Synthesis of CC Mammogram & Multi-view Classification using Neural Network

Synthesis of CC Mammogram & Multi-view Classification using Neural Network
Slide Note
Embed
Share

This project proposal focuses on synthesizing CC view mammograms from MLO view using CR-GAN, followed by multi-view breast cancer classification using Parameterized Hypercomplex Neural Network. The methodology involves tasks such as CC view generation, employing PHResNets for classification, and addressing challenges like code availability and memory errors. The dataset comprises pairs from CBIS-DDSM, INBreast, and MIAS databases, showcasing promising preliminary results in terms of AUC and accuracy.

  • Synthesis
  • Mammogram
  • Classification
  • Neural Network
  • Cancer
auran
auran Follow

Uploaded on Feb 17, 2025 | 1 Views

Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.

Download Presentation

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.

E N D

Presentation Transcript

  1. Project Proposal Synthesis of CC view (from MLO view) mammogram using CR-GAN followed by multi-view breast cancer classification using Parameterized hypercomplex neural network. By Neha Ujjainkar & Abhishek Khandekar

  2. . Problem Statement Synthesis of CC view (from MLO view) mammogram using CR- GAN followed by multi-view breast cancer classification using Parameterized hypercomplex neural network. 2

  3. . Method Task 1: CC view generation from the MLO view by using the CR-GAN network. Task 2: To employ parameterized hypercomplex ResNets (PHResNets) for multi-view breast cancer classification 3

  4. . Dataset 1054 pairs from CBIS-DDSM (3000 x 4500 to 4000 x 5700) 188 pairs from INBreast (3328 x 4084 or 2560 x 3328) 330 pairs from MIAS (1024x1024) 4

  5. . Method 5

  6. . Method 6

  7. . Challenges Challenge 1: CR-GAN code was not available. Resolution: Plan to leverage the original CRGAN. Include Progressive growing adaptation as proposed in the PG-GAN study. Reference: GitHub - ziwei-jiang/PGGAN-PyTorch: A pytorch implementation of Progressive Growing GAN. GitHub - bluer555/CR-GAN: Yu Tian et al. "CR-GAN: Learning Complete Representations for Multi-view Generation 7

  8. . Challenges Challenge 2: Patch Training issue Resolution: Got access to a Lab machine (with a GPU) 8

  9. . Challenges Challenge 3: CUDA out-of-memory error Resolution: Halved the batch size. 9

  10. . Challenges Challenge 4: Code is not for Single view PHResnet. Resolution: Option 1: Try to implement code Option 2: Use the single-view mammogram image (MIAS dataset image) along with the rotated image (same single-view image) to form a 2- view 10

  11. . Preliminary Result AUC Acc. % Pre- training AUC (Ours) Acc. % (Ours) Dataset Model Parm# Task 13M 0.7453 73.944 0.737 74.88 CBIS (MLO + original CC) 2.1 PHResNet18 patches 16M 0.70 71.83 0.739 - 75.35 - 2.2 2.3 PHResNet50 PHResNet18 patches patches CBIS (MLO+ synthesized CC) - - 2.4 PHResNet50 patches patches + CBIS 13M 0.81593 83.019 0.793 83.019 INBreast (MLO + original CC) 2.5 PHResNet18 patches + CBIS 16M 0.76 81.13 0.759 80.00 2.6 PHResNet50 patches + CBIS - - 2.7 PHResNet18 INBreast (MLO + synthesized CC) patches + CBIS - - 2.8 PHResNet50 patches + CBIS 0.50 50 - - MIAS (MLO view) 2.9 PHResNet18 13M patches + CBIS - - 2.1 PHResNet50 16M patches + CBIS - - 2.11 PHResNet18 MIAS(MLO+ synthesized CC view) patches + CBIS - - 2.12 PHResNet50 11

  12. . Timeline and Milestones Sr. No 1 2 Milestones Duration 1 week 1 week Completion Date 10/8/2023 10/16/2023 Defining the problem statement. Submit the Project Proposal. 3 Data Exploration and data analysis for task 2. (non-synthesized image only) 1 week 10/22/2023 Splitting the data and pretraining the network on patches for task 2. (non- synthesized image only) Splitting the data and training the model on the whole image for task 2. (non- synthesized image only) Evaluate the performance of the model for task 2. (non-synthesized image only) Data exploration and data analysis for task 1. Implementation of CR-GAN for task 1. Splitting the data and training the model for task 1. Evaluate the performance of the model for task 1 Data Exploration and data analysis for task 2. (Original MLO +synthesized CC image only) Splitting the data and pretraining the network on patches for task 2. (Original MLO +synthesized CC image only) 4 1 week 10/29/2023 5 1 week 11/5/2023 6 7 8 9 10 1 week 0.5 week 2 weeks 0.5 week 0.25 week 11/11/2023 11/14/2023 11/28/2023 12/2/2023 12/4/2023 11 0.5 week 12/7/2023 12 0.5 week 12/10/2023 Splitting the data and training the model on the whole image for task 2. (Original MLO +synthesized CC image only) Evaluate the performance of the model for task 2. (Original MLO +synthesized CC image only) Final testing. 13 0.5 week 12/12/2023 14 0.5 week 12/14/2023 15 0.5 week 12/17/2023 16 Project Presentation 0.5 week 12/20/2023 17 Submit Final Project Report. 0.5 week 12/23/2023 12

  13. References 1. Yamazaki, A., & Ishida, T. (2022). Two-View Mammogram Synthesis from Single-View Data Using Generative Adversarial Networks. Applied Sciences, 12(23), 12206. https://www.mdpi.com/2076- 3417/12/23/12206 2. Tian, Y., Peng, X., Zhao, L., Zhang, S., & Metaxas, D. N. (2018). CR-GAN: learning complete representations for multi-view generation. arXiv preprint arXiv:1806.11191. https://arxiv.org/abs/1806.11191 3. Geras, K. J., Wolfson, S., Shen, Y., Wu, N., Kim, S., Kim, E., ... & Cho, K. (2017). High-resolution breast cancer screening with multi-view deep convolutional neural networks. arXiv preprint arXiv:1703.07047. https://arxiv.org/abs/1703.07047 4. Lopez, E., Grassucci, E., Valleriani, M., & Comminiello, D. (2022). Multi-View Breast Cancer Classification via Hypercomplex Neural Networks. arXiv e-prints, arXiv-2204. https://arxiv.org/pdf/2204.05798.pdf 5.Liu, Y., Zhang, F., Chen, C., Wang, S., Wang, Y., & Yu, Y. (2021). Act like a radiologist: towards reliable multi- view correspondence reasoning for mammogram mass detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10), 5947-5961. https://ieeexplore.ieee.org/abstract/document/9444895 6.Yang, Z., Cao, Z., Zhang, Y., Tang, Y., Lin, X., Ouyang, R., ... & Ma, J. (2021). MommiNet-v2: Mammographic multi-view mass identification networks. Medical Image Analysis, 73, 102204. https://www.sciencedirect.com/science/article/pii/S1361841521002498 13

  14. . Thank You 14

Related


Introduction to Deep Learning: Neural Networks and Multilayer Perceptrons

Introduction to Deep Learning: Neural Networks and Multilayer Perceptrons

ellie
Rainfall-Runoff Modelling Using Artificial Neural Network: A Case Study of Purna Sub-catchment, India

Rainfall-Runoff Modelling Using Artificial Neural Network: A Case Study of Purna Sub-catchment, India

caspian
Graph Neural Networks

Graph Neural Networks

kornelia
Exploring a Cutting-Edge Convolutional Neural Network for Speech Emotion Recognition

Exploring a Cutting-Edge Convolutional Neural Network for Speech Emotion Recognition

mikail
Artificial Neural Networks From Scratch

Artificial Neural Networks From Scratch

inara
A Deep Dive into Neural Network Units and Language Models

A Deep Dive into Neural Network Units and Language Models

rowyn
AI Projects at WIPO: Text Classification Innovations

AI Projects at WIPO: Text Classification Innovations

efa
Assistive Speech System for Individuals with Speech Impediments Using Neural Networks

Assistive Speech System for Individuals with Speech Impediments Using Neural Networks

albi
Neural Quantum States and Symmetries in Quantum Mechanics

Neural Quantum States and Symmetries in Quantum Mechanics

adelinda
Introduction to Neural Networks in IBM SPSS Modeler 14.2

Introduction to Neural Networks in IBM SPSS Modeler 14.2

anouk
BandNet: Neural Network-Based Multi-Instrument Music Composition

BandNet: Neural Network-Based Multi-Instrument Music Composition

lynette
Insights into Biological Synthesis Techniques and Related Work

Insights into Biological Synthesis Techniques and Related Work

charmaine
Convolutional Neural Networks for Sentence Classification: A Deep Learning Approach

Convolutional Neural Networks for Sentence Classification: A Deep Learning Approach

tata_sen
Advanced Classifiers and Neural Networks

Advanced Classifiers and Neural Networks

elwynto
Neural Processing and the Endocrine System

Neural Processing and the Endocrine System

kbart
Neural Network for Car-Passenger Matching in Ride-Hailing Services by Karim Akhnoukh

Neural Network for Car-Passenger Matching in Ride-Hailing Services by Karim Akhnoukh

pbla
Neural Network Control for Seismometer Temperature Stabilization

Neural Network Control for Seismometer Temperature Stabilization

kal_oes
Neural Network Training and Structure

Neural Network Training and Structure

jen_kno
Neural Network Watermarking Technologies

Neural Network Watermarking Technologies

alad
Fruit Image Recognition Using Neural Network by Ekin Yagis & Zain Fuad

Fruit Image Recognition Using Neural Network by Ekin Yagis & Zain Fuad

parx_4
Deep Generative Bayesian Networks in Machine Learning

Deep Generative Bayesian Networks in Machine Learning

alr_bo
Fatty Acid Metabolism in Animals

Fatty Acid Metabolism in Animals

carmina

More Related Content