components in the segmentation process that started the slice; and an application program code to determine a final threshold using histograms of the labeled components of the segmentation process, and then performing a final segmentation of the slice based on the final threshold.
Click here to view the patent on USPTO website.Get Patents with PatentPC
What is a software medical device?
The FDA refers to software functions which may include ” Software as a Medical Device” (SaMD) as well as “Software in a Medical Device (SiMD) ), which is software that is part of (embedded in) the medical device.
Section 201(h),?21 U.S.C. 321(h)(1) defines an medical device as an instrument, apparatus, instrument, machine, contrivance, implant or in vitro reagent or any other similar or related item, which includes a component or accessory that’s . . . (b) is intended to identify disease or other conditions or treat, ameliorate or prevent them. (c) can have the potential to alter the body’s structure or function. body of other animals. Thus, to be considered a medical device and therefore subject to FDA regulation, your program must meet one of two criteria:
- It should be designed for use to diagnose or treat patients.
- It is not intended to affect the structure or any function of the body
If the software you use is designed to be used by healthcare professionals to diagnose manage, or treat hospital patient records or other healthcare facilities, the FDA is likely to consider the software to be medical devices and subject to review by the regulatory authorities.
Is Your Software a Medical Device?
The current FDA oversight process, which places more emphasis on the functionality of the software than the platform will ensure that FDA is not regulating medical devices that use functions that pose danger to patient safety. Examples of Device Software and Mobile Medical Apps that FDA is focusing on include
- Software functions that help those suffering from mental illness (e.g., depression, anxiety, and post-traumatic stress disorder (PTSD) for instance.) by providing “Skill of the Day” an approach to behavior or audio message that users can access when experiencing anxiety.
- Software functions provide regular education information, reminders or motivational advice to smokers trying to quit, who are recovering from addiction or pregnant women;
- Software functions that make use of GPS location information to notify asthmatics when they’re in high-risk locations (substance users) and to inform them of potential environmental conditions that could cause symptoms.
- Software that utilizes games and videos to motivate patients to take part in exercise at home.
- Software functions that require the user to input the herb or drug they’d like to use simultaneously and give information on the likelihood of interactions being reported in the literature, as well as a summary of what type of interaction was observed;
- Software functions that use patient characteristics like age, sex and other risk factors for behavior to provide patient-specific screening and counseling, as well as preventive advice from well-known and established authorities;
- Software functions that make use of an inventory of common symptoms and provide information on when to visit the doctor.
- Software functions that guide a user through a questionnaire of symptoms and signs to recommend the kind of health care facility most appropriate for their needs.
- These mobile apps allow users to make nurse calls as well as emergency calls with the internet or cell phone technology.
- Apps that let caregivers or patients to notify emergency situations to first responders through mobile phones
- Software functions that track the use of medication and offer the user with a customized reminder system to help improve medication adherence;
- Software functions that provide patients with a way to access their personal health records including access to data gathered during a prior visit to a doctor or historical trends and analysis of vital indicators (e.g., body temperature, blood pressure, heart rate or respiratory rate);
- Software functions that show patterns in personal health incidents (e.g. hospitalization rates or alert notification rate)
- Software functions permit users to either manually or electronically input blood pressure data, and to share it with e-mail as well as track and track it, and upload it into an electronic or personal health record.
- Mobile apps that allow for tracking and reminders regarding oral health, or tools to track users suffering from gum disease.
- Mobile apps give patients suffering from prediabetes advice or tools to help them develop better eating habits, or to increase physical activity;
- Mobile apps that show at the right time pictures or other messages for a substance abuser who wants to end their addiction;
- Software functions that provide drug-drug interactions and relevant information about safety (side effects, drug interactions and active ingredient) in a report basing on demographic data (age and gender), medical data (current diagnosis), and current medications as well as
- Software functions give the surgeon the list of suggested intraocular lens power and suggested the axis of implantation, based on the information provided by the surgeon (e.g. the predicted surgically-induced astigmatism, patient’s axial distance and preoperative corneal astigmatism, etc.)
- Applications, mostly mobile, that converts mobile devices into medical devices that are regulated.
- Software that is connected to the mobile platform through an instrument or lead to measure and display electrical signals coming from the heart (electrocardiograph; ECG).
- Software that attaches a camera to the mobile platform, or other tools within the platform, to view the eye movements, record and analyze the eye movements to detect balance issues
- Software that collects information about potential donors and sends it to a blood collection facility. The software will determine whether a person is eligible to donate blood or other components.
- Software that connects with an existing device type to regulate its operation, function or energy source.
- Software that alters or blocks the functions of an infusion pump.
- Software that controls the deflation or inflation of a blood pressure cuff
- Software that is used to calibrate hearing aids and to evaluate the electroacoustic frequencyand audio intensity characteristics, as well as coming from hearing aids master hearing aids group hearing aids, or auditory trainers for groups.
What does it mean if your software/SaaS is classified as a medical device?
SaaS founders need to be aware of the compliance risks that medical devices pose. Data breaches are one of the biggest risks. Medical devices often contain sensitive patient data, which is why they are subject to strict regulations. This data could lead to devastating consequences if it were to become unprotected. SaaS companies who develop medical devices need to take extra precautions to ensure their products are safe.
So who needs to apply for FDA clearance? The FDA defines a ?mobile medical app manufacturer? is any person or entity who initiates specifications, designs, labels, or creates a software system or application for a regulated medical device in whole or from multiple software components. This term does not include persons who exclusively distribute mobile medical apps without engaging in manufacturing functions; examples of such distributors may include the app stores.
Software As Medical Device Patenting Considerations
The good news is that investors like medical device companies which have double exclusivity obtained through FDA and US Patent and Trademark Office (USPTO) approvals. As such, the exit point for many medical device companies is an acquisition by cash rich medical public companies. This approach enables medical devices to skip the large and risky go-to-market (GTM) spend and work required to put products in the hands of consumers.
Now that we have discussed the FDA review process, we will discuss IP issues for software medical device companies. Typically, IP includes Patents, Trademarks, Copyrights, and Trade secrets. All of these topics matter and should be considered carefully. However, we will concentrate on patents to demonstrate how careless drafting and lack of planning can lead to problems, namely unplanned disclosures of your design that can then be used as prior art against your patent application.
In general, you should file patent application(s) as soon as practicable to get the earliest priority dates. This will help you when you talk to investors, FDA consultants, prototyping firms, and government agencies, among others. Compliance or other documents filed with any government agency may be considered disclosure to third parties and could make the document public. In general, disclosures to third parties or public availability of an invention trigger a one year statutory bar during which you must file your patent application. Failure to file your application within the required time frame could result in you losing your right to protect your invention.
The information from your FDA application may find its way into FDA databases, including DeNovo, PMA and 510k databases and FDA summaries of orders, decisions, and other documents on products and devices currently being evaluated by the FDA. Your detailed information may be gleaned from Freedom of Information Act requests on your application. This risk mandates that you patent your invention quickly.
When you patent your medical device invention, have a global picture of FDA regulatory framework when you draft your patent application. Be mindful of whether your software/SaaS application discusses the diagnosing and treating patients or affecting the structure or function of the body and add language to indicate that such description in the patent application relates to only one embodiment and not to other embodiments. That way you have flexibility in subsequent discussions with the FDA if you want to avoid classification of your software/SaaS/software as a medical device. In this way, if you wish to avoid FDA registration and oversight, you have the flexibility to do so.
An experienced attorney can assist you in navigating the regulatory landscape and ensure that you comply with all applicable laws. This area of law is complex and constantly changing. It is important that you seek legal advice if you have any questions about whether or not your software should be registered with FDA.
Patent PC is an intellectual property and business law firm that was built to speed startups. We have internally developed AI tools to assist our patent workflow and to guide us in navigating through government agencies. Our business and patent lawyers are experienced in software, SaaS, and medical device technology. For a flat fee, we offer legal services to startups, businesses, and intellectual property. Our lawyers do not have to track time as there is no hourly billing and no charges for calls or emails. We just focus on getting you the best legal work for your needs.
Our expertise ranges from advising established businesses on regulatory and intellectual property issues to helping startups in their early years. Our lawyers are familiar with helping entrepreneurs and fast-moving companies in need of legal advice regarding company formation, liability, equity issuing, venture financing, IP asset security, infringement resolution, litigation, and equity issuance. For a confidential consultation, contact us at 800-234-3032 or make an appointment here.