← Back to cohort

Ayesha Zafar

FAST · 2019 · i19-1983

—

Phone

—

GitHub

—

Academic

Program

BS Computer Science

CGPA

—

Year

2019

Education

FAST NUCES

Address

—

DOB

—

Career

Current role

—

Target role

—

Skills

Python, Tensorflow, Keras, Angular, Flask, Visual Studio Code, Google Colab, Deep Learning, Multimodal Imaging, UNET, Feature Fusion, 3D Visualization

Verbatim text

The exact text the LLM saw on the page (or the booklet text from the old import). This is what powers semantic search.

IMADOT

IMADOT is an innovative approach for lung tumor detection that utilizes deep learning and multimodal imaging techniques. By integrating CT and PET scans, IMADOT can perform highly accurate segmentation of tumors, enabling doctors to make better informed decisions in radiotherapy. IMADOT's key features include:
- Multimodal imaging: IMADOT takes inputs from both CT and PET scans, allowing doctors to take advantage of the unique benefits of each modality.
- UNET segmentation: IMADOT employs a UNET deep learning model to perform precise segmentation of lung tumors.
- Feature fusion: IMADOT utilizes feature fusion techniques to enhance the accuracy of tumor segmentation.
- 3D visualization: IMADOT generates a 3D model of tumor segmentation to provide doctors with anatomical information that is difficult to obtain through traditional methods.
- Angular frontend: IMADOT's results, including fusion accuracy, tumor type, and probability, are displayed on a user-friendly Angular frontend.
- Web-based: IMADOT is a web-based application, enabling doctors to access its powerful features from anywhere.

Technology Used:
Python, Tensorflow, Keras, Angular, Flask, Visual Studio Code, Google Colab
Supervisor Name:
Dr. Akhtar Jamil
Group Members:
Ayesha Zafar (i19-1983)
Sardar Muneeb (i19-2015)
Muazz Amir (k19-0215)

AI enrichment

Ayesha Zafar is a Computer Science graduate who contributed to a group project developing IMADOT, a deep learning system for lung tumor detection using multimodal imaging. The project involved implementing UNET segmentation and feature fusion with Python, TensorFlow, and Keras, alongside an Angular web interface.

Skills (AI)

["Python", "TensorFlow", "Keras", "Angular", "Flask", "Deep Learning", "Medical Imaging", "UNET", "Feature Fusion", "3D Visualization"]

Status: ai_done

Provenance

Source file: FAST - School of Computing -Graduate Directory-2023.pdf
From job #14 page 286
Created: 1778170170