Computer Aided Diagnosis of Bone Tumors

Virtama, P; Katevuo, K.; Mäkelä, Petri; Mäkinen, Eero

doi:10.1177/028418517902001a10

Cited by 4 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An analysis of Lodwick's program demonstrated that a general radiologist with the help of Lodwick's program performed better than a different general radiologist without the program's help. 12 The present study and the previous study of Lodwick's program did not test The fact that RIIS was capable of better performance when used by experienced residents than when used by inexperienced residents shows that the performance of RIIS with inexperienced users could be improved if an "accurate" description could be obtained from them. Future expert image interpretation systems need to account for variations in the users ability to "accurately" describe the important findings.…”

Section: Discussloncontrasting

confidence: 78%

Radiology Image Interpretation System: Modified observer performance study of an image interpretation expert system

et al. 1991

View full text Add to dashboard Cite

Application of computer-based expert systems to diagnostic medical problems has been described in many areas including clinical diagnosis and radiology. Expert systems are computer programs that contain encoded expert knowledge to provide expert advice. A modified observer-performance study was done comparing the efficacy of the Radiology Image Interpretation System (RIIS), ah expert system that diagnoses focal bone abnormalities, and radiology residents on a known set of 44 abnormal and 10 normal cases. Modified receiver operating characteristic curves for four inexperienced residents, five experienced residents, and RIIS were generated using the set of known radiographs. The true-positive rates of RIIS and the residents at false-positive rates of 0.05, 0.15, and 0.20 were estimated using the modified receiver operating characteristics curve and were compared using a paired t test. On the average, the RIIS system was less accurate when compared with experienced and inexperienced residents but the difference was only significant for experienced residents at a false-positive rate of 0.05. RIIS performed better than inexperienced residents when RIIS was used by experienced residents but this difference was not significant. Copyright 9 1991 by W.B. Saunders CompanyKEY WORDS: ROC, observer.performer, expert system, diagnoses, image. EXPERT SYSTEMS have been applied to a wide variety of medical problems including clinical diagnosis, radiology, laboratory test interpretation, and chemotherapy protocols. 1 Expert systems ate computer programs that contain encoded knowledge obtained from an expert in a speci¡ field. These programs use simple inference techniques and the encoded knowledge to produce expert advice for the user in the specific field. Several investigators have been studying the application of expert systems to radiographic image interpretation and consultation. 24 These systems have been used asa cognitive aid in their areas of expertise. Lodwick et al 4 produced a program for computer-aided diagnosis of primary bone tumors using an approach based on Bayes' formula of inverse probability. This type of program can estimate conditional probabilities, but may not be as useful asa cognitive aid as expert systems. A probability matrix was estimated using a large number of known cases. This program correctly predicted the pathological diagnosis in 77% of selected cases taken from the group on which the conditional probability matrix was based. 4RIIS was developed to study the application of expert systems to diagnosing bone tumors and other focal bone abnormalities. Knowledge is encoded in Radiology Image Interpretation System (RIIS) in two ways: (1) "if-then" rules and (2) a knowledge base of diseases and findings associated with those diseases. The "if-then" rules are used to make conclusions from specific information. When the "IF" portion of the rule is true then RIIS will conclude that the "THEN" portion of the rule is also true. Multiple "if-then" rules can be concluded sequentiaUy allowing complex analysi...

show abstract

Section: Discussloncontrasting

confidence: 78%

Radiology Image Interpretation System: Modified observer performance study of an image interpretation expert system

et al. 1991

View full text Add to dashboard Cite

show abstract

“…With the help of a computer it is usually possi:ble by analysing the X-rays to make a histo-pathological diagnosis of the bone tumour before starting treatment (Lodwick 1964, Lodwick et al 1965, Virtama et al 1979. It is possible in this way to provide the patient with the best possible treatment.…”

Section: 9mentioning

confidence: 99%

“…Angiography is no substitute for biopsy in making a histo-pathological diagnosis (Gold 1975) but is often a great help in deciding where to take the biopsy sample from (Jacobs 1976). The significance of angiography does not lie in its diagnostic value, but rather in the planning of treatment (Virtama 1979). About 25 % of angiographies have diagnostic value ).…”

Section: Angiographymentioning

confidence: 99%

See 1 more Smart Citation

Primary Malignant Bone Tumours: A Retrospective Study of 869 Cases Reported to the Finnish Cancer Registry between 1962 and 1968

Jussila

1980

Acta Orthopaedica Scandinavica

View full text Add to dashboard Cite

“…[Lodwic63a] and Virtama [Virtam79a] developed computer-aided systems for the diagnosis of bone tumours.…”

Section: Overviewmentioning

confidence: 99%

Segmenting radiographs of the hand and wrist using computer vision

Μανοσ¹

View full text Add to dashboard Cite

"Bone age" age assessment is an important clinical tool in the area of paediatrics. The technique is based upon the appearance and growth of specific bones in a developing child. In particular most methods for "bone age" assessment are based on the examination of the growth of bones of the left hand and wrist on X-ray films. This assessment is useful in the treatment of growth disorders and also is used to predict adult height. One of the most reliable methods for "bone age" assessment is the TW2 method. The drawback of this method is that it is time consuming and therefore its automation is highly desirable. One of the most important aspects of the automation process is image segmentation i.e. the extraction of bones from soft-tissue and background. Over the past 10 years various attempts have been made at the segmentation of handwrist radiographs but with limited success. This can mainly be attributed to the characteristics of the scenes e.g. biological objects, penetrating nature of radiation, faint bone boundaries, uncertainty of scene content, and conjugation of bones. Experience in the field of radiographic image analysis has shown thatsegmentation of radiographic scenes is a difficult task requiring solutions which depend on the nature of the particular problem.There are two main approaches to image segmentation: edge based and region based. Most of the previous attempts at the segmentation of hand-wrist radiographs were edge based. Edge based methods usually require a w-ell defined model of the object boundaries in order to produce successful results. However, for this particular application it is difficult to derive such a model. Region based segmentation methods have produced promising results for scenes which exhibit uncertainty regarding their content and boundaries of objects in the image, as in the case, for example, of natural senes. This thesis presents a segmentation method based on the concept of regions. This method consists of region growing and region merging stages. A technique was developed for region merging which combines edge and region boundai^ information. A bone extraction stage follows which labels regions as either boneor background using heuristic rules based on the grey-level properties of the scene. Finally, a technique is proposed for the segmentation of bone outlines which helps in identifying conjugated bones. Experimental results have demonstrated that this method represents a significant improvement over existing segmentation methods for hand-wrist radiographs, particularly with regard to the segmentation of radiographs with varying degrees of bone maturity.

show abstract

Computer Aided Diagnosis of Bone Tumors

Cited by 4 publications

References 7 publications

Radiology Image Interpretation System: Modified observer performance study of an image interpretation expert system

Radiology Image Interpretation System: Modified observer performance study of an image interpretation expert system

Primary Malignant Bone Tumours: A Retrospective Study of 869 Cases Reported to the Finnish Cancer Registry between 1962 and 1968

Segmenting radiographs of the hand and wrist using computer vision

Contact Info

Product

Resources

About