Migrate from BadMedicine to SynthEHR (#222)

* migrate to useing synthehr
---------

Co-authored-by: James A Sutherland <[email protected]>

BadDicom/Program.cs

@@ -1,4 +1,3 @@
-using BadMedicine;
 using BadMedicine.Dicom;
 using CommandLine;
 using System;
@@ -19,6 +18,7 @@
 using FAnsi.Implementations.Oracle;
 using FAnsi.Implementations.PostgreSql;
 using YamlDotNet.Serialization;
+using SynthEHR;
 
 namespace BadDicom;
 

BadMedicine.Dicom.Tests/DicomDataGeneratorTests.cs

@@ -5,6 +5,7 @@
 using System.IO;
 using System.Linq;
 using CsvHelper;
+using SynthEHR;
 
 namespace BadMedicine.Dicom.Tests;
 
@@ -14,7 +15,7 @@ public class DicomDataGeneratorTests
     public void Test_CreatingOnDisk_OneFile()
     {
         var r = new Random(500);
-        using var generator = new DicomDataGenerator(r, TestContext.CurrentContext.WorkDirectory) {Layout = FileSystemLayout.StudyUID, MaximumImages = 1};
+        using var generator = new DicomDataGenerator(r, TestContext.CurrentContext.WorkDirectory) { Layout = FileSystemLayout.StudyUID, MaximumImages = 1 };
 
 
         var person = new Person(r);
@@ -72,10 +73,10 @@ public void Test_CreatingInMemory_ModalityCT()
     {
         var r = new Random(23);
         var person = new Person(r);
-        using var generator = new DicomDataGenerator(r,new string(TestContext.CurrentContext.WorkDirectory),"CT") {NoPixels = true};
+        using var generator = new DicomDataGenerator(r, new string(TestContext.CurrentContext.WorkDirectory), "CT") { NoPixels = true };
 
         //generate 100 images
-        for(var i = 0 ; i < 100 ; i++)
+        for (var i = 0; i < 100; i++)
         {
             //all should be CT because we said CT only
             var ds = generator.GenerateTestDataset(person, r);
@@ -89,7 +90,7 @@ public void Test_Anonymise()
         var r = new Random(23);
         var person = new Person(r);
 
-        using var generator = new DicomDataGenerator(r,new string(TestContext.CurrentContext.WorkDirectory),"CT");
+        using var generator = new DicomDataGenerator(r, new string(TestContext.CurrentContext.WorkDirectory), "CT");
 
         // without anonymisation (default) we get the normal patient ID
         var ds = generator.GenerateTestDataset(person, r);
@@ -118,24 +119,24 @@ public void Test_CreatingInMemory_Modality_CTAndMR()
         var r = new Random(23);
         var person = new Person(r);
 
-        using var generator = new DicomDataGenerator(r,new string(TestContext.CurrentContext.WorkDirectory),"CT","MR");
+        using var generator = new DicomDataGenerator(r, new string(TestContext.CurrentContext.WorkDirectory), "CT", "MR");
 
         //generate 100 images
-        for(var i = 0 ; i < 100 ; i++)
+        for (var i = 0; i < 100; i++)
         {
             //all should be CT because we said CT only
             var ds = generator.GenerateTestDataset(person, r);
             var modality = ds.GetSingleValue<string>(DicomTag.Modality);
 
-            Assert.That(modality is "CT" or "MR",$"Unexpected modality {modality}");
+            Assert.That(modality is "CT" or "MR", $"Unexpected modality {modality}");
         }
     }
 
     [Test]
     public void TestFail_CreatingInMemory_Modality_Unknown()
     {
         var r = new Random(23);
-        Assert.Throws<ArgumentException>(()=>_=new DicomDataGenerator(r,new string(TestContext.CurrentContext.WorkDirectory),"LOLZ"));
+        Assert.Throws<ArgumentException>(() => _ = new DicomDataGenerator(r, new string(TestContext.CurrentContext.WorkDirectory), "LOLZ"));
 
     }
 
@@ -144,37 +145,37 @@ public void Test_CsvOption()
     {
         var r = new Random(500);
 
-        var outputDir = new DirectoryInfo(Path.Combine(TestContext.CurrentContext.WorkDirectory,nameof(Test_CsvOption)));
+        var outputDir = new DirectoryInfo(Path.Combine(TestContext.CurrentContext.WorkDirectory, nameof(Test_CsvOption)));
         if (outputDir.Exists)
             outputDir.Delete(true);
         outputDir.Create();
 
         var people = new PersonCollection();
-        people.GeneratePeople(100,r);
+        people.GeneratePeople(100, r);
 
-        using (var generator = new DicomDataGenerator(r,outputDir.FullName, "CT"))
+        using (var generator = new DicomDataGenerator(r, outputDir.FullName, "CT"))
         {
             generator.Csv = true;
             generator.NoPixels = true;
             generator.MaximumImages = 500;
 
-            generator.GenerateTestDataFile(people,new FileInfo(Path.Combine(outputDir.FullName,"index.csv")),500);
+            generator.GenerateTestDataFile(people, new FileInfo(Path.Combine(outputDir.FullName, "index.csv")), 500);
         }
 
         //3 csv files + index.csv (the default one
         Assert.That(outputDir.GetFiles(), Has.Length.EqualTo(4));
 
         foreach (var f in outputDir.GetFiles())
         {
-            using var reader = new CsvReader(new StreamReader(f.FullName),CultureInfo.CurrentCulture);
+            using var reader = new CsvReader(new StreamReader(f.FullName), CultureInfo.CurrentCulture);
             var rowcount = 0;
 
             //confirms that the CSV is intact (no dodgy commas, unquoted newlines etc)
             while (reader.Read())
                 rowcount++;
 
             //should be 1 row per image + 1 for header
-            if(f.Name == DicomDataGenerator.ImageCsvFilename)
+            if (f.Name == DicomDataGenerator.ImageCsvFilename)
                 Assert.That(rowcount, Is.EqualTo(501));
         }
     }

BadMedicine.Dicom.Tests/StudyTests.cs

@@ -1,5 +1,6 @@
 using FellowOakDicom;
 using NUnit.Framework;
+using SynthEHR;
 using System;
 
 namespace BadMedicine.Dicom.Tests;

BadMedicine.Dicom/BadMedicine.Dicom.csproj

@@ -1,4 +1,4 @@
-<Project Sdk="Microsoft.NET.Sdk">
+<Project Sdk="Microsoft.NET.Sdk">
 
 	<PropertyGroup>
 		<TargetFramework>net8.0</TargetFramework>
@@ -44,7 +44,7 @@
 	</ItemGroup>
 
 	<ItemGroup>
-		<PackageReference Include="HIC.BadMedicine" Version="1.2.1" />
+		<PackageReference Include="HIC.SynthEHR" Version="2.0.0" />
 		<PackageReference Include="SixLabors.ImageSharp" Version="3.1.4" />
 		<PackageReference Include="SixLabors.ImageSharp.Drawing" Version="2.1.3" />
 	</ItemGroup>

BadMedicine.Dicom/DicomDataGenerator.cs

@@ -1,4 +1,4 @@
-using BadMedicine.Datasets;
+using SynthEHR.Datasets;
 using FellowOakDicom;
 using System;
 using System.IO;
@@ -7,6 +7,7 @@
 using System.Globalization;
 using System.Runtime.InteropServices;
 using CsvHelper;
+using SynthEHR;
 
 namespace BadMedicine.Dicom;
 
@@ -225,7 +226,7 @@ public DicomDataGenerator(Random r, string? outputDir, params string[] modalitie
     }
 
     /// <summary>
-    /// Returns headers for the inventory file produced during <see cref="GenerateTestDataset(BadMedicine.Person,System.Random)"/>
+    /// Returns headers for the inventory file produced during <see cref="GenerateTestDataset(SynthEHR.Person,System.Random)"/>
     /// </summary>
     /// <returns></returns>
     protected override string[] GetHeaders()

BadMedicine.Dicom/DicomDataGeneratorStats.cs

@@ -2,7 +2,8 @@
 using System;
 using System.Collections.Generic;
 using System.Data;
-using BadMedicine.Datasets;
+using SynthEHR.Datasets;
+using SynthEHR;
 
 namespace BadMedicine.Dicom;
 

BadMedicine.Dicom/Series.cs

@@ -1,4 +1,5 @@
 using FellowOakDicom;
+using SynthEHR;
 using System;
 using System.Collections;
 using System.Collections.Generic;
@@ -16,19 +17,19 @@ public class Series : IEnumerable<DicomDataset>
     /// <summary>
     /// The unique identifier for this series
     /// </summary>
-    public DicomUID SeriesUID {get; }
+    public DicomUID SeriesUID { get; }
 
     /// <summary>
     /// The Dicom Study this series is a part of
     /// </summary>
-    public Study Study{get; }
+    public Study Study { get; }
 
     /// <summary>
     /// All dicom images generated for this series.  These can be
     /// written out to file by other processes and do not yet exist
     /// on disk.
     /// </summary>
-    public IReadOnlyList<DicomDataset> Datasets{get; }
+    public IReadOnlyList<DicomDataset> Datasets { get; }
 
     private readonly List<DicomDataset> _datasets = new();
 
@@ -43,13 +44,13 @@ public class Series : IEnumerable<DicomDataset>
     /// Value to use for the <see cref="DicomTag.Modality"/> when writing
     /// out to dicom datasets
     /// </summary>
-    public string Modality {get; }
+    public string Modality { get; }
 
     /// <summary>
     /// Value to use for the <see cref="DicomTag.ImageType"/> when writing
     /// out to dicom datasets
     /// </summary>
-    public string ImageType {get; }
+    public string ImageType { get; }
 
     /// <summary>
     /// Date to use for the <see cref="DicomTag.SeriesDate"/> when writing
@@ -98,11 +99,11 @@ internal Series(Study study, Person person, string modality, string imageType, i
         SeriesDate = study.StudyDate;
         SeriesTime = study.StudyTime;
 
-        SeriesDescription =  part?.SeriesDescription;
+        SeriesDescription = part?.SeriesDescription;
         BodyPartExamined = part?.BodyPartExamined;
 
-        for (var i =0 ; i<imageCount;i++)
-            _datasets.Add(Study.Parent.GenerateTestDataset(person,this));
+        for (var i = 0; i < imageCount; i++)
+            _datasets.Add(Study.Parent.GenerateTestDataset(person, this));
 
         Datasets = new ReadOnlyCollection<DicomDataset>(_datasets);
     }

BadMedicine.Dicom/Study.cs

@@ -1,4 +1,5 @@
 using FellowOakDicom;
+using SynthEHR;
 using System;
 using System.Collections;
 using System.Collections.Generic;

CHANGELOG.md

@@ -7,7 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-...
+* Replace BadMedicine v1.2.1 with SynthEHR v2.0.0
 
 ## [0.1.0] - 2024-03-20
 

Packages.md

@@ -9,7 +9,7 @@
 
 | Package | Source Code |  License | Purpose | Additional Risk Assessment |
 | ------- | ------------|  ------- | ------- | -------------------------- |
-| HIC.BadMedicine | [GitHub](https://github.com/SMI/BadMedicine) | [GPL 3.0](https://www.gnu.org/licenses/gpl-3.0.html) | Handles generating baseline random data (patient date of birth, CHI numberts etc)| |
+| HIC.SynthEHR | [GitHub](https://github.com/HICServices/SynthEHR) | [GPL 3.0](https://www.gnu.org/licenses/gpl-3.0.html) | Handles generating baseline random data (patient date of birth, CHI numberts etc)| |
 | fo-dicom | [GitHub](https://github.com/fo-dicom/fo-dicom) |[MS-PL](https://opensource.org/licenses/MS-PL) | Handles reading/writing dicom tags from dicom datasets | |
 | fo-dicom.Imaging.ImageSharp | [GitHub](https://github.com/fo-dicom/fo-dicom) |[MS-PL](https://opensource.org/licenses/MS-PL) | Handles imaging aspects with fo-dicom | |
 | SixLabors.ImageSharp | [GitHub](https://github.com/SixLabors/ImageSharp) | [Apache 2.0](https://github.com/SixLabors/ImageSharp/blob/main/LICENSE) | Platform-independent replacement for legacy Windows-only System.Drawing.Common | |

README.md

@@ -10,7 +10,7 @@ There are a number of public sources of Dicom clinical images e.g. [TCIA ](https
 - Do not represent the breadth of Modalities/Tags found in a live clinical [PACS](https://en.wikipedia.org/wiki/Picture_archiving_and_communication_system).
 - Take up a lot of space
 
-BadMedicine.Dicom generates dicom images on demand based on an anonymous aggregate model of tag data found in scottish medical imaging.  It is an extension of [BadMedicine](https://github.com/SMI/BadMedicine) which generates traditional EHR records.
+BadMedicine.Dicom generates dicom images on demand based on an anonymous aggregate model of tag data found in scottish medical imaging.  It is an extension of [SynthEHR](https://github.com/SMI/SynthEHR) which generates traditional EHR records.
 
 ## Usage
 
@@ -51,18 +51,18 @@ Database:
   # Contains the table schema (which dicom tags to use for which tables)
   Template: CT.it
   # Database to create/use on the server
-  DatabaseName: BadMedicineTestData
+  DatabaseName: SynthEHRTestData
   # Setting this deduplicates study/series level schemas (works only if tables do not already exist on server)
   MakeDistinct: true
 ```
 
 ## EHR Datasets
 
-If you want to generate EHR datasets with a shared patient pool with the dicom data (e.g. for doing linkage) you can provided the -s (seed) and use the main [BadMedicine](https://github.com/SMI/BadMedicine) application.
+If you want to generate EHR datasets with a shared patient pool with the dicom data (e.g. for doing linkage) you can provided the -s (seed) and use the main [SynthEHR](https://github.com/SMI/SynthEHR) application.
 
 ```
 BadDicom.exe c:\temp\testdicoms 12 10 -s 100
-BadMedicine.exe c:\temp\testdicoms 12 100 -s 100
+SynthEHR.exe c:\temp\testdicoms 12 100 -s 100
 ```
 _Generates a pool of 12 patients and 10 Studies (for random patients) then 100 rows of data for each EHR dataset_
 
@@ -120,7 +120,7 @@ $ sudo yum install libc6-devel libgdiplus
 
 # Tag Data
 
-Basic random patient information (age, CHI etc) are generated by [BadMedicine](https://github.com/SMI/BadMedicine)
+Basic random patient information (age, CHI etc) are generated by [SynthEHR](https://github.com/SMI/SynthEHR)
 
 The following tags are populated in dicom files generated: