Computer-Aided Diagnosis (CAD) for Cervical Cancer Screening and Diagnosis: A New System Design in Medical Image Processing

Li, Wenjing; Raad, Viara Van; Gu, Jia; Hansson, Ulf; Hakansson, Johan; Lange, Holger; Ferris, Daron G.

doi:10.1007/11569541_25

Cited by 19 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. The inputs required are a cross-polarized image, the original cervical ROI mask and a mask representing the Os region 4,6,9 . The preprocessing steps comprise of contrast enhancement and segmentation comprising color based and edge based operations.…”

Section: Algorithm Frameworkmentioning

confidence: 99%

“…The primary feature that is segmented by any image analysis system is the anatomic cervix and is the primary region of interest. There have been many methods that were used to segment the anatomic cervix with high accuracy 6,9 . Most of these methods used color and texture to segment the region of interest (ROI).…”

Section: Introductionmentioning

confidence: 99%

“…There has been tremendous research in the field of automated diagnosis for cervical cancer through optical imaging [1][2][3][4][5][6][7][8] . The primary feature that is segmented by any image analysis system is the anatomic cervix and is the primary region of interest.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving cervical region of interest by eliminating vaginal walls and cotton-swabs for automated image analysis

Venkataraman¹,

Li²

2008

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Image analysis for automated diagnosis of cervical cancer has attained high prominence in the last decade. Automated image analysis at all levels requires a basic segmentation of the region of interest (ROI) within a given image. The precision of the diagnosis is often reflected by the precision in detecting the initial region of interest, especially when some features outside the ROI mimic the ones within the same. Work described here discusses algorithms that are used to improve the cervical region of interest as a part of automated cervical image diagnosis.A vital visual aid in diagnosing cervical cancer is the aceto-whitening of the cervix after the application of acetic acid. Color and texture are used to segment acetowhite regions within the cervical ROI. Vaginal walls along with cottonswabs sometimes mimic these essential features leading to several false positives. Work presented here is focused towards detecting in-focus vaginal wall boundaries and then extrapolating them to exclude vaginal walls from the cervical ROI. In addition, discussed here is a marker-controlled watershed segmentation that is used to detect cottonswabs from the cervical ROI.A dataset comprising 50 high resolution images of the cervix acquired after 60 seconds of acetic acid application were used to test the algorithm. Out of the 50 images, 27 benefited from a new cervical ROI. Significant improvement in overall diagnosis was observed in these images as false positives caused by features outside the actual ROI mimicking acetowhite region were eliminated.

show abstract

Section: Algorithm Frameworkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving cervical region of interest by eliminating vaginal walls and cotton-swabs for automated image analysis

Venkataraman¹,

Li²

2008

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…[16][17][18] Its accuracy depends mainly on the experience and expertise of colposcopist. 19 Thus, approximately, one-third of high grade disease is missed by¯rst colposcopy, 20 or patients may be referred for unnecessary biopsies. 21,22 These avoidable biopsies increase the risk of infection, discomfort in patients, prevent women from attending regular screening and signi¯cantly increasing costs.…”

Section: Introductionmentioning

confidence: 99%

Detection and localization of the hemoglobin and collagen distribution of the uterine cervix

Tien

Quynh

Duc

et al. 2019

J. Innov. Opt. Health Sci.

View full text Add to dashboard Cite

Changes of the blood vessels and collagen are associated with the development of abnormal cervical cells. Recently, optical coherence tomography and Mueller polarization images were used to provide information regarding the presence of collagen fibers in the cervical tissue. However, most of these methods need a lot of time for image recording and are expensive. In addition, the general survey on the absorption and distribution characteristics of collagen and blood in the cervical is still lacking. In this study, we developed a colposcopy combining cross-polarized image and image processing algorithm with an efficient analytical model to map the distribution of blood and collagen in the uterine. For this system’s proof of concept, we captured and processed the case of cervical ectopy and Nabothian cyst. The results show that the distribution of blood and collagen maps matched with anatomical and physiological when compared with Lugol’s iodine images. This technology has some advantages, such as low cost, real time, and can replace the use of acetic acid or Lugol’s iodine in the future.

show abstract

“…Digital colposcopy with automated computer-assisted image analysis technique has been developed to facilitate cervical cancer examinations especially in developing countries where low-resource settings and poor financial conditions are commonly present [80][81][82]. Diagnostic features including vascular features, acetowhitening and mosaicism features from the colposcopic images were extracted for classifications.…”

Section: Supplementary Cervical Screening Methodsmentioning

confidence: 99%

Investigation of fluorescence lifetime imaging for quantitative cervical cancer screening and diagnosis

View full text Add to dashboard Cite

Computer-Aided Diagnosis (CAD) for Cervical Cancer Screening and Diagnosis: A New System Design in Medical Image Processing

Cited by 19 publications

References 15 publications

Improving cervical region of interest by eliminating vaginal walls and cotton-swabs for automated image analysis

Improving cervical region of interest by eliminating vaginal walls and cotton-swabs for automated image analysis

Detection and localization of the hemoglobin and collagen distribution of the uterine cervix

Investigation of fluorescence lifetime imaging for quantitative cervical cancer screening and diagnosis

Contact Info

Product

Resources

About