Supervisor: 

Svetlana Illarionova, Head of Research Group; 

Maxim Sharaev, Head of BIMAI-Lab

Description: 

The project focuses on developing a comprehensive computer vision system for the automatic analysis of breast cancer histopathological images (H&E staining). The system addresses three interconnected tasks:

1. Classification — determining the status of biomarkers (ER+/ER-, PR+/PR-, HER2+/HER2-) from histopathological image patches.
2. Segmentation — delineating tumor cells, stromal cells, and inflammatory cells.
3. Multi-Task Learning (MTL) — simultaneous cell segmentation and prediction of multiple biomarkers.

What experience will the intern gain?
- Deep Learning skills for medical imaging
- Medical image processing skills for DL
- Model evaluation skills
- Reproducing methods from research papers
- Basics of breast cancer histopathology
- Clinical significance of biomarkers (ER, PR, HER2)

Internship duration: 2 months 

Internship start date: flexible 

Requirements for the candidate:

Required:
Python — confident level
PyTorch or TensorFlow/Keras — basic level (training, datasets, DataLoader)
Knowledge of convolutional neural network basics and encoder-decoder architectures
Understanding of segmentation quality metrics: Dice, IoU, Precision/Recall

Preferred:
Familiarity with Vision Transformers (ViT) and the attention mechanism
Understanding of transfer learning and fine-tuning

Plus:
Familiarity with LoRA / PEFT methods
Experience with albumentations, segmentation-models-pytorch, timm

Monthly compensation: not available

Contact person: Illarionova Svetlana, s.illarionova@skoltech.ru