remove vertebra check

add volume check
download parquet file from github instead of hf

Dockerfile

@@ -20,6 +20,9 @@ RUN pip install --no-cache-dir --upgrade pip
 # Copy the current directory contents into the container at $HOME/app setting the owner to the user
 COPY --chown=user . $HOME/app
 
+# Download the parquet file from github
+RUN wget https://github.com/ImagingDataCommons/CloudSegmentatorResults/releases/download/0.0.1/qual_checks_and_quantitative_measurements-wip.parquet
+
 # Install any needed packages specified in requirements.txt
 RUN pip install --no-cache-dir -r requirements.txt
 

filter_data_app.py

@@ -12,19 +12,19 @@ import seaborn as sns
 st.set_page_config(layout="wide")
 
 # Local path to the Parquet file
-LOCAL_PARQUET_FILE = 'qual-checks-and-quant-values.parquet'
+LOCAL_PARQUET_FILE = 'qual_checks_and_quantitative_measurements-wip.parquet'
 
 @st.cache_data
 def load_data(radiomics_feature='Volume from Voxel Summation'):
     cols = [
         'PatientID',
         'StudyInstanceUID',
-        'seriesNumber',
+        'SeriesNumber',
         'bodyPart',
         'laterality',
         'segmentation_completeness',
         'laterality_check',
-        'series_with_vertabra_on_every_slice',
+        'volume_from_voxel_summation_check',
         'connected_volumes',
         'voxel_num',
         radiomics_feature  # Include the selected radiomics feature column
@@ -62,7 +62,7 @@ def create_upset_plot_failures(df):
 
     # Treat 'pass' and null values as passing
     df = df.set_index(~((df['segmentation_completeness'] == 'pass') | df['segmentation_completeness'].isnull())).set_index(~((df['laterality_check'] == 'pass') | df['laterality_check'].isnull()), append=True)
-    df = df.set_index(~((df['series_with_vertabra_on_every_slice'] == 'pass') | df['series_with_vertabra_on_every_slice'].isnull()), append=True)
+    df = df.set_index(~((df['volume_from_voxel_summation_check'] == 'pass') | df['volume_from_voxel_summation_check'].isnull()), append=True)
     df = df.set_index(~((df['connected_volumes'] == 1) | df['connected_volumes'].isnull()), append=True)
     df = df[df.index.to_frame().any(axis=1)]  # Ignore the case when all conditions are false
 
@@ -75,7 +75,7 @@ def create_upset_plot_failures(df):
 def create_upset_plot_passes(df):
     df = df.to_pandas()  # Convert to Pandas DataFrame
     df = df.set_index(df['segmentation_completeness'] == 'pass').set_index(df['laterality_check'] == 'pass', append=True)
-    df = df.set_index(df['series_with_vertabra_on_every_slice'] == 'pass', append=True)
+    df = df.set_index(df['volume_from_voxel_summation_check'] == 'pass', append=True)
     df = df.set_index(df['connected_volumes'] == 1, append=True)
     df = df[df.index.to_frame().any(axis=1)]  # Ignore the case when all conditions are false
 
@@ -96,7 +96,7 @@ def main():
     st.title("Qualitative Checks of TotalSegmentator Segmentations on NLST")
 
     # Sidebar widgets for navigation and filtering
-    page = st.sidebar.selectbox("Choose a page", ["Summary", "Plots"])
+    page = st.sidebar.selectbox("Choose a page", ["Summary", "Plots"], help='Change the selection here to view dynamically generated plots')
 
     # Load the data
     #df = load_data()
@@ -112,7 +112,7 @@ def main():
                     'bodyPart': None,
                     'segmentation_completeness': None,
                     'laterality_check': None,
-                    'series_with_vertabra_on_every_slice': None,
+                    'volume_from_voxel_summation_check': None,
                     'connected_volumes': None,
                     'laterality': None,
                     'radiomics_feature': 'Volume from Voxel Summation',  # Default radiomics feature
@@ -127,7 +127,7 @@ def main():
                 filters.update({
                     'segmentation_completeness': None,
                     'laterality_check': None,
-                    'series_with_vertabra_on_every_slice': None,
+                    'volume_from_voxel_summation_check': None,
                     'connected_volumes': None,
                     'laterality': None,
                     #'radiomics_feature': 'Volume from Voxel Summation' 
@@ -195,7 +195,7 @@ def main():
             # Update options for other filters based on the current selection
             segmentation_completeness_options = [""] + filtered_df['segmentation_completeness'].unique().to_list()
             laterality_check_options = [""] + filtered_df['laterality_check'].unique().to_list()
-            series_with_vertabra_on_every_slice_options = [""] + filtered_df['series_with_vertabra_on_every_slice'].unique().to_list()
+            volume_from_voxel_summation_check_options = [""] + filtered_df['volume_from_voxel_summation_check'].unique().to_list()
             connected_volumes_options = filtered_df['connected_volumes'].unique().to_list()
             laterality_options = [""] + filtered_df['laterality'].unique().to_list()
             voxel_num_options = filtered_df.filter(col('voxel_num').is_not_null()).select('voxel_num').unique().to_pandas().iloc[:, 0].tolist()
@@ -226,12 +226,12 @@ def main():
                 on_change=lambda: apply_filter('laterality_check', st.session_state.laterality_check)
             )
 
-            series_with_vertabra_on_every_slice = st.selectbox(
-                "Series with Vertebra on Every Slice",
-                options=series_with_vertabra_on_every_slice_options,
-                index=series_with_vertabra_on_every_slice_options.index(filters['series_with_vertabra_on_every_slice']) if filters['series_with_vertabra_on_every_slice'] else 0,
-                key='series_with_vertabra_on_every_slice',
-                on_change=lambda: apply_filter('series_with_vertabra_on_every_slice', st.session_state.series_with_vertabra_on_every_slice)
+            volume_from_voxel_summation_check = st.selectbox(
+                "Minimum Volume of 5 mL",
+                options=volume_from_voxel_summation_check_options,
+                index=volume_from_voxel_summation_check_options.index(filters['volume_from_voxel_summation_check']) if filters['volume_from_voxel_summation_check'] else 0,
+                key='volume_from_voxel_summation_check',
+                on_change=lambda: apply_filter('volume_from_voxel_summation_check', st.session_state.volume_from_voxel_summation_check)
             )
 
             connected_volumes = st.selectbox(
@@ -249,6 +249,7 @@ def main():
                                         value=(min(voxel_num_options),max(voxel_num_options)),
                                         on_change=lambda: apply_filter('voxel_num_values', st.session_state.voxel_num_values)
                 )
+
             if min(radiomics_feature_values)!=max(radiomics_feature_values):
                 radiomics_num_values = st.slider(f"{radiomics_feature} Values",
                                         min_value=min(radiomics_feature_values), 
@@ -291,6 +292,7 @@ def main():
         start_idx = (page_number - 1) * page_size
         end_idx = min(start_idx + page_size, len(filtered_df))  # Ensure end_idx does not go beyond the dataframe length
         paginated_df = filtered_df[start_idx:end_idx].to_pandas()  # Convert to Pandas DataFrame
+        paginated_df = paginated_df.rename(columns={"connected_volumes": "connected_components"})
         paginated_df['Viewer Url'] = 'https://viewer.imaging.datacommons.cancer.gov/v3/viewer/?StudyInstanceUIDs='+paginated_df['StudyInstanceUID']
         
         # Display the paginated dataframe
@@ -302,10 +304,10 @@ def main():
             column_config={
                 "Viewer Url":st.column_config.LinkColumn("StudyInstanceUID",
                               display_text=r"https:\/\/viewer\.imaging\.datacommons\.cancer\.gov\/v3\/viewer\/\?StudyInstanceUIDs=(.*)"                               
-                              ),               
+                              ),                            
                                           
             },
-            column_order=("PatientID", "Viewer Url", "seriesNumber","bodyPart","laterality", "segmentation_completeness","laterality_check", "series_with_vertabra_on_every_slice","connected_volumes","voxel_num", radiomics_feature),  
+            column_order=("PatientID", "Viewer Url", "SeriesNumber","bodyPart","laterality", "segmentation_completeness","laterality_check", "volume_from_voxel_summation_check","connected_components","voxel_num", radiomics_feature),  
             hide_index=True,
             use_container_width=True
         )
@@ -379,10 +381,10 @@ def main():
                     SUM(CASE WHEN segmentation_completeness = 'pass' THEN 1 ELSE 0 END) AS pass_count,
                     SUM(CASE WHEN laterality_check = 'pass' THEN 1 ELSE 0 END) AS laterality_pass_count,
                     SUM(CASE WHEN laterality_check is not null THEN 1 ELSE 0 END) AS laterality_check_total_count,
-                    SUM(CASE WHEN series_with_vertabra_on_every_slice = 'pass' THEN 1 ELSE 0 END) AS vertabra_pass_count,
+                    SUM(CASE WHEN volume_from_voxel_summation_check = 'pass' THEN 1 ELSE 0 END) AS volume_check_pass_count,
                     SUM(CASE WHEN connected_volumes = '1' THEN 1 ELSE 0 END) AS volumes_pass_count
                 FROM 
-                    'qual-checks-and-quant-values.parquet'
+                    'qual_checks_and_quantitative_measurements-wip.parquet'
                 GROUP BY 
                     bodyPart, laterality
             )
@@ -394,8 +396,8 @@ def main():
                 CASE WHEN laterality IS NOT NULL 
                     THEN ROUND((laterality_pass_count * 100.0) / NULLIF(laterality_check_total_count, 0), 2) || '% (' || laterality_pass_count || '/' || laterality_check_total_count || ')' 
                     ELSE 'N/A' END AS laterality_check,
-                ROUND((vertabra_pass_count * 100.0) / total_count, 2) || '% (' || vertabra_pass_count || '/' || total_count || ')' AS vertabra_check,
-                ROUND((volumes_pass_count * 100.0) / total_count, 2) || '% (' || volumes_pass_count || '/' || total_count || ')' AS volumes_check
+                ROUND((volume_check_pass_count * 100.0) / total_count, 2) || '% (' || volume_check_pass_count || '/' || total_count || ')' AS volume_check_pass_count,
+                ROUND((volumes_pass_count * 100.0) / total_count, 2) || '% (' || volumes_pass_count || '/' || total_count || ')' AS connected_components_check
             FROM 
                 Checks
             ORDER BY 

qual-checks-and-quant-values.parquet

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9cdb5ac665c8bedf906f07ba1ba05232cf9ab2eb9045caec7fa1a3343222e9f2
-size 1157730459