使用 Amazon Textract 和 Amazon Comprehend Medical 实现无服务器化的医疗文档分析

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "textract:*",
        "s3:*",
        "cloudwatch:*",
        "logs:*",
        "iam:GetPolicy",
        "iam:GetPolicyVersion",
        "iam:GetRole"
      ],
      "Resource": "*"
    },
    {
      "Effect": "Allow",
      "Action": "iam:CreateServiceLinkedRole",
      "Resource": "arn:aws:iam::*:role/aws-service-role/events.amazonaws.com/AWSServiceRoleForCloudWatchEvents*",
      "Condition": {
        "StringLike": {
          "iam:AWSServiceName": "events.amazonaws.com"
        }
      }
    }
  ]
}

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "comprehendmedical:*",
        "s3:*",
        "cloudwatch:*",
        "logs:*",
        "iam:GetPolicy",
        "iam:GetPolicyVersion",
        "iam:GetRole"
      ],
      "Resource": "*"
    },
    {
      "Effect": "Allow",
      "Action": "iam:CreateServiceLinkedRole",
      "Resource": "arn:aws:iam::*:role/aws-service-role/events.amazonaws.com/AWSServiceRoleForCloudWatchEvents*",
      "Condition": {
        "StringLike": {
          "iam:AWSServiceName": "events.amazonaws.com"
        }
      }
    }
  ]
}

import boto3
import json

def lambda_handler(event, context):
    # File definition
    s3Key = event['Records'][0]['s3']['object']['key']
    keyName = s3Key.split('/')[1].split('.')[0]
    outFile = '/tmp/output.json'
    outputKey = 'raw/' + keyName + '/raw.json'
    medicalRaw = "/tmp/medicalraw.txt"
    medicalRawKey = 'raw/' + keyName + '/medicalraw.txt'
    medicalReport = '/tmp/medicalreport.txt'
    medicalReportKey = 'medical/' + keyName + '/medicalreport.txt'

    # S3 and Textract Configuration
    s3Bucket = event['Records'][0]['s3']['bucket']['name']
    fileType = 'FORMS'

    # Call Textract to convert form to json
    textract = boto3.client('textract')
    textractResponse = textract.analyze_document(
        Document={
            'S3Object': {
                'Bucket': s3Bucket,
                'Name': s3Key
            }
        },
        FeatureTypes=[
            fileType
        ]
    )
    with open(outFile, 'w') as outfile:
        outfile.write(json.dumps(textractResponse, indent=4))

    # Ingest content
    for blocks in textractResponse['Blocks'][1:]:
        if blocks['Confidence']:
            if (blocks['Confidence'] >= 70) and (blocks['BlockType'] == 'LINE'):
                with open(medicalReport, 'a') as medicalReportOut:
                    medicalReportOut.write(blocks['Text'] + "\r\n")
            elif (blocks['Confidence'] >= 70) and (blocks['BlockType'] == 'WORD'):
                with open(medicalRaw, 'a') as medicalRawOut:
                    medicalRawOut.write(blocks['Text'] + "\r\n")
            else:
                continue
        else:
            print("oops")

    # Upload outputs to s3
    s3 = boto3.resource('s3')
    try:
        s3.meta.client.upload_file(outFile, s3Bucket, outputKey)
        s3.meta.client.upload_file(medicalReport, s3Bucket, medicalReportKey)
        s3.meta.client.upload_file(medicalRaw, s3Bucket, medicalRawKey)
    except Exception as e:
        print(e)
        print("Upload failed!")
    else:
        print("Upload done!")

import boto3
import json

def lambda_handler(event, context):
    # Configure definition
    s3Bucket = event['Records'][0]['s3']['bucket']['name']
    s3Key = event['Records'][0]['s3']['object']['key']
    keyName = s3Key.split('/')[1].split('.')[0]
    localFinal = '/tmp/result.txt'
    phiFinal = '/tmp/phi.txt'
    manualFinal = '/tmp/manual.txt'
    medicalResult = 'result/' + keyName + '/medicalresult.txt'
    phiResult = 'phi/' + keyName + '/phi.txt'
    manualResult = 'manual/' + keyName + '/manual.txt'

    # Ingest medical report
    try:
        s3 = boto3.client('s3')
    except Exception as e:
        print(e)
        print('connect S3 failed!')
    else:
        print('connect S3 successfully')

    s3_object = s3.get_object(Bucket=s3Bucket, Key=s3Key)
    body = s3_object['Body']

    # Execute medical analysis
    try:
        comprehendMedical = boto3.client('comprehendmedical')
    except Exception as e:
        print(e)
    else:
        print('connect Comprehend Medical successfully')

    detectEntities = comprehendMedical.detect_entities_v2(
        Text=body.read().decode('utf-8')
    )
    detectOutputRaw = detectEntities['Entities']

    # Categorize different types of information
    report_ANATOMY = []
    report_MEDICAL_CONDITION = []
    report_MEDICATION = []
    report_PROTECTED_HEALTH_INFORMATION = []
    report_TEST_TREATMENT_PROCEDURE = []
    report_MANUAL = []

    for ctgy in detectOutputRaw:
        if ctgy['Score'] >= 0.6:
            if ctgy['Category'] == 'ANATOMY':
                report_ANATOMY.append(ctgy)
            elif ctgy['Category'] == 'MEDICAL_CONDITION':
                report_MEDICAL_CONDITION.append(ctgy)
            elif ctgy['Category'] == 'MEDICATION':
                report_MEDICATION.append(ctgy)
            elif ctgy['Category'] == 'PROTECTED_HEALTH_INFORMATION':
                report_PROTECTED_HEALTH_INFORMATION.append(ctgy)
            elif ctgy['Category'] == 'TEST_TREATMENT_PROCEDURE':
                report_TEST_TREATMENT_PROCEDURE.append(ctgy)
            else:
                continue
        else:
            report_MANUAL.append(ctgy)

    result_ANATOMY = []
    result_MEDICAL_CONDITION = []
    result_MEDICATION = []
    result_PROTECTED_HEALTH_INFORMATION = []
    result_TEST_TREATMENT_PROCEDURE = []
    result_MANUAL = []

    if report_ANATOMY:
        for anatomy in report_ANATOMY:
            result_ANATOMY.append(anatomy['Text'])
    if report_MEDICAL_CONDITION:
        for medical_condition in report_ANATOMY:
            result_MEDICAL_CONDITION.append(medical_condition['Text'])
    if report_MEDICATION:
        for medication in report_MEDICATION:
            result_MEDICATION.append(medication['Text'])
    if report_PROTECTED_HEALTH_INFORMATION:
        for protected_health_information in report_PROTECTED_HEALTH_INFORMATION:
            result_PROTECTED_HEALTH_INFORMATION.append(protected_health_information['Text'])
    if report_TEST_TREATMENT_PROCEDURE:
        for test_treatment_procedure in report_TEST_TREATMENT_PROCEDURE:
            result_TEST_TREATMENT_PROCEDURE.append(test_treatment_procedure['Text'])
    if report_MANUAL:
        for test_manual in report_MANUAL:
            result_MANUAL.append(test_manual['Text'])

    with open(localFinal, 'a') as localfile:
        if result_ANATOMY:
            localfile.write('Anatomy:\r\n' + '\r\n'.join(set(result_ANATOMY)))
        if result_MEDICAL_CONDITION:
            localfile.write('\r\n---\r\n')
            localfile.write('Medical Condition:\r\n' + '\r\n'.join(set(result_MEDICAL_CONDITION)))
        if result_MEDICATION:
            localfile.write('\r\n---\r\n')
            localfile.write('Medication:\r\n' + '\r\n'.join(set(result_MEDICATION)))
        if result_TEST_TREATMENT_PROCEDURE:
            localfile.write('\r\n---\r\n')
            localfile.write('Test Treatment Procedure:\r\n' + '\r\n'.join(set(result_TEST_TREATMENT_PROCEDURE)))
    localfile.close()

    with open(phiFinal, 'a') as phifile:
        if result_PROTECTED_HEALTH_INFORMATION:
            phifile.write('Protected Health Information:\r\n' + '\r\n'.join(set(result_PROTECTED_HEALTH_INFORMATION)))
    phifile.close()

    with open(manualFinal, 'a') as manualfile:
        if result_MANUAL:
            manualfile.write('Manually Check:\r\n' + '\r\n'.join(set(result_MANUAL)))
    manualfile.close()

    # Upload outputs to s3
    s3Upload = boto3.resource('s3')
    try:
        s3Upload.meta.client.upload_file(localFinal, s3Bucket, medicalResult)
        s3Upload.meta.client.upload_file(phiFinal, s3Bucket, phiResult)
        s3Upload.meta.client.upload_file(manualFinal, s3Bucket, manualResult)

    except Exception as e:
        print(e)
        print("Upload failed!")
    else:
        print("Upload done!")

aws s3 cp <medical report>.png s3://medical-report-analysis-<unique_identifier>/input/<medical report>.png