Segment Brain Tumors with U-Net | Dataford Interview Questions

Your question is Segment Brain Tumors with U-Net. Take a moment with it on the right.

Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).

Business Context

MedVision AI is building an assistive tool for radiologists to outline tumors in brain MRI scans. Manual segmentation is slow and variable across annotators, so the team wants a model that produces accurate pixel-level masks for review.

Dataset

You are given a medical image segmentation dataset based on multi-modal brain MRI studies. Each study contains four aligned MRI sequences per patient and a pixel-wise tumor mask. The task is to predict a binary segmentation mask for tumor vs background.

Feature Group	Count	Examples
Image channels	4	T1, T1ce, T2, FLAIR MRI sequences
Spatial dimensions	240 x 240	2D slices extracted from 3D volumes
Labels	1	Binary mask: tumor (1), background (0)
Metadata	3	patient_id, slice_index, study_split

Size: ~12,000 2D slices from 350 patient studies, 4 input channels
Target: Binary pixel-wise segmentation mask
Class balance: Highly imbalanced at pixel level; background dominates and many slices contain small tumor regions
Missing data: No missing labels, but image intensity distributions vary across scanners and hospitals

Success Criteria

A good solution should achieve strong overlap between predicted and true masks, with Dice score >= 0.82 on the held-out test set and stable performance across patients. The model should also avoid missing small tumor regions.

Constraints

Inference should complete in <150 ms per 2D slice on a GPU for batch review workflows
The approach should be robust to limited labeled data
The model should preserve fine spatial detail needed for clinical review

Deliverables

Explain what U-Net is and why it is well-suited for medical image segmentation
Build a training pipeline for binary tumor segmentation
Evaluate the model using segmentation-specific metrics
Describe preprocessing and augmentation choices for MRI data
Discuss deployment tradeoffs such as latency, memory use, and false negatives