All classes Brain Tumor Segmentation with U-Net Syllabus · Episode 6 of 6

Class U-Net Brain Tumor Segmentation #6: Evaluation of Dice & IoU, Segmentation Overlay, and Before-After Optimization Comparison

4 views

Tutorial on evaluating medical image segmentation: Dice, IoU, false positive, boxplot, and U-Net baseline vs PSO-optimized U-Net overlay results on test MRI brain tumor data. Episode 6, the conclusion of the series.

Software: Deep Learning (PyTorch U-Net)
Level: Advanced
Duration: ± 10 min
Series total: 1 h 10 min · 6 videos
Published: October 24, 2026

Episode 6 of 6 · view syllabus

Subscribe ▶ Watch the video lesson0 plays

Checking access...

Want to go deeper?

Join one of our courses or ask us directly on WhatsApp.

View the full 6-episode syllabus View Medical Image Segmentation Courses Ask on WhatsApp

Recommended classes for you

Picked from the software, topic, and level of “Class U-Net Brain Tumor Segmentation #6: Evaluation of Dice & IoU, Segmentation Overlay, and Before-After Optimization Comparison”.

Deep Learning CNN-LSTM Pneumonia Detection

6 episodesFree preview

Python · Intermediate–Advanced

Deep Learning CNN-LSTM Pneumonia Detection

6 video lessons with PDF guides, 57 min in total. Starts with: Chest X-ray Dataset: Loading, Exploration & Data Splitting.

57 min 22 0

View class

18 episodesFree preview

Python · Beginner–Advanced

Machine Learning Python

18 video lessons with PDF guides, 3 h 41 min in total. Starts with: Introduction to Machine Learning & First Model.

3 h 41 min 61 0

View class

NSGA-II MOPSO Hybrid Multi-Objective Optimization

6 episodesFree preview

Python · Intermediate–Advanced

NSGA-II MOPSO Hybrid Multi-Objective Optimization

6 video lessons with PDF guides, 59 min in total. Starts with: Multi-Objective Optimization: Pareto Front, Dominance, and Test Functions ZDT/DTLZ.

59 min 9 0

View class

50 episodesFree preview

Agentic AI · Beginner–Intermediate

Agentic AI Without Coding

50 video lessons with PDF guides, 14 h 29 min in total. Starts with: Chatbots, Automation, and AI Agents: What's the Difference?.

14 h 29 min 66 0

View class

100 episodesFree preview

Claude · Beginner–Advanced

Claude from Zero to Expert

100 video lessons with PDF guides, 15 h 1 min in total. Starts with: What Claude Is and How It Differs from ChatGPT and Gemini.

15 h 1 min 62 0

View class

6 episodesFree preview

Python · Intermediate–Advanced

Transfer Learning for Leaf Disease

6 video lessons with PDF guides, 1 h 5 min in total. Starts with: PlantVillage Dataset: Folder Structure, Class Distribution & Data Split.

1 h 5 min 9 0

View class

ANFIS Metaheuristics Time Series Forecasting

6 episodesFree preview

Python · Intermediate–Advanced

ANFIS Metaheuristics Time Series Forecasting

6 video lessons with PDF guides, 59 min in total. Starts with: Non-Linear Time Series: Dataset, Stationarity, and Patterns.

59 min 13 0

View class

EKG Arrhythmia Classification Wavelet Deep Learning

6 episodesFree preview

Python · Intermediate–Advanced

EKG Arrhythmia Classification Wavelet Deep Learning

6 video lessons with PDF guides, 56 min in total. Starts with: EKG & EEG Signals: Characteristics and Public Datasets (MIT-BIH).

56 min 2 0

View class

Need more than a video?

Other ways we can help with Python.

Learn with a mentor

Scheduled AI & Machine Learning courses with live guidance and a certificate.

Course

Multi-Objective Optimization Course: NSGA-II, MOPSO & Hybrid Algorithms (Python)

Course

ECG Arrhythmia Classification Course with Wavelet & Deep Learning (PyTorch)

Course

ANFIS + PSO/GA Course for Non-Linear Time Series Forecasting (Python)

See all in AI & Machine Learning →

Have it built for you

No time to learn Python? Our team can do the project for you.

Service

Python Machine Learning — Prediction Models, Customer Segmentation, Fraud Detection & AI Apps

Service

AI Image Creation with Stable Diffusion — Unlimited Custom Visual Production

★ 4.9

Service

AI Image & Video Creation with Leonardo AI — All-in-One Visuals for Business

★ 4.9

See all in AI & Machine Learning →

Get notified about new Python classes

At most one email a week. Unfollow anytime with one click.

Transcript

The full narration of this video. The current sentence is highlighted while the video plays; click any sentence to jump there.

Show transcript

Introduction

Here is the final result, the tumor boundary from the doctor is yellow, the baseline model result is red, and the PSO-optimized model is green, over the MRI image of an unseen patient. The DICE test data increased from 0.72 to 0.77. Let's start. Welcome to the final episode of the brain tumor segmentation series with the metaheuristic-optimized model. We have two models, the baseline model from episode 4 and the PSO-optimized model from episode 5. Now it's time to answer the research question. Does metaheuristic optimization really improve segmentation? We tested on 17 test patients whose data was never used during training or optimization.

Step 1: Load two models

Create an evaluation underscore sec.py file. We read the winning hyperparameters from the history file, then create two models. Baseline with 16 filters, and the optimized model with 18 filters and dropout 0.16. Each weight is loaded from the PT file we have already saved.

Step 2: Dice, IoU & false positive test data

We predict all the test data, 674 slices, 202 of which have tumors. There are four metrics. DAIS and global IOU. DAIS per slice, which is the average DAIS for each tumor slice, which is more sensitive to small tumors. And false positive slices, the percentage of healthy slices incorrectly labeled as having a tumor by the model. The results show that global DAIS increased from 0.721 to 0.770, IOU from 0.563 to 0.626. DAIS per slice increased from 0.568 to 0.632, and false positives decreased from 5.7 to 3.2%. The improvement in test data is actually greater than in validation data. This indicates that the dropout from the optimized model makes the model more capable of generalization.

Step 3: Dice distribution per slice

Now the box plot of DAIS per tumor slice distribution. The median of the optimized model is higher, and more importantly, the box is much tighter. In the baseline, a quarter of the slices have DAIS below 0.33, usually small tumors that are missed. The optimized model is more consistent. This kind of graph is very useful for the results chapter of the research.

Step 4: Overlay segmentation results

Finally, the overlay on 4 test patients with the largest tumors. The top line is the ground root in yellow from the doctor, the middle line is the baseline in red, the bottom line is the optimized model in green, complete with DAIS per slice. Both models accurately detect the tumor, with DAIS ranging from 0.86 to 0.95. The optimized model follows the tumor boundary contours slightly better in 3 out of 4 examples.

Done!

Done, and the series is complete. We have built a complete research on brain tumor segmentation, MRI dataset with per-patient splitting, image and mask augmentation, units from 0, loss base IDAIS, hyperparameter optimization with PSO and grey wolf optimizer, up to DAIS and IOU evaluation on the test data. For further research, try a wider search space, per-patient cross-validation, or architectures like attention units. Thank you for following this series. Currently working on a thesis, dissertation, or AI research in the field of medical image segmentation? Cerdas Inovasi Digital helps with deep learning implementation, from UNET segmentation, hyperparameter optimization with PSO and grey wolf, up to DAIS, IOU evaluation, and result writing, as well as opening deep learning courses with PyTor. Want to master the entire series, from MRI brain datasets up to hyperoptimized UNET? All 6 episodes, complete with PDF step-by-step guides and source code, are available for premium tutorial subscribers. Subscribe starting from Rp69.000 per month Save 28% with the 12-month package, or one-time payment of Rp999.000 for lifetime access. Want a single class only? Buy single classes with lifetime access. Subscribe now on the premium page cerdasinovasidigital.com Contact us via WhatsApp, or visit cerdasinovasidigital.com Thank you for watching, See you in the next episode.

Ask the class material

Type a question or keyword; we find the part of this episode that explains it and jump the video there.

My notes

Notes are saved with the current video time and are only visible to you.

Questions & answers

Stuck on a step? Ask here; the instructor and other learners can answer.

No questions yet.

Your instructor

Cerdas Inovasi Digital Team

Software developers, BIM & 3D engineers, and AI practitioners

53 video classes1,296 episodes

We build software, BIM models, games and AI automations for clients every day, and turn that hands-on work into step-by-step classes: every step is shown on screen and comes with a PDF guide you can keep.

See our clients →

Memuat

Recommended classes for you

Need more than a video?

Transcript

0:03Introduction

0:52Step 1: Load two models

2:23Step 2: Dice, IoU & false positive test data

4:29Step 3: Dice distribution per slice

5:29Step 4: Overlay segmentation results

7:52Done!

Ask the class material

My notes

Questions & answers

Your instructor

Recommended classes for you

Need more than a video?

Transcript

0:03Introduction

0:52Step 1: Load two models

2:23Step 2: Dice, IoU & false positive test data

4:29Step 3: Dice distribution per slice

5:29Step 4: Overlay segmentation results

7:52Done!

Ask the class material

My notes

Questions & answers

Your instructor

Introduction

Step 1: Load two models

Step 2: Dice, IoU & false positive test data

Step 3: Dice distribution per slice

Step 4: Overlay segmentation results

Done!

Introduction

Step 1: Load two models

Step 2: Dice, IoU & false positive test data

Step 3: Dice distribution per slice

Step 4: Overlay segmentation results

Done!