-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
12b7b28
commit 3e71e29
Showing
16 changed files
with
532 additions
and
50 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,27 @@ | ||
import os | ||
import cv2 | ||
|
||
def enhance_contrast(image_path, output_path, alpha, beta): | ||
# Open the image file | ||
image = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE) # Convert image to grayscale | ||
|
||
# Enhance Image Contrast | ||
image_enhanced = cv2.convertScaleAbs(image, alpha=alpha, beta=beta) | ||
|
||
# Save the enhanced image | ||
cv2.imwrite(output_path, image_enhanced) | ||
|
||
# Set the directory you want to start from | ||
rootDir = '/home/jeff/test_slices' | ||
for dirName, subdirList, fileList in os.walk(rootDir): | ||
print('Found directory: %s' % dirName) | ||
for fname in fileList: | ||
if fname.endswith('.jpg'): | ||
print('\t%s' % fname) | ||
input_path = os.path.join(dirName, fname) | ||
#mkdir if not exist | ||
if not os.path.exists(os.path.join(dirName, 'enhanced')): | ||
os.mkdir(os.path.join(dirName, 'enhanced')) | ||
output_path = os.path.join(dirName, 'enhanced', fname) | ||
print(output_path) | ||
enhance_contrast(input_path, output_path, 3, 0) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,29 @@ | ||
import os | ||
import cv2 | ||
|
||
def enhance_edges(image_path, output_path, low_threshold, high_threshold): | ||
# Open the image file | ||
image = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE) # Convert image to grayscale | ||
|
||
# Apply Gaussian blur to reduce noise | ||
image_blur = cv2.GaussianBlur(image, (5, 5), 0) | ||
|
||
# Apply Canny Edge Detection | ||
edges = cv2.Canny(image_blur, low_threshold, high_threshold) | ||
|
||
# Save the enhanced image | ||
cv2.imwrite(output_path, edges) | ||
|
||
# Set the directory you want to start from | ||
rootDir = '/home/jeff/test_slices' | ||
for dirName, subdirList, fileList in os.walk(rootDir): | ||
print('Found directory: %s' % dirName) | ||
for fname in fileList: | ||
if fname.endswith('.jpg'): | ||
print('\t%s' % fname) | ||
input_path = os.path.join(dirName, fname) | ||
if not os.path.exists(os.path.join(dirName, 'enhanced_edge')): | ||
os.mkdir(os.path.join(dirName, 'enhanced_edge')) | ||
output_path = os.path.join(dirName, 'enhanced_edge', fname) | ||
print(output_path) | ||
enhance_edges(input_path, output_path, 100, 200) # Adjust thresholds as needed |
47 changes: 47 additions & 0 deletions
47
wanshi/visualizations/crona/META-AI_ Guideline Items - Tabellenblatt_updated.csv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,47 @@ | ||
,Guideline Item,Description (specification and/or example content),Item type,AI-specific item?,STARE-HI,TRIPOD,Luo et al.,CONSORT-AI,SPIRIT-AI,Schwendicke et al.,CLEAR Derm,DECIDE-AI,CLEAR,,% Item included in high-level consensus guidelines (Y/P),,Good ML Practice,MI-CLAIM,PRIME,DOME,Shen,Hatt et al.,,% Item included in intermediate-level consensus guidelines (Y/P),,Vihinen,CLAIM,MINIMAR,Stevens et al.,CAIR,PIECES,Zukotynski et al.,El Naqa et al.,Jones et al.,R-AI-DIOLOGY,Volovici et al.,,% Item included in low-level consensus guidelines (Y/P),,% Item included in all guidelines (Y/P),,,General,,Specific | ||
Year,,,,,2009,2015,2016,2020,2020,2021,2022,2022,2023,,,,2019,2020,2020,2021,2022,2023,,,,2012,2020,2020,2020,2021,2021,2021,2021,2022,2022,2022,,,,,,,,, | ||
Inclusion Process,,,,,"""+""",%,*,*,*,*,*,*,*,,,,"""+""",*,*,*,*,#,,,,*,#,*,*,*,#,*,#,*,*,#,,,,,,,,, | ||
Guideline Type,,,,,G,G,G,G,G,S,S,G,S,,,,G,G,S,G,S,S,,,,G,S,G,G,G,S,S,S,S,S,G,,,,,,,,, | ||
Level of Consensus,,,,,H,H,H,H,H,H,H,H,H,,,,M,M,M,M,M,M,,,,L,L,L,L,L,L,L,L,L,L,L,,,,,,,,, | ||
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,, | ||
Clinical Rationale,Topic,Predictive AI,Content,Yes,N,Y,Y,Y,Y,Y,N,Y,Y,,"0,78",,N,N,P,N,N,N,,"0,17",,N,Y,N,N,Y,N,N,N,Y,N,N,,"0,27",,"0,42",,,"0,43",,"0,50" | ||
,Study Design,"Retrospective vs. prospective, prognostic vs. diagnostic",Content,Partially,Y,Y,Y,N,N,Y,N,Y,Y,,"0,67",,N,Y,Y,N,N,Y,,"0,50",,N,Y,N,N,N,N,N,N,N,N,N,,"0,09",,"0,38",,,"0,36",,"0,50" | ||
,Prediction Problem,"Prediction target, outcome parameters, performance metrics",Content,Yes,Y,Y,Y,Y,Y,Y,N,Y,Y,,"0,89",,P,Y,Y,N,N,Y,,"0,67",,N,Y,P,P,P,Y,N,N,Y,P,N,,"0,64",,"0,73",,,"0,79",,"0,75" | ||
,Clinical Setting,Details on the clinical problem and intended use,Content,No,Y,Y,Y,Y,Y,Y,Y,Y,Y,,"1,00",,Y,Y,N,N,P,Y,,"0,67",,N,Y,P,P,Y,Y,N,P,Y,Y,N,,"0,73",,"0,81",,,"0,79",,"0,83" | ||
,Rationale,Relation between prediction problem and clinical goal,Content,Yes,Y,P,Y,Y,Y,P,P,Y,P,,"1,00",,Y,Y,N,N,N,Y,,"0,50",,N,Y,N,P,P,P,N,P,Y,P,N,,"0,64",,"0,73",,,"0,71",,"0,75" | ||
,Existing AI and Statistical Models,"Performance metrics, level of translation, clinical application",Content,Yes,P,Y,Y,N,Y,Y,N,P,Y,,"0,78",,N,P,Y,Y,N,N,,"0,50",,Y,N,N,N,N,P,N,P,P,P,Y,,"0,55",,"0,62",,,"0,64",,"0,58" | ||
,State-of-the-art,Identify state-of-the-art clinical solution and use as a baseline for comparison,Quality,Partially,P,P,N,N,N,P,N,N,P,,"0,44",,P,Y,N,Y,P,N,,"0,67",,P,N,N,N,N,N,N,N,N,N,N,,"0,09",,"0,35",,,"0,43",,"0,33" | ||
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,, | ||
Data,"Data Sources, Types, and Structure","Original data format and volume, facility details, structured vs. unstructured data",Content,Partially,Y,Y,Y,P,P,Y,Y,Y,Y,,"1,00",,P,Y,Y,P,P,Y,,"1,00",,N,Y,Y,Y,Y,Y,Y,Y,Y,Y,Y,,"0,91",,"0,96",,,"0,93",,"1,00" | ||
,Data Selection,Inclusion and exclusion criteria at the level of data and participants,Content,Partially,Y,Y,Y,Y,Y,Y,N,Y,Y,,"0,89",,P,N,N,N,P,P,,"0,50",,N,Y,Y,N,Y,Y,N,N,Y,N,Y,,"0,55",,"0,65",,,"0,71",,"0,67" | ||
,Data Preprocessing,"Data transformation, handling of missing data and outliers",Content,Yes,Y,Y,Y,Y,Y,Y,Y,Y,Y,,"1,00",,P,Y,Y,N,P,Y,,"0,83",,N,Y,N,Y,Y,Y,N,Y,P,Y,Y,,"0,73",,"0,85",,,"0,79",,"0,92" | ||
,Labeling of Input Data,"Clinical outcome vs. expert rating, number and expertise of labellers","Content, Quality",Partially,Y,N,N,Y,Y,Y,P,Y,Y,,"0,78",,Y,N,N,N,P,Y,,"0,50",,N,Y,P,P,P,Y,N,Y,Y,N,P,,"0,73",,"0,69",,,"0,64",,"0,75" | ||
,Rater Variability,Inter- and intrarater variability,Quality,Partially,Y,N,N,N,N,Y,N,N,Y,,"0,33",,N,N,N,N,N,N,,"0,00",,N,Y,N,N,Y,N,N,P,N,N,N,,"0,27",,"0,23",,,"0,14",,"0,33" | ||
,Data Processing Location,"Specification of data processing location (local vs. cloud, external institutions involved in data processing, data flow)",Content,Partially,N,N,N,N,N,Y,N,N,N,,"0,11",,N,N,N,N,Y,N,,"0,17",,N,N,N,N,N,N,N,N,N,Y,N,,"0,09",,"0,12",,,"0,00",,"0,33" | ||
,De-Identification,Address anonymization/de-identification of data,Quality,Partially,N,N,N,N,N,Y,N,N,Y,,"0,22",,N,N,N,N,Y,N,,"0,17",,N,Y,N,N,N,Y,N,N,N,Y,N,,"0,27",,"0,23",,,"0,00",,"0,58" | ||
,Data Dictionary,Release data dictionary with explanations of variables,Content,Partially,N,N,N,N,N,N,N,N,N,,"0,00",,P,N,Y,N,N,N,,"0,33",,N,Y,N,N,N,N,N,N,N,N,N,,"0,09",,"0,12",,,"0,07",,"0,25" | ||
,Data Leakage,"Independence of training/validation/test data (i.e. do not use evaluation sets for feature selection, preprocessing steps or parameter tuning)",Quality,Yes,N,N,N,N,N,N,N,N,P,,"0,11",,Y,Y,N,Y,N,Y,,"0,67",,Y,N,N,P,N,Y,N,P,Y,N,N,,"0,45",,"0,38",,,"0,36",,"0,42" | ||
,Representativeness,Training and test data should be representative of real-world clinical settings,Quality,Yes,P,P,N,N,N,Y,N,N,N,,"0,33",,Y,Y,N,Y,P,P,,"0,83",,N,N,N,N,N,N,N,Y,Y,P,Y,,"0,36",,"0,46",,,"0,43",,"0,50" | ||
,Basic Statistics of the Dataset,Distribution of input and outcomes,Content,Partially,Y,Y,Y,N,N,N,Y,N,N,,"0,44",,Y,N,Y,Y,N,N,,"0,50",,N,Y,Y,N,N,N,N,Y,Y,N,Y,,"0,45",,"0,46",,,"0,50",,"0,42" | ||
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,, | ||
Model Training and Validation,Type of Prediction Model,"Type of algorithm, classification vs. regression",Content,Yes,N,Y,Y,Y,Y,Y,N,Y,Y,,"0,78",,N,P,Y,Y,N,N,,"0,50",,N,Y,Y,N,Y,Y,Y,Y,Y,N,N,,"0,64",,"0,65",,,"0,64",,"0,67" | ||
,Model Development,"Identification and removal of redundant independent variables, model training and selection strategy",Content,Yes,N,Y,Y,N,P,Y,Y,P,Y,,"0,78",,P,Y,Y,Y,P,P,,"1,00",,Y,Y,Y,Y,Y,Y,P,Y,Y,P,P,,"1,00",,"0,92",,,"0,86",,"1,00" | ||
,Model Validation,"Internal vs. external vs. cross validation, validation metrics",Content,Yes,Y,Y,Y,N,N,Y,P,P,Y,,"0,78",,P,P,Y,Y,N,P,,"0,83",,Y,Y,P,Y,Y,Y,Y,Y,Y,P,P,,"1,00",,"0,88",,,"0,86",,"0,92" | ||
,Model Interpretability,Statement on model interpretability,"Content, Quality",Yes,N,N,Y,N,N,Y,N,N,Y,,"0,33",,Y,N,Y,Y,N,N,,"0,50",,N,Y,N,P,N,N,N,P,Y,N,Y,,"0,45",,"0,42",,,"0,36",,"0,50" | ||
,Model Performance and Interpretation,"Outcome metrics, confidence intervals",Content,Yes,Y,Y,Y,P,P,P,Y,Y,Y,,"1,00",,Y,P,P,Y,P,N,,"0,83",,Y,Y,Y,Y,P,Y,N,Y,Y,P,P,,"0,91",,"0,92",,,"1,00",,"0,83" | ||
,Computational Cost,"Model execution time, floating point operations per second",Content,Yes,N,N,N,N,N,N,N,N,N,,"0,00",,N,N,N,Y,N,N,,"0,17",,N,N,N,N,N,N,Y,P,N,N,N,,"0,18",,"0,12",,,"0,07",,"0,17" | ||
,Statistical Methods,Appropriate methods and significance levels for performance comparison of baseline and proposed model,Quality,Partially,Y,Y,N,N,N,Y,N,N,Y,,"0,44",,Y,Y,N,Y,N,N,,"0,50",,P,Y,N,N,N,P,N,Y,Y,N,Y,,"0,55",,"0,50",,,"0,50",,"0,50" | ||
,Performance Errors,Identification and analysis of errors,"Content, Quality",Yes,Y,Y,N,Y,Y,N,P,Y,P,,"0,78",,Y,N,P,N,P,N,,"0,50",,P,Y,N,N,Y,N,N,N,N,N,P,,"0,36",,"0,54",,,"0,64",,"0,50" | ||
,Over-/Underfitting,Assessment of the possibility of over-/underfitting (i.e. by reporting indicators such as train vs. test error),Quality,Yes,N,N,N,N,N,N,N,N,N,,"0,00",,Y,N,N,Y,N,N,,"0,33",,P,N,N,P,N,N,N,Y,N,N,N,,"0,27",,"0,19",,,"0,29",,"0,08" | ||
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,, | ||
Critical Appraisal,Clinical Implications and Practical Value,"Potential augmentations of clinical workflows, potential changes in clinical decision making",Content,Partially,Y,Y,Y,Y,Y,Y,Y,Y,Y,,"1,00",,Y,N,N,N,Y,N,,"0,33",,N,Y,N,N,N,N,N,Y,N,Y,N,,"0,27",,"0,54",,,"0,50",,"0,58" | ||
,Translation,Details on integration into clinical workflow,Content,Partially,N,Y,N,N,N,N,N,Y,N,,"0,22",,Y,N,N,N,P,N,,"0,33",,N,Y,N,N,N,N,N,N,Y,Y,N,,"0,27",,"0,27",,,"0,21",,"0,42" | ||
,Limitations,"Bias, generalizability, interpretation pitfalls",Content,Partially,Y,Y,Y,N,N,P,Y,Y,Y,,"0,78",,Y,N,Y,N,P,N,,"0,50",,N,Y,N,N,N,N,N,Y,P,N,Y,,"0,36",,"0,54",,,"0,43",,"0,67" | ||
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,, | ||
Ethics and Reproducibility,Data Publication,Publication of datasets or inclusion of a statement on public availability,Content,Partially,N,Y,N,N,N,Y,N,Y,Y,,"0,44",,N,Y,N,Y,N,N,,"0,33",,Y,N,Y,Y,Y,N,N,N,Y,N,Y,,"0,55",,"0,46",,,"0,64",,"0,33" | ||
,Code Publication,Publication of code or inclusion of a statement on public availability,Content,Yes,N,Y,N,Y,Y,Y,N,Y,Y,,"0,67",,N,Y,Y,Y,N,N,,"0,50",,N,N,Y,Y,Y,N,P,Y,N,N,Y,,"0,55",,"0,58",,,"0,71",,"0,42" | ||
,AI Intervention Publication,Publication of AI Intervention or inclusion of a statement on public availability,Content,Yes,P,N,N,Y,Y,N,N,N,Y,,"0,44",,N,Y,N,Y,N,N,,"0,33",,N,N,N,N,N,N,N,N,N,N,N,,"0,00",,"0,23",,,"0,36",,"0,17" | ||
,Future Updates,Details on future software/algorithm updates (i.e. how users will be informed),Content,Partially,N,N,N,N,N,N,N,N,N,,"0,00",,P,N,N,N,P,N,,"0,33",,N,N,N,N,N,P,N,N,Y,Y,N,,"0,27",,"0,19",,,"0,07",,"0,42" | ||
,Ethical Statement,Details on IRB approval and informed consent procedure,Content,No,Y,Y,Y,N,N,Y,N,Y,Y,,"0,67",,N,N,N,N,Y,N,,"0,17",,N,N,N,N,Y,N,N,Y,N,N,N,,"0,18",,"0,35",,,"0,36",,"0,33" | ||
,Equity and Access,"Statement on equity, diversity and access to AI application","Content, Quality",Yes,N,N,N,N,N,P,N,P,P,,"0,33",,P,N,N,N,Y,N,,"0,33",,N,N,N,N,N,N,N,N,N,N,N,,"0,00",,"0,19",,,"0,14",,"0,33" | ||
,Legal and Regulatory Aspects,Statement on legal and regulatory aspects,Content,Partially,N,N,N,N,N,Y,N,N,N,,"0,11",,N,N,N,N,Y,N,,"0,17",,N,N,N,N,N,N,N,N,Y,Y,N,,"0,18",,"0,15",,,"0,00",,"0,42" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,38 @@ | ||
group,Guideline Item,% Item included in high-level consensus guidelines (Y/P),% Item included in intermediate-level consensus guidelines (Y/P),% Item included in low-level consensus guidelines (Y/P),% Item included in all guidelines (Y/P) | ||
Clinical Rationale,Topic,"0,75","0,17","0,29","0,43" | ||
,Study Design,"0,63","0,50","0,14","0,43" | ||
,Prediction Problem,"0,88","0,67","0,57","0,71" | ||
,Clinical Setting,"1,00","0,67","0,57","0,76" | ||
,Rationale,"1,00","0,50","0,57","0,71" | ||
,Existing AI and Statistical Models,"0,75","0,50","0,71","0,67" | ||
,State-of-the-art,"0,50","0,67","0,14","0,43" | ||
Data,"Data Sources Types and Structure","1,00","1,00","0,86","0,95" | ||
,Data Selection,"0,88","0,50","0,57","0,67" | ||
,Data Preprocessing,"1,00","0,83","0,71","0,86" | ||
,Labeling of Input Data,"0,75","0,50","0,57","0,62" | ||
,Rater Variability,"0,25","0,00","0,14","0,14" | ||
,Data Processing Location,"0,13","0,17","0,14","0,14" | ||
,De-Identification,"0,13","0,17","0,43","0,24" | ||
,Data Dictionary,"0,13","0,33","0,14","0,19" | ||
,Data Leakage,"0,13","0,67","0,43","0,38" | ||
,Representativeness,"0,38","0,83","0,43","0,52" | ||
,Basic Statistics of the Dataset,"0,75","0,50","0,43","0,57" | ||
Model Training and Validation,Type of Prediction Model,"0,75","0,50","0,57","0,62" | ||
,Model Development,"0,88","1,00","1,00","0,95" | ||
,Model Validation,"0,75","0,83","1,00","0,86" | ||
,Model Interpretability,"0,25","0,50","0,43","0,38" | ||
,Model Performance and Interpretation,"1,00","0,83","0,86","0,90" | ||
,Computational Cost,"0,13","0,17","0,14","0,14" | ||
,Statistical Methods,"0,38","0,50","0,71","0,52" | ||
,Performance Errors,"0,88","0,50","0,43","0,62" | ||
,Over-/Underfitting,"0,13","0,33","0,14","0,19" | ||
Critical Appraisal,Clinical Implications and Practical Value,"1,00","0,33","0,29","0,57" | ||
,Translation,"0,38","0,33","0,43","0,38" | ||
,Limitations,"1,00","0,50","0,43","0,67" | ||
Ethics and Reproducibility,Data Publication,"0,38","0,33","0,43","0,38" | ||
,Code Publication,"0,63","0,50","0,29","0,48" | ||
,AI Intervention Publication,"0,50","0,33","0,00","0,29" | ||
,Future Updates,"0,50","0,33","0,43","0,43" | ||
,Ethical Statement,"0,63","0,17","0,00","0,29" | ||
,Equity and Access,"0,25","0,33","0,00","0,19" | ||
,Legal and Regulatory Aspects,"0,13","0,17","0,29","0,19" |
Oops, something went wrong.