Electronic cleansing of tagged residue in CT colonography: what radiologists need to know

Mang, Thomas; Bräuer, Christian; Gryspeerdt, Stefaan; Scharitzer, Martina; Ringl, Helmut; Lefere, Philippe

doi:10.1186/s13244-020-00848-9

Cited by 5 publications

(4 citation statements)

References 27 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there is now also a technique called faecal tagging. A contrast agent is swallowed and tagged to the faeces, and faeces will have a different contrast compared with the mucosa; thus, cleaning of the bowel may not be necessary in future [61, 62], although this is currently not good enough to be used for screening purposes. Furthermore, CT colonoscopy has in many studies been shown to be effective, but not in a large screening study [31‐33, 63, 64].…”

Section: Methods For Colorectal Cancer Screeningmentioning

confidence: 99%

Aspects of colorectal cancer screening, methods, age and gender

Hultcrantz

2020

J. Intern. Med.

View full text Add to dashboard Cite

Colorectal cancer (CRC) is, besides breast, prostate, lung and skin cancers, the most common cancer worldwide and is suitable for screening. The incidence of CRC varies considerably in different parts of the world: in well-developed countries, the incidence is between 30 and 70 per 100 000 inhabitants, whereas in less-developed countries such as sub-Saharan Africa, it is 10-20/100 000 inhabitants. Women have a lower incidence of CRC, which is usually one-third of total incidence. Several studies have shown that it is possible to decrease mortality from CRC with about 20%, which is evidenced through the data from countries with screening programmes. Though the method of choice to identify blood samples in faecal matter is under debate, the most feasible way is to perform colonoscopy. Other methods include more advanced faecal analyses, testing for mutations from CRC, sigmoidoscopy, CT colonoscopy or optical colonoscopy. Colonoscopy is in most countries not available in sufficient amount and has to be carried out with great accuracy; otherwise, lesions will be missed to identify, thus leading to complications. Gender is an issue in CRC screening, as women have about 20% fewer colorectal adenomas and CRCs, but they also have more right-sided lesions, which are more difficult to detect with tests for faecal blood since they create less blood in faeces. Thus, other strategies may have to be developed for women in order for screening to have the same effect. It is essential to introduce colorectal cancer screening in all countries together with other clinical pieces of advice such as information on smoking, obesity and exercise in order to reduce one of the most dangerous cancers.

show abstract

Section: Methods For Colorectal Cancer Screeningmentioning

confidence: 99%

Aspects of colorectal cancer screening, methods, age and gender

Hultcrantz

2020

J. Intern. Med.

View full text Add to dashboard Cite

show abstract

“…However, conventional EC methods tend to leave residual EC image artifacts that complicate the interpretation of the virtually cleansed CTC images. The image artifacts are caused by the difficulties of differentiating soft tissues from partial-volume boundaries at the interface between fecal tagging and other materials, as well as by the difficulties of differentiating soft tissues from unclearly tagged fecal materials 3 . Resolving such artifacts requires an understanding of the long-distance dependencies of voxels within the CTC image volume.…”

Section: Purposementioning

confidence: 99%

Electronic cleansing in CT colonography using transformer-based UNet

Tachibana,

Näppi,

Okamoto

et al. 2024

Medical Imaging 2024: Imaging Informatics for Healthcare, Research, and Applications

View full text Add to dashboard Cite

We developed a novel 3D transformer-based UNet method for performing electronic cleansing (EC) in CT colonography (CTC). The method is designed to map an uncleansed CTC image volume directly into the corresponding virtually cleansed CTC image volume. In the method, the layers of a 3D transformer-based encoder are connected via skip connections to the decoder layers of a 3D UNet to enhance the ability of the UNet to use long-distance image information for resolving EC image artifacts. The EC method was trained by use of the CTC image volumes of an anthropomorphic phantom that was filled partially with a mixture of foodstuff and an iodinated contrast agent. The CTC image volume of the corresponding empty phantom was used as the reference standard. The quality of the EC images was tested visually with six clinical CTC test cases and quantitatively based on a phantom test set of 100 unseen samples. The image quality of EC was compared with that of a conventional 3D UNet-based EC method. Our preliminary results indicate that the 3D transformer-based UNet EC method is a potentially effective approach for optimizing the performance of EC in CTC.

show abstract

“…However, conventional EC methods that use CT value to identify the enhanced materials on the CTC images produce residual EC image artifacts that can distract the image interpretation by radiologists or by artificial intelligence (AI) systems. These artifacts are caused by difficulties in differentiating soft tissue from partial-volume boundaries between fecal tagging and other materials, as well as by the difficulties in differentiating soft tissue from unclearly tagged fecal materials 4 .…”

Section: Purposementioning

confidence: 99%

3D generative AI for electronic cleansing in CT colonography

Tachibana,

Näppi,

Hironaka

et al. 2024

Medical Imaging 2024: Imaging Informatics for Healthcare, Research, and Applications

View full text Add to dashboard Cite

We developed a novel 3D generative artificial intelligence (AI) method for performing electronic cleansing (EC) in CT colonography (CTC). In the method, a 3D transformer-based UNet is used as a generator to map an uncleansed CTC image volume directly into a virtually cleansed CTC image volume. A 3D-PatchGAN is used as a discriminator to provide feedback to the generator to improve the quality of the EC images generated by the 3D transformer-based UNet. The EC method was trained by use of the CTC image volumes of an anthropomorphic phantom that was filled partially with a mixture of foodstuff and an iodinated contrast agent. The CTC image volume of the corresponding empty phantom was used as the reference standard. The quality of the EC images was tested visually with six clinical CTC test cases and quantitatively based on a phantom test set of 100 unseen sample image volumes. The image quality of EC was compared with that of a previous 3D GAN-based EC method. Our preliminary results indicate that the 3D generative AI-based EC method outperforms our previous 3D GAN-based EC method and thus can provide an effective EC method for CTC.

show abstract

Electronic cleansing of tagged residue in CT colonography: what radiologists need to know

Cited by 5 publications

References 27 publications

Aspects of colorectal cancer screening, methods, age and gender

Aspects of colorectal cancer screening, methods, age and gender

Electronic cleansing in CT colonography using transformer-based UNet

3D generative AI for electronic cleansing in CT colonography

Contact Info

Product

Resources

About