Medical image segmentation basics in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - Medical image segmentation basics

Which metric matters for medical image segmentation and WHY

In medical image segmentation, we want to measure how well the model separates important areas, like tumors, from the rest. The key metrics are Dice coefficient and Intersection over Union (IoU). These metrics compare the overlap between the model's predicted area and the true area marked by doctors.

Dice and IoU tell us how much the predicted shape matches the real shape. High values mean the model is good at finding the exact regions, which is critical for treatment planning.

Confusion matrix for segmentation (pixel-wise)

      | Predicted Positive | Predicted Negative |
      |--------------------|--------------------|
      | True Positive (TP)  | False Negative (FN) |
      | False Positive (FP) | True Negative (TN)  |

    TP: Pixels correctly predicted as part of the target region.
    FP: Pixels wrongly predicted as part of the target region.
    FN: Pixels missed by the model but actually part of the target.
    TN: Pixels correctly predicted as background.
    

From these, Dice = 2*TP / (2*TP + FP + FN) and IoU = TP / (TP + FP + FN).

Precision vs Recall tradeoff with examples

Precision measures how many predicted pixels are truly part of the target. High precision means few false alarms.

Recall measures how many true target pixels the model found. High recall means few misses.

In medical segmentation, missing a tumor pixel (low recall) can be dangerous. So recall is often more important.

Example: If the model marks many pixels as tumor but some are wrong (low precision), doctors can review and remove mistakes. But if the model misses tumor pixels (low recall), it risks missing disease.

What good vs bad metric values look like

Good: Dice and IoU above 0.8 show strong overlap, meaning the model closely matches the true region.

Bad: Dice below 0.5 means poor overlap, so the model misses or wrongly marks many pixels.

Precision and recall should both be high (above 0.8) for reliable segmentation.

Common pitfalls in segmentation metrics

• Accuracy paradox: Since most pixels are background, a model predicting all background can have high accuracy but zero usefulness.
• Data leakage: Using images from the same patient in training and testing can inflate metrics falsely.
• Overfitting: Very high training Dice but low test Dice means the model memorizes training images but fails on new ones.
• Ignoring class imbalance: Small target regions need metrics like Dice, not accuracy, to fairly evaluate.

Self-check question

Your model has 98% accuracy but 12% recall on tumor pixels. Is it good for production? Why not?

Answer: No, it is not good. The high accuracy is misleading because most pixels are background. The very low recall means the model misses almost all tumor pixels, which is dangerous in medical use.

Key Result

Dice coefficient and recall are key metrics to ensure accurate and safe medical image segmentation.

Practice

1. What is the main goal of medical image segmentation?

easy

A. To separate important parts of an image pixel by pixel

B. To classify the whole image into categories

C. To enhance the brightness of medical images

D. To compress the image for storage

Solution

1. Step 1: Understand segmentation purpose

   Medical image segmentation aims to identify and separate regions of interest within an image at the pixel level.

2. Step 2: Compare options

   Only To separate important parts of an image pixel by pixel describes pixel-level separation, which matches segmentation. Other options describe different tasks.

3. Final Answer:

   To separate important parts of an image pixel by pixel -> Option A

4. Quick Check:

   Segmentation = pixel-level separation [OK]

Hint: Segmentation means pixel-level separation of image parts [OK]

Common Mistakes:

• Confusing segmentation with image classification
• Thinking segmentation enhances image brightness
• Mixing segmentation with image compression

2. Which of the following is the correct way to describe the input and output of a segmentation model?

easy

A. Input: Image; Output: Class label

B. Input: Mask; Output: Image

C. Input: Image; Output: Mask showing segmented regions

D. Input: Text; Output: Image

Solution

1. Step 1: Identify model inputs and outputs

   Segmentation models take images as input and output masks that highlight segmented areas pixel-wise.

2. Step 2: Match options to this understanding

   Input: Image; Output: Mask showing segmented regions correctly states input as image and output as mask. Others mismatch input/output types.

3. Final Answer:

   Input: Image; Output: Mask showing segmented regions -> Option C

4. Quick Check:

   Segmentation model output = mask [OK]

Hint: Segmentation outputs masks, not class labels [OK]

Common Mistakes:

• Confusing segmentation output with classification labels
• Swapping input and output roles
• Assuming text input for image tasks

3. Given this Python snippet using a UNet model for segmentation:

pred_mask = unet_model.predict(test_image)
print(pred_mask.shape)

What does pred_mask.shape represent?

medium

A. The dimensions of the predicted segmentation mask

B. The training loss value

C. The number of classes in the dataset

D. The dimensions of the input image

Solution

1. Step 1: Understand prediction output

   The predict method returns the segmentation mask predicted by the model for the input image.

2. Step 2: Interpret shape attribute

   The shape shows the size (dimensions) of this predicted mask, matching the input image size and channels.

3. Final Answer:

   The dimensions of the predicted segmentation mask -> Option A

4. Quick Check:

   pred_mask.shape = mask size [OK]

Hint: Model.predict returns mask; shape shows mask size [OK]

Common Mistakes:

• Thinking shape shows input image size
• Confusing shape with number of classes
• Mixing shape with loss or metric values

4. You wrote this code to train a segmentation model but get an error:

model.fit(images, masks, epochs=10)

What is a likely cause of the error?

medium

A. The model does not support segmentation

B. The images are grayscale but masks are color

C. The epochs parameter is missing

D. The masks are not the same size as the images

Solution

1. Step 1: Check input-output size requirements

   Segmentation training requires masks to have the same spatial size as input images for pixel-wise comparison.

2. Step 2: Identify common error

   If masks differ in size, model.fit will raise an error due to shape mismatch.

3. Final Answer:

   The masks are not the same size as the images -> Option D

4. Quick Check:

   Mask size must match image size [OK]

Hint: Masks must match image size for training [OK]

Common Mistakes:

• Ignoring mask-image size mismatch
• Assuming epochs parameter causes error
• Thinking color difference causes training error

5. You want to improve segmentation accuracy on small tumors in medical images. Which approach is best?

hard

A. Train only on images without tumors

B. Use a UNet model with skip connections to capture fine details

C. Reduce image resolution to speed up training

D. Use a simple linear model without convolution layers

Solution

1. Step 1: Understand model choice for fine details

   UNet with skip connections preserves spatial details, helping segment small structures like tumors.

2. Step 2: Evaluate other options

   Reducing resolution loses detail; training without tumors ignores target; linear models lack spatial understanding.

3. Final Answer:

   Use a UNet model with skip connections to capture fine details -> Option B

4. Quick Check:

   UNet + skip connections = better small object segmentation [OK]

Hint: UNet skip connections help segment small details [OK]

Common Mistakes:

• Reducing resolution loses important details
• Ignoring tumor images during training
• Using non-convolutional models for images