2021
DOI: 10.1080/21681163.2021.1997644
|View full text |Cite
|
Sign up to set email alerts
|

Automatic estimation of ulcerative colitis severity from endoscopy videos using ordinal multi-instance learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
6
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 12 publications
(6 citation statements)
references
References 13 publications
0
6
0
Order By: Relevance
“…Ozawa et al [15] used GoogLeNet [26] to classify images into three EMS levels (Mayo 0, Mayo 1, and Mayo 2-3) due to lack of severe cases. Among the studies in the literature, only Schwab et al [22] used an ordinal classification approach. Their models output a continuous value between 0 and 3, and classes are assigned according to the thresholds; However, class thresholds are determined using a grid search on the test dataset, which limits the generalizability of the proposed method.…”
Section: Related Workmentioning
confidence: 99%
“…Ozawa et al [15] used GoogLeNet [26] to classify images into three EMS levels (Mayo 0, Mayo 1, and Mayo 2-3) due to lack of severe cases. Among the studies in the literature, only Schwab et al [22] used an ordinal classification approach. Their models output a continuous value between 0 and 3, and classes are assigned according to the thresholds; However, class thresholds are determined using a grid search on the test dataset, which limits the generalizability of the proposed method.…”
Section: Related Workmentioning
confidence: 99%
“…Accurate evaluation of treatment effects is important because the type and dosage of treatment medicines are adjusted in accordance with the condition of the patient with UC. Recently, Schwab et al [10] proposed an automatic UC severity estimation method for treatment effectiveness evaluation. Their method assumes a weakly supervised learning scenario because full annotation of all captured images is too costly.…”
Section: Related Workmentioning
confidence: 99%
“…In this paper, we focus on the ordinal multi-instance-learning problem. The most similar work to ours is the ordinal multi-instance-learning approach proposed by Evan et al [ 12 ]. One difference is that we directly model the bag as multi-class and select the instance with minimum loss from the bags as a positive instance of the bags to update the model parameters.…”
Section: Related Workmentioning
confidence: 99%
“…Here, we consider another typical scenario of MIL-ordinal multiple instance learning [ 12 ] (OMIL): the classes of bags are not only ordered, but the instances in the bag are also in a certain rank order. Moreover, the highest level of instance label cannot exceed the label of the bag.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation