Medical image segmentation basics in Computer Vision

Introduction

Medical image segmentation helps doctors see and understand important parts of images like tumors or organs clearly.

When doctors want to find the exact size and shape of a tumor in an MRI scan.

To separate different organs in a CT scan for better analysis.

When planning surgery and needing to know where healthy tissue ends and affected tissue begins.

To track how a disease changes over time by comparing segmented images.

For automatic detection of abnormalities in X-ray images.

Syntax

Computer Vision

model = UNet(input_shape=(height, width, channels), num_classes=number_of_classes)
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(train_images, train_masks, epochs=epochs, batch_size=batch_size)

UNet is a popular model architecture for medical image segmentation.

The model learns to assign each pixel in the image to a class, like tumor or healthy tissue.

Examples

This sets up a UNet model for grayscale images with two classes: background and object.

Computer Vision

model = UNet(input_shape=(128, 128, 1), num_classes=2)
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

This trains the model for 10 rounds using 16 images at a time.

Computer Vision

model.fit(train_images, train_masks, epochs=10, batch_size=16)

This predicts segmentation masks and converts probabilities to class index masks.

Computer Vision

predictions = model.predict(test_images)
segmented_images = np.argmax(predictions, axis=-1)

Sample Model

This code builds a simple UNet-like model, trains it on dummy grayscale images with a square mask, and predicts the segmentation mask for one image.

Computer Vision

import numpy as np
import tensorflow as tf
from tensorflow.keras import layers, models

# Simple UNet-like model for demonstration
def simple_unet(input_shape, num_classes):
    inputs = layers.Input(shape=input_shape)
    c1 = layers.Conv2D(16, 3, activation='relu', padding='same')(inputs)
    p1 = layers.MaxPooling2D()(c1)
    c2 = layers.Conv2D(32, 3, activation='relu', padding='same')(p1)
    u1 = layers.UpSampling2D()(c2)
    concat1 = layers.Concatenate()([u1, c1])
    outputs = layers.Conv2D(num_classes, 1, activation='softmax')(concat1)
    return models.Model(inputs, outputs)

# Create dummy data: 10 images 64x64 grayscale, 2 classes
train_images = np.random.rand(10, 64, 64, 1).astype(np.float32)
train_masks = np.zeros((10, 64, 64, 2), dtype=np.float32)
# Create simple masks: class 1 in center square
train_masks[:, 24:40, 24:40, 1] = 1
train_masks[:, :, :, 0] = 1 - train_masks[:, :, :, 1]

model = simple_unet((64, 64, 1), 2)
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

history = model.fit(train_images, train_masks, epochs=3, batch_size=2, verbose=2)

# Predict on one image
pred = model.predict(train_images[:1])
pred_mask = np.argmax(pred, axis=-1)
print('Predicted mask shape:', pred_mask.shape)
print('Unique classes in predicted mask:', np.unique(pred_mask))

Important Notes

Medical image segmentation models often need many labeled images to learn well.

Segmentation output is usually a mask showing which pixels belong to which class.

Accuracy alone may not be enough; metrics like Dice score are common for segmentation.

Summary

Medical image segmentation separates important parts of images pixel by pixel.

UNet is a common model used for this task because it captures details well.

Training needs images and matching masks showing the correct 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