Identification of Granulomas in the Skin in Various Diseases
This project focuses on the identification and analysis of granulomas in skin tissue across various dermatological and systemic diseases. Granulomas are organized collections of immune cells that appear in conditions such as sarcoidosis, tuberculosis, leprosy, foreign-body reactions, and certain autoimmune disorders. The project aims to study histopathological skin images to recognize granuloma presence, morphology, and distribution.
Mentor Details:
Prof. Iris Barshak
Mentor Details:
Requirments:
Develop AI based solution for recognizing granulomas in skin biopsy images.
Problem Statement
Diagnosing granulomatous skin diseases relies heavily on histopathological examination, which can be time-consuming and subject to inter-observer variability. Granulomas may present with subtle morphological differences depending on the underlying disease, making consistent identification challenging. There is a need for standardized and potentially automated approaches to assist pathologists in recognizing granulomas in skin biopsies.
Project Objectives
Develop AI based solution for recognizing granulomas in skin biopsy images.
Technical Scope
Image analysis
Object detection
Segmentation
Required Knowledge and Prerequisites
Core Requirements
Understanding of fundamental computer vision concepts
Experience with convolutional neural networks (CNNs)
Familiarity with deep learning frameworks (e.g., PyTorch, TensorFlow)
Recommended Background
Ability to work with image and video datasets
Project Difficulty and Expected Level
Overall Difficulty: Medium
This project is well-suited for:
Teams of 1–3 students
This project can also be done coding free with the DeePathology STUDIO
Expected Outcomes
Automated granuloma identification