Computer-aided diagnosis
Computer-aided detection, also called computer-aided diagnosis, are systems that assist doctors in the interpretation of medical images. Imaging techniques in X-ray, MRI, endoscopy, and ultrasound diagnostics yield a great deal of information that the radiologist or other medical professional has to analyze and evaluate comprehensively in a short time. CAD systems process digital images or videos for typical appearances and to highlight conspicuous sections, such as possible diseases, in order to offer input to support a decision taken by the professional.
CAD also has potential future applications in digital pathology with the advent of whole-slide imaging and machine learning algorithms. So far its application has been limited to quantifying immunostaining but is also being investigated for the standard H&E stain.
CAD is an interdisciplinary technology combining elements of artificial intelligence and computer vision with radiological and pathology image processing. A typical application is the detection of a tumor. For instance, some hospitals use CAD to support preventive medical check-ups in mammography, the detection of polyps in colonoscopy, and lung cancer.
Computer-aided detection systems are usually confined to marking conspicuous structures and sections. Computer-aided diagnosis systems evaluate the conspicuous structures. For example, in mammography CAD highlights microcalcification clusters and hyperdense structures in the soft tissue. 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. Computer-aided simple triage is another type of CAD, which performs a fully automatic initial interpretation and triage of studies into some meaningful categories. CAST is particularly applicable in emergency diagnostic imaging, where a prompt diagnosis of critical, life-threatening condition is required.
Although CAD has been used in clinical environments for over 40 years, CAD usually does not substitute the doctor or other professional, but rather plays a supporting role. The professional is generally responsible for the final interpretation of a medical image. However, the goal of some CAD systems is to detect earliest signs of abnormality in patients that human professionals cannot, as in [|diabetic retinopathy], architectural distortion in mammograms, ground-glass nodules in thoracic CT, and non-polypoid lesions in CT colonography.
History
In the late 1950s, with the dawn of modern computers researchers in various fields started exploring the possibility of building computer-aided medical diagnostic systems. These first CAD systems used flow-charts, statistical pattern-matching, probability theory, or knowledge bases to drive their decision-making process.In the early 1970s, some of the very early CAD systems in medicine, which were often referred as “expert systems” in medicine, were developed and used mainly for educational purposes. Examples include the MYCIN expert system, the Internist-I expert system and the CADUCEUS expert system. Diagnostic robots, as automatic diagnosis systems are capable of gathering data for medical diagnosis with its knowledge based subsystem, and tools such as a tendon-actuated, anthropomorphic finger, skin-like sensors for tactile perception, were conceived of.
The researchers were at first aiming at building entirely automated CAD / expert systems, with unrealistic optimism about the capability of computers. However, after the breakthrough paper "Reducibility among Combinatorial Problems" by Richard M. Karp, it became clear that developing algorithms to solve groups of important computational problems had limitations as well as potential opportunities.
In response to the new understanding of the various algorithmic limitations that Karp discovered in the early 1970s, researchers started realizing the serious limitations of CAD and expert systems in medicine, which prompted them to develop new kinds of CAD systems by using advanced approaches. Thus, by the late 1980s and early 1990s the focus shifted in the use of data mining approaches for the purpose of using more advanced and flexible CAD systems.
In 1998, the first commercial CAD system for mammography, the ImageChecker system, was approved by the US Food and Drug Administration. In the following years several commercial CAD systems for analyzing mammography, breast MRI, medical imagining of lung, colon, and heart also received FDA approval. CAD systems came to be used as a diagnostic medical decision-making aid for physicians.
In February 2013, IBM announced that Watson software system's first commercial application would be for utilization management decisions in lung cancer treatment at Memorial Sloan–Kettering Cancer Center in conjunction with WellPoint. In 2013, IBM Watson's business chief Manoj Saxena said that 90% of nurses in the field who used Watson followed its guidance.
Methodology
CAD is fundamentally based on highly complex pattern recognition. X-ray or other types of 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
- Image noise reduction
- Leveling of image quality for clearing the image's different basic conditions e.g. different exposure parameter.
- Filtering
- Differentiation of different structures in the image, e.g. heart, lung, ribcage, blood vessels, possible round lesions
- Matching with anatomic databank
- Sample gray-values in volume of interest
Every detected region is analyzed individually for special characteristics:
- Compactness
- Form, size and location
- Reference to close by structures / ROIs
- Average grey level value analyze within a ROI
- Proportion of grey levels to border of the structure inside the ROI
After the structure is analyzed, every ROI is evaluated individually for the probability of a TP. The following procedures are examples of classification algorithms.
- Nearest-Neighbor Rule
- Minimum distance classifier
- Cascade classifier
- Naive Bayes classifier
- Artificial neural network
- Radial basis function network
- Support vector machine
- Principal component analysis
Relation to provider metrics
Sensitivity and specificity
CAD systems seek to highlight suspicious structures. Today's CAD systems cannot detect 100% of pathological changes. The hit rate can be up to 90% depending on system and application. A correct hit is termed a True Positive, while the incorrect marking of healthy sections constitutes a False Positive. The less FPs indicated, the higher the specificity is. A low specificity reduces the acceptance of the CAD system because the user has to identify all of these wrong hits. The FP-rate in lung overview examinations could be reduced to 2 per examination. In other segments the FP-rate could be 25 or more. In CAST systems the FP rate must be extremely low to allow a meaningful study triage.Absolute detection rate
The absolute detection rate of a radiologist is an alternative metric to sensitivity and specificity. Overall, results of clinical trials about sensitivity, specificity, and the absolute detection rate can vary markedly. Each study result depends on its basic conditions and has to be evaluated on those terms. The following facts have a strong influence:- Retrospective or prospective design
- Quality of the used images
- Condition of the x-ray examination
- Radiologist's experience and education
- Type of lesion
- Size of the considered lesion
Challenges
Some challenges are related to various algorithmic limitations in the procedures of a CAD system including input data collection, preprocessing, processing and system assessments. Algorithms are generally designed to select a single likely diagnosis, thus providing suboptimal results for patients with multiple, concurrent disorders. Today input data for CAD mostly come from electronic health records. Effective designing, implementing and analyzing for EHR is a major necessity on any CAD systems.
Due to the massive availability of data and the need to analyze such data, big data is also one of the biggest challenges that CAD systems face today. The increasingly vast amount of patient data is a serious problem. Often the patient data are complex and can be semi-structured or unstructured data. It requires highly developed approaches to store, retrieve and analyze them in reasonable time.
During the preprocessing stage, input data must be normalized. The normalization of input data includes noise reduction and filtering.
Processing may contain a few sub-steps depending on applications. Basic three sub-steps on medical imaging are segmentation, feature extraction / selection, and classification. These sub-steps require advanced techniques to analyze input data with less computational time. Although much effort has been devoted to creating innovative techniques for these procedures of CAD systems, no single best algorithm has emerged for any individual step. Ongoing studies in building innovative algorithms for all the aspects of CAD systems is essential.
There is also a lack of standardized assessment measures for CAD systems. This fact may cause the difficulty for obtaining approval for commercial use from governing bodies such as the FDA. Moreover, while many positive developments of CAD systems have been proven, studies for validating their algorithms for clinical practice have not been confirmed.
Other challenges are related to the problem for healthcare providers to adopt new CAD systems in clinical practice. Some negative studies may discourage the use of CAD. In addition, the lack of training of health professionals on the use of CAD sometimes brings the incorrect interpretation of the system outcomes.