\n
\n About Datasets \n
\n
\n - study_id:\n The study ID. Each study may include multiple series of images.\n
\n
\n
![\"Spondylolisthesis](\"attachment:c0236b45-3dc9-46b2-9fc8-9b1e6bc24711.jpg\")
\n
\n
\n - condition:\n There are three core conditions: spinal canal stenosis, neural_foraminal_narrowing, and subarticular_stenosis. The latter two are considered for each side of the spine.\n
\n
\n - level:\n The relevant vertebrae, such as l3_l4\n
\n
\n - series_id:\n The imagery series ID.\n
\n
\n - instance_number:\n The image's order number within the 3D stack.\n
\n
\n - [x/y]:\n The x/y coordinates for the center of the area that defined the label.\n
\n
\n - [normal_mild/moderate/severe]:\n The three prediction columns.\n
\n
\n - row_id:\n A slug of the study ID, condition, and level such as 12345_spinal_canal_stenosis_l3_l4.\n
\n
\n
\n The DataFrame contains 1975 observations (rows) and 26 variables (columns).
\n
\n
\n Information about the types of variables and memory usage is provided. study_id is of type int64 (integer), while the other 25 variables are of type object (text). The total memory usage is approximately 401.3 KB.
\n
\n
\n The number of unique values for each variable is shown. study_id has 1975 unique values, while each of the other 25 variables has three distinct unique values.
\n
\n
\n The number of missing values (NaN or NULL) is reported for each variable. Some variables contain missing values. The variables left_subarticular_stenosis_l1_l2 and right_subarticular_stenosis_l1_l2 have the highest number of missing values (164 and 161 missing values, respectively).
\n
\n
\n
\n 'spinal_canal_stenosis_l5_s1' and 'spinal_canal_stenosis_l1_l2' variables show that approximately 96% of values are categorized as 'Normal/Mild'. This indicates that spinal canal stenosis is generally mild at these levels.
\n
\n
\n For the 'spinal_canal_stenosis_l4_l5' variable, we observe a higher occurrence of 'Severe' and 'Moderate' categories. This suggests that more severe cases of stenosis are prevalent at this level.
\n
\n
\n In 'neural_foraminal_narrowing_l4_l5' and 'neural_foraminal_narrowing_l5_s1' variables, regardless of left or right side, the 'Moderate' category is notably higher compared to other spinal levels. This indicates that moderate narrowing is common at these levels.
\n
\n
\n The 'right_subarticular_stenosis_l1_l4' variable shows a significant presence of the 'Moderate' category. This suggests that moderate stenosis is common at this level.
\n
\n
\n At the levels of 'left_subarticular_stenosis_l4_l5' and 'left_subarticular_stenosis_l4_l5', there is an observable predominance of 'Severe' and 'Moderate' values. This suggests the presence of severe stenosis cases at these levels.
\n
\n
\n
\n This study was conducted using a RandomForestClassifier model to predict the severity of specific health conditions. The dataset included various conditions and their levels recorded for each study. During data preparation, missing values were filled, categorical variables were converted into numerical formats, and the model was trained on the training data.
\n
\n
\n The results consisted of predicted probabilities for Normal/Mild, Moderate, and Severe outcomes for each study and condition. These probabilities were rescaled for Normal/Mild and Moderate classes and calculated for the Severe class. The outcomes were organized to display estimated severity ratios for each study and condition.
\n
\n
\n This study illustrates how machine learning models can be employed to predict health conditions' severity and how these predictions can be organized and presented effectively.
\n
\n
\n
🌟 I would like to thank RSNA for organizing the competition and providing the valuable dataset. Your contributions play a significant role in advancing medical imaging technologies.
\n
\n
![\"Sample](\"attachment:17455c68-c73a-41fb-b5b5-c23ba68f8d7d.jpg\")
\n
\n
Thank you for taking the time to review my project. Your feedback and comments are extremely valuable for improving my projects. Please feel free to share your thoughts and suggestions with me 💬
\n
![\"Spondylolisthesis](\"attachment:4ffaac17-aa75-4f8a-9134-860cf49db7b7.jpg\")
\n ![\"Sample](\"attachment:a08ddfe2-82b8-4b61-87fd-a79fb34c99b3.jpg\")
\n