Hybrid CNN + Radiomics for PET DICOM Classification An advanced deep learning approach combining spatial feature extraction with quantitative medical imaging features. ⚙️ Setup 📊 Dataset 🧠 Hybrid Model 📈 Evaluation Imports Data Prep Architecture Training ROC-AUC 📂 Project Contents & Features ▼ ✅ Loads PET DICOM images ✅ Extracts simple radiomics features ✅ Combines CNN + radiomics (hybrid model) ✅ Trains and evaluates using ROC-AUC 1. Environment Setup & Imports We initialize the environment using PyTorch and necessary medical imaging libraries like Pydicom and SimpleITK....

RNN vs Transformer RNN (Recurrent Neural Network) — Word-by-Word Processing RNNs process text sequentially , one word at a time. At each step, the model reads the current word and updates a hidden memory state that carries information from all previous words. This means each new word depends on the previous words through that hidden state. :contentReference[oaicite:0]{index=0} RNNs are inherently sequential — the next step cannot start until the previous one finishes. :contentReference[oaicite:1]{index=1} Analogy: Imagine an assembly line where each worker only knows what the previous worker passed on — nothing else. Transformers — All Words at Once Using Self-Attention Instead of processing words one by one, Transformers look at the entire sentence simultaneously using a mechanism called ...

What is an LSTM? LSTM (Long Short-Term Memory) is a special kind of Recurrent Neural Network (RNN) designed to remember important information over long time sequences and forget useless stuff. A smart notebook that decides what to remember , what to forget , and what to use right now . Classic RNNs forget quickly. LSTMs were invented to fix that. Mathematical Intuition Each LSTM cell has 3 gates + memory . Let: x t = input at time t h t-1 = previous hidden state c t-1 = previous memory (cell state) Forget Gate – What should I forget? f_t = σ(W_f [h_{t-1}, x_t] + b_f) Outputs values between 0 and 1 0 → forget completely 1 → keep completely Input Gate i_t = σ(W_i [h_{t-1}, x_t] + b_i) ~c_t = tanh(W_c [h_{t-1}, x_t] + b_c) Update Me...