All classes Deep Learning CNN-LSTM Pneumonia Detection Syllabus · Episode 4 of 6

Class Deep Learning CNN-LSTM Pneumonia Detection #4: Hybrid CNN-LSTM Architecture: Spatial Features + Sequence

3 views

PyTorch CNN-LSTM hybrid architecture tutorial for medical images: combining CNN spatial features with bidirectional LSTM. Episode 4 of the pneumonia detection series from chest X-rays.

Software: Deep Learning (PyTorch)
Level: Advanced
Duration: ± 7 min
Series total: 57 min · 6 videos
Published: October 24, 2026

Episode 4 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 Deep Learning Courses Ask on WhatsApp

Recommended classes for you

Picked from the software, topic, and level of “Class Deep Learning CNN-LSTM Pneumonia Detection #4: Hybrid CNN-LSTM Architecture: Spatial Features + Sequence”.

6 episodesFree preview

Python · Intermediate–Advanced

Electric Load Forecasting with LSTM

6 video lessons with PDF guides, 53 min in total. Starts with: Hourly Electricity Load Data: Daily, Weekly, and Seasonal Patterns.

53 min 0 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

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 10 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 69 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 74 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

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

6 episodesFree preview

Python · Intermediate–Advanced

Brain Tumor Segmentation with U-Net

6 video lessons with PDF guides, 1 h 10 min in total. Starts with: Brain MRI Dataset & Tumor Mask: Loading, Visualization & Patient-wise Splitting.

1 h 10 min 28 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 hybrid CNN-LSTM architecture we designed ourselves. CNN extracts spatial features from the ronken, then the bidirectional LSTM reads the feature map row by row, from the top of the lung down to the base, like a doctor's eye tracing the image. We also check the tensor shape at each stage to make sure nothing is wrong. Let's start. Hello, welcome to episode four of the hybrid CNN-LSTM model series for early detection of lung diseases. This is the core of our research. CNN is very good at recognizing local patterns such as edges and textures, but it doesn't pay much attention to the relationship between distant parts of the image. LSTM, a type of recurrent neural network, excels at understanding sequences and context. By combining both, the model can see local details as well as patterns from top to bottom of the lung.

Step 1: CNN Section

Create a model file named underscore hybrid dot py. The first part is the CNN, the same as the baseline, 3 blocks on to the, back norm, relu, and max pull. For 64x64 images, the output is a 64-channel feature map of size 8x8. Using the same CNN makes the comparison with the baseline fair. The difference in results truly comes from the addition of LSTM. The second part is the bidirectional or bidirectional LSTM.

Step 2: Bidirectional LSTM

The input size is 64 channels x 8 columns, that is 512, with hidden size 128. Because it's bidirectional, the output is 256. One direction reads from top to bottom, the other from bottom to top. Then dropout and linear to the two classes. The key lies in the forward method.

Step 3: Feature Map to Sequence

Feature maps have the shape back, channel, height, width. With permute, we move height to the front, then reshape, so that each row of the feature map becomes one time step containing 512 numbers. Thus, LSTM reads eight time steps, each representing one horizontal lung stripe. The output of the last time step is used for classification.

Step 4: Checking Tensor Shape

When designing the architecture, always check the tensor shape. We send back four random images, then print the shape at each stage. Input 4, 1, 64, 64, output CNN 4, 64, 8, 8, sequence LSTM 4, 8, 512, and final output 4, 2. The number of parameters is around 680 thousand, much larger than the CNN baseline which is around 32 thousand, due to the LSTM weights.

Done!

Done. We have designed the hybrid CNN-LSTM architecture, understood how to convert feature maps into sequences, used bidirectional LSTM, and verified the tensor shape. In the next episode, we will train this model with class weights, learning rate scheduler, and early stopping. Working on a thesis, dissertation, or AI research in the field of medical imaging? Cerdas Inovasi Digital helps implement deep learning, from CNN, LSTM, hybrid models, up to CAM grade interpretation and result writing, as well as opening deep learning courses with Python. Want to master the entire series, from Röntgen datasets to evaluation and CAM grading? All six episodes, complete with step-by-step PDF guides and source code, are available to premium tutorial subscribers. Subscribe starting at Rp69.000 per month, save 28% with the 12-month package, or pay once Rp999.000 for lifetime access. Want a single class only? Buy individual classes with lifetime access. Subscribe now at the premium page cerdasinovasidigital.com. Contact our WhatsApp, or visit cerdasinovasidigital.com. Thank you for watching, see you in the next episode. Thank you for watching,

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

1:00Step 1: CNN Section

2:49Step 2: Bidirectional LSTM

3:19Step 3: Feature Map to Sequence

4:05Step 4: Checking Tensor Shape

5:39Done!

Ask the class material

My notes

Questions & answers

Your instructor

Recommended classes for you

Need more than a video?

Transcript

0:03Introduction

1:00Step 1: CNN Section

2:49Step 2: Bidirectional LSTM

3:19Step 3: Feature Map to Sequence

4:05Step 4: Checking Tensor Shape

5:39Done!

Ask the class material

My notes

Questions & answers

Your instructor

Introduction

Step 1: CNN Section

Step 2: Bidirectional LSTM

Step 3: Feature Map to Sequence

Step 4: Checking Tensor Shape

Done!

Introduction

Step 1: CNN Section

Step 2: Bidirectional LSTM

Step 3: Feature Map to Sequence

Step 4: Checking Tensor Shape

Done!