Added IBSI 2 reference.

paper/paper.bib

@@ -163,7 +163,6 @@ @ARTICLE{Shahzadi2022-wk
 }
 
 
-
 @ARTICLE{Bettinelli2022-ml,
   title    = "A Novel Benchmarking Approach to Assess the Agreement among
               Radiomic Tools",
@@ -180,3 +179,36 @@ @ARTICLE{Bettinelli2022-ml
   pmid     = "35230182",
   doi      = "10.1148/radiol.211604"
 }
+
+
+@ARTICLE{Whybra2024-yb,
+  title     = "The Image Biomarker Standardization Initiative: Standardized
+               Convolutional Filters for Reproducible Radiomics and Enhanced
+               Clinical Insights",
+  author    = "Whybra, Philip and Zwanenburg, Alex and Andrearczyk, Vincent and
+               Schaer, Roger and Apte, Aditya P and Ayotte, Alexandre and
+               Baheti, Bhakti and Bakas, Spyridon and Bettinelli, Andrea and
+               Boellaard, Ronald and Boldrini, Luca and Buvat, Ir{\`e}ne and
+               Cook, Gary J R and Dietsche, Florian and Dinapoli, Nicola and
+               Gabry{\'s}, Hubert S and Goh, Vicky and Guckenberger, Matthias
+               and Hatt, Mathieu and Hosseinzadeh, Mahdi and Iyer, Aditi and
+               Lenkowicz, Jacopo and Loutfi, Mahdi A L and L{\"o}ck, Steffen
+               and Marturano, Francesca and Morin, Olivier and Nioche,
+               Christophe and Orlhac, Fanny and Pati, Sarthak and Rahmim, Arman
+               and Rezaeijo, Seyed Masoud and Rookyard, Christopher G and
+               Salmanpour, Mohammad R and Schindele, Andreas and Shiri, Isaac
+               and Spezi, Emiliano and Tanadini-Lang, Stephanie and Tixier,
+               Florent and Upadhaya, Taman and Valentini, Vincenzo and van
+               Griethuysen, Joost J M and Yousefirizi, Fereshteh and Zaidi,
+               Habib and M{\"u}ller, Henning and Valli{\`e}res, Martin and
+               Depeursinge, Adrien",
+  journal   = "Radiology",
+  publisher = "Radiological Society of North America",
+  volume    =  310,
+  number    =  2,
+  pages     = "e231319",
+  month     =  feb,
+  year      =  2024,
+  issn      = "0033-8419",
+  doi       = "10.1148/radiol.231319"
+}

paper/paper.md

@@ -12,50 +12,49 @@ authors:
     orcid: 0000-0002-0342-9545
     affiliation: "2, 3, 4"
 affiliations:
-  - name: "National Center for Tumor Diseases (NCT/UCC) Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and; Helmholtz Association/Helmholtz-Zentrum Dresden–Rossendorf (HZDR), Dresden, Germany"
+  - name: "National Center for Tumor Diseases Dresden (NCT/UCC), Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; Helmholtz-Zentrum Dresden-Rossendorf (HZDR), Dresden, Germany"
     index: 1
-  - name: OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital 
-      Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, Dresden, Germany
+  - name: OncoRay – National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl
+      Gustav Carus, TUD Dresden University of Technology, Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany
     index: 2
-  - name: German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Dresden, 
-      Dresden, Germany
+  - name: German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany
     index: 3
-  - name: Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav 
-      Carus, Technische Universität Dresden, Dresden, Germany
+  - name: Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
     index: 4
-date: 30 October 2023
+date: 7 February 2024
 bibliography: paper.bib
 ---
 
 # Summary
 
 Medical imaging provides non-invasive anatomical and functional visualisation of the human body. It is used 
-clinically for diagnostics, prognostics and treatment planning. Many current uses of medical imaging involve 
-qualitative or semi-quantitive assessment by experts. Radiomics seeks to automate analysis of medical imaging for 
+clinically for diagnostic, prognostic, treatment planning and other purposes. Many current uses of medical imaging 
+involve qualitative or semi-quantitive assessment by experts. Radiomics seeks to automate analysis of medical imaging for 
 clinical decision support. At its core, radiomics involves the extraction and machine learning-based analysis of 
 quantitive features from medical images. However, very few--if any--radiomics tools have been translated to the 
 clinic [@Huang2022-mi]. One of the essential prerequisites for translation is reproducibility and validation in 
 external settings [@OConnor2017-iv]. This can be facilitated through the use of standardised radiomics software. 
 Here we present `mirp`, a Python package for standardised processing of medical imaging and computation of 
 quantitative features. Researchers can use `mirp` for their own radiomics analyses or to reproduce and validate 
-radiomics of others.
+radiomics analyses of others.
 
 # Statement of need
 
 Lack of standardised radiomics software is one of the reasons for poor translation of radiomics tools to the clinic.
 The Image Biomarker Standardisation Initiative has created reference standards for radiomics software: 1. a 
 reference standard for basic image processing and feature extraction steps [@Zwanenburg2020-go]; and 2. a reference 
-standard for image filters [TODO:ADD WHEN PUBLISHED]. There is currently a lack of fully IBSI-compliant radiomics 
+standard for image filters [@Whybra2024-yb]. There is currently a lack of fully IBSI-compliant radiomics 
 packages in Python. Python is important for the radiomics field because commonly used machine learning and deep 
 learning packages such as `scikit-learn` and `pytorch` are interfaced using Python. `mirp` facilitates both by offering a 
 user-friendly API for standardised image processing and feature extraction for machine learning-based radiomics, and 
 standardised image processing for deep learning-based radiomics.
 
 `mirp` is intended to be used by researchers in the radiomics field to perform their own radiomics analyses on the 
 one hand, and to externally reproduce and validate results of other researchers. It was originally created in 2016 and 
-regularly updated to conform with the IBSI reference standards and improve usability. Previous versions of `mirp` 
+regularly updated to conform with the IBSI reference standards and to improve usability. Previous versions of `mirp` 
 were used by e.g. @Leger2017-si, @Zwanenburg2019-jg, @Shahzadi2022-wk and @Bettinelli2022-ml. The current 
-version (2.0.0) sees major improvements in user experience with a unified API and better documentation.
+version (2.1.0) sees major improvements in user experience with a unified API, better documentation, and easier 
+installation using `pip`.
 
 `mirp` follows an end-to-end design principle and abstracts away intermediate steps for the user. In this sense it 
 is not a toolkit such as `scikit-image` or `opencv`. The following functions are exposed to the user:
@@ -73,8 +72,10 @@ The above are implemented as functions. `mirp.deep_learning_preprocessing`, `mir
 `mirp.extract_images` and `mirp.extract_features_and_images` allow for parallel processing using the `ray` package. 
 These functions also have generator-variants that yield output one-by-one. 
 
-`mirp` supports all standard medical imaging formats, notably DICOM, NIfTI and NRRD. It also supports `numpy` arrays 
-as a generic fallback option.
+`mirp` supports standard medical imaging formats as input, notably DICOM, NIfTI and NRRD. It also supports `numpy` 
+arrays as a generic fallback option, and has specific routines for handling computed tomography (CT), positron 
+emission tomography (PET), magnetic resonance imaging (MRI) and radiotherapy dose maps. It supports both 
+radiotherapy structure sets (RTSTRUCT) and segmentation (SEG) files as DICOM-based masks.
 
 In conclusion, `mirp` offers a much-needed solution for standardized radiomics. With its user-friendly Python 
 interface, researchers can conduct radiomics analyses and, crucially, reproduce and validate the work of others, 
@@ -96,7 +97,7 @@ used alternatives are listed in Table 1.
 | Graphical user interface | no                                        | no                                                   | yes                                    | yes                                   | no                                                |
 | Website                  | [GitHub](https://github.com/oncoray/mirp) | [GitHub](https://github.com/AIM-Harvard/pyradiomics) | [GitHub](https://github.com/cerr/CERR) | [website](https://www.lifexsoft.org/) | [GitHub](https://github.com/mvallieres/radiomics) | 
 Table 1: Comparison of `mirp` with other popular alternatives. Note that compliance with the first and second 
-reference standards of the Image Biomarker Standardisation Initiative (IBSI-1 and IBSI-2, respectively) is 
+set of reference standards of the Image Biomarker Standardisation Initiative (IBSI-1 and IBSI-2, respectively) is 
 based on claims of the developers, and not verified by the authors.
 
 # Acknowledgements