Speaker:  Yuval Tamir

M.Sc. student under the supervision of Hedva Spitzer

Wednesday, December 26^th, 2018 at 15:30

Room 011, Kitot Bldg., Faculty of Engineering

Companding algorithm for enabling detection of malignant lesions in HDR CT mandibular images
 

Abstract

            Compressing and expanding (companding) HDR computerized Tomography (CT) images of X-ray to a single window is still a relevant challenge for several body organs, even though different approaches have been examined. Besides the general need for simplification of the window setting method for diagnosis requirements, there are clinical needs for resection of malignant lesions in the mandible, for example. In this kind of organ (mandible) the lesions often exist in both the soft tissue and the bone. A suggested algorithm has to take into account the requirement to expose differently the same range of specific grey levels, which is presented at different body tissues.

We propose an adaptive multi-scale contrast companding (AMCC) algorithm. A contrast appears stronger or weaker according to its own value and according to its context contrast, at the different spatial resolutions. The AMCC algorithm successfully compands, with adaptive set of parameters, a large variety of mandibular CT HDR images and natural images as well. Two collaborating physicians evaluated the tumor boundaries, by the single presentation method in 108 mandibular CT window setting and algorithm output images. They found that 92% of all algorithm output images showed at least the same evaluations as the window method did, while 50% of the algorithm output images even yielded improved evaluations. When the evaluation of each slice was done simultaneously, by using both window setting (bone and soft tissue) and algorithm output images, 93% of the evaluations showed preference for the algorithm’s output images. We suggest here, for the first time, a low-cost method for companding the HDR images and ability to perform resection with optimal boundaries definition of mandibular lesions.

(The talk will be given in English)

Speaker:     Dr. Gaddi Blumrosen
                   IBM Research

SUNDAY, January 6^th, 2019
15:00 - 16:00

Room 011, Kitot Bldg., Faculty of Engineering

Activity recognition for medical diagnosis– old, current and future technologies

Abstract

Motion and activity recognition and characterization, plays a major role in our life. Activity includes body’s daily life activities, body’s gestures, and its more wide sense also facial expressions. Accurate characterization of the activity, can contribute to well-being by assisting in fields like sport, and in medicine, where it enable detect abnormalities in human behavior, estimate medical score in diseases like Huntington, and Parkinson diseases, and enable continuous monitoring of medical condition. The advantage of automated medical diagnosis, while doing daily life activities are: 1) higher accuracy by applying advanced machine learning techniques and massive trained data, that can overcome human limitation and biases; 2)save patient time travel time to the clinic, clinician time, and minimize hospital resources; and 3) can be used to tune in real-time, drag delivery. In this talk, we will review the current activity assessment methodologies, like inertial sensors and video, and will show new ways for seamless activity monitoring, achieved by deploying new sensing techniques, like radar, sonar, Kinect, and pressure sensors. We will further present advanced methods, that were tailored to the sensors, and can recognize the activity type, level, and estimate medical scores.

Short Bio

Gaddi Blumrosen is a scientist specializing in activity recognition, medical assessment, and medical and biological signal modeling and processing. He holds a BsC, MsC, from the Technion, Tel Aviv, respectively in electrical engineering, and Phd degree from Hebrew University in computer science and biomedical engineering. His research span different areas of signal processing and modeling, and was published in over 25 papers in leading peer reviewed journals and conferences, and he holds 4 patents. In recent years, he conducted research in Tel Aviv University in collaboration of Tel-hashomer, Berkeley, MGH-Harvard medical school, and in New York University, in activity analysis, in providing methods to determine electrical stimulation parameters, and in facial expression analysis. Recently, Gaddi has finished two years research position in sensing computational biology in IBM research at the Computational Biology Center (CBC), where he used signal processing and machine learning techniques for gestures recognition, and for evaluation of Parkinson disease severity.