Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

Using Artificial Neural Networks for Lung Cancer Detection

DZone's Guide to

Using Artificial Neural Networks for Lung Cancer Detection

Many radiology therapists are adapting machine learning algorithms to do less manual/routine work, speed up diagnosis, and increase the quality of medical care.

· AI Zone
Free Resource

Find out how AI-Fueled APIs from Neura can make interesting products more exciting and engaging. 

Lung cancer is a major health problem and the leading cause of death among all types of cancer. Over the last seven years, computer tomography has allowed more cancers to be diagnosed at an early stage, and the mortality rate has been reduced by 20%.

Computer tomography, or CT scanning, is the main method of lung cancer diagnosis and is becoming increasingly popular. The more it’s used for lung cancer detection, the more tomographic images are produced worldwide. The fact that tomograms are usually processed manually by radiation therapists means medical personnel are flooded by routine work. That being said, tomogram processing is not an easy task. Increasing loads of complex work can reduce the quality of diagnosis and prevent health professionals from delivering medical care in time.

Why Manual Tomogram Processing Is Flawed

  • Diagnosis is slowed down.

  • Radiation therapists are overloaded with complex manual work.

  • A false diagnosis caused by a human factor can take place.

Machine learning and neural networks make it possible to automatically process X-ray pictures, tomograms, MRIs, and PET images to detect diseases. Many brands and research labs are adapting machine learning algorithms to speed up diagnosis and increase the quality of medical care.

Training an Image Processing Algorithm for Cancer Detection

The goal was to teach the algorithm to find abnormal areas called nodules in lungs. These nodules can represent cancer. To train neural networks, we used a dataset of 1,000 cancer CT scans with marked-up annotated lesions from LIDC-IDR.

The source images were in DICOM format: inhomogeneous and heavy. So we first needed to standardize all the images.

Preprocessing

  1. First, we converted voxels into world coordinates and in reverse.

    The object in different coordinate systems

  2. Then, we normalized data to avoid network failures.

  3. After that, we expressed CT numbers in a standardized and convenient form using the Hounsfield Unit. Here is a table of densities in HU.

    Materia

    HU

    Air

    -1000

    Lungs

    -500

    Fat

    From -100 to -50

    Water

    0

    Blood

    From +30 to +45

    Muscles

    From +10 to +40

    Soft tissues

    From +100 to +300

    Bones

    From +700 to +3000

  4. In the end, we rescaled all voxels to 1х1х1 mm to make use of a 3D CNN.

Segmentation

Lung structure masksLung structure masks







We segmented lungs to find nodules. Bright areas on the image represent either blood vessels or air. Using a -400 HU threshold, we segmented the lung structure and created a binary mask of lungs.

Training Neural Networks to Find Abnormal Areas

First, we applied image classification and separated all images into two groups: suspicious and normal. Then, we localized all suspicious areas using the neural network U-Net. See its architecture below.











We chose U-Net as one of the best networks for medical image processing. Moreover, this type of network is really good at cellular structure recognition. See the proof below.

U-Net segmenting cellular structures during ISBI 2012U-Net segmenting cellular structures during ISBI 2012

We trained our network to detect solitary pulmonary nodules. U-Net performed very well and found almost all abnormal areas. However, it detected some areas as “abnormal” by mistake.

From left to right: the expected result and the actual result









During the next step, we reduced the number of false positives and improved the detection accuracy using a 3D CNN.

3D CNN architecture




A 3D convolutional neural network was trained to classify abnormal areas found by the first network and separate them into valid and false. As a result, the number of false positives reduced drastically. The accuracy rate was equal to 0.925.

True Positive                                                          False Positive

A

B


Localizing nodules: A = found correctly; B = found by mistake.

The Outcome

The entire algorithm is great at finding abnormal areas in lungs. Even false positives were not a big problem since they were mostly located very close to real cancer. Furthermore, the algorithm often classified such areas with false positives as “suspicious” so that radiology therapists could check them anyway and detect cancer.

We believe this solution can be used to help radiology therapists do less manual, routine work and speed up cancer diagnosis.

To find out how AI-Fueled APIs can increase engagement and retention, download Six Ways to Boost Engagement for Your IoT Device or App with AI today.

Topics:
ai ,machine learning ,neural network ,healthcare ,cancer care

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}