From 294bf1dd06cbb082c6d66b715ee8044adbfe44a2 Mon Sep 17 00:00:00 2001 From: Chris Date: Thu, 9 May 2024 15:49:31 -0500 Subject: [PATCH 1/4] updates --- gdcdictionary/schemas/imaging_series.yaml | 100 +++++++++++++++------- 1 file changed, 71 insertions(+), 29 deletions(-) diff --git a/gdcdictionary/schemas/imaging_series.yaml b/gdcdictionary/schemas/imaging_series.yaml index dedd801..3dc97c8 100644 --- a/gdcdictionary/schemas/imaging_series.yaml +++ b/gdcdictionary/schemas/imaging_series.yaml @@ -18,24 +18,29 @@ systemProperties: - state - created_datetime - updated_datetime - - file_state - - error_type + links: - exclusive: false required: true subgroup: - - name: core_metadata_collections + - name: datasets + backref: imaging_series + label: member_of + target_type: dataset + multiplicity: many_to_many + required: false + - name: cases backref: imaging_series - label: data_from - target_type: core_metadata_collection + label: related_to + target_type: case multiplicity: many_to_one required: false - name: imaging_studies backref: imaging_series - label: related_to + label: member_of target_type: imaging_study - multiplicity: many_to_one + multiplicity: many_to_many required: false required: @@ -50,25 +55,11 @@ properties: $ref: "_definitions.yaml#/ubiquitous_properties" - manufacturer: - description: (0008, 0070) Manufacturer - type: string - - manufacturer_model_name: - description: (0008, 1090) Manufacturer's Model Name - type: string - - modality: - description: (0008, 0060) Modality - type: string - - series_description: - description: (0008, 103e) Series Description - type: string - - series_uid: - description: (0020, 000e) Series Instance UID - type: string + authz: + description: The authz of the imaging series, if applicable; used for + type: array + items: + type: string data_category: term: @@ -85,10 +76,61 @@ properties: $ref: "_terms.yaml#/data_type" type: string - core_metadata_collections: - description: The submitter_id or id of the core_metadata_collection to which the imaging_series belongs, i.e., a link to a record in the parent node. - $ref: "_definitions.yaml#/to_one" + dicom_viewer_url: + description: A URL where the imaging series can be viewed. + type: string + + file_name: + description: The file_name of the imaging series file, if applicable. + type: string + file_size: + description: The file_size in bytes of the imaging series file, if applicable. + type: integer + + manifest: + description: The list of object_ids for the imaging series, if applicable. + type: array + items: + type: string + + md5sum: + description: The md5sum of the imaging series file, if applicable. + type: string + + Manufacturer: + description: (0008, 0070) Manufacturer + type: string + + ManufacturerModelName: + description: (0008, 1090) Manufacturer's Model Name + type: string + + Modality: + description: (0008, 0060) Modality + type: string + + object_id: + description: The object_id (data GUID) of the imaging series file, if applicable. + type: string + + SeriesDescription: + description: (0008, 103e) Series Description + type: string + + SeriesInstanceUID: + description: (0020, 000e) Series Instance UID + type: string + + # links imaging_studies: description: The submitter_id or id of the imaging_study this imaging_series belongs to, i.e., a link to a record in the parent node. $ref: "_definitions.yaml#/to_one" + + cases: + description: The submitter_id or id of the case observed in this imaging_series, i.e., a link to a record in the parent node. + $ref: "_definitions.yaml#/to_one" + + datasets: + description: The submitter_id or id of the dataset this imaging_series belongs to, i.e., a link to a record in the parent node. + $ref: "_definitions.yaml#/to_many" \ No newline at end of file From ac763d497ac95d30dc88ac3243a78c22d572204e Mon Sep 17 00:00:00 2001 From: Chris Date: Mon, 13 May 2024 15:09:45 -0500 Subject: [PATCH 2/4] updates --- gdcdictionary/schemas/_definitions.yaml | 5 -- gdcdictionary/schemas/case.yaml | 94 +++-------------------- gdcdictionary/schemas/dataset.yaml | 57 +------------- gdcdictionary/schemas/imaging_series.yaml | 34 +++----- gdcdictionary/schemas/imaging_study.yaml | 77 ++++--------------- 5 files changed, 38 insertions(+), 229 deletions(-) diff --git a/gdcdictionary/schemas/_definitions.yaml b/gdcdictionary/schemas/_definitions.yaml index 96d99aa..d55e104 100755 --- a/gdcdictionary/schemas/_definitions.yaml +++ b/gdcdictionary/schemas/_definitions.yaml @@ -231,11 +231,6 @@ ubiquitous_properties: submitter_id: description: "A human-readable, unique identifier for a record in the metadata database. It can be used in place of the UUID for identifying or recalling a record (e.g., in data queries or uploads/exports)." type: string - case_ids: - description: "A list of one or more case submitter_ids associated with this data." - type: array - items: - type: string state: $ref: "#/state" project_id: diff --git a/gdcdictionary/schemas/case.yaml b/gdcdictionary/schemas/case.yaml index 25dda48..70328eb 100755 --- a/gdcdictionary/schemas/case.yaml +++ b/gdcdictionary/schemas/case.yaml @@ -41,99 +41,25 @@ properties: $ref: "_definitions.yaml#/ubiquitous_properties" - age_at_index: - description: The study participant's age, in years, at the index event. The index event is determined by the data submitter and used as an anchor date for all temporal variables. Note that an age of 0 indicates a participant who is younger than 1 year old. For participants with ages greater than 89 years, please use the property 'age_at_index_gt89'. + PatientAge: + description: (0010,1010) the patient's age at imaging. type: number - maximum: 89 - minimum: 0 - - age_at_index_gt89: - description: Indicates whether the subject's age at the time of the study was greater than 89 years. - enum: - - "Yes" - - "No" - - covid19_positive: - description: "An indicator of whether the patient has ever had a positive COVID-19 test or been diagnosed with one of the following ICD-10 COVID-19 conditions: COVID-19 (U07. 1), Influenza due to unidentified influenza virus with other manifestations (J11.8), Post COVID-19 condition (U09.9), Myalgic encephalomyelitis/chronic fatigue syndrome (G93.32), or Sequelae of other specified infectious and parasitic diseases (B94.8). For more information about a patient's specific COVID-19 diagnosis, details can be found under Condition." - enum: - - "Yes" - - "No" - - "Indeterminate" - - "Not Reported" - - country_of_residence: - description: The country where the subject resides. + + PatientID: + description: (0010,0020) A unique identifier for the patient. type: string - ethnicity: - term: - $ref: "_terms.yaml#/ethnicity" - enum: - - Hispanic or Latino - - Not Hispanic or Latino - - Not Reported - - gen3_linked_subjects_available: - description: Indicates whether there is data available for the subject in other data resources. - type: boolean - - icu_indicator: - description: Indicates whether the subject has been admitted to the ICU. - type: boolean - - index_event: - description: The event used as the anchor or start date for all temporal data elements. This acts as day 0 on a timeline of events relating to the patient. + PatientSex: + description: (0010,0040) the patient's sex; the biologic character or quality that distinguishes male and female from one another as expressed by analysis of the person's gonadal, morphologic (internal and external), chromosomal, and hormonal characteristics type: string - linked_external_data: - description: A list of all external data resources that are confirmed to have data for the case. - type: array - items: - type: string - - long_covid_diagnosis: - description: "An indicator of whether the patient has ever been diagnosed with one of the following ICD-10 long COVID-19 conditions: U09.9 (Post COVID-19 condition, unspecified), G93.32 (Myalgic encephalomyelitis/chronic fatigue syndrome), and B94.8 (Sequelae of other specified infectious and parasitic diseases). 'Positive' means the patient was diagnosed with a long COVID condition, while 'Not Reported' means the patient has never been diagnosed with a long COVID condition." - enum: - - Positive - - Not Reported + EthnicGroup: + description: (0010,2160) The ethnic group to which the patient belongs. + type: string race: term: $ref: "_terms.yaml#/race" - enum: - - American Indian or Alaska Native - - Asian - - Black or African American - - Native Hawaiian or other Pacific Islander - - Other - - White - - Not Reported - - sex: - description: The biologic character or quality that distinguishes male and female from one another as expressed by analysis of the person's gonadal, morphologic (internal and external), chromosomal, and hormonal characteristics. - enum: - - Female - - Male - - Not Reported - - site_id: - description: A de-identified code used to classify a case as part of a specific data submission. - type: string - - token_record_id: - description: An ID used to link a de-identified case in MIDRC to the same case in an external data resource. - type: string - - treatment_info: - description: Indicates whether detailed treatment information is available for the subject. - type: boolean - - ventilator_indicator: - description: Indicates whether the subject has been on a ventilator. - type: boolean - - zip: - description: The three-digit United States zip code of residence for any population greater than 20,000. For zip codes where the three digit number represents a population less than 20,000 "000" will be provided. type: string datasets: diff --git a/gdcdictionary/schemas/dataset.yaml b/gdcdictionary/schemas/dataset.yaml index 4826fc3..7bafcf3 100644 --- a/gdcdictionary/schemas/dataset.yaml +++ b/gdcdictionary/schemas/dataset.yaml @@ -31,53 +31,24 @@ links: required: - submitter_id - type - - data_description - projects + - collection_id uniqueKeys: - [id] - [project_id, submitter_id] properties: + $ref: "_definitions.yaml#/ubiquitous_properties" - #system properties, do not change or remove: - created_datetime: - $ref: "_definitions.yaml#/datetime" - - id: - $ref: "_definitions.yaml#/UUID" - - project_id: - $ref: "_definitions.yaml#/project_id" - - state: - $ref: "_definitions.yaml#/state" - - submitter_id: - description: A human-readable identifier for the study's record in the database. It can be used in place of the UUID for identifying or recalling a record. - type: string - - type: - description: The name of the node in the database to be used in queries. In this case "dataset". - enum: - - dataset - - updated_datetime: - $ref: "_definitions.yaml#/datetime" - - # additional properties to describe the dataset - acknowledgement: - description: Publication acknowledgement(s) for the published dataset. + collection_id: + description: A unique identifier for the dataset. type: string data_citation: description: The citation for the published dataset. type: string - data_contributor: - description: The name of the organization or individual that the contributed dataset belongs to. - type: string - data_description: description: A brief, free-text description of the data files and associated metadata provided for this dataset. type: string @@ -106,26 +77,6 @@ properties: description: The primary body site studied in this dataset. type: string - publication_citation: - description: The major or main publication(s) associated with the data itself or with the publication that published the dataset. - type: string - - research_description: - description: If the dataset is related to a research study, provide a brief, free-text description or abstract of the study being performed, for example, the hypothesis being tested and a very brief description of the materials, methods and results. - type: string - - research_design: - description: A summary of the goals of the research or a general description of the research's relationship to a clinical application. - type: string - - research_objective: - description: The general objective of the research; what the researchers hope to discover or determine. - type: string - - research_setup: - description: A high level description of the setup used to achieve the research objectives. - type: string - projects: description: The code of the project that this dataset belongs to, i.e., a link to the parent node. $ref: "_definitions.yaml#/to_one_project" diff --git a/gdcdictionary/schemas/imaging_series.yaml b/gdcdictionary/schemas/imaging_series.yaml index 3dc97c8..045ec94 100644 --- a/gdcdictionary/schemas/imaging_series.yaml +++ b/gdcdictionary/schemas/imaging_series.yaml @@ -55,11 +55,9 @@ properties: $ref: "_definitions.yaml#/ubiquitous_properties" - authz: - description: The authz of the imaging series, if applicable; used for - type: array - items: - type: string + BodyPartExamined: + description: (0018, 0015) Body Part Examined. + type: string data_category: term: @@ -80,24 +78,12 @@ properties: description: A URL where the imaging series can be viewed. type: string - file_name: - description: The file_name of the imaging series file, if applicable. - type: string - - file_size: - description: The file_size in bytes of the imaging series file, if applicable. - type: integer - - manifest: - description: The list of object_ids for the imaging series, if applicable. + object_ids: + description: The list of file identifiers (object_ids, DRS URIs, or data GUIDs, etc.) for the imaging series, if applicable. type: array items: type: string - md5sum: - description: The md5sum of the imaging series file, if applicable. - type: string - Manufacturer: description: (0008, 0070) Manufacturer type: string @@ -110,10 +96,6 @@ properties: description: (0008, 0060) Modality type: string - object_id: - description: The object_id (data GUID) of the imaging series file, if applicable. - type: string - SeriesDescription: description: (0008, 103e) Series Description type: string @@ -122,6 +104,10 @@ properties: description: (0020, 000e) Series Instance UID type: string + ViewPosition: + description: (0018,5101) Radiographic view associated with Patient Position (0018,5100). + type: string + # links imaging_studies: description: The submitter_id or id of the imaging_study this imaging_series belongs to, i.e., a link to a record in the parent node. @@ -133,4 +119,4 @@ properties: datasets: description: The submitter_id or id of the dataset this imaging_series belongs to, i.e., a link to a record in the parent node. - $ref: "_definitions.yaml#/to_many" \ No newline at end of file + $ref: "_definitions.yaml#/to_many" diff --git a/gdcdictionary/schemas/imaging_study.yaml b/gdcdictionary/schemas/imaging_study.yaml index c7f7b9f..300c5ce 100644 --- a/gdcdictionary/schemas/imaging_study.yaml +++ b/gdcdictionary/schemas/imaging_study.yaml @@ -47,90 +47,41 @@ properties: $ref: "_definitions.yaml#/ubiquitous_properties" - age_at_imaging: - description: The study participant's age, in years, at the time the imaging study was performed. Note that an age of 0 indicates a participant who is younger than 1 year old. For participants with ages greater than 89 years, please use the property 'age_at_index_gt89'. - type: number - maximum: 89 - minimum: 0 - age_at_imaging_gt89: - description: Indicates whether the age of the patient in years at the time the imaging study was performed is greater than 89 years. - enum: - - "Yes" - - "No" +disease_type +primary_site + - body_part_examined: + BodyPartExamined: description: (0018, 0015) Body Part Examined. type: array items: type: string - days_from_study_to_neg_covid_test: - description: The number of days from the imaging study to the patient's negative COVID-19 test(s). This property takes a list of values, each of which represents a COVID-19 test for the patient. A positive value for this property means that a negative COVID-19 test result was obtained for the patient that many days after the imaging study was performed. A negative value indicates that a negative COVID-19 test result was obtained prior to the date of imaging. - type: array - items: - type: integer - - days_from_study_to_pos_covid_test: - description: The number of days from the imaging study to the patient's positive COVID-19 test(s). This property takes a list of values, each of which represents a COVID-19 test for the patient. A positive value for this property means that a positive COVID-19 test result was obtained for the patient that many days after the imaging study was performed. A negative value indicates that the positive COVID-19 test result was obtained prior to the date of imaging. - type: array - items: - type: integer - - days_to_study: - description: The number of days between the case's index date and the date of the imaging study. + PatientAge: + description: (0010,1010) The patient's age at the time of the imaging study. type: number - - image_data_modified: - description: An indicator of whether any post-clinical modification of image pixel data has been performed on the study. - type: boolean - - loinc_code: - description: The LOINC code assigned based on the study description provided. - type: string - - loinc_contrast: - description: The LOINC indicator noting whether the image was completed with or without contrast, as associated with the assigned LOINC code. - type: string - - loinc_long_common_name: - description: The LOINC long common name associated with the assigned LOINC code. - type: string - - loinc_method: - description: The LOINC method or imaging modality associated with the assigned LOINC code. - type: string - - loinc_system: - description: The LOINC system or body part examined associated with the assigned LOINC code. - type: string - - study_description: + + StudyDescription: description: (0008, 1030) Study Description. type: string - study_modality: + Modality: description: The modalities of the imaging study; derived from (0008, 0060) Modality. type: array items: type: string - study_uid: + StudyInstanceUID: description: (0020, 000d) Study Instance UID type: string - study_year: - description: The year when imaging study was performed; year component of Study Date (0008, 0020). - type: integer - - study_year_shifted: - description: Indicates whether the study year has been shifted for de-identification. - type: boolean - cases: - description: The submitter_id or id of the case observed in this imaging_study, i.e., a link to a record in the parent node. + description: The submitter_id or id of the case/patient observed in this imaging_study, i.e., a link to a record in the parent node. $ref: "_definitions.yaml#/to_one" datasets: description: The submitter_id or id of the dataset this case belongs to, i.e., a link to a record in the parent node. - $ref: "_definitions.yaml#/to_many" \ No newline at end of file + $ref: "_definitions.yaml#/to_many" + + From 2cedc1908b3955d392040c486f9bb93930594089 Mon Sep 17 00:00:00 2001 From: Chris Date: Mon, 13 May 2024 15:15:23 -0500 Subject: [PATCH 3/4] fixed typo --- gdcdictionary/schemas/imaging_study.yaml | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/gdcdictionary/schemas/imaging_study.yaml b/gdcdictionary/schemas/imaging_study.yaml index 300c5ce..ba220c7 100644 --- a/gdcdictionary/schemas/imaging_study.yaml +++ b/gdcdictionary/schemas/imaging_study.yaml @@ -58,10 +58,18 @@ primary_site items: type: string + disease_type: + description: The primary type of disease studied in this imaging study, if applicable. + type: string + PatientAge: description: (0010,1010) The patient's age at the time of the imaging study. type: number + primary_site: + description: The primary body site studied in this imaging study. + type: string + StudyDescription: description: (0008, 1030) Study Description. type: string @@ -82,6 +90,4 @@ primary_site datasets: description: The submitter_id or id of the dataset this case belongs to, i.e., a link to a record in the parent node. - $ref: "_definitions.yaml#/to_many" - - + $ref: "_definitions.yaml#/to_many" \ No newline at end of file From c971d739748da8e4691818208ddc4224c227e914 Mon Sep 17 00:00:00 2001 From: Chris Date: Mon, 13 May 2024 15:17:34 -0500 Subject: [PATCH 4/4] another typo fix --- gdcdictionary/schemas/imaging_study.yaml | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/gdcdictionary/schemas/imaging_study.yaml b/gdcdictionary/schemas/imaging_study.yaml index ba220c7..1a9736b 100644 --- a/gdcdictionary/schemas/imaging_study.yaml +++ b/gdcdictionary/schemas/imaging_study.yaml @@ -47,11 +47,6 @@ properties: $ref: "_definitions.yaml#/ubiquitous_properties" - -disease_type -primary_site - - BodyPartExamined: description: (0018, 0015) Body Part Examined. type: array @@ -62,6 +57,12 @@ primary_site description: The primary type of disease studied in this imaging study, if applicable. type: string + Modality: + description: The modalities of the imaging study; derived from (0008, 0060) Modality. + type: array + items: + type: string + PatientAge: description: (0010,1010) The patient's age at the time of the imaging study. type: number @@ -74,12 +75,6 @@ primary_site description: (0008, 1030) Study Description. type: string - Modality: - description: The modalities of the imaging study; derived from (0008, 0060) Modality. - type: array - items: - type: string - StudyInstanceUID: description: (0020, 000d) Study Instance UID type: string