update readmes

README.md

@@ -1 +1,20 @@
+# Deep Learning-Based Mapping of Tumor Infiltrating Lymphocytes in Whole Slide Images of 23 Types of Cancer  
+
+#### Shahira Abousamra, Rajarsi Gupta, Le Hou, Rebecca Batiste, Tianhao Zhao, Anand Shankar, Arvind Rao, Chao Chen, Dimitris Samaras, Tahsin Kurc, and Joel Saltz, Frontiers in Oncology, 2022.
+
+This is the code associated with our journal. 
+A deep learning workflow to classify 50x50 um tiled image patches (100x100 pixels at 20x magnification) as TIL positive or negative based on the presence of TILs in gigapixel whole slide images (WSIs) from the Cancer Genome Atlas (TCGA). This workflow generates TIL maps to study the abundance and spatial distribution of TILs in 23 different types of cancer.
+
+**WSI Prediction:** 
+The code for TIL map prediction on WSIs is in the folder: `u24\_lymphocyte`.
+To run it through docker, use the docker file: `Dockerfile`.
+Instructions for running the docker are availabel in the folder: `docker\_readme`.
+
+**Source codes for the tensor flow models:** 
+are in the folder `src_incep_vgg_tf`.
+
+**Source codes for processing predictions on test data:** 
+are in the folder `process_results`.
+
+
 

u24_lymphocyte/README.md

@@ -4,28 +4,15 @@ This software implements the pipeline for the lymphocyte classification project.
 
 List of folders and functionalities are below: 
 
-scripts/: contains scripts that connect several sub-functionalities together for complete functionalities such as generating camicroscope heatmaps given svs images.
+scripts/: contains scripts that connect several sub-functionalities together for complete functionalities such as patch extraction and prediction.
 
 conf/: contains configuration. 
 
-csv_generation/: generates csv files which are the input of the clustering algorithm. 
-
-data/: a place where should contain all logs, input/output images, trained CNN models, and large files. 
-
-download_heatmap/: downloads grayscale lymphocyte or tumor heatmaps, and thresholds grayscale heatmaps to binary heatmaps. 
-
-heatmap_gen/: generate json files that represents heatmaps for camicroscope, using the lymphocyte and necrosis CNNs' raw output txt files. 
+data/: a place where should contain all logs, input/output images, and large files. 
 
 patch_extraction/: extracts all patches from svs images. Mainly used in the test phase. 
 
-patch_extraction_from_list/: extracts patches from a list. Used in scenarios like extracting training patches, and extracting stratified sampled patches for rethresholding purpose. 
-
-patch_labeling_web/: a website that label each image as positive/negative/ignore. 
-
-patch_sampling/: samples patches in a stratified manner. Input: grayscale heaetmaps. Output: a list of patches for patch_extraction_from_list/ to extract. 
-
 prediction/: CNN prediction code. 
 
-training/: CNN training code. 
+heatmap_gen/: generate json files that represents heatmaps for quip, using the lymphocyte and necrosis CNNs' raw output txt files. 
 
-third_party/: third party code for CNN.