Computer-aided diagnosis

Computer-assisted detection (CAD) is a procedure in medical science that supports the doctors interpretations and findings. Imaging techniques in X-ray diagnostics yield a great deal of information, the radiologist has to analyze and evaluate comprehensively in a short time. CAD-Systems help scan digital images, e.g. from computed tomography, for typical appearances and to highlight conspicuous sections (possible diseases).

CAD is a relatively young interdisciplinary technology combining elements of artificial intelligence and digital image processing with radiological image processing. A typical application is the detection of a tumor. In this application, CAD supports the preventive medical check up in mammography (diagnosis of breast cancer), the detection of a polyp in the colon, and lung cancer.

Additional recommended knowledge

What is the Correct Way to Check Repeatability in Balances?

Daily Visual Balance Check

Weighing the right way

Avail

CAD-Systems are usually confined to marking conspicuous structures and sections. Additional Computer Assisted Diagnosis – CADx evaluates the conspicuous structures. For example mammography CAD highlights changes in the soft tissue or micro calcification in x-ray images differently. This allows the radiologist to draw conclusions about the condition of the pathology. Another application is CADq, which quantifies e.g. the size of a tumor or the tumor’s behavior in contrast medium uptake. At this stage CAD can not and may not substitute the doctor, but plays a supporting role. In any case the doctor is responsible fort the final diagnosis.

Application range

CAD is used in the diagnosis of breast cancer, lung cancer, colon cancer and prostate cancer.

Breast cancer

CAD is used in screening mammography (X-ray examination of the female breast). Screening mammography is used for the early detection of breast cancer. CAD is especially established in US and the Netherlands and is used in addition to human evaluation, usually by a radiologist. The first CAD system for mammography was developed in a research project at the University of Chicago. Today it is commercially offered by the company R2. There are currently some non-commercial projects being developed, such as Ashita Project, a gradient-based screening software by Alan Hshieh, as well. However, while achieving high sensitivities, CAD systems tend to have very low specificity and the benefits of using CAD remain uncertain. Some studies suggest a positive impact on mammography screening programs,^[1] but others show no improvement.^[2][3]

Procedures to evaluate mammography based on magnetic resonance imaging exist too.

Lung cancer (bronchial carcinoma)

In the diagnosis of lung cancer computed tomography with special three-dimensional CAD Systems are established and considered as gold standard. At this a volumetric dataset with up to 3.000 single images is prepared and analyzed. Round lesions (lung cancer, metastases and benign changes) from 1 mm are detectable. Today all well-known vendors of medical systems offer corresponding solutions.

Early detection of lung cancer becomes more important. The 5-year-survival-rate of lung cancer stagnated the last 30 years and is now at approximately just 15%. Lung cancer takes more victims than breast cancer, prostate cancer and colon cancer together. This is due to the asymptomatic growth of this cancer. In the majority of cases it is to late for a successful therapy if the patient develops first symptoms (e.g. chronic croakiness or hemoptysis ). But if the lung cancer is detected early (mostly by chance), there is a survival rate at 47% according to the American Cancer Society. ^[4] At the same time the standard x-ray-examination of the lung is the most frequently x-ray examination with a 50% share. Indeed the random detection of lung cancer in the early stage (stage 1) in the x-ray image is difficult. It is a fact that round lesions vary from 5-10 mm are easily overlooked. ^[5] The routine application of CAD Chest Systems may help to detect small changes without initial suspicion. Philips was the first vendor to present a CAD for early detection of round lung lesions on x-ray images.^[6]

Sensitivity and specificity

CAD Systems shall highlight suspicious structures. Nevertheless today’s CAD Systems can not detect 100% of pathological changes. The hit rate (sensitivity) is up to 90% depending on system and application. ^[7] A correct hit is termed as True Positive (TP). At the same time healthy sections are highlighted, which are termed as False Positive (FP). The less FP that are indicated, the higher the specificity is. A bad specificity reduces the acceptance of the CAD System, because the radiologist have to identify all of these wrong hits. The FP-rate in lung overview examinations (CAD Chest) could be reduced to 2 per examination. In other segments (e.g. CT lung examinations) the FP-rate could be 25 or more.

Absolute detection rate

The absolute detection rate of the radiologist is more important than the sensitivity and specificity. Depending on the experience, education and application CAD Chest Systems can help to increase the detection rate. In mammography the average increase is 20-30%. The early detection of round lung lesions can be increased by 50%. Overall, the results of clinical trials about sensitivity, specificity, and the absolute detection rate can strongly diversify. Each result depends on its basic conditions and has to be evaluated on its own. The following facts have a strong influence:

• In retrospect or prospective design of clinical trial
• Quality of the used images
• Condition of the x-ray examination
• The radiologist’s experience and education
• Type of tumor
• Size of the considered tumor

Methodology

CAD is fundamentally based on highly complex pattern recognition. X-ray images are scanned for suspicious structures. Normally a few thousand images are required to optimize the algorithm. Digital image data are copied to a CAD server in a DICOM-format and are prepared and analyzed in several steps.

1. Preprocessing for

• Reduction of artifacts (bugs in images)
• Image noise reduction
• Leveling (harmonization) of image quality for clearing the image’s different basic conditions e.g. different exposure parameter.

2. Segmentation for

• Differentiation of different structures in the image, e.g. heart, lung, ribcage , possible round lesions
• Matching with anatomic databank

3. Structure/ROI (Region of Interest) Analyze Every detected region is analyzed individually for special characteristics:

• Compactness
• Form, size and location
• Reference to close-by structures / ROIs
• Average greylevel value analyze within a ROI
• Proportion of greylevels to border of the structure inside the ROI

4. Evaluation / classification After the structure is analyzed, every ROI is evaluated individually (scoring) for the probability of a TP. Therefore the procedures are:

• Nearest-Neighbor Rule
• Minimum distance classifier
• Cascade Classifier
• Bayesian Classifier
• Multilayer perception
• Radial basis function network (RBF)
• SVM

If the detected structures have reached a certain threshold level, they are highlighted in the image for the radiologist. Depending on the CAD system these markings can be permanently or temporary saved. The latter’s advantage is that only the markings which are approved by the radiologist are saved. False hits should not be saved, because an examination at a later date becomes more difficult then.

References

1. ^ Effect of Computer-Aided Detection on Independent Double Reading of Paired Screen-Film and Full-Field Digital Screening Mammograms Per Skaane, Ashwini Kshirsagar, Sandra Stapleton, Kari Young and Ronald A. Castellino
2. ^ Taylor P, Champness J, Given-Wilson R, Johnston K, Potts H (2005). Impact of computer-aided detection prompts on the sensitivity and specificity of screening mammography. Health Technology Assessment 9(6), 1-70.
3. ^ Fenton JJ, Taplin SH, Carney PA, Abraham L, Sickles EA, D'Orsi C et al. Influence of computer-aided detection on performance of screening mammography. N Engl J Med 2007 April 5;356(14):1399-409.
4. ^ http://www.cancer.org/downloads/CRI/6976.00.pdf
5. ^ Wu N, Gamsu G, Czum J, Held B, Thakur R, Nicola G: Detection of small pulmonary nodules using direct digital radiography and picture archiving and communication systems. J Thorac Imaging. 2006 Mar;21(1):27-31. PMID 16538152
6. ^ xLNA (x-Ray Lung Nodule Assessment) [1]
7. ^ T. Wollenweber, B. Janke, A. Teichmann, M. Freund: Korrelation zwischen histologischem Befund und einem Computer-assistierten Detektionssystem (CAD) für die Mammografie. Geburtsh Frauenheilk 2007; 67: 135-141 DOI:10.1055/s-2006-955983