Abbad M.

Key Skills

Software

Other

OpenCV AI Kit (OAK)

Top Subject Matter

Cardiovascular diagnostics and non-invasive vascular health assessment

Cardiovascular medical imaging and video-based abnormality detection

Top Data Types

Video

Document

Top Task Types

Segmentation

Diagnosis

Freelancer Overview

Project Engineer - SDE, HTIC IIT Madras Research Park (ARTSENS product development and AI-driven healthcare research). Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other and OpenCV AI Kit (OAK). Education includes Bachelor of Technology, National Institute of Technology, Calicut (2023) and Senior Secondary Education, Ghss Tirurangadi (2018). AI-training focus includes data types such as Medical, DICOM, and Video and labeling workflows including Segmentation and Diagnosis.

Labeling Experience

Project Engineer - SDE, HTIC IIT Madras Research Park (ARTSENS product development and AI-driven healthcare research)

OtherSegmentation

Worked as a Project Engineer supporting an AI-driven cardiovascular healthcare product by building and refining data pipelines for imaging-derived analytics. Contributed to non-invasive vascular health assessment workflows that relied on computer vision preprocessing and supervised model evaluation for downstream diagnostics. Assisted with research and iterative testing to improve device accuracy and performance using insights from large-scale patient datasets. • Supported integration of advanced imaging and data analysis features into the ARTSENS platform. • Compiled and analyzed large printer fleet and patient data (~800,000 patients) to generate rightsizing recommendations. • Conducted AI-driven healthcare market research and feasibility analysis using SQL and data analytics. • Helped translate research findings into data-driven strategic recommendations using dashboards and reports.

2023 - Present

CVIP 2023 (project/publication): Automated Deep Learning Technique for Accurate Detection of Regional Wall Motion Abnormality in Echocardiographic Videos

OpenCV AI Kit (OAK)VideoDiagnosis

Developed an automated deep learning system to detect Regional Wall Motion Abnormality (RWMA) from echocardiographic videos for myocardial infarction-related diagnostic support. Implemented a preprocessing pipeline including left ventricular chamber segmentation using U-net, followed by 3D CNN-based RWMA binary classification. Evaluated performance on the HMC-QU dataset and an additional hospital dataset, reporting high accuracy and clinically relevant metrics. • Built CNN architectures for RWMA binary classification on echocardiographic video inputs. • Implemented U-net-based LV segmentation from apical four-chamber (A4C) images. • Performed model evaluation across multiple datasets and reported accuracy, precision, recall, and F1 score. • Demonstrated effectiveness of automated LV segmentation and RWMA identification for cardiovascular diagnostics.

2024 - 2024

Education

Work History