-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
c20f219
commit 0676db1
Showing
1 changed file
with
107 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,2 +1,107 @@ | ||
| # Malaria-Detection-from-Cell-Images-using-Deep-Learning | ||
| Malaria Detection from Cell Images using Deep Learning - NasNetMobile Model | ||
| ### Malaria Detection from Microscopic-Tissue Images with Deep Learning (Auto ML, Custom Convolutional Neural Network, NasNetMobile) | ||
| <pre> | ||
| Domain : Computer Vision, Machine Learning | ||
| Sub-Domain : Deep Learning, Image Recognition | ||
| Techniques : Deep Convolutional Neural Network, Transfer Learning, ImageNet, Auto ML, NASNetMobile | ||
| Application : Image Recognition, Image Classification, Medical Imaging | ||
| </pre> | ||
|
|
||
| ### Description | ||
| <pre> | ||
| 1. Detected Cancer from microscopic tissue images (histopathologic) with Auto ML (Google’s “NASNet”). | ||
| 2. For training, concatenated global pooling (max, average), dropout and dense layers to the output layer for final output prediction. | ||
| 3. Attained validation accuracy of 95.6% and loss 0.30 on 250K+ (6.5GB+) image cancer dataset. | ||
| </pre> | ||
|
|
||
| #### Code | ||
| <pre> | ||
| GitHub Link : <a href=https://github.com/anjanatiha/Malaria-Detection-from-Cell-Images-using-Deep-Learning>Histopathologic Cancer Detection(GitHub)</a> | ||
| GitLab Link : <a href=https://gitlab.com/anjanatiha/Malaria-Detection-from-Cell-Images-using-Deep-Learnin>Histopathologic Cancer Detection(GitLab)</a> | ||
| Portfolio : <a href=https://anjanatiha.wixsite.com/website>Anjana Tiha's Portfolio</a> | ||
| </pre> | ||
|
|
||
| #### Dataset | ||
| <pre> | ||
| Dataset Name : Malaria Cell Images Dataset | ||
| Dataset Link : <a href=https://www.kaggle.com/iarunava/cell-images-for-detecting-malaria>Malaria Cell Images Dataset (Kaggle)</a> | ||
| <!--- | ||
| Original Paper : <a href=https://jamanetwork.com/journals/jama/fullarticle/2665774>Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer </a> | ||
| Authors: Babak Ehteshami Bejnordi, Mitko Veta, Paul Johannes van Diest | ||
| JAMA (The Journal of the American Medical Association) | ||
| <cite>Ehteshami Bejnordi B, Veta M, Johannes van Diest P, et al. Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer. JAMA. 2017;318(22):2199–2210. doi:10.1001/jama.2017.14585</cite> | ||
| </pre> | ||
| --> | ||
|
|
||
| ### Dataset Details | ||
| <pre> | ||
| Dataset Name : Malaria Cell Images Dataset | ||
| Number of Class : 2 | ||
| </pre> | ||
|
|
||
| | Dataset Subtype | Number of Image | Size of Images (GB/Gigabyte) | | ||
| | :-------------- | --------------: | ---------------------------: | | ||
| | **Total** | 27,588 | 337 MB | | ||
| | **Training** | 20,670 | - MB | | ||
| | **Validation** | 6,888 | - MB | | ||
| | **Testing** | - | - | | ||
|
|
||
|
|
||
| ### Model and Training Prameters | ||
| | Current Parameters | Value | | ||
| | :------------------- | ----------------------------------------------------------: | | ||
| | **Base Model** | NashNetMobile | | ||
| | **Optimizers** | Adam | | ||
| | **Loss Function** | Categorical Crossentropy | | ||
| | **Learning Rate** | 0.0001 | | ||
| | **Batch Size** | 176 | | ||
| | **Number of Epochs** | 10 | | ||
| | **Training Time** | 45 Min | | ||
|
|
||
|
|
||
| ### Model Performance Metrics (Prediction/ Recognition / Classification) | ||
| | Dataset | Training | Validation | Test | | ||
| | :------------------- | -------------: | ------------: | --------: | | ||
| | **Accuracy** | 96.47% | 95.72% | - | | ||
| | **Loss** | 0.14 | 0.30 | - | | ||
| | **Precision** | --- | --- | - | | ||
| | **Recall** | --- | --- | - | | ||
| | **Roc-Auc** | --- | --- | - | | ||
|
|
||
|
|
||
| ### Other Experimented Model and Training Prameters | ||
| | Parameters (Experimented) | Value | | ||
| | :------------------------ | -----------------------------------------------------: | | ||
| | **Base Models** | NashNet(NashNetMobile) | | ||
| | **Optimizers** | Adam | | ||
| | **Loss Function** | Categorical Crossentropy | | ||
| | **Learning Rate** | 0.0001, 0.00001, 0.000001, 0.0000001 | | ||
| | **Batch Size** | 32, 64, 176 | | ||
| | **Number of Epochs** | 10 | | ||
| | **Training Time** | 45 Min | | ||
|
|
||
| <!--- | ||
| ##### Sample Output: | ||
| <kbd> | ||
| <img src=https://github.com/anjanatiha/Histopathologic-Cancer-Detection/blob/master/demo/sample/sample.png> | ||
| </kbd> | ||
| <kbd> | ||
| <a href=https://github.com/anjanatiha/Histopathologic-Cancer-Detection/blob/master/demo/images/result.png>See More Images</a> | ||
| </kbd> | ||
| ##### Confusion Matrix: | ||
| <kbd> | ||
| <img src=https://github.com/anjanatiha/Histopathologic-Cancer-Detection/blob/master/demo/report/CM.png alt="Confusion Matrix" width=800px height=600px> | ||
| </kbd> | ||
| --> | ||
| #### Tools / Libraries | ||
| <pre> | ||
| Languages : Python | ||
| Tools/IDE : Kaggle | ||
| Libraries : Keras, TensorFlow, NasNetMobile | ||
| </pre> | ||
|
|
||
| #### Dates | ||
| <pre> | ||
| Duration : February 2019 - Current | ||
| Current Version : v1.0.0.9 | ||
| Last Update : 03.14.2019 | ||
| </pre> |