Add run files

.dockerignore

@@ -0,0 +1,8 @@
+*
+!.streamlit/
+!figures/
+!utils/
+!app.py
+!index.html
+!style.css
+!requirements.txt

.streamlit/config.toml

@@ -0,0 +1,8 @@
+[theme]
+primaryColor="#F63366"
+backgroundColor="#FFFFFF"
+secondaryBackgroundColor="#F0F2F6"
+textColor="#262730"
+font="sans serif"
+serverAddress = "0.0.0.0"
+serverPort = 8501

Dockerfile

@@ -0,0 +1,45 @@
+ARG image = nvidia/cuda:11.3.1-runtime-ubuntu20.04
+FROM nvidia/cuda:11.3.1-runtime-ubuntu20.04
+
+RUN apt update && \
+    apt install -y bash \
+                   build-essential \
+                   git \
+                   curl \
+                   ca-certificates \
+                   python3 \
+                   python3-pip && \
+    rm -rf /var/lib/apt/lists
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip && \
+    python3 -m pip install --no-cache-dir --extra-index-url https://download.pytorch.org/whl/cu113 \
+    torch \
+    torchvision \
+    torchaudio
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install ffmpeg libsm6 libxext6  -y && rm -rf /var/lib/apt/lists
+
+RUN pip install --no-cache-dir git+https://github.com/bowang-lab/MedSAM.git
+
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+
+# Switch to the "user" user
+USER user
+# Set home to the user's home directory
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
+
+CMD ["streamlit", "run", "app.py"]

README.md

@@ -3,10 +3,8 @@ title: Medsam Segment Anything
 emoji: 🐨
 colorFrom: indigo
 colorTo: blue
-sdk: streamlit
-sdk_version: 1.21.0
-app_file: app.py
-pinned: false
+sdk: docker
+app_port: 7860
 license: apache-2.0
 ---
 

app.py

@@ -0,0 +1,143 @@
+import streamlit as st
+
+st.set_page_config(layout="wide")
+
+import random
+
+import numpy as np
+import pandas as pd
+from PIL import Image
+from streamlit_drawable_canvas import st_canvas
+from utils import utils
+
+SAM_MODEL = utils.get_model('vit_b')
+
+
+def click_process(model, show_mask, radius_width):
+
+    bg_image = st.session_state['image']
+    width, height   = bg_image.size[:2]
+    container_width = 700
+    scale           = container_width/width
+    scaled_hw = (container_width, int(height * scale))
+
+    if 'result_image' not in st.session_state:
+        st.session_state.result_image = bg_image.resize(scaled_hw)
+
+    canvas_result = st_canvas(
+        fill_color="rgba(255, 255, 0, 0.8)",
+        background_image = bg_image,
+        drawing_mode='point',
+        width = container_width,
+        height = height * scale,
+        point_display_radius = radius_width,
+        stroke_width=2,
+        update_streamlit=True,
+        key="point",)
+
+    # ! Warn: Can cause infinite loop or high cpu usage
+    if not show_mask:
+        print("rerun no mask")
+        st.experimental_rerun()
+
+    elif canvas_result.json_data is not None:
+        df = pd.json_normalize(canvas_result.json_data["objects"])
+        input_points = []
+        input_labels = []
+
+        for _, row in df.iterrows():
+            x, y = int(row["left"] + row["width"]/2), int(row["top"] + row["height"]/2)
+            x = int(x/scale)
+            y = int(y/scale)
+            input_points.append([x, y])
+            if row['fill'] == "rgba(0, 255, 0, 0.8)":
+                input_labels.append(1)
+            else:
+                input_labels.append(0)
+
+        masks = []
+        if model:
+            masks = utils.model_predict_masks_click(model, input_points, input_labels)
+
+            if len(masks) == 0:
+                return bg_image
+
+            bg_image = np.asarray(bg_image)
+            color = np.concatenate([random.choice(utils.get_color()), np.array([0.6])], axis=0)
+            im_masked = utils.show_click(masks,color)
+            im_masked = Image.fromarray(im_masked).convert('RGBA')
+            result_image = Image.alpha_composite(Image.fromarray(bg_image).convert('RGBA'),im_masked).convert("RGB")
+            result_image = result_image.resize(scaled_hw)
+            return result_image
+        else:
+            return np.asarray(bg_image)
+
+    return np.asarray(bg_image)
+
+
+def image_preprocess_callback(model):
+    if 'uploaded_image' not in st.session_state:
+        return
+    if st.session_state.uploaded_image is not None:
+        with st.spinner(text="Uploading image..."):
+            image = Image.open(st.session_state.uploaded_image).convert("RGB")
+        if model:
+            np_image = np.asanyarray(image)
+            with st.spinner(text="Extracing embeddings.."):
+                model.set_image(np_image)
+        st.session_state.image = image
+    else:
+        with st.spinner(text="Cleaning up!"):
+            if 'image' in st.session_state:
+                st.session_state.image = None
+            if 'result_image' in st.session_state:
+                del st.session_state['result_image']
+            if model:
+                model.reset_image()
+
+def main():
+    with open('index.html', encoding='utf-8') as f:
+        html_content = f.read()
+
+    st.markdown(html_content, unsafe_allow_html=True)
+
+    with st.container():
+        col1, col2, col3 = st.columns(3)
+
+        with col1:
+            option = st.selectbox('Segmentation mode', ('Click'))
+
+        with col2:
+            st.write("Show or Hide Mask")
+            show_mask = st.checkbox('Show mask',value = True)
+
+        with col3:
+            radius_width = st.slider('Radius/Width for Click/Box',0,20,5,1)
+
+    with st.container():
+        st.write("Upload Image")
+        st.file_uploader(label='Upload image',type=['png','jpg','tif'], key='uploaded_image', on_change=image_preprocess_callback, args=(SAM_MODEL,), label_visibility="hidden")
+
+    result_image = None
+    canvas_input, canvas_output = st.columns(2)
+    if 'image' in st.session_state:
+        with canvas_input:
+            st.write("Select Interest Area/Objects")
+            if st.session_state.image is not None:
+                if option == 'Click':
+                    with st.spinner(text="Computing masks"):
+                        result_image = click_process(SAM_MODEL, show_mask, radius_width)
+        with canvas_output:
+            if result_image is not None:
+                st.write("Result")
+                st.image(result_image)
+
+    else:
+        print(f'embedding is empty - {option} - {show_mask} - {radius_width}')
+        # if 'image' in st.session_state:
+            # if st.session_state.image is None:
+                # st.session_state.clear()
+
+
+if __name__ == '__main__':
+    main()

index.html

@@ -0,0 +1,46 @@
+<!DOCTYPE html>
+<html>
+	<head>
+		<link rel="stylesheet" href="file/style.css" />
+		<link rel="preconnect" href="https://fonts.googleapis.com" />
+		<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
+		<link href="https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@400;600;700&display=swap" rel="stylesheet" />
+		<title>Bilateral View Hypercomplex Breast Classification</title>
+	</head>
+	<body>
+		<div class="container">
+			<h1 class="title">MedSAM: Segment Anything in Medical Images</h1>
+			<h2 class="subtitle">Kalbe Digital Lab</h2>
+			<section class="overview">
+				<div class="grid-container">
+					<h3 class="overview-heading"><span class="vl">Overview</span></h3>
+					<p class="overview-content">
+						MedSAM, a foundation model for universal medical image segmentation. MedSAM is adapted from the SAM model on an unprecedented scale, with more than one million medical image-mask pairs.
+						<br />
+						Reference: <a href="https://arxiv.org/abs/2304.12306" target="_blank">https://arxiv.org/abs/2204.05798</a>
+					</p>
+				</div>
+				<div class="grid-container">
+					<h3 class="overview-heading"><span class="vl">Dataset</span></h3>
+					<div>
+						<p class="overview-content">The model is trained using a diverse and large-scale medical image segmentation dataset with 1,090,486 medical image-mask pairs, covering 15 imaging modalities, over 30 cancer types, and a multitude of imaging protocols.</p>
+						<ul>
+							<li>Target: Capturing a broad spectrum of anatomies and lesions across different modalities.</li>
+							<li>Task: Segmentation</li>
+							<li>Modality: Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Endoscopy, Ultrasound, Pathology, Fundus, Dermoscopy, Mammography, and Optical Coherence Tomography (OCT).</li>
+						</ul>
+					</div>
+				</div>
+				<div class="grid-container">
+					<h3 class="overview-heading"><span class="vl">Model Architecture</span></h3>
+					<div>
+						<p class="overview-content">Parameterized Hypercomplex ResNets-18 Variants (PHYResNet).</p>
+						<img class="content-image" src="file/figures/medsam.png" alt="model-architecture" />
+					</div>
+				</div>
+			</section>
+			<h3 class="overview-heading"><span class="vl">Demo</span></h3>
+			<p class="overview-content">Please select the example below or upload 2 pairs of mammography exam result.</p>
+		</div>
+	</body>
+</html>

license

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+torch
+torchvision
+Pillow
+numpy
+pandas
+distinctipy

style.css

@@ -0,0 +1,79 @@
+* {
+	box-sizing: border-box;
+}
+
+body {
+	font-family: 'Source Sans Pro', sans-serif;
+	font-size: 16px;
+}
+
+.container {
+	width: 100%;
+	margin: 0 auto;
+}
+
+.title {
+	font-size: 24px !important;
+	font-weight: 600 !important;
+	letter-spacing: 0em;
+	text-align: center;
+	color: #374159 !important;
+}
+
+.subtitle {
+	font-size: 24px !important;
+	font-style: italic;
+	font-weight: 400 !important;
+	letter-spacing: 0em;
+	text-align: center;
+	color: #1d652a !important;
+	padding-bottom: 0.5em;
+}
+
+.overview-heading {
+	font-size: 24px !important;
+	font-weight: 600 !important;
+	letter-spacing: 0em;
+	text-align: left;
+}
+
+.overview-content {
+	font-size: 14px !important;
+	font-weight: 400 !important;
+	line-height: 30px !important;
+	letter-spacing: 0em;
+	text-align: left;
+}
+
+.content-image {
+	width: 100% !important;
+	height: auto !important;
+}
+
+.vl {
+	border-left: 5px solid #1d652a;
+	padding-left: 20px;
+	color: #1d652a !important;
+}
+
+.grid-container {
+	display: grid;
+	grid-template-columns: 1fr 2fr;
+	gap: 20px;
+	align-items: flex-start;
+	margin-bottom: 0.7em;
+}
+
+@media screen and (max-width: 768px) {
+	.container {
+		width: 90%;
+	}
+
+	.grid-container {
+		display: block;
+	}
+
+	.overview-heading {
+		font-size: 18px !important;
+	}
+}

utils/utils.py

@@ -0,0 +1,72 @@
+
+from segment_anything import SamPredictor, sam_model_registry
+import torch
+import numpy as np
+from distinctipy import distinctipy
+import streamlit as st
+
+
+def get_checkpoint_path(model):
+    return 'checkpoint/medsam_vit_b.pth'
+
+
+def get_color():
+    return distinctipy.get_colors(200)
+
+
+@st.cache_resource
+def get_model(model):
+    device         = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    build_sam      = sam_model_registry[model]
+    model          = build_sam(checkpoint=get_checkpoint_path(model)).to(device)
+    predictor      = SamPredictor(model)
+    if torch.cuda.is_available():
+        torch.cuda.empty_cache()
+    return predictor
+
+
+@st.cache_data
+def show_everything(sorted_anns):
+    if len(sorted_anns) == 0:
+        return
+    #sorted_anns = sorted(anns, key=(lambda x: x['stability_score']), reverse=True)
+    h, w        = sorted_anns[0]['segmentation'].shape[-2:]
+    #sorted_anns = sorted_anns[:int(len(sorted_anns) * stability_score/100)]
+    if sorted_anns == []:
+        return np.zeros((h,w,4)).astype(np.uint8)
+    mask = np.zeros((h,w,4))
+    for ann in sorted_anns:
+        m      = ann['segmentation']
+        color  = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
+        mask  += m.reshape(h,w,1) * color.reshape(1, 1, -1)
+    mask = mask * 255
+    st.success('Process completed！', icon="✅")
+    return mask.astype(np.uint8)
+
+
+def show_click(masks, colors):
+    h, w         = masks[0].shape[-2:]
+    masks_total = np.zeros((h,w,4)).astype(np.uint8)
+    for mask, color in zip(masks, colors):
+        if np.array_equal(mask,np.array([])):continue
+        masks = np.zeros((h,w,4)).astype(np.uint8)
+        masks = masks + mask.reshape(h,w,1).astype(np.uint8)
+        masks = masks.astype(bool).astype(np.uint8)
+        masks = masks * 255 * color.reshape(1, 1, -1)
+        masks_total += masks.astype(np.uint8)
+    st.success('Process completed!', icon="✅")
+    return masks_total
+
+def model_predict_masks_click(model,input_points,input_labels):
+    if input_points == []:return np.array([])
+    input_labels = np.array(input_labels)
+    input_points = np.array(input_points)
+    masks, _, _ = model.predict(
+        point_coords=input_points,
+        point_labels=input_labels,
+        multimask_output=False,
+    )
+    if torch.cuda.is_available():
+        torch.cuda.empty_cache()
+
+    return masks