pangyuteng

META

• Description: MediaStorageSOPClassUID Tag: (0x0002,0x0002) Level: ERROR
• Description: MediaStorageSOPInstanceUID Tag: (0x0002,0x0003) Level: ERROR
• Description: TransferSyntaxUID Tag: (0x0002,0x0010)

pangyuteng

FROM tensorflow/tensorflow:2.2.0-gpu-jupyter

RUN python -m pip install --upgrade pip
COPY requirements.txt .
RUN pip install -r requirements.txt

pangyuteng

new pc setup ( work windows OS)

just install the below only (work machine, win os) for git bash

• wsltty (to use as main terminal, because copy-pasting works in terminal).

  • you'll first need to install wsl and docker-desktop

pangyuteng

**/__pycache__/*

pangyuteng

FROM nvidia/cuda:10.0-cudnn7-devel-ubuntu18.04

# install python 3.7 and pip
RUN apt-get update \
    && apt-get install -y --no-install-recommends \
        build-essential \
        software-properties-common \
        pkg-config \
        rsync \

pangyuteng

** PLEASE NOTE ***
there are many other solutions for computing SUV, see below link for more info.
https://qibawiki.rsna.org/index.php/Standardized_Uptake_Value_(SUV)

This gist contains code to perform the below with python (3.7).

+ download data from TCIA via tcia-rest api. (download.py, tciaclient.py)

pangyuteng

rdp with reverse tunnel

TARGET (within VPN) -- INTERMEDIATE -- LAPTOP

If you want to connect to TARGET and are not able to setup vpn from LAPTOP to TARGET. You can try RDP with the below setup via an intermediate server (in the cloud, or local server at home).

• run below in TARGET:

pangyuteng

pangyuteng

# sample code to augment image,mask and keypoints with albumentations

import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
import albumentations as A

image = np.random.rand(256,256)
image[64:128,64:128]+=0.5
mask = np.zeros((256,256))

pangyuteng

FROM ubuntu:18.04

RUN apt-get update && apt-get install -yq \
        autotools-dev \
        build-essential \
        ca-certificates \
        vim curl wget \        
        cmake g++

WORKDIR /opt/sources