{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# **Overview**\nTraumatic injury is the most common cause of death in the first four decades of life and a major public health problem around the world. There are estimated to be more than 5 million annual deaths worldwide from traumatic injury. Prompt and accurate diagnosis of traumatic injuries is crucial for initiating appropriate and timely interventions, which can significantly improve patient outcomes and survival rates. Computed tomography (CT) has become an indispensable tool in evaluating patients with suspected abdominal injuries due to its ability to provide detailed cross-sectional images of the abdomen.\n\nInterpreting CT scans for abdominal trauma, however, can be a complex and time-consuming task, especially when multiple injuries or areas of subtle active bleeding are present. This challenge seeks to harness the power of artificial intelligence and machine learning to assist medical professionals in rapidly and precisely detecting injuries and grading their severity. The development of advanced algorithms for this purpose has the potential to improve trauma care and patient outcomes worldwide.\n\nThis notebook is particularly going to be one of those notebooks in which the mine expertise of the domain knowledge is very less. But this challenge got me intimidating to try for what insights I can pull out of it.  \n\nCheers !! Let's dive in !\n\n# So What exactly is Abdominal Trauma?\nAbdominal trauma is an injury to the abdomen. Signs and symptoms include abdominal pain, tenderness, rigidity, and bruising of the external abdomen. Complications may include blood loss and infection.\n\nDiagnosis may involve ultrasonography, computed tomography, and peritoneal lavage, and treatment may involve surgery. It is divided into two types blunt or penetrating and may involve damage to the abdominal organs. Injury to the lower chest may cause splenic or liver injuries.\n\n![Abdotrauma.png](attachment:ed81a1ba-9bdc-4afd-b59b-e0155ca3d0fe.png)\n<br>Abdominal trauma resulting in a right kidney contusion (open arrow) and blood surrounding the kidney (closed arrow) as seen on CT.\n\n## Signs and Symptoms\nAbdominal trauma refers to injuries or damage to the structures within the abdominal cavity, which includes organs such as the liver, spleen, kidneys, intestines, and more. Signs and symptoms of abdominal trauma can vary depending on the severity and location of the injury. If you suspect someone has sustained abdominal trauma, it's important to seek medical attention immediately. Here are some common signs and symptoms to watch out for:\n\n1. **Pain:** Abdominal pain can range from mild discomfort to severe and intense pain. The location and nature of the pain can provide clues to the specific injured area.\n\n2. **Tenderness:** The injured person may experience tenderness when pressure is applied to the abdomen. This tenderness may be localized to a specific area.\n\n3. **Bruising:** Visible bruising on the abdomen or around the sides (flanks) could indicate trauma to the underlying structures.\n\n4. **Swelling:** Swelling or distension of the abdomen can occur due to internal bleeding or other injuries.\n\n5. **Nausea and vomiting:** These symptoms can be a result of the body's response to trauma and pain.\n\n6. **Difficulty breathing:** In some cases, abdominal trauma can cause pain and pressure on the diaphragm, making breathing difficult.\n\n7. **Rigid abdomen:** If the abdominal muscles become tense and rigid, it could be a sign of internal bleeding or a serious injury.\n\n8. **Changes in bowel movements:** Abdominal trauma might lead to changes in bowel movements, including constipation or diarrhea.\n\n9. **Blood in urine or stool:** Blood in urine (hematuria) or stool (melena) can indicate damage to the urinary or digestive systems.\n\n10. **Shock:** Severe abdominal trauma can lead to shock, characterized by low blood pressure, rapid heartbeat, and cold, clammy skin.\n\n11. **Dizziness and lightheadedness:** Blood loss from internal injuries can lead to a drop in blood pressure, causing these symptoms.\n\n12. **Fever:** An elevated body temperature could be a sign of infection, which might occur as a complication of abdominal trauma.\n\nRemember that some symptoms might not be immediately apparent, especially in cases of internal bleeding. If you suspect someone has sustained abdominal trauma, it's crucial to seek immediate medical attention. Do not attempt to diagnose or treat abdominal trauma yourself, as it requires professional evaluation and medical intervention.\n\n## Major Causes:\nAbdominal trauma refers to injuries sustained to the structures within the abdominal cavity. These injuries can be caused by various factors, ranging from accidents to medical conditions. Here are some common causes of abdominal trauma:\n\n1. **Blunt Force Trauma:** This occurs when a blunt object strikes the abdomen, causing injury without penetrating the skin. Common causes include:\n\n   - Motor vehicle accidents\n   - Falls from a height\n   - Physical assaults or altercations\n   - Sports-related injuries\n\n2. **Penetrating Trauma:** Penetrating trauma involves an object breaking through the skin and entering the abdominal cavity. Causes include:\n\n   - Stab wounds from knives or other sharp objects\n   - Gunshot wounds\n\n3. **Sports Injuries:** Certain sports, especially contact sports, can lead to abdominal trauma due to collisions or direct impact.\n\n4. **Industrial Accidents:** Accidents in industrial settings, such as machinery malfunctions or falling objects, can result in abdominal injuries.\n\n5. **Domestic Accidents:** Accidents at home, such as falling down stairs or tripping, can also cause abdominal trauma.\n\n6. **Workplace Injuries:** Jobs that involve heavy lifting, machinery operation, or physical labor can increase the risk of abdominal trauma.\n\n7. **Child Abuse:** Non-accidental trauma, such as child abuse or shaken baby syndrome, can lead to abdominal injuries in children.\n\n8. **Motorcycle or Bicycle Accidents:** Accidents involving motorcycles or bicycles can cause abdominal trauma due to the lack of protective barriers.\n\n9. **Explosions and Blasts:** Explosive events, such as bombings or industrial explosions, can cause severe abdominal injuries due to the force of the blast and flying debris.\n\n10. **Sports Equipment Impact:** In contact sports like football, hockey, or martial arts, direct impact from sports equipment or opponents can cause abdominal trauma.\n\n11. **Medical Procedures:** Invasive medical procedures or surgeries in the abdominal area can lead to trauma, although these are typically controlled environments.\n\n12. **Abdominal Organ Rupture:** The rupture of internal organs like the spleen, liver, or kidney due to trauma or underlying conditions can cause significant abdominal trauma.\n\n13. **Seatbelt Injuries:** In car accidents, seatbelts can sometimes cause abdominal injuries due to the force exerted on the abdomen during a collision.\n\nIt's important to note that abdominal trauma can range from mild to severe and life-threatening. Any suspected abdominal trauma should be evaluated by medical professionals promptly to determine the extent of the injury and provide appropriate treatment.\n\n\n<br><br><br>\n**Now, Let's get started with our notebook !!**","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_kg_hide-output":false,"execution":{"iopub.status.busy":"2023-08-13T10:56:18.425277Z","iopub.execute_input":"2023-08-13T10:56:18.426828Z","iopub.status.idle":"2023-08-13T10:56:18.434516Z","shell.execute_reply.started":"2023-08-13T10:56:18.426756Z","shell.execute_reply":"2023-08-13T10:56:18.433207Z"}},"attachments":{"ed81a1ba-9bdc-4afd-b59b-e0155ca3d0fe.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"# Importing Libraries","metadata":{}},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings('ignore')","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-08-13T16:44:08.25885Z","iopub.execute_input":"2023-08-13T16:44:08.259221Z","iopub.status.idle":"2023-08-13T16:44:08.268034Z","shell.execute_reply.started":"2023-08-13T16:44:08.259195Z","shell.execute_reply":"2023-08-13T16:44:08.266999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nimport os\nimport pydicom\nfrom pydicom.data import get_testdata_files\nimport plotly.express as px\nfrom pprint import pprint\nimport nibabel as nib\nfrom ipywidgets import interact","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:08.26948Z","iopub.execute_input":"2023-08-13T16:44:08.269857Z","iopub.status.idle":"2023-08-13T16:44:08.97621Z","shell.execute_reply.started":"2023-08-13T16:44:08.269793Z","shell.execute_reply":"2023-08-13T16:44:08.974908Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Checking all the data components/files we have in our data.","metadata":{}},{"cell_type":"code","source":"main_folder = \"/kaggle/input/rsna-2023-abdominal-trauma-detection/\"\n!ls {main_folder}","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:08.977983Z","iopub.execute_input":"2023-08-13T16:44:08.978658Z","iopub.status.idle":"2023-08-13T16:44:09.241905Z","shell.execute_reply.started":"2023-08-13T16:44:08.978623Z","shell.execute_reply":"2023-08-13T16:44:09.240524Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Reading \"train.csv\" file","metadata":{}},{"cell_type":"code","source":"train = pd.read_csv(main_folder + \"train.csv\")\ntrain.head()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:09.244725Z","iopub.execute_input":"2023-08-13T16:44:09.245234Z","iopub.status.idle":"2023-08-13T16:44:09.273077Z","shell.execute_reply.started":"2023-08-13T16:44:09.245207Z","shell.execute_reply":"2023-08-13T16:44:09.271668Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Number of rows and columns:\", train.shape) \nprint()\nprint('*************************************')\nprint()\nprint(train.info())\nprint()\nprint('*************************************')\nprint()\nprint(\"Number of Unique Values:\\n\",train.nunique())\nprint()\nprint('*************************************')\nprint()\nprint(\"Duplicate Values:\\n\",train.duplicated().sum())\nprint()\nprint('*************************************')\nprint()\nprint(\"Null Values:\\n\",train.isnull().sum())","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:09.274442Z","iopub.execute_input":"2023-08-13T16:44:09.274776Z","iopub.status.idle":"2023-08-13T16:44:09.296249Z","shell.execute_reply.started":"2023-08-13T16:44:09.274744Z","shell.execute_reply":"2023-08-13T16:44:09.294477Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- There are total 3147 rows and 15 columns.\n- It seems data is well structed like a one-hot encoding is already done on the columns as a particular column categorized into several columns and there are no null values.\n- Also each column just contains binary values (0 or 1).","metadata":{}},{"cell_type":"markdown","source":"# Reading \"train_series_meta.csv\" file","metadata":{}},{"cell_type":"code","source":"train_series_meta = pd.read_csv(main_folder + \"train_series_meta.csv\")\ntrain_series_meta.head()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:09.298596Z","iopub.execute_input":"2023-08-13T16:44:09.299084Z","iopub.status.idle":"2023-08-13T16:44:09.323686Z","shell.execute_reply.started":"2023-08-13T16:44:09.299048Z","shell.execute_reply":"2023-08-13T16:44:09.322993Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Number of rows and columns:\", train_series_meta.shape) \nprint()\nprint('*************************************')\nprint()\nprint(train_series_meta.info())\nprint()\nprint('*************************************')\nprint()\nprint(\"Number of Unique Values:\\n\",train_series_meta.nunique())\nprint()\nprint('*************************************')\nprint()\nprint(\"Duplicate Values:\\n\",train_series_meta.duplicated().sum())\nprint()\nprint('*************************************')\nprint()\nprint(\"Null Values:\\n\",train_series_meta.isnull().sum())","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:09.324527Z","iopub.execute_input":"2023-08-13T16:44:09.324814Z","iopub.status.idle":"2023-08-13T16:44:09.34245Z","shell.execute_reply.started":"2023-08-13T16:44:09.324791Z","shell.execute_reply":"2023-08-13T16:44:09.341507Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- There are total 4711 rows and 4 columns.\n- Here the only column with all unique values in series_id with all different values.\n- We have repetiting patient IDs too, so can say particular patient having multiple data entries.","metadata":{}},{"cell_type":"markdown","source":"# Feature Engineering\n- Though the data already seeme usable the way it is, but let's still have some fun with columns.\n- As I already mentioned before, that column seems one-hot encoded already so we'll just try to reverse it by merging all in a compact way.","metadata":{}},{"cell_type":"code","source":"train['bowel'] = (train.iloc[:, 1:3] == 1).idxmax(1)\ntrain['extravasation'] = (train.iloc[:, 3:5] == 1).idxmax(1)\ntrain['kidney'] = (train.iloc[:, 5:8] == 1).idxmax(1)\ntrain['liver'] = (train.iloc[:, 8:11] == 1).idxmax(1)\ntrain['spleen'] = (train.iloc[:, 11:14] == 1).idxmax(1)\n\ntrain.head()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:09.344125Z","iopub.execute_input":"2023-08-13T16:44:09.344681Z","iopub.status.idle":"2023-08-13T16:44:09.383159Z","shell.execute_reply.started":"2023-08-13T16:44:09.344646Z","shell.execute_reply":"2023-08-13T16:44:09.381895Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Hmmm !! seems like our work is done now almost. Now let's delete the old used columns.","metadata":{}},{"cell_type":"code","source":"train = train.drop(columns =['bowel_healthy','bowel_injury','extravasation_healthy','extravasation_injury','kidney_healthy','kidney_low','kidney_high','liver_healthy','liver_low','liver_high',\n                             'spleen_healthy','spleen_low','spleen_high'])\ntrain.head()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:09.384364Z","iopub.execute_input":"2023-08-13T16:44:09.384639Z","iopub.status.idle":"2023-08-13T16:44:09.398358Z","shell.execute_reply.started":"2023-08-13T16:44:09.384617Z","shell.execute_reply":"2023-08-13T16:44:09.396956Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- But wait !! now we are able to understand this categorical data too easy but how will the computer understand it now ?? Huh !\n- For that now let's change these categorical values into numerical values by mapping.\n<br><br>\n- Seems like we took a long route to explore this. But trying some new ways is a way to explore too,<br>\nSo, now let's move forward !!","metadata":{}},{"cell_type":"code","source":"train['bowel'] = train['bowel'].replace(['bowel_injury','bowel_healthy'], [0, 1])\ntrain['extravasation'] = train['extravasation'].replace(['extravasation_injury', 'extravasation_healthy'], [0, 1])\ntrain['kidney'] = train['kidney'].replace(['kidney_low','kidney_high','kidney_healthy'], [0, 1, 2])\ntrain['liver'] = train['liver'].replace(['liver_low','liver_high','liver_healthy'], [0, 1, 2])\ntrain['spleen'] = train['spleen'].replace(['spleen_low','spleen_high','spleen_healthy'], [0, 1, 2])\n\ntrain.head()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:09.399358Z","iopub.execute_input":"2023-08-13T16:44:09.399884Z","iopub.status.idle":"2023-08-13T16:44:09.426897Z","shell.execute_reply.started":"2023-08-13T16:44:09.399857Z","shell.execute_reply":"2023-08-13T16:44:09.425514Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Reading \"image_level_labels.csv\" file","metadata":{}},{"cell_type":"code","source":"image_labels = pd.read_csv(main_folder + \"image_level_labels.csv\")\nimage_labels.head()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:09.428295Z","iopub.execute_input":"2023-08-13T16:44:09.428598Z","iopub.status.idle":"2023-08-13T16:44:09.445019Z","shell.execute_reply.started":"2023-08-13T16:44:09.428556Z","shell.execute_reply":"2023-08-13T16:44:09.444373Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Number of rows and columns:\", image_labels.shape) \nprint()\nprint('*************************************')\nprint()\nprint(image_labels.info())\nprint()\nprint('*************************************')\nprint()\nprint(\"Number of Unique Values:\\n\",image_labels.nunique())\nprint()\nprint('*************************************')\nprint()\nprint(\"Duplicate Values:\\n\",image_labels.duplicated().sum())\nprint()\nprint('*************************************')\nprint()\nprint(\"Null Values:\\n\",image_labels.isnull().sum())","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:09.445754Z","iopub.execute_input":"2023-08-13T16:44:09.445984Z","iopub.status.idle":"2023-08-13T16:44:09.467111Z","shell.execute_reply.started":"2023-08-13T16:44:09.445958Z","shell.execute_reply":"2023-08-13T16:44:09.465611Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- Here it seems we don't have all unique values for any column.\n- It clearly seems that a particular patient must be having too many multiple records.\n- There are no null values though.","metadata":{}},{"cell_type":"markdown","source":"# Reading \"train_dicom_tags.parquet\" file","metadata":{}},{"cell_type":"code","source":"train_dicom_tags = pd.read_parquet(main_folder + \"train_dicom_tags.parquet\")\ntrain_dicom_tags.head()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:09.471069Z","iopub.execute_input":"2023-08-13T16:44:09.471326Z","iopub.status.idle":"2023-08-13T16:44:12.885203Z","shell.execute_reply.started":"2023-08-13T16:44:09.471305Z","shell.execute_reply":"2023-08-13T16:44:12.883898Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Number of rows and columns:\", train_dicom_tags.shape) \nprint()\nprint('*************************************')\nprint()\nprint(train_dicom_tags.info())\nprint()\nprint('*************************************')\nprint()\nprint(\"Number of Unique Values:\\n\",train_dicom_tags.nunique())\nprint()\nprint('*************************************')\nprint()\nprint(\"Duplicate Values:\\n\",train_dicom_tags.duplicated().sum())\nprint()\nprint('*************************************')\nprint()\nprint(\"Null Values:\\n\",train_dicom_tags.isnull().sum())","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:12.886472Z","iopub.execute_input":"2023-08-13T16:44:12.88684Z","iopub.status.idle":"2023-08-13T16:44:28.917879Z","shell.execute_reply.started":"2023-08-13T16:44:12.886812Z","shell.execute_reply":"2023-08-13T16:44:28.916911Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Data Visualization","metadata":{}},{"cell_type":"markdown","source":"## Checking the distribution of patients having any injury","metadata":{}},{"cell_type":"code","source":"fig = px.pie(train, names=train['any_injury'].map({1: 'Patient Injured', 0: 'No Injury'}), height=500, width= 500, color_discrete_sequence=['#D3D3D3','#71797E'], title='Injuries reported in patients')\nfig.update_traces(textfont_size=15)\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:28.919796Z","iopub.execute_input":"2023-08-13T16:44:28.920173Z","iopub.status.idle":"2023-08-13T16:44:29.155164Z","shell.execute_reply.started":"2023-08-13T16:44:28.920142Z","shell.execute_reply":"2023-08-13T16:44:29.15355Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Checking (Bowel, Extravasation) organs Health in patients","metadata":{}},{"cell_type":"code","source":"for column in train.columns[2:4]:\n    fig = px.pie(train, names=train[column].map({1: 'Healthy', 0: 'Injury'}), height=450, width= 450, color_discrete_sequence=['#E5E4E2','#71797E', '#D3D3D3'], \n             title=f' Pie-Chart of {column}')\n    fig.update_traces(textfont_size=15)\n    fig.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:29.15658Z","iopub.execute_input":"2023-08-13T16:44:29.156973Z","iopub.status.idle":"2023-08-13T16:44:29.257358Z","shell.execute_reply.started":"2023-08-13T16:44:29.156935Z","shell.execute_reply":"2023-08-13T16:44:29.255743Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Checking (Kidney, Liver, Spleen) Organs Health in patients","metadata":{}},{"cell_type":"code","source":"for column in train.columns[4:]:\n    fig = px.pie(train, names=train[column].map({2: 'Healthy', 1: 'High Level Injury', 0: 'Low Level Injury'}), height=500, width= 500, color_discrete_sequence=['#E5E4E2','#71797E', '#D3D3D3'], \n             title=f' Pie-Chart of {column}')\n    fig.update_traces(textfont_size=15)\n    fig.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:29.259151Z","iopub.execute_input":"2023-08-13T16:44:29.259602Z","iopub.status.idle":"2023-08-13T16:44:29.404988Z","shell.execute_reply.started":"2023-08-13T16:44:29.25954Z","shell.execute_reply":"2023-08-13T16:44:29.404146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.histplot(train_series_meta['aortic_hu'],kde=True)\nplt.title('Histplot of volume of the Aorta in hounsfield units',fontsize=15)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:29.406103Z","iopub.execute_input":"2023-08-13T16:44:29.407089Z","iopub.status.idle":"2023-08-13T16:44:29.990507Z","shell.execute_reply.started":"2023-08-13T16:44:29.407042Z","shell.execute_reply":"2023-08-13T16:44:29.989383Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- If we closely observe we can see that there is a fine horizontal line ending at -1000, i.e. indicating a negative value which is not practically feasible.\n- Lets check for such negative values.","metadata":{}},{"cell_type":"code","source":"train_series_meta[train_series_meta['aortic_hu']<0]","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:29.991796Z","iopub.execute_input":"2023-08-13T16:44:29.992101Z","iopub.status.idle":"2023-08-13T16:44:30.004395Z","shell.execute_reply.started":"2023-08-13T16:44:29.992073Z","shell.execute_reply":"2023-08-13T16:44:30.003174Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- It seems there was one record which was the main reason behind that. \n- So now, we will take its mod and proceed further","metadata":{}},{"cell_type":"code","source":"sns.histplot(np.abs(train_series_meta['aortic_hu']), kde=True)\nplt.title('Histplot of volume of the Aorta in hounsfield units',fontsize=15)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:30.005942Z","iopub.execute_input":"2023-08-13T16:44:30.006316Z","iopub.status.idle":"2023-08-13T16:44:30.368037Z","shell.execute_reply.started":"2023-08-13T16:44:30.006287Z","shell.execute_reply":"2023-08-13T16:44:30.36662Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Checking whether organs scanned properly during scaning","metadata":{}},{"cell_type":"code","source":"sns.set_style('whitegrid')\nfig,axes = plt.subplots(figsize=(6,6))\nax = sns.countplot(x='incomplete_organ',data=train_series_meta, palette=['#e3784d','#87ace8'])\nfor container in ax.containers:\n    ax.bar_label(container)\nplt.title('Organs not covered by the scan',fontsize=15)\nplt.show()\n\nfig = px.pie(train_series_meta, names=train_series_meta['incomplete_organ'].map({1: 'Organs covered by scan', 0: 'No organs covered by scan'}), height=550, width= 550,\n             color_discrete_sequence=['#D3D3D3','#71797E'], title='Organs covered during scan')\nfig.update_traces(textfont_size=15)\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:30.36961Z","iopub.execute_input":"2023-08-13T16:44:30.369962Z","iopub.status.idle":"2023-08-13T16:44:30.618735Z","shell.execute_reply.started":"2023-08-13T16:44:30.36993Z","shell.execute_reply":"2023-08-13T16:44:30.617365Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- Well, for like 4398 records (93.4%) incdicating organs were scanned properly. On the contrary, number is quite less.","metadata":{}},{"cell_type":"code","source":"health_columns = [\"kidney\", \"liver\", \"spleen\"]\n\ncorrelation_matrix = train[health_columns].corr()\n\nsns.heatmap(correlation_matrix, annot=True, cmap=\"PuBu\", linewidths=.5)\nplt.title(\"Correlation Heatmap of Organs\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:30.620058Z","iopub.execute_input":"2023-08-13T16:44:30.62032Z","iopub.status.idle":"2023-08-13T16:44:30.878935Z","shell.execute_reply.started":"2023-08-13T16:44:30.620298Z","shell.execute_reply":"2023-08-13T16:44:30.877942Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- There is no such big correlation among variables affecting overall analysis.","metadata":{}},{"cell_type":"markdown","source":"## Now checking Injuries shown in patients image labels","metadata":{}},{"cell_type":"code","source":"image_labels['injury_name'].unique()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:30.880053Z","iopub.execute_input":"2023-08-13T16:44:30.880316Z","iopub.status.idle":"2023-08-13T16:44:30.887972Z","shell.execute_reply.started":"2023-08-13T16:44:30.880294Z","shell.execute_reply":"2023-08-13T16:44:30.886582Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.set_style('whitegrid')\nfig,axes = plt.subplots(figsize=(6,6))\nax = sns.countplot(x='injury_name',data=image_labels, palette=['#e3784d','#87ace8'])\nfor container in ax.containers:\n    ax.bar_label(container)\nplt.title('Count of different injury affected persons',fontsize=15)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:30.889331Z","iopub.execute_input":"2023-08-13T16:44:30.889639Z","iopub.status.idle":"2023-08-13T16:44:31.103008Z","shell.execute_reply.started":"2023-08-13T16:44:30.889614Z","shell.execute_reply":"2023-08-13T16:44:31.101876Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"- There is not big difference between the  patients affected by both injuries, but can surely say Still extravasation cases are quite more active.","metadata":{}},{"cell_type":"markdown","source":"## Slice Thickness Distributions used for various CT-Scans","metadata":{}},{"cell_type":"code","source":"sns.set_style('whitegrid')\nfig,axes = plt.subplots(figsize=(20,6))\nax = sns.countplot(x='SliceThickness',palette='rocket', data=train_dicom_tags)\nfor container in ax.containers:\n    ax.bar_label(container)\nplt.title('Slice Thickness',fontsize=15)\nplt.xticks(rotation=45)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:31.104455Z","iopub.execute_input":"2023-08-13T16:44:31.104803Z","iopub.status.idle":"2023-08-13T16:44:31.699144Z","shell.execute_reply.started":"2023-08-13T16:44:31.104774Z","shell.execute_reply":"2023-08-13T16:44:31.697479Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Reading \".dcm\" files","metadata":{}},{"cell_type":"code","source":"sample_image = \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/35794/42578/140.dcm\"","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:31.700645Z","iopub.execute_input":"2023-08-13T16:44:31.701229Z","iopub.status.idle":"2023-08-13T16:44:31.706616Z","shell.execute_reply.started":"2023-08-13T16:44:31.701198Z","shell.execute_reply":"2023-08-13T16:44:31.705046Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_observation_data(path):\n    '''\n    Get information from the .dcm files\n    '''\n    dataset = pydicom.read_file(path)\n    \n    # Dictionary to store the information from the image\n    observation_data = {\n        \"Rows\" : dataset.get(\"Rows\"),\n        \"Columns\" : dataset.get(\"Columns\"),\n        \"SOPInstanceUID\" : dataset.get(\"SOPInstanceUID\"),\n        \"ContentDate\" : dataset.get(\"ContentDate\"),\n        \"SliceThickness\" : dataset.get(\"SliceThickness\"),\n        \"InstanceNumber\" : dataset.get(\"InstanceNumber\"),\n        \"ImagePositionPatient\" : dataset.get(\"ImagePositionPatient\"),\n        \"ImageOrientationPatient\" : dataset.get(\"ImageOrientationPatient\"),\n    }\n\n    # String columns\n    str_columns = [\"SOPInstanceUID\", \"ContentDate\", \n                   \"SliceThickness\", \"InstanceNumber\"]\n    for k in str_columns:\n        observation_data[k] = str(dataset.get(k)) if k in dataset else None\n\n    \n    return observation_data","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:31.70842Z","iopub.execute_input":"2023-08-13T16:44:31.708793Z","iopub.status.idle":"2023-08-13T16:44:31.720424Z","shell.execute_reply.started":"2023-08-13T16:44:31.708761Z","shell.execute_reply":"2023-08-13T16:44:31.719626Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Getting more info about the sample dcm image","metadata":{}},{"cell_type":"code","source":"example = get_observation_data(sample_image)\npprint(example)","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:31.721387Z","iopub.execute_input":"2023-08-13T16:44:31.721926Z","iopub.status.idle":"2023-08-13T16:44:31.745418Z","shell.execute_reply.started":"2023-08-13T16:44:31.721885Z","shell.execute_reply":"2023-08-13T16:44:31.743833Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Previewing DCM Image","metadata":{}},{"cell_type":"code","source":"def plot_image(Image_path):\n    ds = pydicom.dcmread(Image_path)\n    plt.imshow(ds.pixel_array, cmap=plt.cm.bone)\n    plt.show()\n    \nplot_image(sample_image)","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:31.747338Z","iopub.execute_input":"2023-08-13T16:44:31.748008Z","iopub.status.idle":"2023-08-13T16:44:32.031956Z","shell.execute_reply.started":"2023-08-13T16:44:31.747969Z","shell.execute_reply":"2023-08-13T16:44:32.031218Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Segmentations","metadata":{}},{"cell_type":"code","source":"sample_filename = \"/kaggle/input/rsna-2023-abdominal-trauma-detection/segmentations/10252.nii\"\n\nsample_img = nib.load(sample_filename)\narray = sample_img.get_fdata()\nprint(\"img shape ->\", array.shape)","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:32.032884Z","iopub.execute_input":"2023-08-13T16:44:32.033434Z","iopub.status.idle":"2023-08-13T16:44:32.0704Z","shell.execute_reply.started":"2023-08-13T16:44:32.033409Z","shell.execute_reply":"2023-08-13T16:44:32.069641Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(sample_img)","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:32.07133Z","iopub.execute_input":"2023-08-13T16:44:32.072151Z","iopub.status.idle":"2023-08-13T16:44:32.078886Z","shell.execute_reply.started":"2023-08-13T16:44:32.072115Z","shell.execute_reply":"2023-08-13T16:44:32.076806Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Calculateing the middle slice, and previewing along the Z-axis","metadata":{}},{"cell_type":"code","source":"middle_slice = array[:,:,array.shape[2] // 2]\n\nplt.imshow(middle_slice, cmap='gray')\nplt.xlabel('X')\nplt.ylabel('Y')\nplt.title('Middle Slice along Z-axis')\nplt.colorbar(label='Intensity')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:32.08064Z","iopub.execute_input":"2023-08-13T16:44:32.081093Z","iopub.status.idle":"2023-08-13T16:44:32.445432Z","shell.execute_reply.started":"2023-08-13T16:44:32.081054Z","shell.execute_reply":"2023-08-13T16:44:32.444112Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Visualizing Images as a slider","metadata":{}},{"cell_type":"code","source":"def show_slice(i):\n    plt.imshow(array[:,:,i], cmap='gray')\n    plt.show()\n\ninteract(show_slice, i=(0, array.shape[2]-1))","metadata":{"execution":{"iopub.status.busy":"2023-08-13T16:44:32.446653Z","iopub.execute_input":"2023-08-13T16:44:32.446951Z","iopub.status.idle":"2023-08-13T16:44:32.723032Z","shell.execute_reply.started":"2023-08-13T16:44:32.446926Z","shell.execute_reply":"2023-08-13T16:44:32.721476Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# STAY TUNED !!\nThe notebook's work is in progress. As this one's competition is specifically going to be quite exploratory to me as I have no in-depth domain knowledge of competition specific medical field but as I am quite good at EDA so I'll give it all as a part of my learning. Also after spending quite a good amount of time in undertanding and implementing notebooks, let this be the competition I take my step forward in learning new techniques and ways by following along with the competition. I am learning a lot while covering all this and coming across many new libraries, keywords and some wonderful resources too. For sure I'll conclude all the references of my learnings in the coming updates and will keep on exploring more insights. ","metadata":{}},{"cell_type":"markdown","source":"### <p style=\"text-align:center;\"><span style=\"color:red\">💬 Thanks for reading till the end!! If you liked the notebook till here then please do Upvote👍. I am all ears to advice/remarks if you think anything needs to be added/modified.!!😃</span></p>","metadata":{}}]}