Tag: Neural networks

AI-Assisted Tissue Sparing in Urology

Tissue sparing is a common practice during surgeries. This approach aims to remove as little as possible of the surrounding tissue during a procedure. Studies

Image Analysis and AI for BPH

Recent developments in the field of deep learning and artificial intelligence can aid in BPH detection, classification and treatment. Analyzing ultrasound and MRI images, and using deep-learning segmentation tools to process them, gives a baseline for severity classification by the physician. Follow-up scans can be accurately compared to baseline scans for optimal treatment decision. Real-time tracking, 3D image reconstruction, and fusion can all provide better guidance during stent placement and urinary tract dilation. Prostatectomy procedure can be kept within boundaries at all times.

Endoscopic Procedures using Intravenous OCT

Recently, OCT has emerged as an alternative modality that provides high resolution images. While ultrasound imaging cannot be replaced, adding Intravenous Optical Coherence Tomography (IVOCT) to endoscopy procedures significantly improves image resolution and increases the ability to detect plaque and segment it.

Using AI to Analyse Intravenous Ultrasound Images

Intravenous ultrasound (IVUS) has been used for many years in the diagnosis of cardiovascular diseases. The recent use of deep learning based on convolutional neural networks has shown improved accuracy, and has also enabled additional applications such as plaque detection.

Segmentation in Orthopedics with Deep Learning

Segmentation is highly important both for examination and planning of knee replacement, hip replacement, shoulder surgery, lesion detection, osteotomy and many other orthopedic procedures. Deep Learning is repeatedly being proven to be the most powerful framework for various tasks, and segmentation in orthopedics is no exception. RSIP Vision’s CTO Ilya Kovler explains how to improve the segmentation in orthopedics thanks to AI and deep learning.

Surgical Instrument Segmentation

Using computer vision to identify tools being employed at different stages of a procedure is not only another step toward robotic surgery, it’s a simple, yet very useful tool to streamline and safeguard the surgical process. Surgical instrument (tool) segmentation and classification is a computer vision algorithm that complements workflow analysis. It automatically detects and identifies tools used during the procedure, and assess whether they are used by the surgeon correctly.

AI-based Surgical Workflow Analysis, another big step towards the future of robotic surgery

Surgical workflow analysis is an important safety guard for the surgeon: with it, a computer is able to scan a video of a surgery, either offline after it has already been performed or online during the surgery itself, and automatically identify at what stage the surgery is at. Read about RSIP Vision’s approach, built on many years of experience in the development of practical applications.

Challenges and AI Solutions for Endoscopy

As endoscopic and microscopic image processing, and surgical vision are evolving as necessary tools for computer assisted interventions (CAI), researchers have recognized the need for

Multiplex IF Analysis

The use of deep learning for analysis of multiplex IF has allowed for a much greater accuracy level for the correct phenotypic classification of cells. When combined with RSIP Vision‘s advanced nuclear detection capability, it allows for the simultaneous analysis of multiple florescent markers on a cell by cell basis. This tool is well suited for multiple applications, especially when using multiple markers to characterize distinct cell populations such as in immune-oncology and IBD.

Circulating Tumor Cells (CTCs)

Circulating tumor cells (CTCs) are rare cancer cells that originate from a tumor and then travel through the patient’s blood or lymphatic system. CTCs have

Coronary Arteries Segmentation

Coronary artery disease (CAD) or ischemic heart disease (IHD) has become one of the most common causes of morbidity and mortality worldwide. Patients who suffer

Great Vessels Segmentation with Deep Learning

The great vessels conduct blood to and from the heart. These vessels include the aorta, superior and inferior vena cava, pulmonary arteries and pulmonary veins.

Middle and Inner Ear Segmentation with Deep Learning

Ear pathologies are common in all age groups, and are one of the leading causes for visiting a doctor. In most cases, proper diagnosis can

Larynx Segmentation with Deep Learning

The larynx, also known as the voice box, is a triangular structure in charge of important functions including breathing, voice production and supplying protection to

Lymph Node Segmentation Module

Lymph nodes are routinely examined and assessed during physical examination of patients in a clinic or hospital setting. Enlarged lymph nodes can be indicators of

Brain Ventricles Segmentation with Deep Learning

Early diagnosis and treatment of ventricular system pathologies is crucial. Brain CT has become a leading diagnostic tool due to its high availability and quick image generation, which is useful in emergency room settings such as stroke or traumatic brain injury (TBI). Backed by cutting edge deep neural network and advanced Artificial Intelligence techniques, CT imaging can perform a very accurate brain ventricles segmentation and supply the physicians with crucial information regarding presence of hemorrhage, ischemia, tumors, hydrocephalus, and other pathologies.

Brain Hemorrhage Segmentation with Deep Learning

Prompt diagnosis, monitoring and treatment of intracranial hemorrhage are essential to avoid brain structure damage. This task is made possible by recent AI-based advancements. Image analysis algorithms based on deep learning can rapidly estimate the hemorrhage volume and measure the edematous area around it. Automated image processing algorithms produce a 3D model of the ventricular system, which can ultimately be useful in guidance of the neurosurgeon during brain procedures.

Detection and Tracking of Tumors

RSIP Vision’s oncology software combines detection of lesions and tumors in the human body with tracking those findings along CT scans performed during the research: in particular lung, lymph nodes and liver. These tools enable a quick and accurate assessment of the efficacy of the new treatment.

Automated RECIST Measurement

The golden standard for measuring tumors is the RECIST score. RSIP Vision developed an automated module to accurately measure the RECIST score from CT scans as well as the exact 3D volume of the tumors. Changes in volume are a reliable measure of the progression or remission of the tumor, enabling to evaluate the responsiveness of the treatment in a relatively short time.

Intrusion Detection with Deep Learning

Detecting physical and virtual intrusions is a key process in ensuring information and property security. Physical intrusion detection refers to all attempts at break-ins to

Visible lung cancer on CT scan of chest and abdomen

Chest CT Scan Analysis with Deep Learning

Chest radiography, with modalities such as X-Ray and CT, is now the common practice for the detection and analysis of the progression of lung tumors,

Object Tracking at High fps

Object tracking in video sequences is a classical challenge in computer vision, which finds applications in nearly all domains of the industry: from assembly line

High Resolution Image Reconstruction

Recovering a high-resolution (HR) image from a low resolution one is a classical problem in computer vision for which many algorithms have been developed to

Automated Defect Inspection Using Deep Learning

Convention computer vision technique for automated optical inspection of defects have given satisfactory results, until recent years when deep learning and neural network architectures dramatically improved the detection. Deep learning engineers at RSIP Vision use U-Nets and central image monomers (also called Hu moments) to give our clients the quality of control that they request.

Deep Learning in Cardiology

1.1 Segmentation tasks [10] suggest a new fully convolutional network architecture for the task of cardiovascular MRI segmentation. The architecture is based on the idea

Deep Learning in Pulmonology

Deep learning has been successfully applied in various applications in pulmonary imaging, including CT registration, airway mapping, real time catheter navigation, and pulmonary nodule detection.

Deep Learning in Ophthalmology

Recent works suggest novel deep learning tools for detection, segmentation and characterization of eye disorders. Accurate segmentation of retinal fundus lesions and anomalies in imaging

Deep Learning in Brain Imaging

Recent years’ AI-based advancements in brain imaging have been outstanding. Many of them are precious for the physician to avoid or reduce structural damage and save lives. This article resumes some of those breakthrough innovations in brain imaging brought by Artificial intelligence, computer vision, deep learning and image analysis in performing crucial tasks of automated segmentation, registration, classification, image enhancement and more.

Deep Learning in Medical Imaging

Until only a few years ago, traditional computer vision techniques have provided excellent results to detection and segmentation task. More recently, with the advent of deep learning and neural networks also in medical imaging, we obtain surprisingly better results in all task, be it detection, segmentation, classification and the like. In this article we review the state-of-the-art in the newest model in medical image analysis.

Wafer Macro Defects Detection and Classification

Typical wafer (VLSI) defects are numerous and their detection is a key task in every semiconductor production line. High-resolution scanners are expensive and the process of checking for any local defect is long. Cheaper Macro defects scanning allows to check every wafer rather than recur to sampling-base defect detection. Moreover, our automated wafer defect detection and classification uses state-of-the-art deep learning techniques, able to provide faster and more accurate classifications free of human errors.

Echo Cancellation Using Deep Learning

Complete cancellation of returned acoustic echo signal is still an unresolved issue in signal processing. When a signal from a speaker in one end of

Classification and Segmentation of Dendritic Cells

Dry eye disease (DED) is one of the most common ophthalmic disorders. Inflammation of the ocular surface is controlled by corneal antigen-presenting cells called dendritic

Fingerprint Segmentation Using Deep Learning

Automatic fingerprint recognition systems are based on the extraction of features from scanned fingerprint image. A successful preprocessing of the scan is an important first

Hemorrhage and Edema segmentation with Deep Learning

Intracranial Hemorrhage and Edema Segmentation

An intracranial hemorrhage (ICH) is a condition in which a blood vessel erupts inside the brain, causing internal bleeding. If not treated correctly and immediately,

3D Cardiac MRI automatic segmentation

3D cardiac segmentation from MRI is a precious tool in the hand of the physician to assess pathologies and treatment. RSIP Vision employ Artificial Intelligence techniques for cardiology in order to perform 3D automatic cardiac segmentation. Deep Learning and Convolutional Neural Networks are called in to achieve state-of-the-art accuracy in the fastest time. This article and the accompanying video explain the challenges presented by this task and the way our algorithms provide a world-class solution.

Object Detection Methods for Robots

Robots need to recognize objects, if we want them to perform their activity. To solve this challenge, they take advantage of object detection and classification algorithms which give them the ability to be efficient and practical in the recognition tasks. Machine learning software enable robots to detect all instances of an object. This article details the different classes of object detection methods for robots, including the most sophisticated ones, based on Convolutional Neural Networks.

CT Segmentation in orthopedic surgery

CT image segmentation is a typical phase of orthopedic surgeries in which a visualization system is called to visually support the surgeon’s task. This system

Coronary CT Angiography with Deep Learning

The production of 3D CT images of the heart requires a fast image processing technology, applied simultaneously on multiple scanned layers. To automatically separate the different components of the image, our software locates in the images the muscular layer (myocardium) of the heart needed for the rest of the segmentation in coronary CT angiography. Minimum graph cuts is the technique which provides the clearest tracking and the strongest segmentation results.

Automatic semantic tagging of images

Sites containing huge amounts of content must necessarily recommend only a narrow and relevant list to users. Recommender systems can be seen as tool to automatically generate personalized search preferences, with the purpose of keeping the balance between monetized targeted suggestions and satisfactory user experience. Automatic semantic tagging helps them do just this.

Detecting Mitosis Using Deep Neural Networks

State and progression of breast cancer are assessed through prognostic factors, one of which is the mitotic figure. In a histological sample taken from patients, the fraction of breast tissue cells undergoing replication is used to grade the cancer. RSIP Vision’s algorithms allow fast detection, recognition and classification of the mitotic state of a cell using automatic computational autonomous tools: deep neural networks help distinguish complex patterns in images and finally differentiate between mitotic and non-mitotic cells.

Lungs tumors and nodules segmentation with Deep Learning

It is visually more difficult to identify lung tumors than nodules, since the latter are supposed to have an elliptical shape, while the chromatic aspect of the former is quite hard to distinguish from healthy tissues on a CT image. We use Deep Learning neural networks to overcome this difficulty in a way that is quick to perform, reliable and memory efficient. Our software of computer vision in pulmonology detects and classifies tumors and nodules in the fastest time, to provide our clients a quick and reliable 3D segmentation of lung tumors with Deep Learning.

Airways segmentation with Deep Learning

Image processing is a fundamental technique in the quest to identify lung cancer, one of the main causes of death among both men and women, and many other lung pathologies. For the worst diseases, survival rate depends on the stage in which the disease is diagnosed and correct segmentation of airway vessels offers the most effective solution to determine the lesion’s size and location, significantly improving diagnosis and treatment. Our solution is built upon Deep Learning and neural networks.

Kidney Segmentation

The most dramatically common kidney diseases are: kidney cancer, hitting 50,000 new patients every year only in the U.S.; and kidney failures, which leave the organ unable to remove wastes. Laparoscopic partial nephrectomy operations remove or reduce kidney tumors and some renal malfunctions. We at RSIP Vision help by providing a semi-automatic and very accurate kidney segmentation technique, built on deep learning and neural networks to create a kidney model which would be specific for each patient.

Vessel Segmentation Using Deep Learning

Various segmentation methods, whether based on Convolution Neural Networks or traditional image processing techniques, can be used to delineate the vascular tree in clinical imaging. Given the few features distinguishing veins from arteries (usually brighter and thinner than veins), the challenge consists of training a binary classifier assigning each pixel to the category of vein or artery. This article covers the advantages of using CNNs and deep neural networks for the classification and segmentation of vessels in fundus images.

Finding Cysts, Part Five: Final Detection

The goal is to automatically detect the appearance of Cystoid Macular Edema (CME) in Optical Coherence Tomography (OCT) images. The deep learning technique used, Convolutional Neural Networks, takes as an input patches of pixels from within the retina. These patches were generated from previous segmentation of retinal images. A further segmentation of the retina is performed using an image processing algorithm called SLIC. Every superpixel thus generated, after being labeled as in the OCT scan, is fed into the neural network to detect the cyst.

Automatic Detection of Macular Cysts

A series of five articles on our Cysts Detection project using deep learning and Convolutional Neural Networks: 1) our cyst detection method; 2) the cyst denoising process; 3) the retinal layer segmentation; 4) the automatical seed-detection; 5) the final detection of the cysts. Our method is exceptionally successful at finding the cysts themselves and most of their area. Remarkable results are achieved even when using relatively small datasets in the training process.

Get in touch

Please fill the following form and our experts will be happy to reply to you soon

Tag: Neural networks

Get in touch

Recent News

Upcoming Events

Subscribe to Our Magazines

Follow us