fix the build

angioPyFunctions.py

@@ -1,3 +1,6 @@
+import os
+os.environ.setdefault("ASTROPY_SKIP_CONFIG_UPDATE", "1")
+
 import numpy
 import scipy.interpolate
 import skimage.filters
@@ -6,6 +9,13 @@ import scipy.ndimage
 import scipy.optimize
 import predict
 from PIL import Image
+import astropy.config.configuration as _astro_config
+
+if not hasattr(_astro_config, "update_default_config"):
+    def _noop_update_default_config(*args, **kwargs):
+        return None
+    _astro_config.update_default_config = _noop_update_default_config
+
 from fil_finder import FilFinder2D
 import astropy.units as u
 from tqdm import tqdm

angioPySegmentation.py

@@ -77,7 +77,6 @@ files = sorted(glob.glob(DicomFolder+"/*"))
 for file in files:
     exampleDicoms[os.path.basename(file)] = file
 
-
 # Main text
 st.markdown("<h1 style='text-align: center;'>AngioPy Segmentation</h1>", unsafe_allow_html=True)
 st.markdown("<h5 style='text-align: center;'> Welcome to <b>AngioPy Segmentation</b>, an AI-driven, coronary angiography segmentation tool.</h1>", unsafe_allow_html=True)
@@ -93,14 +92,62 @@ st.markdown("")
 
 #     print("CHANGED!")
 
+input_mode = st.sidebar.radio(
+    "Input source",
+    ("Example DICOM", "Upload Image"),
+    key="input_mode_selector",
+)
 
-DropDownDicom = st.sidebar.selectbox("Select example DICOM file:",
-                        options = list(exampleDicoms.keys()),
-                        # on_change=changeSessionState(st.session_state.key),
-                        key="dicomDropDown"
-                    )
+pixelArray = None
+selected_label = None
+selected_path = None
+
+if input_mode == "Example DICOM":
+    if exampleDicoms:
+        DropDownDicom = st.sidebar.selectbox(
+            "Select example DICOM file:",
+            options=list(exampleDicoms.keys()),
+            key="dicomDropDown",
+        )
+
+        selected_label = DropDownDicom
+        selected_path = exampleDicoms[DropDownDicom]
+
+        try:
+            print(f"Trying to load {selected_path}")
+            dcm = pydicom.dcmread(selected_path, force=True)
 
-selectedDicom = exampleDicoms[DropDownDicom]
+            pixelArray = dcm.pixel_array
+
+            # Just take first channel if it's RGB?
+            if len(pixelArray.shape) == 4:
+                pixelArray = pixelArray[:, :, :, 0]
+        except Exception as err:
+            st.sidebar.error(f"Unable to read DICOM '{selected_label}': {err}")
+            pixelArray = None
+    else:
+        st.sidebar.info("Add DICOM files to the `Dicoms/` folder or switch to image upload.")
+else:
+    uploaded_file = st.sidebar.file_uploader(
+        "Upload angiography frame (PNG or JPG)",
+        type=["png", "jpg", "jpeg"],
+        key="uploaded_frame",
+    )
+
+    if uploaded_file is not None:
+        selected_label = uploaded_file.name
+        selected_path = uploaded_file.name
+
+        try:
+            uploaded_image = Image.open(uploaded_file)
+            if uploaded_image.mode != "L":
+                uploaded_image = uploaded_image.convert("L")
+
+            image_array = numpy.array(uploaded_image)
+            pixelArray = numpy.expand_dims(image_array, axis=0)
+        except Exception as err:
+            st.sidebar.error(f"Could not read uploaded image: {err}")
+            pixelArray = None
 
 stepOne = st.sidebar.expander("STEP ONE", True)
 stepTwo = st.sidebar.expander("STEP TWO", True)
@@ -121,34 +168,24 @@ st.markdown(css, unsafe_allow_html=True)
 
 # while True:
 # Once a file is uploaded, the following annotation sequence is initiated 
-if selectedDicom is not None:
-        try:
-            print(f"Trying to load {selectedDicom}")
-            dcm = pydicom.dcmread(selectedDicom, force=True)
-
-            # handAngle = dcm.PositionerPrimaryAngle
-            # headAngle = dcm.PositionerSecondaryAngle
-            # dcmLabel = f"{'LAO' if handAngle > 0 else 'RAO'} {numpy.abs(handAngle):04.1f}° {'CRA' if headAngle > 0 else 'CAU'} {numpy.abs(headAngle):04.1f}°"
+if pixelArray is None:
+        st.info("Select an example DICOM or upload a PNG/JPG frame to start the segmentation workflow.")
+else:
+        if pixelArray.ndim == 4:
+            pixelArray = pixelArray[:, :, :, 0]
+        if pixelArray.ndim == 2:
+            pixelArray = numpy.expand_dims(pixelArray, axis=0)
 
-            pixelArray = dcm.pixel_array
-
-            # Just take first channel if it's RGB?
-            if len(pixelArray.shape) == 4:
-                pixelArray = pixelArray[:,:,:,0]
-
-            n_slices = pixelArray.shape[0]
-
-            slice_ix = 0
-        except:
-            selectedDicom = None
-            # continue
+        n_slices = pixelArray.shape[0]
+        slice_ix = 0
 
         with tab1:
 
             with stepOne:
                 st.write("Select frame for annotation. Aim for an end-diastolic frame with good visualisation of the artery of interest.")
 
-                slice_ix = st.slider('Frame', 0, n_slices-1, int(n_slices/2), key='sliceSlider')
+                if n_slices > 1:
+                    slice_ix = st.slider('Frame', 0, n_slices-1, int(n_slices/2), key='sliceSlider')
 
 
                 predictedMask = numpy.zeros_like(pixelArray[slice_ix, :, :])
@@ -183,6 +220,8 @@ if selectedDicom is not None:
                     selectedFrame = pixelArray[slice_ix, :, :]
                     selectedFrame = cv2.resize(selectedFrame, (512,512))
 
+                    canvas_key = f"canvas-{selected_label}" if selected_label else "canvas-default"
+
                     # Create a canvas component
                     annotationCanvas = st_canvas(
                         fill_color="red",  # Fixed fill color with some opacity
@@ -195,11 +234,12 @@ if selectedDicom is not None:
                         width=512,
                         drawing_mode="point",
                         point_display_radius=2,
-                        key=st.session_state.dicomDropDown,
+                        key=canvas_key,
                     )
 
 
                     # Do something interesting with the image data and paths
+                    objects = pd.DataFrame()
                     if annotationCanvas.json_data is not None:
                         objects = pd.json_normalize(annotationCanvas.json_data["objects"]) # need to convert obj to str because PyArrow
 
@@ -222,7 +262,6 @@ if selectedDicom is not None:
                             predictedMask = predict.CoronaryDataset.mask2image(mask)
                             # predictedMask = predictedMask.crop((0, 0, imageSize[0], imageSize[1]))
                             predictedMask = numpy.asarray(predictedMask)
-
             with col2:
                 col2a, col2b, col2c = st.columns((1,10,1))
 

normalize_k1.py

@@ -0,0 +1,33 @@
+from pathlib import Path
+
+import numpy as np
+from PIL import Image
+from skimage import exposure
+
+
+def normalize_image(
+    src: Path,
+    dst: Path,
+    target_size=(512, 512),
+    png_low: int = 16,
+    png_high: int = 238,
+) -> None:
+    """Convert JPEG to grayscale, resize, and match PNG intensity distribution."""
+    img = Image.open(src).convert("L")
+    img = img.resize(target_size, Image.Resampling.BICUBIC)
+
+    arr = np.array(img, dtype=np.float32)
+    arr = exposure.rescale_intensity(arr, in_range="image", out_range=(png_low, png_high))
+    arr = np.clip(arr, png_low, png_high)
+    arr = ((arr - png_low) / (png_high - png_low) * 255.0).astype(np.uint8)
+
+    dst.parent.mkdir(parents=True, exist_ok=True)
+    Image.fromarray(arr, mode="L").save(dst)
+
+
+if __name__ == "__main__":
+    src = Path("/Users/fatemehtahavori/Downloads/atk1/K-1.jpg")
+    dst = Path("normalized_outputs") / f"{src.stem}_normalized.png"
+
+    normalize_image(src, dst)
+    print(f"Saved normalized frame to {dst.resolve()}")

requirements.txt

@@ -1,29 +1,29 @@
 # Automatically generated by https://github.com/damnever/pigar.
 
-astropy==5.2.2
+astropy>=7.0.0
 efficientnet-pytorch==0.7.1
 fil-finder==1.7.2
-matplotlib==3.7.2
+matplotlib>=3.10.0
 mpld3==0.5.9
-numpy==1.24.4
-opencv-python==4.8.0.76
-pandas==2.0.3
-Pillow==9.5.0
+numpy>=2.0.0
+opencv-python>=4.10.0
+pandas>=2.3.0
+Pillow>=10.0.0
 plotly==5.16.1
 pretrainedmodels==0.7.4
 pydicom==2.4.3
-PyYAML==6.0.1
-scikit-image==0.21.0
-scikit-learn==1.3.0
-scipy==1.10.1
-setuptools==47.1.0
-SimpleITK==2.2.1
+PyYAML>=6.0.1
+scikit-image>=0.25.0
+scikit-learn>=1.7.0
+scipy>=1.16.0
+setuptools>=65.0.0
+SimpleITK>=2.5.2
 streamlit<=1.38.0
 streamlit-drawable-canvas==0.9.3
 streamlit-plotly-events==0.0.6
-tifffile==2023.7.10
-timm==0.9.6
-torch==2.0.1
-torchvision==0.15.2
-tqdm==4.61.1
+tifffile>=2023.7.10
+timm>=0.9.6
+torch>=2.8.0
+torchvision>=0.23.0
+tqdm>=4.61.1
 pooch